The complex interactions between flexible needles and tissues present significant challenges in predicting the needle shape during the puncture procedure. In particular, the accurate prediction of flexible needle shape during insertion into complex multilayer tissues, especially when measurement feedback involves non-Gaussian noise, remains an open problem. In this article, we develop a novel reinforcement learning-based active modeling scheme to predict the deflection of the robotic flexible needle. First, the active modeling scheme is constructed by deriving an extended Kalman filter under the maximum correntropy criterion to enhance insensitivity to non-Gaussian noise. Subsequently, based on this scheme, the reinforcement active modeling (RAM) framework is built by incorporating reinforcement learning to compensate for the modeling residuals. Specifically, the theoretical convergence of the proposed scheme is proved by using the Banach fixed-point theorem, thereby ensuring the reliability of needle shape prediction. Finally, a series of comparative experiments is carried out on a self-built robotic flexible needle. The experimental results demonstrate the superior performance of the proposed deflection predictor. Under non-Gaussian noise conditions, the proposed RAM scheme achieves a generalization prediction error reduction of 46.4% in RMSE and over 76.1% in Var during insertion into unknown multilayer tissue.

Gaussian process regression (GPR) models are becoming increasingly tightly integrated into robotic systems, particularly in the context of robot model predictive control (MPC) operating in complex environments. Because data generated by robots are typically collected online and exhibits heteroscedasticity (i.e., the noise variance depends on the input), traditional GPR may not be suitable. Thus, an incremental heteroscedastic GPR (IHGPR) method is proposed, which takes advantage of incremental sparse spectrum GPR (I-SSGPR) and the framework of improved most likely heteroscedastic GPR (improved MLHGPR). The predictive distribution is not only in an explicit form but also differentiable, rendering a plug-and-play solution for optimization-based control. The efficacy of the proposed approach is demonstrated through a series of empirical evaluation experiments, highlighting its time efficiency and capacity to accurately capture heteroscedastic signals. To illustrate its versatile applicability in robotic system control, we integrate IHGPR into a robust MPC (RMPC) method to online fit the state-and input-dependent heteroscedastic stochastic disturbances and present the applicability and efficiency through simulation results.

Learning from Demonstrations (LfD) methods are applied to transfer human skills to robots from expert demonstrations, enabling them to perform complex tasks. However, existing methods often struggle to handle such long-horizon human skills as cleaning or wiping stains on the surface, which involve multiple periodic and transitional movement primitives. To address this limitation, this paper proposes a novel framework for segmenting, learning, and generalizing multi-periodic human skills, enabling robots to effectively learn different movement primitives and execute these skills in new environments. Specifically, the framework introduces an unsupervised learning method to segment long-horizon human demonstrations into periodic and discrete movement primitives. Further, a novel type of discrete dynamical movement primitives, namely transitional movement primitives, is employed to enhance the fluidity of combining different periodic movement primitives in skills. These primitives collectively form a lightweight state machine during task execution, where state transitions are governed by visual perception, thereby enabling generalization to long-horizon tasks composed of arbitrary numbers of periodic subtasks. To validate the effectiveness of the proposed approach, we conduct extensive experimental evaluations, including step-by-step validation of each method in simulation and the implementation of the entire presented framework in the real world. The results confirm that the proposed framework accurately learns and generalizes multi-periodic human skills, providing a feasible solution for transferring complex multi-periodic demonstrations to robots in practical applications. The project website can be found at: https://nkrobotlab.github.io/LAMPS/

Needle puncture is a fundamental technique in minimally invasive surgical procedures. However, the limited flexibility of flexible needles and their complex interactions with tissues make it challenging to avoid critical organs along the puncture path. Preoperative path planning, which generates feasible collision-free trajectories, can effectively reduce repeated punctures and mitigate patient discomfort. To address this challenge, a flexible needle with increased maximum curvature is designed, which introduces more complex kinematic characteristics and poses greater challenges for trajectory planning under kinematic constraints. Then, for the first time, a convex feasible set (CFS)-based flexible needle trajectory planning method is developed to tackle the non-convex optimization problem posed by obstacle avoidance in unstructured surgical environments. Specifically, our method explicitly incorporates kinematic and curvature constraints, enabling direct generation of feasible trajectories without additional post-processing. Finally, comparative experiments on a self-developed robotic-assisted flexible needle system demonstrate the superior performance of the proposed algorithm. In particular, the proposed trajectory generation method allows the flexible needle to effectively avoid obstacles and accurately reach the target.

Aerial robots have demonstrated significant potential in suspended cargo transportation, especially in industries such as logistics and food delivery. Due to the underactuated and nonlinear dynamics of the cable-suspended system, directly tracking a given trajectory with a multicopter without modifying its controller often leads to significant payload swing. This compromises the safety and stability of the cargo. To address the aforementioned issue, this paper proposes an online trajectory refinement method for a variable-length cable-suspended aerial transportation robot, independent from the control layer. By incorporating payload swing angle information, the reference trajectory is refined in real-time, effectively suppressing payload oscillations during transportation. Specially, Lyapunov techniques and LaSalle’s invariance theorem are employed to rigorously guarantee the feasibility of the designed trajectory refinement scheme. Finally, hardware experiments are conducted to validate the effectiveness and superiority of the proposed method. The results demonstrate that the refined trajectory not only enables precise positioning of the multicopter, but also effectively suppresses payload oscillations during transportation, significantly enhancing the safety and reliability of the aerial cargo delivery.

Autonomous Aerial Vehicles (AAVs), particularly quadrotors, have gained substantial attention in recent years due to their high agility, substantial convenience, and significant potential in hazardous missions such as military surveillance and disaster relief. This paper focuses on the aerial throwing problem, aiming to develop a time-optimal method for air-dropping cable-suspended payloads. The contributions of the paper are: 1) a fast approach is presented to streamline the quadrotor’s state management by directly mapping and planning at the quadrotor state space (position, velocity, acceleration); 2) a clearly defined initial guess is provided for aerial suspended throwing tasks, which speeds up the planning process. This methodology not only enhances the convenience of quadrotor navigation, but also fosters a more direct and efficient control scheme. The efficacy and feasibility of the proposed method are validated through both numerical simulations and practical experiments, demonstrating the potential for rapid and accurate payload throwing with cable-suspended systems. Note to Practitioners—This study is driven by the need to enhance aerial payload throwing task in hazardous scenarios, such as disaster relief and military surveillance where precision and speed are crucial. While quadrotors serve as agile platforms for such operations, existing methods lack a rapid planning approach that can directly plan at the quadrotor state space (position, velocity, acceleration). Our work introduces a warm start strategy, which significantly hastens the planning process, enabling faster throwing of cable-suspended payloads. Future extensions of this work could focus on integrating adaptive elements that respond to environmental feedback in real-time, thus broadening the practical applicability of the method in real-world conditions.

Landing a quadrotor on a mobile platform moving with various unknown trajectories presents special challenges, including the requirements of fast trajectory planning/replanning, accurate control, and the adaptability for different target trajectories, especially when the platform is non-cooperative. However, previous works either assume the platform moves along a predefined trajectory or decouple planning from control which may cause a delay in tracking. In this work, we integrate planning and control into a unified framework and present an efficient off-policy Meta-Reinforcement Learning (Meta-RL) algorithm that enables a quadrotor (agent) to land on a mobile platform with various unknown trajectories autonomously. In our approach, we disentangle task-specific policy parameters by a separate adapter network to shared low-level parameters and learn a probabilistic encoder to extract common structures across different tasks. Specifically, during meta-training, we sample different trajectories from the task distribution, and then the probabilistic encoder accumulates the necessary statistics from past experience into the latent variables that enable the policy to perform the task. At meta-testing time, when the quadrotor is faced with an unseen trajectory, the latent variables can be sampled according to past interactions between the quadrotor and the mobile platform and held constant during an episode, enabling rapid trajectory-level adaptation. We assume similar tasks share a common low-dimensional structure in the representation of the policy network and the task-specific information is learned in the head of the policy. Accordingly, we further propose a separate adapter net as a supervised learning problem. The adapter net learns the weights of the policy’s output layer for each meta-training task given by the environment interactions from the agent. When adapting to a new task during meta-testing, we fix the shared model layers and predict the head weights for the new task using the trained adapter network. This ensures that the pretrained policy can efficiently adapt to different tasks, which boosts the out-of-distribution performance. Our method can directly control the pitch, roll, yaw angle, and thrust of the quadrotor, yielding a fast response to the trajectory change. Simulation results show the superiority of our method both in success rate and adaptation efficiency over other RL algorithms on meta-testing tasks. The real-world experimental results compared with traditional planning and control algorithms demonstrate the satisfactory performance of our autonomous landing method, especially its robustness in adapting to unknown dynamics.Note to Practitioners—Given the challenge posed by the motion uncertainty when a quadrotor lands on a mobile platform with an unknown trajectory, there hasn’t been a well-established solution, as far as we know. This paper introduces meta-reinforcement learning, incorporating a latent variable encoder to extract common features from training tasks, and designing an adapter network to enhance the ability of policy networks to adapt to new tasks, thereby enhancing the landing performance of the agent. The proposed method demonstrates promising results in both simulation and experiments.

This paper presents an intelligent control scheme for multirotors, where accurate trajectory tracking, strong robustness and reliable generalization are guaranteed by the dual-feedback sliding-mode (DFSM) guided deep reinforcement learning (RL). Different from current solutions, the proposed method explores optimal learning strategy on the sliding surface according to the DFSM demonstrations, where the elegantly designed parallel evaluation takes full advantage of model knowledge and learning exploration. Specifically, the intelligent tracking control is achieved in a two-step design. First, the DFSM algorithm is designed for multirotors, where the linear and nonlinear feedback terms work cooperatively. Second, the DFSM-guided deep RL is put forward to achieve intelligent switching on the sliding surface, where position and velocity errors are both considered to generate accurate switching decisions. In the framework, explorations and the DFSM demonstrations are evaluated in parallel, where only the explorations that are better than the DFSM baseline, are kept for policy improvement. In this way, the DFSM algorithm keeps pushing the RL policy to explore better strategy, where the unavoidable bad experiences arisen from exploration are identified accurately. Practical comparative experimental results are included to verify the effectiveness of the proposed strategy.Note to Practitioners—This paper is motivated by the practical problem of controlling multirotor system in uncertain environments. Up until now, most existing approaches are proposed without taking full advantage of model knowledge and deep learning techniques simultaneously, which lacks of reliability in practical application. To deal with the problem, a new dual-feedback sliding-mode (DFSM) guided deep reinforcement learning (RL) strategy is proposed, where the dual feedback and guided RL are designed to achieve satisfactory tracking control and simultaneously handle uncertainties. Specifically, by introducing double-check framework, the RL strategy explores optimal switching policy on the sliding surface according to the DFSM demonstrations, guaranteeing strong robustness and reliable generalization of the obtained RL policy in uncertain environments. The key feature of the framework is that the DFSM-driven training guarantees practice-oriented tracking control in a DFSM-RL cooperative manner. Comparative experiments are implemented to verify the tracking performance of the proposed intelligent control strategy.

The unmanned aerial manipulator system has shown great application potential in rotor blade repairing, bridge inspection, and goods delivery. Allowing additional alternatives in tasks, dual-arm always provides more flexibility, versatility, and manipulability compared to a single arm. Unfortunately, the inherent defects of unignorable nonlinearities and complex dynamic coupling between the multirotor and the manipulator have limited the practical application of dual-arm aerial manipulator systems. It is noteworthy that the dynamic coupling between the multirotor UAV (unmanned aerial vehicle) and the dual-arm manipulator is much more complicated than the case of the single-arm, and may degrade the control performance significantly as the CoM (center of mass) of the system changes with the movement of the manipulator. To this end, this paper presents a novel control method based on dual-arm movement compensation. Specifically, the kinematic and dynamic model of the system is first established, based on which the force effect of the manipulator exerting on the multirotor UAV is estimated by the disturbance observer and then compensated. By using Lyapunov techniques, it is proven that the error signal can converge asymptotically. As far as we know, this paper presents the first controller design for dual-arm aerial manipulator systems with rigorous stability analysis. Finally, the effectiveness and robustness of the proposed method are verified through a significant number of comparison experiments, and the results of these experiments demonstrate that the proposed method can reduce the positioning error obviously compared to the comparison methods. Taking the PID method as the benchmark for comparison, it is obvious that the proposed method exhibits the greatest reduction in both maximum and average errors compared to the baseline method, indicating superior control precision than the other comparison methods. For the result of the proposed method in$\bm x$-direction, one can find a substantial reduction ranging from 16.69% to 38.57% for the maximum error, and 22.24% to 45.66% for the mean error. Shifting focus to the$\bm y$-direction, the error reduction for the proposed method is even more remarkable, ranging from 68.10% to 81.80% at maximum, and 66.31% to 86.33% for the mean error. As for the$\bm z$-direction, the error reduction by the proposed method remained significant, ranging from 50.67% to 86.38% at maximum, and with a mean error reduction of 33.11% to 80.39%.Note to Practitioners—This paper is motivated by the problem of executing such tasks as load transportation and coordinate manipulation for aerial robots in flight. By integrating the dual-arm manipulator, the flexibility, versatility, and manipulability of the unmanned aerial manipulator system is further extended. However, the uncertain center of mass of the system during operation may badly increase the control difficulty of the dual-arm aerial manipulator system. Moreover, the strong nonlinearity and complex coupling existing between the multirotor and the manipulator also induce urgently solved problems in practical aerial manipulation tasks. To this end, this paper proposes a novel dual-arm movement compensation based control scheme by utilizing an elaborately designed disturbance observer to deal with the unestimated part of disturbance exerting on the multirotor by arm operation. With rigorous theoretical analysis, the convergence of the error signal is proven. Additionally, groups of hardware experiments further verify the effectiveness and robustness of the suggested control method. In future studies, we will improve the autonomy level of the system by integrating onboard sensors.

The utilization of a well-established flapping wing robot simulation holds significant importance in the advancement of flapping wing mechanisms and algorithms. This research paper introduces a pioneering application-oriented flapping wing robot simulation platform that exhibits high compatibility with diverse mechanical designs and adaptability to various robotic tasks. Initially, the paper presents the blade element theory and the quasi-steady model as computational approaches for determining the aerodynamics of flapping wings based on their kinematics. The computation incorporates translational lift, translational drag, rotational lift, added mass force, and clap-and-fling mechanism. The simulation platform is validated through flight control tasks, providing a comprehensive assessment of its performance. Moreover, this study addresses the challenges of attitude tracking and trajectory tracking control for a specially designed flapping wing robot. The proposed control strategies are evaluated through real flight experiments, offering practical insights into the robot flight capabilities. Note to Practitioners—One of the primary contributions of this research is the introduction of a novel and robust flapping wing flight controller that effectively addresses the challenges associated with attitude tracking control and positional trajectory tracking. The proposed controller demonstrates superior performance compared to existing algorithms, as evidenced by comparative simulations conducted on the developed simulation platform. Furthermore, real flight experiments are performed on a self-made flapping wing robot using the same control algorithm and parameters employed in the simulations. Another highlight lies in the transferability from simulation to reality. The utilization of a high-fidelity simulation platform enables in-depth exploration and scrutiny of complex behaviors manifested in diverse flight tasks. This, in turn, allows for meticulous analysis and examination to gain valuable insights into the practical implementation of flapping wing robot flight.

Hysteresis is a typical nonlinear characteristic that exists in mechanical systems, which brings significant challenges to the robust tracking control of twisted tendon-sheath systems. In this paper, an active data-driven model is proposed to describe the hysteresis phenomenon of a twisted tendon-sheath system based on the Koopman operator, and a robust controller is designed to cancel the effect of the model error and deal with the physical constraints in practical applications. First, by utilizing the Koopman theory, an active data-driven model is built to describe the twisted tendon-sheath hysteresis system in a straightforward linear form. Then, an active model is proposed based on a modified set-membership filter to estimate the finite-dimensional approximation error. Furthermore, a robust controller is developed by taking advantage of both the magnitude and bound of the model error (obtained by the active model) to enhance the control performance while considering security constraints. To the best of our knowledge, the rule-based constraint term is first considered in the data-driven model-based control scheme to prevent potential instabilities for the twisted tendon-sheath system. The theoretical stability of the closed-loop system is proven by using the barrier Lyapunov theory to ensure the security boundary. Extensive experiments are also carried out on a self-built robotic ureteroscopy prototype to demonstrate the superior tracking performance and robustness of the proposed method. Note to Practitioners—This paper is motivated by the accurate transmission problems of twisted tendon-sheath hysteresis systems, which aims to provide a precise active modeling method and a robust controller for the robotic-assisted instrument (e.g., endoscope, catheter, etc.) twisting in the sheath/orifice. Most existing studies on tendon-sheath hysteresis systems realize trajectory tracking controllers by using parametric-model-based compensation, which still lacks a practical data-driven modeling approach to characterize the hysteresis phenomenon in the linear form, and ignore the security constraints of tendon outputs. Based on the set-membership filter, this paper builds an active Koopman-based model, which is a practical method to follow for systems characterized by complex dynamics. Subsequently, by employing the constructed active model and a rule-based term to handle output constraints, a robust controller is elaborately designed to realize accurate tracking control for twisted tendon-sheath hysteresis systems. In particular, no priori knowledge of the complex dynamics is required in the implementation and gains selection of the proposed controller, which holds theoretically and practically significance for various tendon-sheath hysteresis systems. A series of comparative hardware experiments further validate the effectiveness and robustness of the suggested control scheme. In future work, we will aim to extend the applicability of the proposed active modeling and control scheme to interventional procedures of endoscopic operation robots for complex steerings with varying sheath configurations.

In this paper, an efficient motion planning approach with grid-based generalized Voronoi diagrams (G$^2$VD) is newly proposed for mobile robots. Different from existing approaches, the novelty of this work is twofold: 1) a new state lattice-based path searching approach is proposed, in which the search space is reduced to a novel Voronoi corridor to further improve the search efficiency; 2) an efficient quadratic programming-based path smoothing approach is presented, wherein the clearance to obstacles is considered to improve the path clearance of hard-constrained path smoothing approaches. We validate the efficiency and smoothness of our approach in various challenging simulation scenarios and outdoor environments. It is shown that the computational efficiency is improved by 17.1% in the path searching stage, and path smoothing with the proposed approach is 6.6 times faster than an advanced sparse-banded structure-based path smoothing approach and 53.3 times faster than the popular timed-elastic-band planner. A video showing outdoor navigation on our campus is available at https://youtu.be/iMXGthgvp58.Note to Practitioners—This paper is motivated by the challenges of motion planning problems of mobile robots. An efficient motion planning approach called G$^2$VD planner is proposed by combining path searching, path smoothing, and time-optimal velocity planning. Extensive simulation and experimental results show the effectiveness of the proposed motion planning approach. However, the prediction information of dynamic obstacles is not incorporated in the proposed motion planner, thus the motion planner may be a bit sluggish in response to dynamic obstacles. Furthermore, we plan to integrate the intention/trajectory prediction of pedestrians/vehicles into the proposed framework to enhance the foreseeability of the motion planner.

By utilizing a suspension cable to connect the payload with the quadrotor, transport tasks can be accomplished while preserving the unmanned aerial vehicle’s agility and maneuverability, particularly in environments that are impassable for ground vehicles. Equipping onboard visual sensors and utilizing image-based visual servoing techniques, the application range of aerial transportation systems is poised to be significantly expanded in scenarios like autonomous landing and goods release. Unfortunately, within the system, there exist multiple layers of dynamic couplings between image features, quadrotor rotation, translation, and payload motion. These intricacies give rise to numerous difficulties in achieving smooth anti-swing transportation. To overcome the aforementioned difficulties, this paper presents the first image-based visual servoing control scheme for the aerial transportation system with variable-length cable. Specifically, the image moments defined on the rotated virtual image plane are taken as the image features, whose dynamics is independent of the quadrotor rotational motion. Subsequently, a generalized virtual image feature signal is introduced by organically combining the cable length and payload swing angles with the image feature, which is further exploited in the anti-swing control scheme design. The equilibrium point of the overall closed-loop system is proved to be asymptotically stable through Lyapunov techniques and LaSalle’s Invariance Theorem. Hardware experiments are conducted on a self-built aerial transportation platform to verify the proposed controller’s basic and functional performance in terms of rapid anti-swing and accurate target position and cable length tracking. Note to Practitioners—This paper is motivated by the requirement to improve the autonomy level and payload swing suppression ability of the aerial transportation system through visual servoing techniques. By installing onboard monocular camera and the cable length adjustment mechanism, the application scope of the aerial transportation system can be significantly expanded. However, due to the “double” underactuated characteristic, the visual features couple with both the quadrotor motion and the payload motion, hence, it is quite challenging to realize visual servoing control for cable-suspended aerial transportation systems with simultaneous payload swing suppression and quadrotor positioning. Accounting for the foregoing problems, this paper proposes an image-based visual servoing anti-swing control scheme. With the elaborately constructed generalized virtual image feature signal, the designed controller could improve the anti-swing ability with a completed theoretical analysis. Furthermore, two groups of hardware experiments are conducted to validate the effectiveness of the suggested control method. In future studies, we intend to design more effective control scheme for payload delivery issue with consideration of the visibility of the mobile platform.

Underactuated robot systems, due to their unique flexibility and economy, are widely used in modern industry and intelligent manufacturing. However, their underactuated nature and complex nonlinearity make the control problem challenging. In addition, most existing control methods for underactuated systems take the measurable actuated and unactuated states as an implicit premise and do not consider the unknown measurement sensitivity of sensors. Unfortunately, due to space/costs or manufacturing technology limitations in practical underactuated robot systems, it is difficult to measure unactuated states and achieve the ideal working mode of sensors. To this end, an adaptive fuzzy control scheme is proposed for a class of uncertain underactuated robot systems without unactuated state sensors, which stabilizes the system even with actuated state measurement errors. Specifically, the dynamics of underactuated systems are reconstructed into a nontriangular normal form, and the backstepping design is completed by using the boundedness of fuzzy basis functions. At the same time, the explosion of complexity is avoided by using dynamic surface control technology. Moreover, the proposed update law availably compensates parameter/structure uncertainties for underactuated robot systems. The asymptotic stability of the closed-loop system is proved by incorporating Lyapunov candidates with sensitivity information. Finally, the proposed control scheme is applied to a tower crane system, whose effectiveness is verified by hardware experiments.Note to Practitioners—This paper is motivated by the common sensor problems in uncertain underactuated robot systems control. Some states in underactuated systems are called unactuated states because they have no direct corresponding control inputs. Such states bring significant challenges to controllers design of underactuated systems. Furthermore, most existing control methods require all states to be measurable and ignore the measurement uncertainty of sensors. However, in many practical situations, it is difficult to install unactuated state sensors, and there are inevitable measurement errors in actuated state sensors. These factors make the feedback controllers developed for underactuated systems difficult to practically apply. To address these issues, this paper presents a control scheme that does not require unactuated state measurements and model information, which can still stabilize underactuated systems to the origin even in the presence of actuated state measurement errors. The stability is rigorously proven theoretically and the experimental results obtained on a self-built tower crane platform demonstrate the feasibility and effectiveness of the proposed control scheme. In future efforts, we intend to apply the proposed control scheme to practical industrial underactuated robot systems.

The control problem of underactuated mechatronic systems is one of the key representatives of complex nonlinear dynamical systems. Starting from the dynamical structures of underactuated systems is usually one of the most direct and effective ways to design controllers. However, controllers developed for specific dynamic models are often difficult to be directly generalized to other underactuated systems. Moreover, due to the lack of control inputs, designing robust controllers for unmatched disturbances (acting on unactuated states) remains a challenging problem. Therefore, based on the Euler-Lagrange dynamics of multi-input-multi-output (MIMO) underactuated systems, this paper gives four coordinate transformations according to different configurations of the inertia matrix, whichextendsthe Olfati transformation to some extent and finallyunifiesunderactuated systems into normal forms. A sliding manifold and an adaptive neural network sliding mode controller are developed with the derived normal forms, which improves transient performance andavoidsthe chattering problem in traditional sliding mode controllers by combining an estimation error-driven adaptive law, a high-order sliding-mode differentiator, and the super-twisting algorithm. More importantly, the stability is guaranteed by Lyapunov techniques even in the presence ofbothpersistent matched disturbances and asymptotically vanishing unmatched disturbances. Furthermore, the proposed control strategy is applied to overhead cranes and tower cranes, whose superior control performance is verified by hardware experiments.

As a kind of soft actuator with inherent compliance, pneumatic artificial muscles (PAMs) have great application potential in robots. However, some challenging issues, such as high nonlinearities, sensor noises, and external disturbances, inevitably bring enormous difficulties to the accurate control of PAM-driven robots. To this end, this paper proposes an adaptive output feedback fuzzy switching control method for switched-form PAM-driven parallel robot systems, utilizing admittance models to rebuild compliant trajectories. Specifically, based on the nonrecursive high-order sliding mode (HOSM) differentiators with fixed-time convergence, unmeasurable velocity signals can be reconstructed to eliminate the adverse effects of measurement noises, decreasing the time delay of feedback signals. Moreover, a soft switching strategy is designed to flexibly adjust the switching weights and intervals of fuzzy structures, maintaining smooth control commands. Further, by introducing a nonsingular terminal sliding manifold, tracking errors can rapidly converge to a small neighborhood around the origins within a finite time, and all closed-loop variables are proved to be bounded through the Lyapunov stability theory. Finally, several groups of experiments are carried out on a self-built PAM-driven parallel robot to verify the effectiveness of the suggested method.

Mechanical systems often face unpredictable surrounding situations in applications, which bring lots of intangible uncertainties into system operations. Further, some robot systems, especially, pneumatic artificial muscle (PAM)-driven robot systems, also have accumulative nonlinearities, such as rate-dependent hysteresis, creep, and periodic/regular time-varying parameters, increasing design difficulties of high-accuracy controllers. This paper develops a long short-term memory neural network (LSTM-NN)-enhanced adaptive controller for PAM-driven parallel robot systems with transient and steady-state performance constraints. Specifically, a continuous-time LSTM-NN structure is introduced to recover unknown lumped dynamics, improving the approximation ability of time-dependent terms with accumulative effects. Moreover, a new two-stage error transformation function is designed to flexibly adjust the desired transient and steady-state performance, facilitating better adaptation to task requirements. To our knowledge, this paper proposes the first solution of utilizing the LSTM-NN-based neuroadaptive method for soft actuator-driven robots to enhance tracking accuracy with transient/steady-state performance improvement. The detailed stability analysis and several groups of experimental results on the self-built platform are provided to verify the feasibility and versatility of the proposed method.

Designing intelligent game strategies for autonomous air combat has suffered from the vast exploration space, lengthy decision-making process, and sparse rewards. Some existing approaches adopt the hierarchical framework to improve the exploration efficiency. However, in these methods, agents in different layers are typically trained independently and operate at fixed frequencies, which limits their performance and hampers their ability to respond to highly dynamic combat situations. In view of this, we present PJOH-TED2, a partial-joint-optimization-based hierarchical (PJOH) learning framework with a time-event dual-driven (TED2) mechanism, for one-on-one beyond-visual-range (BVR) air combat. Specifically, the PJOH learning framework embeds the partial joint optimization mechanism into hierarchical reinforcement learning (HRL), thus improving the exploration efficiency dramatically while enhancing the integration across hierarchical levels. Moreover, the TED2 mechanism combines the advantages of event-driven and time-driven methods, which promote the dynamic response speed of agents as well as avoid redundant actions. In addition, we evaluated this work through a series of games against the state-of-the-art (SOTA) methods in a high-fidelity air combat simulation environment. The results empirically demonstrate that the proposed approach outperforms four SOTA methods with a win rate of at least 71%. Finally, this approach achieved the 1st place in learning methods in the intelligent air game algorithm challenge (IAGAC) by the Chinese Institute of Command and Control among 43 teams.

Polygonal collision avoidance (PCA) is short for the problem of collision avoidance between two polygons (i.e., polytopes in planar) that own their dynamic equations. This problem suffers the inherent difficulty in dealing with nonsmooth boundaries and recently optimization-defined metrics, such as signed distance field (SDF) and its variants, have been proposed as control barrier functions (CBFs) to tackle PCA problems. In contrast, we propose an optimization-free smooth CBF method in this article, which is computationally efficient and proved to be nonconservative. It is achieved by three main steps: a lower bound of SDF is expressed as a nested Boolean logic composition first, then its smooth approximation is established by applying the latest log-sum-exp method, after which a specified CBF-based safety filter is proposed to address this class of problems. To illustrate its wide applications, the optimization-free smooth CBF method is extended to solve distributed collision avoidance of two underactuated nonholonomic vehicles and drive an underactuated container crane to avoid a moving obstacle, respectively, for which numerical simulations are also performed.

Although knowledge transfer methods are developed for many-task optimization problems, they tend to utilize solutions from a single task for knowledge transfer. Indeed, there are usually multiple relevant source tasks with commonality. Multisource data fusion can capture complementary knowledge of distinct source tasks to better assist the optimization of target tasks. However, biases potentially flow with the interaction between tasks during multisource fusion, resulting in performance degeneration. Thus, how to select multiple relevant source tasks and perform multisource knowledge transfer is challenging. To address these issues, this article proposes a multisource knowledge fusion (MKF) method based on graph attention networks. In MKF, tasks are structured using a relational graph, in which each vertex represents a task and each directed edge from vertex u to v represents that u is a source task of v. Particularly, for each task, multiple source tasks are selected based on the distribution similarity and evolutionary performance. In the graph, local message is passed from source tasks to target tasks using graph attention networks, which automatically learn the adjacency weight of each directed edge and aggregate solutions from multiple source tasks to obtain fused representations for target tasks. These fused representations are adopted to generate new solutions through mutation. In this way, multisource knowledge is fused and transferred according to their importance to the target task. Integrating MKF into differential evolution, a new algorithm named MKF-DE is put forward. Experimental results on GECCO2020MaTOP and CEC2022MaTOP show that MKF-DE outperforms state-of-the-art algorithms on most instances.

In many real-world scenarios (e.g., product manufacturing), multiple heterogeneous robots cooperate to complete complex tasks with precedence constraints. In these heterogeneous multirobot systems, the multirobot task allocation problem is important and has attracted increasing attention. The problem usually involves multiple optimization objectives for decision making. However, existing approaches meet challenges on multi-objective problems with large-scale tasks and precedence constraints in terms of solution diversity and convergence. Therefore, this paper formulates a tri-objective model and proposes a cooperative ant colony system (CACS) to optimize three objectives, i.e., minimizing the makespan, average robot traveling time, and average task waiting time. In CACS, three ant colonies are created to simultaneously optimize the three objectives. To coordinate with the precedence constraints of the problem, solutions are encoded as a task-alliance sequence. A new solution construction method is developed to generate feasible solutions using dynamic heuristic information and two pheromone matrices. Particularly, one matrix deposits pheromone between tasks for task selection and the other between tasks and robots for alliance building. To further improve solution diversity and convergence, a fusion-based local search is adopted to generate high-quality solutions by combining information from multiple colonies. Thirty instances are constructed with different numbers of tasks and robots under complex precedence constrains. Experimental results show that CACS outperforms state-of-the-art methods in terms of the inverted generational distance and hypervolume metrics.

As a low-cost cargo delivery manner, cable-suspended aerial transportation system is highly regarded by researchers. However, existing works seldom consider the relative distance adjustment between the payload and the multirotor, which greatly limits the application scope, such as tunnel traversing or payload releasing. In addition, treating the hook and the payload as a single point mass while ignoring the hook effect results in an inaccurate description of the dynamic model. To address the aforementioned problems, the dynamic model of the variable-length cable-suspended aerial transportation system is established accurately through Lagrange's equation with consideration of the motion of the multirotor, the payload, and the hook. Subsequently, an adaptive control method is presented through energy-based analysis, and swing angle related fuzzy rules are established to dynamically adjust the control parameters, which can simultaneously achieve multirotor positioning, payload hoisting/lowering, and hook/payload swing suppression. Moreover, the cable length is constrained within a feasible range by an elaborately designed auxiliary control signal. Lyapunov techniques and LaSalle's invariance theorem are utilized to prove the asymptotic convergence of the closed-loop system. Finally, a series of simulations are conducted to verify the control performance of the designed method.

This article proposes a novel hierarchical motion planning strategy for multirotors, where the virtual goal (VG) oriented deep reinforcement learning (RL) and motion optimization are designed cooperatively to achieve efficient, flexible and smooth navigation in unknown environments. Specifically, the intelligent hierarchical motion planning is achieved in a three-step design. First, the dynamic VG generation algorithm is proposed considering the perception range of onboard sensors and current velocity, which transforms the global navigation into a real-time point-to-VG planning, thereby guaranteeing efficient computation even in resource-limited multirotors. Second, instead of generating motion actions, the upper-layer deep RL is designed to make spatial-temporal decisions of VG online, which outputs time allocation and spatial distribution commands according to current observation. Third, based on upper-layer's decisions, local optimization and control are implemented accordingly. Different from existing solutions, high-performance planning is guaranteed by the online VG oriented intelligent decision making, where the data-driven learning and model-driven optimization are integrated to navigate the multirotors. Comparative experiments are carried out in both physical simulation and indoor environments, which demonstrate the satisfactory performance of the proposed motion planning strategy in terms of feasibility, efficiency, navigation smoothness, and flexibility.

With excellent maneuver performance and flexibility, quadrotor unmanned aerial vehicles (UAVs) are widely used in aerial transportation. However, the aerial transportation system with dual quadrotors exhibits high degrees of freedom, strong nonlinearities, and complex state couplings, which makes it more difficult to realize simultaneous quadrotor positioning and cargo swing suppression. Compared with the traditional description of cargo swing dynamics with four angles in the previous work, the spatial swing angle is introduced in a more intuitive way to reflect the swing dynamics of the cargo. On this basis, the dynamic model of the system is established according to Lagrange's equations. Then, a nonlinear adaptive controller is proposed, in which a dynamic compensation term is introduced to compensate for the lateral forces along the cables, and a spatial swing angle-related term is designed to enhance cargo swing damping. Meanwhile, considering the influence of unknown air resistance on quadrotors and cargo during transportation, an adaptive term is applied. Subsequently, Lyapunov techniques and LaSalle's invariance principle are used to prove the stability of the closed-loop system. Finally, based on the self-built general experimental platform, both indoor and outdoor experiments have been carried out to validate the practicability and effectiveness of the proposed method.

In a capacitated vehicle routing problem (CVRP), multiple vehicles are planned to travel for serving customers so as to reduce transportation costs in logistics. Taking each CVRP as a task, multiple CVRPs can form a multi-task optimization problem. Based on the similarity between tasks, knowledge transfer methods are developed to improve optimization performance by utilizing the search experience of related tasks. However, existing methods tend to use one task only for knowledge transfer. Indeed, in a target task, the different parts of customer distributions are similar to that of multiple related tasks. The information of multiple source tasks can be fused to assist the optimization of target tasks. Thus, this paper proposes a genetic algorithm with fragment-based knowledge transfer (FKT-GA), which fuses route fragments from multiple related tasks to assist the optimization of target tasks. In FKT-GA, multiple source tasks are selected for each target task based on distribution features that are invariant to rotation, shift, and scaling. Solutions of source tasks are aligned to target spaces for sampling route fragments, which are integrated to construct high-quality solutions for target tasks. In addition, mutation and crossover operators are developed to enhance solution diversity. Experimental results on fifteen 6-task instances show that FKT-GA outperforms state-of-the-art algorithms in terms of solution optimality. The proposed FKT can improve algorithm performance.

Salamander-like robots, renowned for their versatile locomotion, present unique challenges in the development of effective path-following controllers due to their distinctive movement patterns and complex body structures. Conventional path-following controllers, while effective for various bionic robots, struggle with the intricate modeling for salamander-like robots and often require laborious manual tuning. Conversely, learning-based methods offer promising alternatives but face issues such as reliance on environmental interactions, short-sighted prediction, and irrational design of state space and reward function. To overcome these limitations, this article proposes a diffusion model-based hierarchical control framework that treats path tracking as a sequence generation problem. The diffusion model's capability to model joint distributions of state, action, and reward sequences enables it to outperform other learning-based approaches in efficient data utilization, stable training, and long-horizon dependency modeling. Our framework integrates a high-level policy driven by guided diffusion with a low-level controller for parsing commands into executable movements via inverse kinematics, reducing the action space and improving learning efficiency. In addition, we design a more reasonable state space and reward function tailored to the path-following task, addressing shortcomings in prior learning-based controllers. Furthermore, we optimize the diffusion model (DM) by developing lightweight network architectures and incorporating advanced attention mechanisms, to ensure its practical deployment on physical robots with limited computational resources, without compromising performance. Extensive simulations and real-world experiments demonstrate the framework's effectiveness, efficiency, and robustness in diverse path-following tasks for salamander-like robots, marking a significant advancement in the control of biomimetic robots.

In dynamic time-linkage optimization, current decisions influence the future state of environments. To make good decisions that have a positive impact on future states, existing methods usually build a model to predict the future rewards of solutions for decision making. However, these prediction models present low accuracy since decision data are not enough to train such a complex model. To address this issue, this article proposes a contrastive-learning-based decision making (CLDM) method, which builds a contrastive model to learn the relationship between solutions but not absolute rewards and adopts a quick decision strategy to select solutions. In CLDM, a clustering-based time-linkage detection (CD) strategy is developed to measure the intensity of the time linkage, which determines whether to make decisions based on future rewards. To represent the relative relationship between solutions, a large number of contrastive samples are constructed using the limited historical decisions. A contrastive model is trained for solution comparison in terms of the combination of current fitness and future rewards. Candidate solutions are clustered into multiple groups to filter poor ones, and a few solutions are preserved to rank using the contrastive model. The winner is taken as the decision solution. Integrating CLDM into particle swarm optimization (PSO), a new algorithm named contrastive-learning-based PSO (CL-PSO) is put forward. Experimental results on multiple dynamic time-linkage optimization instances demonstrate that CL-PSO outperforms state-of-the-art algorithms in terms of solution quality. CL-PSO can also well solve the mobile robot path planning problem.

Collaborative double boom cranes (CDBCs) play a crucial role in modern industries, offering superior hoisting capabilities and adaptability. However, the intricate dynamic characteristics of CDBCs, combined with demanding working requirements, pose significant challenges for control safety and efficiency. The existing control methods for CDBCs primarily focus on two-dimensional space and lack theoretical guarantees for rapid error convergence, which limits working efficiency. Furthermore, safety concerns arise when collision-free reference trajectories are unavailable or incomplete during dynamic operations. To this end, this article proposes a novel fixed-time tracking control method with obstacle avoidance and prescribed performance for three-dimensional (3-D) CDBCs. As thefirstcollision-free tracking method for 3-D CDBCs, the proposed method stands as a noteworthy contribution aimed at improving safety, accuracy, and efficiency. By simultaneously considering pitch and rotation motions, the proposed method expands the working space and efficiency of 3-D CDBCs. Elaborately designed sliding surfaces ensure fixed-time convergence, thereby improving response speed. For safe complete trajectory tracking, the proposed method can limit transient tracking errors within a prescribed performance function, preventing collisions from unexpected errors. In scenarios with unavailable or incomplete safe reference trajectories, autonomous obstacle avoidance is achieved through potential function design, thereby enhancing operation safety. Additionally, a thorough closed-loop stability analysis is provided based on Lyapunov methods. Finally, experimental results on a built CDBC prototype offer validation for the tracking and obstacle avoidance performance of the proposed method under various working conditions.

The safety-critical control of underactuated mechanical systems (UMSs) with both collocated and noncollocated configuration constraints is considered in this article. Based on the popular safety filter (SF) method using high-order control barrier function-based quadratic programs (HOCBF-QPs), this article further overcomes the difficulties caused by the singularity points of time-varying constraints and the underactuation characteristic. Specifically, the time-varying problem is addressed by transforming it into an extended time-invariant one. Then, the existing high-order CBF (HOCBF) theory is applied to construct singularity-free HOCBFs for UMS. Next, a Lipschitz continuous SF is proposed to handle multiple constraints in a hierarchical manner. Finally, experiments are performed on a 3-degrees of freedom boom crane platform to validate the effectiveness.

In the context of tracking multiple targets on a novel mobile robot, it is essential to obtain the three-dimensional coordinates of specified targets based on tracking boxes. Most existing multi-target tracking algorithms neglect the inherent constraints of the novel mobile robot, such as insufficient computational power, dynamically complex working environments, and irregularly occluded targets. To address these limitations, we propose a robust tracking algorithm with occlusion resistance (hereinafter referred to as ROTrack). ROTrack compensates for the predictions of Kalman filter (KF) by incorporating Inertial Measurement Unit (IMU) information, enabling the tracker to achieve more accurate tracking in dynamic environments. Additionally, MobileSAM is employed to handle occlusion issues and obtain the correct three-dimensional coordinates of the targets. At the same time, a depth-triggered segmentation strategy is proposed to reduce computational resource consumption. The effect of ROTrack is demonstrated through alignment between IMU signals and Camera Motion Compensation (CMC) data in BoT-SORT. Real-world tracking tests validate the robustness and real-time capability of ROTrack.

Hysteresis has posed significant challenges to the modeling and control of flexible endoscopic robots, which impedes the advancement of automated endoscopic operation. Despite numerous hysteresis modeling approaches aimed at improving accuracy, there are still several unresolved issues, such as inappropriate model selection and non-ideal assumption of noise. Focusing on these challenges, a novel reinforcement active modeling (RAM) scheme is proposed in this paper. By incorporating reinforcement learning, this method augments an Extended Kalman Filter (EKF)-based active modeling strategy, which improves the insensitivity and generalization ability to non-Gaussian noise that is not introduced in training. Finally, a series of comparative experiments are conducted on the self-built flexible endoscopic robot to validate the improvement achieved by the proposed scheme. Compared with some widely-applied methods, the proposed scheme achieved at least 63.8% improvement in the root mean square error (RMSE) in modeling accuracy under Gaussian noise conditions, and at least 36.5% improvement in RMSE under Poisson noise conditions.

Nondestructive detection methods, based on vibrational spectroscopy, are vitally important in a wide range of applications including industrial chemistry, pharmacy and national defense. Recently, deep learning has been introduced into vibrational spectroscopy showing great potential. Different from images, text, etc. that offer large labeled data sets, vibrational spectroscopic data is very limited, which requires novel concepts beyond transfer and meta learning. To tackle this, we propose a task-enhanced augmentation network (TeaNet). The key component of TeaNet is a reconstruction module that inputs randomly masked spectra and outputs reconstructed samples that are similar to the original ones, but include additional variations learned from the domain. These augmented samples are used to train the classification model. The reconstruction and prediction parts are trained simultaneously, end-to-end with back-propagation. Results on both synthetic and real-world datasets verified the superiority of the proposed method. In the most difficult synthetic scenarios TeaNet outperformed CNN by 17%. We visualized and analysed the neuron responses of TeaNet and CNN, and found that TeaNet's ability to identify discriminant wavenumbers was excellent compared to CNN. Our approach is general and can be easily adapted to other domains, offering a solution to more accurate and interpretable few-shot learning.

Morphology analysis based on atomic force microscopy (AFM) imaging contributes to understanding the characteristics of specimens more deeply. The preliminary and crucial step of implementing morphology analysis is to precisely segment the target area from the complex background. In this study, an automated AFM image segmentation strategy based on a well-designed U-shaped neural network is proposed to achieve accurate and robust segmentation for AFM images of different samples, thus realizing morphology analysis in micro-nano scale. Specifically, the centralized information interaction strategy cooperated with a two-path attention module is introduced to realize efficient cross-scale information interaction, which can fundamentally avoid the negative effects induced by spatial interpolation. Besides, the global information flows are adopted to guide the global information extracted by atrous spatial pyramid pooling to each level of the top-down pathway, which ensures that the high-level semantic information is not diluted during the top-down transmission process, thus locating the target area more precisely. Moreover, an AFM image dataset is constructed to train the network, which will be available online for free to facilitate other data-based AFM research. The segmentation results demonstrate that the proposed strategy has better performance on multiple AFM images compared with traditional Otsu method, fully convolutional network and U-Net. The application of the proposed method is carried out to exhibit the effectiveness in automated morphology analysis.Note to Practitioners—Despite the growing demand of AFM-based morphology analysis in many fields, the automated analysis is still lacking limited by accuracy and robustness of AFM image segmentation. Since manual segmentation, sometimes tedious and time-consuming, heavily depends on the personal judgment, it is thus necessary to develop automated segmentation methods. Although traditional automated segmentation algorithms have good performance on certain types of images, they may be difficult to apply in different scenarios, especially for micro-nano images, due to the limited robustness. Therefore, this paper proposes an automated image segmentation algorithm based on an improved U-shaped neural network to achieve accurate morphology analysis for AFM images. The proposed automated morphology analysis workflow will be a practical tool to help reduce human workload and subjective errors, as well as enhancing the accuracy and robustness of the analysis process. In addition, the constructed AFM image dataset can greatly facilitate the research on data-based AFM image analysis of other practitioners. Moreover, practitioners can benefit from our algorithm to improve the accuracy and robustness of image segmentation in other practical applications.

With strong load capacity and high maneuverability of payload attitude regulation, dual rotary cranes (DRCs) are widely applied for transportation and assembly tasks in infrastructure construction. For DRCs, to achieve safe and accurate control of the payload position and attitude, it is necessary to enhance the motion synchronization of two cranes, under the premise of controlling more state variables with fewer control inputs based on nonlinear coupling dynamics; moreover, the finite-time convergence of positioning errors is also expected to be guaranteed for high efficiency. To this end, this paper proposes an assembly-oriented finite-time coordinated controllerwithoutany linearization to the nonlinear crane dynamics, which realizes accurate and stable regulation of the payload position and attitude through coordinated boom motions. To our knowledge, the proposed controller provides thefirstclosed-loop control solution to realize both horizontal and non-horizontal payload hoisting for DRCs based on practical assembly demands. Theoretically, through elaborate design of the synchronization error and coupling errors, the real-time information exchange between the two cranes is realized for thefirsttime, which enhances the boom motion synchronization while suppressing payload swings. Furthermore, by introducing continuous terminal sliding mode surfaces with a multi-layer nested structure, the finite-time convergence of the boom positioning errors and the synchronization error is ensured with chattering reduction. Additionally, rigorous closed-loop stability analysis is provided based on Lyapunov techniques and Barbalat’s Lemma. Finally, the effectiveness and robustness of the proposed controller are verified by hardware experimental results.Note to Practitioners—This paper is motivated by the coordinated motion control problem of dual rotary cranes (DRCs), which aims to achieve safe and accurate control of the payload position and attitude oriented on practical assembly demands. At present, most control methods for DRCs only realize horizontal payload transportation, which not only ignores the requirements of payload attitude regulation in assembly tasks, but also lacks the guarantee for boom motion coordination and the finite-time convergence of state variables. To address these issues, based on the nonlinear crane dynamicswithoutany linearization, this paper proposes an assembly-oriented finite-time coordinated controller for DRCs, which achieves precise and stable regulation of the payload position and attitude through coordinated boom motions, and simultaneously enhances the system rapidity by ensuring the finite-time convergence of boom positioning errors. Furthermore, the detailed controller design and stability analysis process is provided, and the effectiveness of the proposed method is verified by hardware experiments. In the future research, we will try to apply the proposed method to practical operations of DRCs for complex assembly tasks of large heavy objects.

Pneumatic artificial muscles (PAMs), as a kind of soft actuators, can overcome compliance limitations of traditional rigid actuators to improve the adaptability of robots. However, some inherent strong nonlinearities and time-varying properties of PAMs, e.g., complex hysteresis and creep, may lead to a lot of control problems. In addition, PAM-driven systems are also faced with input constraints (e.g., deadzones, saturations, and unidirectional inputs), unknown/unmodeled dynamics and external disturbances, which badly degrade the control performance and even cause accidents. Therefore, this paper proposes anewhysteresis compensation-based immersion and invariance (I&I) adaptive fuzzy control method for PAM-driven humanoid robot manipulators, which can approximate the unknown functions and estimate the unknown parameters. To our knowledge, this is thefirstmethod for PAM-driven systems that compensates for system nonlinearities (not onlycomplex hysteresis,but alsoinput deadzones) by utilizing thepriorinformation in inverse hysteresis models, andsimultaneouslyestimates the unknown functions and parameters by designing a fuzzy update law and a parameter update law based on I&I methodology, respectively, which increases thecontrol frequencyof systems and improves tracking performance during high-speed motions. Finally, we apply the proposed approach on a self-built PAM-driven humanoid robot manipulator to validate its effectiveness and robustness.Note to Practitioners—Faced with the practical requirements of robots that interact closely with humans, improving the adaptability and compliance of robots by utilizing soft actuators, such as PAMs, can satisfy current demands. Moreover, PAMs also have many expective characteristics (e.g., high power density, light material, low costs, clean power, etc.), which makes PAMs occupy an important status in the field of soft robotics. However, unknown parameters/structures, strong nonlinearities, and input constraints, may badly degrade the control performance of PAMs. Based on the above characteristics, this paper proposes anewhysteresis compensation-based adaptive fuzzy controller for PAM-driven humanoid robot manipulators, which realizesaccurate trackingcontrol during high-speed motions by using inverse hysteresis models to compensate for strong nonlinearities in PAMs, and a fuzzy update law and a parameter update law based on I&I methodology are utilized to estimate unknown parameters/structures. In addition, the proposed controller cansimultaneouslycompensate for input deadzones by utilizing the hysteresis information, which improves thecontrol frequencyof the manipulators, and can rapidly suppress tracking errors. Experimental results are provided to validate the effectiveness of the presented method. In the future, more effective compensation methods, such as rate-dependent hysteresis models, will further be carried out to compensate for system nonlinearities.

For underactuated robots working in complex environments, an important objective is to drive all variables (particularly for unactuated end-effectors) to move along the specific path and restrict positions/velocities to avoid obstacles, rather than using only point-to-point control. Unfortunately, most path planning methods are only suitable to fully actuated systems or depend on linearized models. The main motivations of our work are to directly fulfill motion constraints and achieve path following for both actuated and unactuated states (e.g., payload swing of cranes) when lacking effective control inputs. To this end, this article presents a new time-optimal trajectory planning-based motion control method for general underactuated robots. By constructing auxiliary signals (in Cartesian space) to express all actuated/unactuated variables (in joint space), their position/velocity constraints are converted into some convex/nonconvex inequalities related to a to-be-optimized path parameter and its derivatives. Then, an optimization algorithm is constructed to solve the available path parameter and derive a group of time-optimal trajectories for actuated states. As we know, this is the first study to ensure path following and necessary full-state constraints for actuated/unactuated states. Then, a tradeoff among path-constrained motions, time optimization, and state constraints is achieved together. This article takes the rotary crane as an example and provides detailed analysis of calculating desired trajectories based on the proposed planning frame, whose effectiveness is also verified through hardware experiments.

With the increasingly wide applications of underactuated systems, the necessary switching actions in complex multiple-mode tasks may induce overlarge errors, chattering, or even instability. In different working scenarios, there usually exist different plant parameters, dynamic characteristics, and external disturbances, which may further degrade operation performance. To this end, this article designs a learning-based adaptive fuzzy switching controller to compensate for uncertainties online in various modes and realize exponential convergence of actuated states. During multiple-mode operations, bothactuatedandunactuatedconstraints are guaranteed by constructing integral constraint terms as time-variant gains, which introduce control energy in advance, to drive all state variables to converge to their desired values,rather thandirect braking force that may destroy the transient performance ofunactuatedstates (e.g., residual payload swing induced by rapid braking in cranes). Further, when underactuated systems suffer from matched/mismatched disturbances, amodel-independentdisturbance observer is elaborately designed to improve anti-disturbance performance, ensure the boundedness of closed-loop signals, and restrict all variablesin every mode. Based on Lyapunov methods and the concept of average dwell time, the closed-loop stability of entire switched systems is theoretically analyzed and proven; then, the effectiveness of the proposed switching controllers is verified by hardware experiments.

Multiple autonomous underwater vehicles (AUVs) are popular for executing submarine missions, which involve multiple targets distributed in a large and complex underwater environment. The path planning of multiple AUVs is a significant and challenging problem, which determines the location of surface points for AUV launch and plans the paths of AUVs for target traveling. Most existing works model the problem as a single-objective static optimization problem. However, the target missions may change over time, and multiple optimization objectives are usually expected for decision making. Thus, this article models the problem as a dynamic multiobjective optimization problem and proposes a cooperative evolutionary computation algorithm to provide diverse and high-quality solutions for decision makers. In the proposed method, solutions are represented using a bilayer encode scheme, in which the first layer indicates the surface location points and the second layer represents the traveling sequences of target missions. Multiple populations for multiple objectives framework is adopted to efficiently solve the dynamic multiobjective AUV optimization problem. In addition, a recombination-based sampling strategy is developed to improve convergence by fusing the information of multiple populations. Once a change occurs, an incremental response strategy is adopted to generate high-quality solutions for population evolution. Based on the dataset of New Zealand bathymetry, six complex underwater scenarios are constructed with a size of 50 km × 50 km× 10 km and 400 target missions for tests. Experimental results show that the proposed method outperforms the state-of-the-art algorithms in terms of solution diversity and optimality.

As pneumatic artificial muscles (PAMs) are similar to biological muscles in structure and movement mechanisms, parallel robots actuated by PAMs have development prospects in rehabilitation and industry, with advantages such as compliance, high safety, strong bearing capacity, and satisfactory dynamic performance. However, the parameter uncertainties and model complexity related to inherent characteristics of parallel robots actuated by PAMs (e.g., time-varying, coupling, hysteresis, creep, and high nonlinearity), bring challenges to accurate dynamic modeling and controller design. Therefore, to achieve satisfactory tracking performance, this article presents an adaptive compensation tracking controller with error constraints for parallel robots actuated by PAMs. The proposed controller deals with parameter uncertainties by estimating system parameters to ensure accurate tracking, which is indicated as an effective solution for a combination of PAMs and parallel robots. Furthermore, using desired trajectory signals in the complicated regression matrix, the online computational burden is significantly reduced. Moreover, to improve operation safety further, an auxiliary term with a theoretical demonstration guarantees that the tracking errors are maintained within allowable ranges. Then, the closed-loop stability is demonstrated by Lyapunov techniques. As far as we know, it is the first time that the challenges of parameter uncertainties, computational burdens, and error constraints of parallel robots actuated by PAMs are simultaneously addressed, which has both theoretical significance and practical value. Finally, the hardware experiments are implemented under different scenarios, and the results indicate that the proposed method achieves satisfactory tracking performance.

Recently, it is becoming increasingly possible to apply aerial transportation systems to real-world applications. However, current research works on cable-suspended transportation systems present practical limitations due to the fixed-length cable. With the introduction of the cable adjustment mechanism, various complicated tasks, such as limited space crossing, offshore sample collection, and even landing the payload on a mobile platform, can be accomplished by actively changing the distance between the quadrotor and the payload. In order to complete the aforementioned tasks, a trajectory tracking control method is in urgent need for the variable-length-cable-suspended aerial transportation systems. To this end, an adaptive tracking control approach with the consideration of unknown resistance coefficients is designed in this article. Subsequently, Lyapunov techniques and Barbalat's Lemma are utilized to prove the convergence for the equilibrium point of the closed-loop system. Finally, hardware experiments are meticulously conducted based on a self-built experimental platform, which verify the satisfactory performance of the proposed method in antiswing aerial transportation and payload landing onto the mobile platform.

Cross-modality recognition has many important applications in science, law enforcement and entertainment. Popular methods to bridge the modality gap include reducing the distributional differences of representations of different modalities, learning indistinguishable representations or explicit modality transfer. The first two approaches suffer from the loss of discriminant information while removing the modality-specific variations. The third one heavily relies on the successful modality transfer, could face catastrophic performance drop when explicit modality transfers are not possible or difficult. To tackle this problem, we proposed a compact encoder-decoder neural module (cmUNet) to learn modality-agnostic representations while retaining identity-related information. This is achieved through cross-modality transformation and in-modality reconstruction, enhanced by an adversarial/perceptual loss which encourages indistinguishability of representations in the original sample space. For cross-modality matching, we propose MarrNet where cmUNet is connected to a standard feature extraction network which takes as inputs the modality-agnostic representations and outputs similarity scores for matching. We validated our method on five challenging tasks, namely Raman-infrared spectrum matching, cross-modality person re-identification and heterogeneous (photo-sketch, visible-near infrared and visible-thermal) face recognition, where MarrNet showed superior performance compared to state-of-the-art methods. Furthermore, it is observed that a cross-modality matching method could be biased to extract discriminant information from partial or even wrong regions, due to incompetence of dealing with modality gaps, which subsequently leads to poor generalization. We show that robustness to occlusions can be an indicator of whether a method can well bridge the modality gap. This, to our knowledge, has been largely neglected in the previous works. Our experiments demonstrated that MarrNet exhibited excellent robustness against disguises and occlusions, and outperformed existing methods with a large margin (>10%). The proposed cmUNet is a meta-approach and can be used as a building block for various applications.

In this article, a learning-based trajectory generation framework is proposed for quadrotors, which guarantees real-time, efficient, and practice-reliable navigation by online making human-like decisions via reinforcement learning (RL) and imitation learning (IL). Specifically, inspired by human driving behavior and the perception range of sensors, a real-time local planner is designed by combining learning and optimization techniques, where the smooth and flexible trajectories are online planned efficiently in the observable area. In particular, the key problems in the framework, temporal optimality (time allocation), and spatial optimality (trajectory distribution) are solved by designing an RL policy, which provides human-like commands in real-time (e.g., slower or faster) to achieve better navigation, instead of generating traditional low-level motions. In this manner, real-time trajectories are calculated using convex optimization according to the efficient and accurate decisions of the RL policy. In addition, to improve generalization performance and to accelerate the training, an expert policy and IL are employed in the framework. Compared with existing works, the kernel contribution is to design a real-time practice-oriented intelligent trajectory generation framework for quadrotors, where human-like decision-making and model-based optimization are integrated to plan high-quality trajectories. The results of comparative experiments in known and unknown environments illustrate the superior performance of the proposed trajectory generation strategy in terms of efficiency, smoothness, and flexibility.

With the wide applications of underactuated robotic systems, more complex tasks and higher safety demands are put forward. However, it is still an open issue to utilize "fewer" control inputs to satisfy control accuracy and transient performance with theoretical and practical guarantee, especially for unactuated variables. To this end, for underactuated robotic systems, this article designs an adaptive tracking controller to realize exponential convergence results, rather than only asymptotic stability or boundedness; meanwhile, unactuated states exponentially converge to a small enough bound, which is adjustable by control gains. The maximum motion ranges and convergence speed of all variables both exhibit satisfactory performance with higher safety and efficiency. Here, a data-driven concurrent learning (CL) method is proposed to compensate for unknown dynamics/disturbances and improve the estimate accuracy of parameters/weights, without the need for persistency of excitation or linear parametrization (LP) conditions. Then, a disturbance judgment mechanism is utilized to eliminate the detrimental impacts of external disturbances. As far as we know, for general underactuated systems with uncertainties/disturbances, it is the first time to theoretically and practically ensure transient performance and exponential convergence speed for unactuated states, and simultaneously obtain the exponential tracking result of actuated motions. Both theoretical analysis and hardware experiment results illustrate the effectiveness of the designed controller.

In this article, a unified motion modeling approach for the 3-D snake robot is proposed, which enables motion prediction of all kinds of gaits generated by the backbone curve method on the ground. More specifically, the motion of the snake robot is novelly decomposed into two components, namely, the curve component and the shift component, which are explicitly related to the backbone curve's parameters and control's input. Considering the actual behavior of snake robots, a nonslip assumption is made to facilitate the modeling approach. Based on that, the ground-contacting points of the robot's links during shift control are conveniently analyzed, which helps to determine the moving direction of the curve components. Finally, with ground contacting points and backbone curve parameters determined, the characteristics of the two components, as well as the motion model, are successfully obtained. Utilizing this modeling approach, the widely used gaits, such as sidewinding, crawler, and S-pedal, are successfully modeled and then carefully analyzed to predict the movement of the snake robot with arbitrary given control input. Three groups of experiments are conducted, with the collected results showing the satisfactory accuracy of the obtained models. Compared with existing methods, the proposed modeling approach achieves a much more precise prediction, both in the direction and magnitude of snake robot motions.

Pneumatic artificial muscle (PAM) actuators exhibit practical compliance and great payload-to-weight ratios when driving robotic exoskeletons. However, filling with highly compressed gas makes PAMs susceptible to sensor noises, which may degrade the state response and increase control efforts. In addition, most of the existing optimal controllers require linearized operations or complex network calculations. To this end, a supervised learning control method with preassigned-time performance is studied, which achieves satisfactory motion control of the compliant PAM robots. In particular, the utilized dynamic observer with time-varying gains significantly reduces the effect of observation noises, and enhances the state convergence speed by combining with the preassigned-time constraints. Simultaneously, the improved supervised learning algorithm further optimizes input air consumption, which only involves the iterative adjustment of network weights. In contrast to the literature, this article presents a new solution to minimize energy consumption of the compliant PAM robots, while ensuring that the output states converge within the preassigned time, independent of parameter design. Rigorous stability analysis is provided and several experiments validate the tracking efficacy of the proposed method.

When lifting and transporting large payloads in the marine environment, the dual ship-mounted crane system plays a very important role for cargos transportation, which exhibits strong load capacity and high flexibility. However, apart from the nonlinearity and underactuation characteristic, some unknown or uncertain unmatched wave disturbances may also cause positioning errors, which may induce various risks during the transportation process; besides, lots of existing methods ignore a part of the cooperative crane motions, and the control issue of dual ship-mounted crane system with five degrees of freedoms (5 DOF) is still open. In terms of the aforementioned problems, an adaptive dynamic programming (ADP)-based optimal learning sliding mode controller is proposed in this paper. Specifically, under the frame of adaptive dynamic programming, the Hamilton-Jacobi-Bellman (HJB) equation can be addressed. Then, based on the gradient attenuation algorithm, critic neural networks (NNs) are trained depending on the designed updating law and the approximate optimal learning controller can be obtained. Lyapunov techniques and Lasalle’s invariance principle are used to guarantee asymptotic stability of the dual ship-mounted cranes system. Finally, a series of simulation results are depicted to show the effectiveness of the proposed optimal learning sliding mode controller. Note to Practitioners—In this paper, the control problem of a 5 DOF dual ship-mounted cranes system with unmatched wave disturbance is studied. Due to the complex nonlinear characteristics of the dual ship-mounted cranes and the need to consider the cooperative lifting and wave disturbances, the operation of the dual ship-mounted cranes are very challenging. Moreover, it brings more difficulties to the design of this kind of controller due to its nonlinear underactuated property. Existing control methods for dual ship-mounted cranes are based on linearized or oversimplified crane models, or require accurate model. To solve these kinds of problems, this paper proposes a new control approach for dual ship-mounted cranes suffering from unmatched wave disturbances to achieve satisfactory performance. The stability analysis of the closed-loop systems equilibrium point is implemented by Lyapunov techniques, implying that the accurate positioning and fast payload swings suppression against unmatched wave disturbances are achieved concurrently. In the future studies, we will apply the proposed control method to industrial dual ship-mounted cranes systems to improve their working safety and efficiency.

This article proposes a novel asymptotic robust control approach for rotorcraft unmanned aerial vehicles (UAVs), which can effectively eliminate the impact of external disturbances and the model uncertainties. Different from existing works, the proposed method alleviates the assumption that disturbances should have no variations in the existing observers for uncertainties. In addition, the equilibrium point of the entire observer-controller system is asymptotically stable without the assumption of the boundness of the outer-loop signals or the time-scale separation assumption. Specifically, two observer-based estimators are designed to estimate the model uncertainty and the external disturbance for the force and torque, respectively. On this basis, a nonlinear hierarchical tracking controller is then proposed with the feedforward compensated disturbance term. Despite the nonlinear coupled dynamics and the disturbances, a generic framework for the stability analysis is proposed to yield the asymptotic stability of the equilibrium point of the entire controller-observer system. Comparative experiments are conducted to show the superior performance of the proposed approach in terms of higher tracking accuracy and stronger robustness. Note to Practitioners—Most of the existing observer-based control approaches can only govern the rotorcraft closed-loop system to be ultimately uniformly bounded. The highly coupled dynamics and mismatched uncertainties in practice make the effective asymptotic robust control of rotorcrafts very challenging. A novel robust control approach for rotorcraft UAVs is proposed to yield the asymptotic stability of the equilibrium point despite the nonlinear coupled dynamics and the disturbances. The key insight of this work to guarantee the asymptotic stability of the system is that the nominal signals (i.e., the output of the nominal auxiliary dynamics) are fed back to the controller. In addition, the attitude error signal is proved to be exponentially convergent, which can further help prove the asymptotic stability of the entire controller-observer system. Comparative experiments are conducted to show the applicability of the proposed approach.

This article presents a novel neural network-based hybrid mode-switching control strategy, which successfully stabilizes the flapping wing aerial vehicle (FWAV) to the desired 3-D position. First, a novel description for the dynamics, resolved in the proposed vertical frame, is proposed to facilitate further position loop controller design. Then, a radial base function neural network (RBFNN)-based adaptive control strategy is proposed, which employs a switching strategy to keep the system away from dangerous flight conditions and achieve efficient flight. The learning process of the neural network pauses, resumes, or alternates its update strategy when switching between different modes. Moreover, saturation functions and barrier Lyapunov functions (BLFs) are introduced to constrain the lateral velocity within proper ranges. The closed-loop system is theoretically guaranteed to be semiglobally uniformly ultimately bounded with arbitrarily small bound, based on Lyapunov techniques and hybrid system analysis. Finally, experimental results demonstrate the excellent reliability and efficiency of the proposed controller. Compared to existing works, the innovations are the put forward of the vertical frame and the cooperative switching learning and control strategies.

Dynamic multiobjective optimization poses great challenges to evolutionary algorithms due to the change of optimal solutions or Pareto front with time. Learning-based methods are popular to extract the changing pattern of optimal solutions for predicting new solutions. They tend to use all variables as features (i.e., inputs) to build prediction models. However, there are usually some irrelevant and redundant variables, which increase training difficulty and decrease prediction accuracy. This article proposes a new interaction-based prediction (IP) method, which captures the correlation of variables with prediction targets and selects the most relevant variables to build prediction models using neural networks. In particular, the interaction between variables is detected to remove redundant variables. In addition, a correction procedure is developed to further improve predicted solutions according to the prediction error in past environments. The predicted solutions are used to update the population according to a specifically designed update strategy. Integrating the IP method into the framework of multiobjective evolutionary algorithm based on decomposition (MOEA/D), a new algorithm named IP-DMOEA is put forward. Experimental results on a typical dynamic multiobjective test suite demonstrate the better performance of the proposed IP-DMOEA than state-of-the-art algorithms in terms of convergence speed and solution quality. The proposed IP-DMOEA is also successfully applied to the multirobot task scheduling problem.

In recent years, with the rapid development of marine engineering, ship-mounted crane control for transporting payloads in the water has attracted more attention. Compared with the case of transporting payloads above water, ship-mounted cranes with underwater payloads are more difficult to control. On the one hand, the underwater payload is directly affected by the hydrodynamic force, and the dynamics of ship-mounted cranes is much more complex, nonlinear, and coupled; on the other hand, the unactuated underwater payload swing is quite sensitive to external disturbances; thus, the harsh marine environment will bring great challenges to the antiswing control of underwater payloads. To address the above issues, this article puts forward a coupling characteristic indicator(CCI)-based nonlinear control method to realize accurate positioning and swing suppression for ship-mounted cranes hoisting payloads in the water, which not only simultaneously suppresses actuated boom overshoots and constrainsunactuatedpayload swing, but also indicates whether the coupling terms are beneficial or harmful to make full use of them to improve transient control performance. Rigorous theoretical derivation proves the closed-loop stability. To the best of our knowledge, this is thefirstsolution to handle state constraints and utilizing the coupling characteristics of ship-mounted cranes for transferring payloads in the water. Finally, the proposed controller is applied to a self-made hardware platform, and the experimental results show that the designed method achieves satisfactory control performance.

With the increasing demands of high-precision hoisting, a growing number of to-be-hoisted large-scale heavy payloads not only need accurate positioning transportation, but alsorequire specific attitude adjustments, which mostly relies on dual boom cranes (DBCs) in practice due to their powerful capability. To achieve effective non-horizontal payload hoisting, the two booms of DBCs should reach different positions while guaranteeing safety, high efficiency, and energy conservation, which makes coordinated boom motions particularly difficult. To this end, an optimal collaborative motion planning method for DBCs is proposed in this paper without any linearization, which realizes fast, accurate, and energy-saving payload transportation with swing suppression. To the best of our knowledge, the proposed method provides the first solution for DBCs to transport payloads to the desired non-horizontal attitudes, and simultaneously achieves comprehensive optimization of multiple performance indicators, including transportation time, energy consumption, etc., on the premise of safety. On the theoretical side, novel collaborative auxiliary signal construction and parametric design guarantee the coordination of boom motions, and the solving process of optimal trajectories is simplified through elaborate convex optimization problem reformulation and analysis. At last, the effectiveness and adaptability of the proposed method are verified by hardware experiments under different working requirements.

Due to limited workspace and safety requirements for practical underactuated mechanical systems, it is necessary to restrict all to-be-controlled variables and their velocities within preset ranges, avoid collisions/overshoots, and improve braking performance. However, due to fewer available control inputs, it is quite challenging to ensure error elimination and full-state constraints for both actuated/unactuated variables, including displacements/angles and their derivatives (i.e., velocity signals) together. To handle the above issues, this article designs a new adaptive full-state constraint controller for a class of uncertain multi-input-multi-output (MIMO) underactuated systems. First, different output constraint-related auxiliary functions are constructed in the Lyapunov function candidate to generate nonlinear displacement-/angle-limited terms to control all state variables. Then, this article handles velocity constraints in a new manner, where the elaborately designed velocity constraint-related terms are directly introduced into the presented controller (instead of the Lyapunov function candidate), and strict theoretical analysis is provided by utilizing reduction to absurdity. Hence, both actuated and unactuated velocity constraints are ensured to further improve transient performance. In addition, the impact of model uncertainties is addressed online to realize accurate positioning control for all state variables. Compared with current studies of underactuated systems, this article presents the first adaptive controller to address output and velocity constraints for actuated and unactuated variables together; moreover, their asymptotic convergence is proven by strict stability analysis, which is important both theoretically and practically. In the end, the feasibility and robustness of the proposed controller are verified by hardware experiments.

Cooperative heterogeneous multirobot systems have attracted increasing attention in recent years. They use multiple heterogeneous robots to execute complex tasks in a coordinated way. The allocation of heterogeneous robots to cooperative tasks is a significant and challenging optimization problem. However, little work has gone into scheduling large-scale cooperative tasks with precedence constraints and multiple conflicting optimization objectives. Existing methods are insufficient to address the issue. We propose a multiobjective model and develop strength learning particle swarm optimization (SLPSO) to optimize multiple objectives. In this article, the problem is converted into a two-step problem of task permutation construction and robot subset selection. In order to coordinate with the time-extended property of the problem, SLPSO utilizes a hybrid encode scheme: an element-based representation for task permutations and a binary representation for robot coalitions. A strength learning strategy with heuristic information guides particles to enhance their best-performing objectives for improving swarm convergence. In addition, an estimation-based local search is developed to improve spare solutions for enhancing swarm diversity, which determines the search direction by estimating fitness improvements. Experimental results on thirty problem instances are elaborated to demonstrate that the proposed SLPSO significantly outperforms the state-of-the-art algorithms in terms of inverted generational distance and hypervolume metrics. The proposed SLPSO can obtain a set of high-quality and diversified solutions.

Featured with high power density, excellent flexibility, shock absorption capacity, etc., pneumatic muscles (PMs) promote the development of exoskeleton robots and rehabilitation equipment. However, the complex nonlinearities of PMs limit efficiency optimization in closed-loop control, while the force-displacement coupling, soft materials, deficient workspace, etc., make it more difficult to simultaneously increase motion speeds and ensure the safety of multiple PM-actuated (PMA) robots. Although force sensors can currently be replaced by applying state estimation techniques, the amplification effects of measurement noises still compromise control accuracy and stability in practice. To this end, this article proposes a reinforcement learning-based robust motion control method with the prescribed performance, which achieves efficient and satisfactory tracking control for PMA robotic arms. In particular, by elaborately incorporating an integral term, a robust generalized proportional integral observer is used to eliminate measurement noises. Meanwhile, by using an actor–critic network to optimize control performance, an error-transformation-based continuous controller is designed to guarantee the uniformly ultimately boundedness of tracking errors. Compared with most existing methods, this article provides the first solution to restrict the entire transient and steady-state performance of PMA robotic arms, improve the noise suppression capability, and optimize the control efficiency simultaneously. Finally, complete stability analysis based on Lyapunov techniques is provided, and several groups of hardware experiments demonstrate the practicability and robustness of the proposed method.

The robotic flexible endoscope is developed rapidly in the field of surgery robots due to its high flexibility and safety. However, some inherent features, e.g., high nonlinearity, material creep, complex dynamic hysteresis behaviors, and the unknown coupling effects between bending and twisting motions, can lead to the significant degradation on three-dimensional (3-D) positioning performance of the endoscope. Aiming at these challenges, this paper built a practical multi-motion hysteresis phenomenon model for the bending and twisting motions of the robotic flexible endoscope with consideration of the coupling effects. Then, the time-optimal synchronous terminal motion planner is first proposed for the 3-D motions of the robotic endoscope to decouple the coupling effects in an intuitive separate control scheme. Finally, a series of hardware experiments are conducted on a robotic flexible ureteroscope platform. The accuracy of the proposed model and the trajectory-planning-based decoupling strategy is comprehensively validated. Particularly, the experimental results with the proposed trajectory planner show the satisfactory performance of vibration suppression and over-shoot suppression.

We study stochastic decentralized optimization for the problem of training machine learning models with large-scale distributed data. We extend the widely used EXTRA and DIGing methods with variance reduction (VR), and propose two methods: VR-EXTRA and VR-DIGing. The proposed VR-EXTRA requires the time of $O((\kappa_s+n)\log\frac{1}{\epsilon})$ stochastic gradient evaluations and $O((\kappa_b+\kappa_c)\log\frac{1}{\epsilon})$ communication rounds to reach precision $\epsilon$, which are the best complexities among the non-accelerated gradient-type methods, where $\kappa_s$ and $\kappa_b$ are the stochastic condition number and batch condition number for strongly convex and smooth problems, respectively, $\kappa_c$ is the condition number of the communication network, and $n$ is the sample size on each distributed node. The proposed VR-DIGing has a little higher communication cost of $O((\kappa_b+\kappa_c^2)\log\frac{1}{\epsilon})$. Our stochastic gradient computation complexities are the same as the ones of single-machine VR methods, such as SAG, SAGA, and SVRG, and our communication complexities keep the same as those of EXTRA and DIGing, respectively. To further speed up the convergence, we also propose the accelerated VR-EXTRA and VR-DIGing with both the optimal $O((\sqrt{n\kappa_s}+n)\log\frac{1}{\epsilon})$ stochastic gradient computation complexity and $O(\sqrt{\kappa_b\kappa_c}\log\frac{1}{\epsilon})$ communication complexity. Our stochastic gradient computation complexity is also the same as the ones of single-machine accelerated VR methods, such as Katyusha, and our communication complexity keeps the same as those of accelerated full batch decentralized methods, such as MSDA. To the best of our knowledge, our accelerated methods are the first to achieve both the optimal stochastic gradient computation complexity and communication complexity in the class of gradient-type methods.

For pose stabilization task of nonholonomic mobile robots, this article proposes a novel integrated interactive framework, bridging the gap between visual servoing and simultaneous localization and mapping (SLAM). The framework consists of two cooperative components, control module for servoing task and SLAM module for feedback signals estimation. In most visual servoing methods, feedback signals for the servoing controller are estimated by means of multiple-view geometry assuming the target scene being always within the camera field of view (FOV). To handle the challenge that the target scene gets out of view during servoing process, the desired image is associated with the initial map by a two-step strategy, and an incremental map is constructed to guarantee available feedback signals estimation. In addition, on the basis of the kinematic model of the mobile robot and velocities designed by the servo controller, the predicted pose is exploited to discard moving objects in the camera FOV, thus making the proposed framework effective in dynamic scenes. Experimental results operated in different scenes without prior information demonstrate the effectiveness of the proposed approach to handle the FOV problem and dynamic scenes.Note to Practitioners—Traditional visual servoing stabilization approaches usually require that the feature points in the target scene remain within the FOV of the camera for feedback signals calculation, which is often neglected. Motivated by the requirement of continuous feedback signals to the servo controller, the SLAM technique is introduced to relax the FOV constraint during the servoing process. A novel integrated interactive framework is proposed in this article to further increase the applicability of the servoing system in practice, in which the SLAM module is also redesigned for the flexibility in dynamic scenes. The SLAM module provides feedback signals for the servo controller; meanwhile, velocities designed by the servo controller are utilized for the prediction mechanism in the SLAM module to discard features on moving objects. Experiments validate the applicability of the proposed framework in different scenarios.

To solve the autonomous navigation problem in complex environments, an efficient motion planning approach is newly presented in this paper. Considering the challenges from large-scale, partially unknown complex environments, a three-layer motion planning framework is elaborately designed, including global path planning, local path optimization, and time-optimal velocity planning. Compared with existing approaches, the novelty of this work is twofold: 1) a novel heuristic-guided pruning strategy of motion primitives is proposed and fully integrated into the state lattice-based global path planner to further improve the computational efficiency of graph search, and 2) a new soft-constrained local path optimization approach is proposed, wherein the sparse-banded system structure of the underlying optimization problem is fully exploited to efficiently solve the problem. We validate the safety, smoothness, flexibility, and efficiency of our approach in various complex simulation scenarios and challenging real-world tasks. It is shown that the computational efficiency is improved by 66.21% in the global planning stage and the motion efficiency of the robot is improved by 22.87% compared with the recent quintic Bézier curve-based state space sampling approach. We name the proposed motion planning framework E$\mathbf {^{3}} $MoP, where the number 3 not only means our approach is a three-layer framework but also means the proposed approach is efficient in three stages. Note to Practitioners—This paper is motivated by the challenges of motion planning problems of mobile robots. A three-layer motion planning framework is proposed by combining global path planning, local path optimization, and time-optimal velocity planning. For mobile robot navigation applications in semi-structured environments, optimization-based local planners are recommended. Extensive simulation and experimental results show the effectiveness of the proposed motion planning framework. However, due to the non-convexity of the path optimization formulation, the proposed local planner may get stuck in local optima. In future research, we will concentrate on extending the proposed local path optimization approach with the theory of homology classes to maintain several homotopically distinct local paths and seek global optima.

Due to high biological adaptability and flexibility, pneumatic artificial muscle (PAM) systems are widely employed in exoskeleton robots to accomplish rehabilitation training with repetitive motions. However, some intrinsic characteristics of PAMs and inevitable practical factors, e.g., high nonlinearity, hysteresis, uncertain dynamics, and limited working space, may badly degrade tracking performance and safety. Hence, this paper designs a new learning-based motion controller for PAMs, to simultaneously compensate for model uncertainties, eliminate tracking errors, and satisfy preset motion constraints. Particularly, when PAMs suffer from periodically non-parametric uncertainties, the elaborately designed continuous update algorithm can repetitively learn them online to enhance tracking accuracy, without employing upper/lower bounds of unknown parts for controller design and gain selections. Meanwhile, some non-periodic uncertainties are handled by a robust term, whose value is only related to the initial states of PAMs, instead of exact upper bounds of unknown dynamics. From safety concerns, we introduce error-related saturation terms to limit initial amplitudes of control inputs within saturation constraints and avoid overlarge errors inducing overlarge acceleration. Meanwhile, the constraint-related auxiliary term is utilized to keep tracking errors within allowable ranges. To the best of our knowledge, this paper presents the first learning-based error-constrained controller for uncertain PAM-actuated exoskeleton robots, to realize high-precision tracking control and improve safety without additional gain conditions. Moreover, the asymptotic convergence of tracking errors is strictly proven by Lyapunov-based stability analysis. Finally, based on a self-built exoskeleton robot, the effectiveness of the proposed controller is verified by hardware experiments. Note to Practitioners—This work is motivated by the practical requirements of exoskeleton robots in rehabilitation training and exploration fields. Currently, PAM systems, as a kind of new flexible actuator equipment, are playing increasingly important roles in the development of exoskeleton robot control. However, uncertain (or time-varying) parameters/structures and highly nonlinear dynamics, such as creep and hysteresis, may badly increase the control difficulty of PAMs. Moreover, higher and higher tracking accuracy and safety requirements also induce urgently solved problems to practical PAM-actuated exoskeleton robots, e.g., smooth start, motion constraints, and rapid error elimination. To this end, this paper proposes a new learning-based adaptive controller, which realizes accurate tracking control for PAM-actuated exoskeleton robots by utilizing an elaborately designed repetitive learning algorithm and a robust term to handle periodic and non-periodic uncertainties, respectively. More importantly, the proposed controller simultaneously enhances transient performance of PAMs, including gradually improved tracking accuracy, effective constraints for startup acceleration and tracking errors. Additionally, it is not required to consider the upper bounds of unknown dynamics and additional gain selection conditions, which is theoretically and practically important for PAM systems. Some hardware experiments further verify the effectiveness and robustness of the suggested controller. In our future work, we intend to design more effective methods for PAMs with unmeasurable states and time-delay.

In the field of modern industrial engineering, many mechanical systems are underactuated, exhibiting strong nonlinear characteristics and high flexibility. However, the lack of control inputs brings about many difficulties for controller design and stability/convergence analysis., some unavoidable practical issues, e.g., plant uncertainties and actuator deadzones, make the control of underactuated systems even more challenging. Hence, with the aid of elaborately constructed finite-time convergent surfaces, this article provides the first solution to address the control problem for a class of multi-input-multi-output (MIMO) underactuated systems subject to plant uncertainties and actuator deadzones. Specifically, this article overcomes the main obstacle in sliding-mode surface analysis for MIMO underactuated systems, that is, by the presented analysis method, the asymptotic stability of the system equilibrium point is strictly proven based on the composite surfaces. In addition, the unknown parts of the actuated/unactuated dynamic equations and actuator deadzones can be simultaneously handled, which is important for real applications. Furthermore, we apply the proposed method to two kinds of typical underactuated systems, that is: 1) tower cranes and 2) double-pendulum cranes, and implement a series of hardware experiments to verify its effectiveness and robustness.

Recently, the pneumatic artificial muscle (PAM) that can reproduce natural muscle functionalities has become one of the core actuator mechanisms of intelligent interactive soft robots. Unfortunately, some inherent defects (e.g., unignorable nonlinearities, hysteresis, low shrinkage frequencies, etc.) have limited the application progress of humanoid PAM arm robots. Additionally, the input constraints (e.g., saturations, dead zones, unidirectional inputs, etc.), unexpected external disturbances, unidentifiable system parameters, and inevitable unmodeled dynamics are usually complicated, which cannot be easily eliminated through existing adaptive control methods. This article proposes an adaptive fuzzy-sliding mode control method for humanoid PAM arm robotswithoutany information of precise model structures and system parameters, which can suppress the unexpected effects of complicated unknown functions and achieve high performance tracking control,simultaneously. To the best of our knowledge, the proposed controller is thefirstmethod for the humanoid PAM arm robots that considers the nonlinear input constraints including unidirectional conditions, saturations, and dead zones,simultaneously. Next, all the input constraints, system parameter uncertainties, unmodeled dynamics, and external disturbances can be estimated adaptively by utilizing the proposed fuzzy update law. Particularly, a sliding mode control law is designed to compensate possible fuzzy approximation errors, and rigorous Lyapunov-based stability analysis is provided to ensure that the state errors can converge to zero withinfinitetime. Hardware experiments are carried out later tovalidate the effectiveness and robustness of the proposed method.

With large load capacity and flexible payload attitude adjustment capability, dual rotary cranes (DRCs) play crucial roles in infrastructure construction with heavy hoisting demands. However, as a kind of collaborative control systems, DRCs have complex collaborative constraints, and large-scale payloads cannot be simply regarded as mass points; moreover, due to the lack of control inputs, some state variables can only be indirectly controlled through complicated nonlinear coupling relationships, which make the controller design and corresponding analysis particularly difficult. Additionally, in practical applications of DRCs, many factors (such as boom motion overshoots, inaccurate gravity (torque) compensation, etc.) are prone to result in unexpected steady errors, large payload swing, and boom collisions, which may result in inaccurate assembly, and even lead to safety accidents. To this end, this article proposes an adaptive nonlinear proportional-integral-derivative-like collaborative control method for DRCs, which can realize accurate and efficient antiswing hoisting. To our knowledge, this is thefirstcontroller embedded with integral termswithoutany linearization during the controller design or stability analysis, which can effectively reduce steady errors, and keep boom motions within safety ranges by adaptive gravity (torque) compensation and elaborately designed constraint terms. Theoretically, the closed-loop stability and convergence are proven through strict mathematical analysis by using Lyapunov techniques and LaSalle’s invariance theorem. Finally, several groups of hardware experimental results are presented for effectiveness and robustness verification.

In the field of practical engineering, the performance of mechatronic systems is influenced by model uncertainties, velocity unavailability, input nonlinearities (e.g., actuator deadzones/faults), etc.Moreover, some complex nonlinear dynamics do not satisfy the linear parameterization condition. Hence, due to intractable approximation errors, some existing controllers may obtainonlyuniformly ultimately bounded results and require velocity feedback to accomplish online estimation. To overcome the aforementioned obstacles, this article designs a new output feedback controller to fulfill accurate trajectory tracking and obtain state estimates for a class of Euler–Lagrange (EL) mechatronic systems. Specifically, we first construct a group of auxiliary variables to accurately recover velocitieswithoutnumerical differential operations. Then, by employingonlythe available output information, unknown model knowledge and actuator deadzones/faults are simultaneously approximated online; more importantly, the asymptotic stability of the system equilibrium point is guaranteed by strict theoretical analysis. Another merit of the proposed controller is that the approximation errors are addressed in anew way, wherenodiscontinuous robust terms are required; hence, the chattering problem is effectively alleviated. To the best of our knowledge, for uncertain EL mechatronic systems with actuator deadzones/faults, this article proposes thefirstsolution to eliminate tracking errors and accurately recover unmeasurable states bycontinuouscontrol signals. The asymptotic convergence of closed-loop signals is proven based on Lyapunov methods, and the performance of the proposed controller is validated by hardware experiments.

Underactuated dual boom crane (DBC) systems exhibit complicated nonlinearity and strong coupling due to the lack of independent actuators. Moreover, plant parameters may change in different transportation tasks and are difficult to be measured accurately, which leads to inaccurate gravity (torque) compensation and further brings positioning errors. Hence, most existing controllers based on exact model knowledge cannot ensure satisfactory control performanceany longer. In order to handle the above issues, this article designs an adaptive sliding mode tracking controller for DBC systems based on the original complicated nonlinear dynamicswithoutany linearization/simplification operations, which is thefirstone to effectively achieve both anti-swing and trajectory tracking control in the presence of parametric uncertainties. Not only can the state variables converge to the proposed sliding surface within finite time but also payload swing angles can be completely eliminated; consequently, the working efficiency and operation safety are further guaranteed. The corresponding stability and convergence for the equilibrium point of the closed-loop system are proven by rigorous mathematical analysis based on the Lyapunov techniques and Barbalat’s lemma. Hardware experimental results demonstrate the effectiveness and robustness of the presented controller.

As a typical underactuated mechanical system, offshore ship-mounted cranes are widely used to carry out the tasks of transferring cargos from one ship to another in the marine environment. Different from land-fixed cranes as well as traditional harbor cranes, offshore ship-to-ship crane systems work in two noninertial (ship) frames, while the target locations of the cargos are also inevitably influenced by the movements of the target ship. Besides, various external disturbances, which are caused by persistent sea waves, sea winds, or currents, etc., bring much more challenges to the control task of offshore ship-to-ship crane systems. To properly address these practical problems, in this article, we propose an increased adaptive neural network (NN)-based anti-swing tracking control strategy for such coordinated offshore crane systems, with a ship-motion prediction algorithm suggested to generate the target trajectories for cargos, and an adaptive NN proposed to deal with complicated unknown wave-induced disturbances. Bounded tracking performance is also guaranteed through a complete Lyapunov-based stability analysis. To the best of our knowledge, without any simplification of the original nonlinear dynamics, this article provides a high-performance adaptive control approach to deal with the anti-interference tracking control problem for offshore ship-to-ship crane systems, which are subjected to trajectories uncertainties as well as unknown wave motions disturbances. Furthermore, comparative hardware experimental results are presented to demonstrate the efficiency of the proposed control method.

In this article, a virtual-goal-guided rapidly exploring random tree (RRT)-based visual servoing approach is proposed for nonholonomic mobile robots to simultaneously satisfy the field-of-view (FOV) constraint and the velocity constraints during the motion toward the desired pose. The presented approach contains two parts: 1) trajectory planning in the scaled Euclidean space and 2) trajectory tracking control. For the trajectory planning part, a new virtual-goal-guided RRT algorithm is designed to guarantee the FOV constraint and the velocity constraints by iteratively exploring the scaled Euclidean space in the presence of unknown image depth. Specifically, a virtual goal directly behind the desired pose is set to guide the tree to extend laterally into the area wherein the robot is easier to satisfy the FOV constraint. In addition, the lateral extension of the tree also helps decrease the lateral error of the robot as much as possible. Following each successful extension toward the virtual goal node, a greedy extension from the newly explored node to the desired pose is attempted using a polar stabilization controller, so that the planned trajectory can accurately arrive at the desired pose. Each newly explored edge in the scaled space is projected into the image space to check for the FOV limit. For the visual tracking part, the final searched trajectory in the scaled space is first transformed into image feature trajectories, which are then tracked by an image-based visual tracking controller. Experiments validate the effectiveness of the proposed approach.

Underactuated systems are widely applied in industry, construction, manufacturing, etc., and the complex working environment puts forward higher demands for safety and transient performance. Hence, it is necessary to consider how to simultaneously ensure actuated and unactuated motion constraints by fewer control inputs, especially when systems suffer from model uncertainties, unavailable velocities, etc. Unfortunately, it is still a significant challenge to overcome in real applications and theoretical analysis. Additionally, most existing studies merely consider the specific control objects and few general methods are applicable to a class of underactuated systems. To this end, we design a new adaptive output-feedback controller for a class of uncertain underactuated systems. Compared with existing methods only handling actuated constraints, an important merit of this article is that by introducing the elaborately designed coupling term composed of actuated and unactuated constraints together, all state variables are kept within the preset time-variant ranges and converge to their desired values. Furthermore, a new Lyapunov function candidate is utilized to provide a theoretical guarantee. As far as we know, without the need of exact model knowledge and velocity feedback, this article provides the first solution to achieve accurate motion control and state constraints for both actuated and unactuated variables, which is meaningful both theoretically and practically. Meanwhile, the asymptotic stability of the equilibrium point for the closed-loop system is proven by utilizing Lyapunov techniques and Barbalat’s lemma. For verification, the presented controller is applied to underactuated overhead and rotary cranes, respectively, together with detailed theoretical analysis and experimental validations.

Due to the head swinging and the body winding, the self-localization and path following for snake-like robots based on vision are very challenging. In this paper, a novel pantilt compensation method and curve parameter compensation path following controller are proposed to solve these problems, which can achieve high-precision path following. More specifically, to realize real-time positioning of the snakelike robot, a camera-mounted pan-tilt is equipped on the head of the snake-like robot, and the Apritag detection is used after the angle between the Apriltag plane and the camera plane being compensated. Then, due to the modeling approximation, the snake-like robot with a simplified controller usually deviates from the desired path, so a curve parameter compensation path following controller is proposed to eliminate the deviation and improve the following accuracy. Finally, the experiments show that with proposed methods, the snake-like robot can converge to the desired path stably and accurately.

Local planning is one of the key technologies for mobile robots to achieve full autonomy and has been widely investigated. To evaluate mobile robot local planning approaches in a unified and comprehensive way, a mobile robot local planning benchmark called MRPB 1.0 is newly proposed in this paper. The benchmark facilitates both motion planning researchers who want to compare the performance of a new local planner relative to many other state-of-the-art approaches as well as end users in the mobile robotics industry who want to select a local planner that performs best on some problems of interest. We elaborately design various simulation scenarios to challenge the applicability of local planners, including large-scale, partially unknown, and dynamic complex environments. Furthermore, three types of principled evaluation metrics are carefully designed to quantitatively evaluate the performance of local planners, wherein the safety, efficiency, and smoothness of motions are comprehensively considered. We present the application of the proposed benchmark in two popular open-source local planners to show the practicality of the benchmark. In addition, some insights and guidelines about the design and selection of local planners are also provided. The benchmark website [1] contains all data of the designed simulation scenarios, detailed descriptions of these scenarios, and example code.

In this paper, a novel navigation learning method in continuous action space among crowds based on relational graph is proposed which can be directly deployed on differential-drive mobile robots without any change. More specifically, in order to increase generalization ability in crowd sizes, Graph Convolutional Network (GCN) is at first adopted to extract the relationships between robot and pedestrians. Then the relation features are further utilized as the inputs of the pedestrian state prediction network, the actor network, and the critic network. To efficiently and safely learn the navigation policy, all networks are pretrained through imitating ORCA which is a state-of-the-art algorithm in crowd navigation, and then a model-based reinforcement learning (RL) method which combines the model prediction and the clipped advantage-weighted regression is proposed to finetune the networks. Finally, simulation experiments are performed and it’s verified that the proposed learning method performs significantly better than ORCA and the other state-of-the-art RL methods.

The aerial transportation system is a kind of nonlinear underactuated mechatronic system, which suspends the cargo beneath the rotorcraft’s fuselage and undertakes two basic missions of rotorcraft positioning and cargo swing suppression. Currently, most available methods need simplifications such as the near hovering hypothesis and dimension reduction operations, which may badly degrade the control performance when state variables get far away from the equilibrium point. In addition, integral terms, which can eliminate the steady errors, are not reflected in controller design and stability analysis processes. To tackle the aforementioned issues, this article provides a novel nonlinear control approach with an elaborately constructed integral term for aerial transportation systems, which not only achieves satisfactory antiswing and positioning performance but also reduces steady errors in practical flight. Meanwhile, the actuating constraint is taken into consideration so as to avoid saturation problems. Without linearization operations, we prove the closed-loop asymptotic stability of the equilibrium by the explicit Lyapunov-based analysis. As far as we know, this article is the first solution for controller design with the consideration of both steady errors elimination and actuating constraints. Finally, several groups of hardware experimental results are provided to validate the effectiveness of the presented control scheme.Note to Practitioners—This article is motivated by the requirement of effective control schemes for aerial transportation systems. The unexpected cargo swing motion may lead to safety accidents; thus, the dual objective of swing suppression and rotorcraft positioning is the focus of research. Nevertheless, with underactuated property, the cargo swing motion cannot be directly controlled. Up until now, at the cost of model accuracy, most existing methods utilize the simplified models in near hovering state or 2-D transverse plane to reduce the control difficulty. Accounting for the foregoing problems, this article presents a novel control scheme with improved antiswing and positioning performance. With an elaborately constructed integral term, the designed controller could improve the positioning accuracy of the rotorcraft with the guaranteed theoretical analysis. Moreover, to avoid the problem of actuator saturation, the control inputs are restricted in allowable ranges during the transportation process. All these aspects are verified by rigorous theoretical analysis and groups of hardware experiments in different conditions. In future studies, we will apply the suggested control scheme in practical applications.

Tower crane systems exhibit high nonlinearity and underactuation, making the control issue challenging. Most reported methods for tower crane systems utilize linearized models, and accurate plant parameters (e.g., cargo mass, jib moment inertia) and full state feedback are usually required; moreover, most existing works only consider a part of the crane motions, and the control issue of five degree-of-freedom (5-DOF) tower cranes (i.e., 2-DOF cargo swing, slew, hoisting, and translation) is still open. However, tower cranes are practically influenced by uncertainties and disturbances, which may make linearized models ineffective; additionally, exact values of plant parameters may be difficult to obtain, and velocity signals are usually not directly measurable in practice. To address the aforementioned problems, this article proposes an adaptive output feedback control method for 5-DOF varying-cable-length tower cranes. As far as we know, this article provides the first adaptive output feedback controller, designed and analyzed without linearizing the dynamic equations, which can simultaneously achieve cargo hoisting/lowering, jib slew, trolley translation, and swing suppression, by avoiding using velocity-related feedback signals. Resorting to an elaborately constructed virtual spring-mass system, the control objectives are satisfactorily achieved even without involving any velocity signals with theoretical/experimental guarantee. Moreover, by elaborately designing a new adaptive law, the exact values of unknown cargo masses can be estimated through online identification. We provide rigorous stability/convergence analysis for the closed-loop system. Hardware experiment results are included for effectiveness/robustness verification.

Rotorcrafts, with satisfactory maneuver performance and ability under complex terrains unreachable for ground robots, are playing important roles for goods transportation. In this article, we focus on the control of the cable-suspended transportation way due to its lower costs and more agility of the rotorcraft's rotational motion. Compared with traditional crane systems and single rotorcrafts without loads, the aerial transportation system presents “double” underactuated property, stronger system nonlinearity, and more complex dynamic coupling, which are huge challenges for control schemes design. Meanwhile, aerial transportation usually suffers from external disturbances and uncertainties presented with aerodynamic damping coefficients and rope length. Additionally, overshoots of the rotorcraft's position are potential threats for flight safety, especially in confined and complex environments. To address these problems, a novel adaptive control scheme is designed, which ensures effective rotorcraft positioning and payload swing suppression with restricted overshoot amplitudes. Asymptotic results are obtained with rigorous theoretical derivations provided by the Lyapunov-based stability analysis and LaSalle's invariance theorem. Real-time experiments are performed to validate the effectiveness of the proposed control scheme even in the presence of external disturbances. To the best of our knowledge, this is the first method designed for aerial transportation systems which achieves simultaneous rotorcraft positioning and swing suppression, together with insurance for overshoot restriction even in the presence of parametric uncertainties.

To meet real-world production demands, two or more cranes are used to cooperatively complete transportation tasks. Dual boom cranes (DBCs) are widely used in large construction sites owing to their strong load capacity. However, for typical nonlinear underactuated multi-crane systems, most of the existing control methods focus on the overhead crane systems with simpler dynamic characteristics and not enough attentions are paid to DBCs with stronger coupling and more complex dynamics. Based on the existing model, geometric constraints are analyzed to obtain the relationship between the higher-order derivatives of state variables, which can simplify the dynamic model of DBCs reasonably. The dynamic relationship between the boom pitch angles and the payload attitude is analyzed accurately. Moreover, the oscillation period of DBCs is obtained, and an extra insensitive input shaper is designed by rigorous mathematical derivation. Finally, simulation results verify that the input shaping control method has a satisfactory anti-swing ability and can realize accurate positioning.

Path following is a challenging task for legged robots. In this paper, we present a hierarchical control architecture for path following of a quadruped salamander-like robot, in which, the tracking problem is decomposed into two sub-tasks: high-level policy learning based on the framework of reinforcement learning (RL) and low-level traditional controller design. More specifically, the high-level policy is learned in a physics simulator with a low-level controller designed in advance. To improve the tracking accuracy and to eliminate static errors, a soft Actor-Critic algorithm with state integral compensation is proposed. Additionally, to enhance the generalization and transferability, a compact state representation, which only contains the information of the target path and the abstract action similar to front-back and left-right, is proposed. The proposed algorithm is trained offline in the simulation environment and tested on the self-developed real quadruped salamander-like robot for different path following tasks. Simulation and experiments results validate the satisfactory performance of the proposed method.

In this article, a novel real-time acceleration-continuous path-constrained trajectory planning algorithm is proposed with an appealing built-in tradeoff mechanism between the cruise motion and time-optimal motion. Different from existing approaches, the proposed approach smoothens time-optimal trajectories with bang-bang input structures to generate acceleration-continuous trajectories while preserving the completeness property. More importantly, a novel built-in tradeoff mechanism is proposed and embedded into the trajectory planning framework so that the proportion of the cruise motion and time-optimal motion can be flexibly adjusted by changing a user-specified functional parameter. Thus, the user can easily apply the trajectory planning algorithm for various tasks with different requirements on motion efficiency and cruise proportion. Moreover, it is shown that feasible trajectories are computed more quickly than optimal trajectories. Rigorous mathematical analysis and proofs are presented for those aforementioned theoretical results. Comparative simulations and experimental results on an omnidirectional wheeled mobile robot demonstrate that flexible tunings between the cruise and time-optimal motions can be achieved in a higher computational efficiency manner by the proposed algorithm. Note to Practitioners-This article is motivated by the time-optimal and smooth motion planning problem for mobile robots along given paths. Existing approaches generally use the piecewise polynomial interpolations to smoothen and adjust feasible trajectories. This article proposes a novel path-constrained trajectory planning approach, which preserves properties of completeness and a high-efficient tradeoff mechanism between the optimal and cruise motions when achieving a globally optimal and acceleration-continuous trajectory. Comparative experimental results with other methods show the effectiveness of the proposed approach. In future research, we will attempt to integrate the proposed approach with typical path planning methods to achieve a complete and high-efficient motion planning framework.

As a class of underactuated systems, cooperative dual rotary crane systems (DRCSs) are widely used to complete the task of large payload transportation in complex environments, since the working capacity of single cranes is quite limited. However, the control issues of DRCS fail to receive enough attention at present. Compared with single cranes, DRCSs contain more state variables, geometric constraints, and coupling relationships. Therefore, the complex kinematic and dynamic characteristics make controller design/stability analysis very challenging for DRCS. In order to solve these problems, based on the dynamic model of DRCS established by Lagrange's method, an output feedback control method with consideration for actuator constraints is designed to realize accurate dual boom positioning and rapid elimination of payload swings. The stability of the equilibrium point for the closed-loop system is analyzed by using Lyapunov techniques and LaSalle's invariance principle. To the best of our knowledge, this article yields the first solution for effective control of DRCS, which needs no velocity feedback, respects the actuator constraints, and is designed and analyzed without linearizing the complicated nonlinear dynamic equations. Finally, a series of hardware experiments on a self-built experimental platform is carried out to illustrate the effectiveness of the proposed controller.

Pneumatic artificial muscle (PAM) systems are a kind of tube-like actuators, which can act roughly like human muscles by performing contractile or extensional motions actuated by pressurized air. At present, it is still an open and challenging issue to tackle positioning and tracking control problems of PAM systems, due to inherent characteristics, e.g., unidirectional inputs, high nonlinearities, hysteresis, time-varying characteristics, etc. In this paper, a new adaptive control method is proposed for PAM systems, which achieves satisfactory tracking performance. To this end, an update law is designed to estimate unknown system parameters online. Also, some control input transforming operations are applied to address unidirectional constraints (i.e., control inputs of PAM systems should always be positive). As far as we know, compared with most of the existing control methods, this paper gives the first continuous control solution for PAM systems that can simultaneously compensate parametric uncertainties, reject external disturbances, and meet unidirectional constraints. Without linearizing the nonlinear dynamics, the closed-loop system is theoretically proven to be asymptotically stable at the equilibrium point with the stability analysis. In addition, a series of hardware experiments are implemented on a self-built hardware platform, indicating that the proposed method achieves satisfactory tracking control and exhibits robustness against parametric uncertainties and disturbances.

This article proposes a novel adaptive image-based output feedback visual servoing approach to control a multirotor to the desired pose by using a minimum onboard sensor suite, which consists of an inertial measurement unit and a monocular camera. Different from “perspective moment,” a new type of image feature is designed as “rotated perspective moment,” whose dynamics is independent of roll, pitch, and yaw rates. On this basis, a nonlinear adaptive observer is designed to estimate the scaled linear velocity, which is more accurate, since the observer does not involve noisy angular velocity measurements. Then, a novel image-based output feedback controller is proposed with the designed image features and the observer, wherein the new saturated integral terms of linear and angular velocity errors are introduced into the controller design, respectively, to compensate system uncertainties. As a result, the steady-state error is decreased considerably. In addition, without the assumption of the separation principle between the observer and the controller, the small-angle approximation, or the time-scale separation assumption, the error signals of image features, attitude, velocity, and observer estimation can all converge to the origin asymptotically, which is proven by rigorous Lyapunov analysis. Comparative experiments are conducted to show the superior performance of the proposed approach in terms of more accurate velocity estimation, smaller steady-state errors, and stronger robustness.

As a type of indispensable oceanic transportation tools, ship-mounted crane systems are widely employed to transport cargoes and containers on vessels due to their extraordinary flexibility. However, various working requirements and the oceanic environment may cause some uncertain and unfavorable factors for ship-mounted crane control. In particular, to accomplish different control tasks, some plant parameters (e.g., boom lengths, payload masses, and so on) frequently change; hence, most existing model-based controllers cannot ensure satisfactory control performance any longer. For example, inaccurate gravity compensation may result in positioning errors. Additionally, due to ship roll motions caused by sea waves, residual payload swing generally exists, which may result in safety risks in practice. To solve the above-mentioned issues, this paper designs a neural network-based adaptive control method that can provide effective control for both actuated and unactuated state variables based on the original nonlinear ship-mounted crane dynamics without any linearizing operations. In particular, the proposed update law availably compensates parameter/structure uncertainties for ship-mounted crane systems. Based on a 2-D sliding surface, the boom and rope can arrive at their preset positions in finite time, and the payload swing can be completely suppressed. Furthermore, the problem of nonlinear input dead zones is also taken into account. The stability of the equilibrium point of all state variables in ship-mounted crane systems is theoretically proven by a rigorous Lyapunov-based analysis. The hardware experimental results verify the practicability and robustness of the presented control approach.

Reinforcement learning (RL) combined with deep neural networks has led to a number of great achievements for robot control in virtual computer environments, where sufficient data can be obtained without any difficulty to train various models. However, thus far, only few and relatively simple tasks have been accomplished for practical robots, which is mainly caused by the following two reasons. First, training with real robots, especially with dynamic systems, is too complicated to be fully and accurately represented in simulations. Second, it is very costly to obtain training data from real systems. To address these two problems effectively, in this article, a path-integral-based RL algorithm is proposed for the task of path following of an autoassembly mobile robot, wherein three kernel techniques are introduced. First, a generalized path-integral-control approach is proposed to obtain the numerical solution of a stochastic dynamical system, wherein the calculation of the gradient and kinematics inverse is avoided to ensure fast and reliable training convergence. Second, a novel parameterization method using Lyapunov techniques is introduced into the RL algorithm to ensure good performance of the system when directly transferring simulation results into practical systems. Third, the optimal parameters for all discrete initial states are first learned offline and then tuned online to improve the generalization and real-time performance. In addition to the optimization control for the mobile robot, the proposed method also possesses general applicability for a class of nonlinear systems such as crane systems. Simulation and experimental results are included and analyzed to illustrate the superior performance of the proposed algorithm.

In this paper, a novel 2-D laser-based autonomous exploration approach for mobile robots is proposed, which is based on a novel polygon map construction approach and graph-based simultaneous localization and mapping (SLAM) with directional endpoint features. This approach is composed of three modules: graph-based SLAM using directional endpoint features, polygon map construction, and exploration. Different from existing approaches in the field of 2-D SLAM, the newly proposed 2-D graph-SLAM is based on 3-D “directional endpoint” features; on this basis, a well-known data structure “circular-doubly linked list” is applied to construct a novel polygon map for navigation. Note that it is efficient for circular-doubly linked list to initialize and update the polygon map. In addition, we propose a new information entropy calculation approach to quantify the entropy of the polygon map. Then for each candidate goal, we could obtain corresponding information gain and make next decision through collision detection. Comparative experimental results with respect to the well-known Gmapping and Karto SLAM are presented to show superior performance of the proposed graph-based SLAM. The autonomous exploration experiments in the office and hallway environments show the effectiveness of the proposed approach for robotic mapping and exploration tasks.

We propose, in this paper, an observer-based nonlinear feedback controller for four degrees of freedom (4-DOF) offshore ship-mounted tower cranes, which includes a robust-type term to address the observation uncertainty, and a switching logic tuning mechanism to update the involved unknown parameter. As a typical nonlinear underactuated mechatronic system, unlike the land-fixed tower cranes, an offshore ship-mounted tower crane also suffers from persistent disturbances caused by sea waves or currents, which leads to many difficulties and challenges in the controller design of such systems. Existing offshore crane control methods require either linearizations or approximations when performing analysis; moreover, most of them are only applicable for simplified 2-DOF crane models, and the ranges of system state errors cannot be guaranteed during the overall process. Motivated by these facts, to achieve simultaneous accurate jib/trolley positioning and fast payload swings suppression against complex unknown external disturbances, in particular, a disturbance observer is first designed in this paper, based on which a novel nonlinear switching logic-based control scheme for offshore cranes with jib rotation and horizontal transportation is proposed. As far as we know, the proposed method yields the first observer-based feedback closed-loop control without simplification operations to the original 4-DOF offshore tower crane dynamics and achieves the first asymptotic stability of the closed-loop system's equilibrium point for offshore cranes. To support the theoretical derivation, the corresponding stability analysis of the closed-loop system's equilibrium point is implemented by Lyapunov techniques. Numerous simulation and hardware experimental results are presented to demonstrate the superior performance of the proposed method. Note to Practitioners-This paper is motivated by the issue of controlling a four- degree-of-freedom (4-DOF) offshore ship-mounted tower crane system under the effects of unknown external disturbances. In practical applications, the persistent disturbances caused by sea waves or currents can always happen and make the offshore crane operation very challenging. Moreover, it brings more difficulties in the controller design for such a system due to its nonlinear underactuated property. Existing control approaches for offshore cranes are developed based upon linearized or oversimplified crane models or require exact model knowledge, and they may not work well in the presence of harsh sea conditions. Toward this end, this paper suggests a new control approach for 4-DOF offshore tower cranes suffering from sea wave effects to achieve a satisfactory performance. The asymptotic stability of the closed-loop system's equilibrium point is derived, implying that the accurate jib/trolley positioning and fast payload swings suppression against complex unknown external disturbances are achieved simultaneously. Preliminary physical experiments implemented on a self-built offshore tower crane hardware test bed verify the effectiveness and the robustness of the proposed observer-based control method. In the future research, we will apply the suggested control approach to industrial offshore crane systems to improve their working efficiency.

A tower crane is a nonlinear mechatronic system with complicated underactuated characteristics, which is widely used in modern construction sites. At present, most existing methods for tower cranes are proposed by linearizing the original nonlinear dynamics near equilibrium points, which are, thus, prone to suffering from unexpected steady errors due to such factors as unmodeled dynamics, imperfect friction compensation, etc., since they have not included integral terms in either controller design or stability analysis. Therefore, in this paper, an improved feedback controller with an elaborately constructed integral term is proposed for 3-D tower cranes without linearization, which can achieve both antiswing and positioning control while being able to effectively reduce steady errors in the presence of, e.g., inaccurate friction compensation. Furthermore, asymptotic stability results are proven through rigorous theoretical analysis. Owing to no linearization, the proposed controller is applicable when state variables (e.g., cargo swing angles) are not close enough to the equilibrium points, which makes it suitable for complicated working conditions. Hardware experimental results are included to verify the effectiveness of the proposed controller.

In this paper, a multilevel humanlike motion planning approach is proposed for indoor mobile robots. Compared with existing approaches, the novelty of this paper is twofold: 1) the proposed path planning framework is multilevel and humanlike to ensure both foreseeability and flexibility, wherein functions of human brain, eyes, and legs are corresponding to global path planning, sensor-level path planning, and action-level path planning, respectively, and 2) along the planned path, a new velocity-adjustable trajectory planning algorithm is put forward which is provably complete and time optimal considering multiple constraints from both the robot and the environment. Experimental results show that the proposed approach has a better performance in terms of efficiency, smoothness, foreseeability, and flexibility, and autonomous navigation is realized in large-scale, dynamic, partially unknown, and unstructured indoor environments.

This paper proposes a novel monocular visual servoing strategy, which can drive a wheeled mobile robot to the desired pose without a prerecorded desired image. Compared with existing methods that adopt the teaching pattern for visual regulation, this scheme can still work well in the situation that the desired image has not been previously acquired. Thus, with the aid of this method, it is more convenient for mobile robots to execute visual servoing tasks. Specifically, to deal with nonexistence of the desired image, the reference frame is craftily defined by taking advantage of visual targets and the planar motion constraint, and the pose estimation algorithm is designed for the mobile robot with respect to the reference frame. Then, an adaptive visual regulation controller is developed to drive the mobile robot to the intermediate frame, where the parameter updating law is constructed for the unknown feature height based on the concurrent learning framework. Stability analysis shows that regulation errors and height identification error can converge simultaneously. Afterwards, the mobile robot is driven to the metric desired pose with the identified feature height. Both simulation and experimental results are provided to validate the performance of this strategy.

As a class of typical representatives for conveyance, shipboard crane systems are usually fixed on ship decks to transport cargoes on the sea, which is greatly different from land-fixed cranes. Due to some disturbances induced by sea waves, payload positions are always difficult to control precisely. In addition, unless equipped with velocity sensors, it would be difficult to obtain velocity signals for feedback control, by noting that the traditional way of numerical differentiation operations (to recover velocities from positions/angles) may induce extra noises in practice. In this paper, we propose an observer-based dynamic feedback control method to deal with the foregoing issues. Specifically, both boom/rope positioning and payload swing elimination can be achieved simultaneously by utilizing only measurable displacement/angle feedback signals. Moreover, as far as we know, this paper gives the first input-saturated control method including nonlinear coupling terms to realize the objective of effective positioning and swing suppression without the requirement of velocity feedback, which is developed on the basis of the complicated nonlinear shipboard crane dynamics with no linearization operations during controller design or stability analysis. Meanwhile, the corresponding velocity signals are accurately recovered online by means of the suggested observer. In addition, the amplitudes of the control inputs can be guaranteed within the allowable ranges to avoid falling into saturation. The asymptotic stability for the equilibrium point of the crane system in closed loop with the controller and the observer is proven by rigorous analysis with Lyapunov techniques and LaSalle's invariance theorem. After a series of hardware experiments, we validate the effectiveness and robustness of the presented controller.

Among various large-scale mechanical equipments, a rotary crane is one of the most practical hoisting machineries utilized in factories and docks. However, the inaccurate measurement of friction coefficients and the requirement of accurate gravity-related compensation may inevitably increase the difficulty for controlling such systems. For most existing control methods, the exact model knowledge is required; otherwise, positioning errors would unavoidably appear, which brings many limitations for their practical applications. To deal with these problems, in this paper, a novel adaptive control approach is suggested, in which a novel update law is designed to achieve accurate identifications of unknown parameters as well as exact compensation of the gravity-related lumped term. Moreover, the payload can be transported to its specified location precisely via the boom's rotation with effective payload swing suppression. Specifically, without linearizing the nonlinear dynamic model of the rotary crane system, the state variables are ensured to be asymptotically convergent to the equilibrium point, which is proven strictly in theory by utilizing Lyapunov techniques and LaSalle's invariance principle. Finally, experimental results indicate the effectiveness and practicability of the proposed approach.

In real-world applications, industrial cranes commonly suffer from effects caused by the so-called double-pendulum phenomenon in many situations. However, at present, the double-pendulum phenomenon is usually directly roughly neglected when designing control methods. For double-pendulum cranes, most currently available approaches are open loop control; the existing feedback methods are mostly developed based on linearized dynamic models (around the equilibrium point) or designed without adding integral terms in the control laws, which may cause positioning errors in the presence of unmodeled dynamics. To address these problems, this paper proposes a new quasi-proportional integral derivative control method to effectively control underactuated double-pendulum crane systems. Then, we provide rigorous theoretical analysis for the equilibrium point of the closed-loop system based on the original nonlinear dynamic equations. To our knowledge, this paper gives the first plant-parameter-free controller that incorporates both integral action and actuating constraints without any linearizing operations during controller design or closed-loop analysis, which theoretically ensures that the controller can work well in the presence of unmodeled dynamics (e.g., insufficient friction compensation), actuating constraints, and large swing angles (i.e., not satisfying linearization conditions). Finally, hardware experimental results are provided to examine the effectiveness of the suggested control method.

In mechanical engineering, multi-translational oscillator with rotational actuator (multi-TORA) systems have been introduced to study the self-synchronized phenomenon as well as to investigate the vibration damping problem associated with many vibrational mechatronic systems, e.g., hand-held drills. Due to the lack of available actuators, multi-TORA systems are typically underactuated. Multi-TORA systems consist of a series of single TORA subsystems connected to and coupled with each other by elastic springs. For practical multi-TORA systems, the plant parameters are usually unknown or difficult to measure. Moreover, they exhibit strong nonlinear coupling behaviors. These factors bring much difficulty for both controller design and analysis. The control problem for underactuated multi-TORA systems with parametric uncertainties is challenging and still open. To address the above issues, this paper proposes a nonlinear increased motion control scheme for multi-TORA systems with parametric uncertainties. Specifically, a novel energy function is constructed and some extra coupling terms are introduced into the proposed controller for improving the transient performance. Then, based on Lyapunov techniques, we rigorously prove the asymptotic stability for the equilibrium point of the closed-loop system. As far as we know, this paper gives the first smooth control law to yield global asymptotic control results for underactuated multi-TORA systems suffering from unknown/uncertain plant parameters. To verify the effectiveness of the proposed controller, a series of hardware experiments are carried out on a self-built double-TORA hardware testbed, which indicate that the controller achieves effective control results in various conditions.

In this paper, we propose an acceleration-level pseudo-dynamic visual servoing structure for the nonholonomic mobile robots, based on which we design two different adaptive controllers-backstepping and dynamic surface control (DSC) in the presence of unknown depth information. Different from existing kinematic controllers, which directly regard linear and angular velocities as control inputs, this paper designs acceleration control that is integrated to easily obtain smooth velocity signals to be accurately executed by the robot. Two controllers are designed and analyzed with Lyapunov techniques: 1) a backstepping controller yielding asymptotical stability and 2) a dynamic surface controller ensuring system errors to be ultimately uniformly bounded. The unknown depth is handled by designing an adaptive parameter estimation law in both methods. Finally, a comparison between backstepping and DSC is given based on the experimental results and the design procedures.

In practical applications, industrial cranes may exhibit double-pendulum swing effects, due to many factors, such as large payload scales and non-negligible hook masses. Currently, for double-pendulum cranes, most available methods are open-loop controllers designed based on linearized crane dynamics; even for existing closed-loop approaches, they are also mostly developed using linearized dynamics and require the exact knowledge of system parameters, which makes them sensitive to parametric uncertainties. To handle these issues, we present an adaptive antiswing control strategy for crane systems with double-pendulum swing effects and uncertain/unknown parameters, which can make the trolley accurately reach the target position with reduced overshoots and effectively eliminate the double-pendulum swing angles at the same time. A complete stability analysis, based upon the full nonlinear dynamics (i.e., without linearizing the dynamics), is included to support the theoretical derivations. We present hardware experimental results to demonstrate that the proposed controller achieves better performance than existing ones and exhibits good robustness.

In practical applications, boom cranes are widely used as useful transportation tools in various fields, owing to such advantages as high flexibility, good mobility, strong operability, and so on. As a typical nonlinear underactuated system, a boom crane presents complicated dynamical characteristics mainly due to its complex multidimensional movements like rotational motions, pitching motions, as well as payload swings, which brings much difficulty for controller design. In this paper, a new nonlinear controller is proposed for underactuated boom cranes. Specifically, the presented control scheme can achieve 2-D rotary positioning and 2-D swing suppression simultaneously, with an additional coupling term as well as an overshoot-limiting term being incorporated to increase the transient performance. Consequently, the asymptotic stability of the closed-loop system's equilibrium point is proven by utilizing Lyapunov techniques and LaSalle's invariance theorem. To the best of our knowledge, the proposed approach is the first closed-loop control method to solve the positioning and anti-oscillation problem for 3-D boom cranes without needing to linearize the original nonlinear dynamics for controller design or analysis, which is of great significance. Finally, hardware experimental results are presented to demonstrate the efficiency of the proposed control method.

Presently, ship-mounted cranes are playing more and more important roles in modern ocean transportation and logistics. Different from traditional land-fixed crane systems, ship-mounted cranes present much more complicated nonlinear dynamical characteristics and they are persistently influenced by different mismatched disturbances due to harsh sea environments, e.g., sea waves, ocean currents, sea winds, and so forth; these unfavorable factors bring about many challenges for the development of effective control schemes. This paper presents a novel nonlinear stabilizing control strategy for underactuated ship-mounted crane systems. Specifically, some novel coordinate change procedures are first introduced to tackle the disturbing terms by transforming the original dynamics into a new form, which facilitates both controller design and stability analysis. After that, a nonlinear control law is constructed to regulate the cargo position to the desired location asymptotically, in the presence of ship roll and heave movements. The boundedness and convergence of the closed-loop signals are proven with Lyapunov-based analysis. To the best of our knowledge, this is the first closed-loop scheme that can achieve asymptotic control results, without linearizing/approximating the original nonlinear dynamics when performing controller design and stability analysis, for underactuated ship-mounted cranes with ship roll and heave movements. Hardware experimental results are included to show that the proposed control method can achieve satisfactory control performance and it admits strong robustness against external perturbations.

In this paper, a new background modeling method called stacked multilayer self-organizing map background model (SMSOM-BM) is proposed, which presents several merits such as strong representative ability for complex scenarios, easy to use, and so on. In order to enhance the representative ability of the background model and make the parameters learned automatically, the recently developed idea of representative learning (or deep learning) is elegantly employed to extend the existing single-layer self-organizing map background model to a multilayer one (namely, the proposed SMSOM-BM). As a consequence, the SMSOM-BM gains several merits including strong representative ability to learn background model of challenging scenarios, and automatic determination for most network parameters. More specifically, every pixel is modeled by a SMSOM, and spatial consistency is considered at each layer. By introducing a novel over-layer filtering process, we can train the background model layer by layer in an efficient manner. Furthermore, for real-time performance consideration, we have implemented the proposed method using NVIDIA CUDA platform. Comparative experimental results show superior performance of the proposed approach.

Many theoretic approaches for feedback stabilization control of nonholonomic mobile robots cannot be directly applied to practical robots since various kinematic constraints such as the velocity and acceleration limits are not considered in existing methods. To deal with this issue, we aim to propose a generic approach which first uses an (arbitrary) feedback stabilizer to generate the `path' and then rebuilt the corresponding `trajectory' along this `path' to meet various kinematic constraints, which ultimately gives a practical satisfactory solution for local trajectory planning. Specifically, a general framework is established to transform feedback stabilizers into a feasible and highly efficient trajectory planner by using path generation and optimal velocity planning techniques, considering both kinematic and differential constraints. Extensive simulation results are provided to validate the proposed approach.

The problem that using visual feedback to control the distance and orientation of the mobile robot with respect to a static sphere object is considered in this paper. Firstly, a unit virtual sphere is added on the classical camera model to obtain accurately the direction of the object. After measurable signal analysis, the kinematics model of the system is obtained. Then a switched controller and a continuous adaptive controller are developed to drive the mobile robot to the desired pose. Lastly, in order to estimate the distance between the camera and the object, a nonlinear observer is designed to give an exact estimation for the radius of the object, thus no metric information of the object is needed. Simulation results are collected to validate the effectiveness of the proposed method.

The present paper exploits a partially saturated nonlinear control law for underactuated crane systems, which is achieved by converting the crane model into an objective (or equivalently, desired closed-loop) system. The proposed method guarantees “soft” trolley start by incorporating a smooth saturated function into the control law. More specifically, we first establish an objective system with guaranteed signal convergence and stability performance; then based on the structure of the objective dynamics, a partially saturated control law is derived straightforwardly by solving one partial differential equation, without performing any partial feedback linearization operations on the original crane model. The convergence and stability performance of the objective (i.e., closed-loop) system is guaranteed with Lyapunov techniques and LaSalle's invariance theorem. To validate the practical performance of the proposed method, we implement hardware experiments to illustrate that the new method achieves superior performance with reduced control efforts.

This paper designs an innovative prediction-based interception control strategy to enable a wheeled mobile robot to intercept a dynamic target with a specified angle, which can be potentially utilized in such applications as service robots. Specifically, visual information is collected and then utilized to estimate the state of the moving target, based on which, the follow-up pose of the target is calculated so as to improve the interception accuracy. A prediction-based controller is then proposed to drive the wheeled robot to efficiently intercept a dynamic target with a specified angle, whose stability is proven by Lyapunov techniques. Both simulation and experimental results are provided to demonstrate the superior performance of the proposed approach.

In this paper, an uncalibrated visual servo regulation strategy is designed for a nonholonomic mobile robot equipped with an eye-in-hand camera, which drives the mobile robot to the target pose with exponential convergence. Specifically, a novel fundamental matrix-based algorithm is firstly proposed to rotate the robot to point toward the desired position, with the camera intrinsic parameters estimated simultaneously by employing the fundamental matrix and a projection homography matrix. Subsequently, by utilizing the obtained camera intrinsic parameters, a straight-line motion controller is developed to drive the robot to the desired position, with the orientation of the robot always facing the target position. Another pure rotation controller is finally adopted to correct the orientation error. The exponentially convergent properties of the visual servo errors are proven with mathematical analysis. The performance of the proposed uncalibrated visual servo regulation method is further validated by simulation results.

Inspired by the desire to achieve fast payload transportation as well as sufficient swing suppression, a novel phase plane based motion planning method is proposed for underactuated overhead cranes. Specifically, the variation law of the underactuated system states in the phase plane is firstly derived via mathematical analysis for the phase portraits. Based on this, an analytical three-segment acceleration trajectory (namely, a trapezoid velocity trajectory) with the coupling behavior being taken into consideration is obtained under actual crane control constraints. To deal with the jerk (discontinuity) problem, we then present two modified acceleration trajectories by introducing some transition stages and performing some rigorous analysis. Moreover, the trajectories generated by the proposed method can evaluate the maximum payload swing and the arrival time for a given transportation task in advance, which provides essential control indexes for crane operation. Simulation results are provided to illustrate the superior performance of the proposed trajectory planning method.

A 2-1/2-D visual servoing strategy, which is based on a novel motion-estimation technique, is presented for the stabilization of a nonholonomic mobile robot (which is also called the “parking problem”). By taking into account the planar motion constraint of mobile robots, the proposed motion-estimation technique can be applied in both planar and nonplanar scenes. In addition, this approach requires no matrix estimation or decomposition, and it avoids ambiguity and degeneracy problems for the homography or fundamental matrix-based algorithms. Moreover, the field-of-view (FOV) constraint of the onboard camera is largely alleviated because the presented algorithm works well with few feature points. In order to incorporate the advantages of position-based visual servoing and image-based visual servoing, a composite error vector is defined that includes both image signals and the estimated rotational angle. Subsequently, a smooth time-varying feedback controller is adopted to cope with the nonholonomic constraints, which yields global exponential convergent rate for the closed-loop system. On the basis of the perturbed linear system theory, we show that practical exponential stability can be achieved, despite the lack of depth information, which is inherent for monocular camera systems. Both simulation and experiment results are collected to investigate the feasibility of the proposed approach.

In this paper, we consider the problem of building a probability map for an unknown hostile environment by utilizing a team of UAVs. Specifically, we first present a centralized map building scheme for the Boeing open experimental platform (OEP) environment, the strategy is then modified into a decentralized map building algorithm to increase the robustness of the system. Some simulation results are provided to demonstrate the validity of the proposed algorithms

A monocular camera-based vision system attached to a mobile robot (i.e., the camera-in-hand configuration) is considered in this paper. By comparing corresponding target points of an object from two different camera images, geometric relationships are exploited to derive a transformation that relates the actual position and orientation of the mobile robot to a reference position and orientation. This transformation is used to synthesize a rotation and translation error system from the current position and orientation to the fixed reference position and orientation. Lyapunov-based techniques are used to construct an adaptive estimate to compensate for a constant, unmeasurable depth parameter, and to prove asymptotic regulation of the mobile robot. The contribution of this paper is that Lyapunov techniques are exploited to craft an adaptive controller that enables mobile robot position and orientation regulation despite the lack of an object model and the lack of depth information. Experimental results are provided to illustrate the performance of the controller.

In this paper, the 3-dimensional (3D) position of a camera held by the end-effector of a cartesian robot manipulator is regulated to a constant desired position despite (i) the lack of depth information of the actual or desired camera position from a target, (ii) the lack of a 3D model of the target object, and (iii) the lack of information of intrinsic and extrinsic camera calibration matrices. Specifically, by fusing 2D image-space and 3D task-space information (i.e., 2.5D visual servoing), an adaptive controller is developed that is proven to ensure asymptotic position regulation of the cartesian robot. The stability of the proposed controller is proven through a rigorous Lyapunov-based stability analysis.

In this paper, we utilize a Lyapunov-based design approach. to construct a visual servoing controller for a robot manipulator that ensures uniformly ultimately bounded (UUB) end-effector position tracking performance despite parametric uncertainty throughout the entire robot/camera system. The UUB end-effector tracking result exploits information from both a fixed camera and a camera-in-hand. although both cameras contain parametric uncertainty in the calibration parameters (e.g., focal length, image center, scaling factors, and camera position and orientation). The advantages of the cooperative camera configuration are that: (i) the fixed camera can be mounted so that a large robot workspace is visible, (ii) the camera-in hand is mounted so that a high resolution, close-up view of an object is achieved, facilitating the potential for more precise robotic motion. and (iii) the fixed camera provides a mechanism for treating the problem of determining the relative velocity of the robot end-effector with respect to the object for the camera-in-hand object tracking problem when the camera is uncalibrated.