The underwater hexapod robot, driven by eight thrusters and six C-shaped legs, can perform complex locomotion tasks such as climbing rough terrain. Unlike conventional point-contact legs, the C-shaped leg rolls on the terrain. The rolling fashion brings significantly complex loop-closure kinematic constraints and complicates the finding of feasible gaits. In addition, when C-shaped legs roll on rough terrain, their contact condition will change in real-time, leading to time-varying contact force, which may result in the leg slipping or even the robot falling. To address the two issues, we propose gait planning and thruster force allocating methods for rough terrain climbing. First, we propose a sampling-based gait planner that extends random trees in task space and finds feasible gaits to fulfill the loop-closure kinematic constraints, which avoids designing the complex sampling and steering procedures in an implicitly-defined manifold. Second, by designing a gait interval-based cost function, we propose an optimal sampling-based planner to find smooth climbing gaits. Third, by establishing a simplified single rigid body (SRB) model, we formulate an optimization problem to allocate thruster forces to guarantee that contact forces cannot lead to the leg slipping. Finally, the effectiveness and practicality of the proposed methods are validated via extensive Gazebo simulations as well as hardware experiments. Note to Practitioners—The motivation for this paper stems from the need to develop a practical rough terrain climbing algorithm for a thruster-assisted underwater hexapod robot that can walk the underwater structure with any dip angles to perform some meticulous small-range operations such as hull cleaning, fracture detection, and damage restoration. However, existing climbing algorithms mainly focus on finding legs’ torques or footsteps for point-contact legged robots. They may fail to be directly used in the underwater robot simultaneously driven by thrusters and C-shaped rolling-contact legs. Then, we propose an optimal gait planning method to find C-shaped legs’ smooth desired rotation angles and an optimal thruster force allocation method to regulate each support leg’s contact force to avoid slipping. Finally, the gait planning method can also be applied to other rolling-contact legged robots, and the thruster force allocation method can help other thruster-assisted legged robots perform complex locomotion tasks.

Collaborative robots are predicted to interact physically with humans in human-cyber-physical systems (HCPSs). Robotic hands are able to record force and temperature simultaneously through soft and conformable sensors applied over finger surfaces and conforming to the complex curved geometries of automatic machines with tactile perception. Here, skin-inspired triple tactile (SITT) sensors are integrated into robotic fingers to enable precise bimanual grasping. The SITT sensor has skin-inspired multilayer microstructures, which integrate three sensors, namely, an interdigital electrode sensor, a flexible force sensor, and a temperature sensor. The SITT sensor can simultaneously or independently measure a material’s dielectric property, tactile force and temperature. An HCPS based on SITT sensors, a data acquisition board, bimanual robotic hands, and human-robot interaction software is developed for efficient bimanual manipulation. Through 3C assembly experiments, the designed HCPS is demonstrated to execute complex tasks. This research presents a novel methodology for constructing robust tactile sensors for robotic fingers in a bimanual manipulation system, and it presents significant potential across various aspects of intelligent production, including sensitive object handling, adaptive manipulation, and interactive robotics applications.Note to Practitioners—This work aims to overcome the challenge of skin-inspired triple tactile (SITT) sensors developed for robotic fingers in a human-robot collaborative assembly scenario, which can also be used in many other similar human-robot/machine collaborations (e.g., wearable prosthetics with tactile feedback) with practical value. Its capability to accurately measure the touched objects’ information (e.g., material dielectric property, force, temperature) is crucial for the bimanual robot to successfully interact with human operators. HCPS is valuable for its potential to achieve complicated interactions among humans, cyber systems, and physical resources. Collaborative robots with tactile sensors are expected to interact physically with humans in the HCPS. In this paper, we report SITT sensors integrated on robotic fingers to enable precise bimanual grasping. They can simultaneously or independently measure material dielectric properties and tactile forces and record temperature. By combining tactile perception information and a related control method, our smart bimanual robotic hands with the developed HCPS demonstrates the capability to execute 3C assembly in intelligent manufacturing. In the future, additional application scenarios will be designed for the HCPS platform, and some traditional tasks (such as a single arm for collaborative assembly) will be replaced by our hardware and software systems.

Since precisely sensing the underwater environment is a challenging prerequisite for safe and reliable underwater operation, interest in underwater image processing is growing at a rapid pace. In engineering applications, there are redundant underwater images addressed in real-time on the remotely operated vehicle (ROV). It puts the equipment or operators under great pressure. To relieve this pressure by transmitting images selectively according to the degradation degree, we propose an end-to-end hybrid-input convolutional neural network (HI-CNN) to predict the degradation of underwater images. First, we propose a feature extraction module to extract the features of original underwater images and saliency maps concurrently, which is composed of two branches with the same structure and shared parameters. Second, we design an end-to-end model to predict the quality scores of original images, which consists of a feature extraction module and a prediction module. Finally, we establish a real-world dataset to make the proposed model be duplicated in the practical underwater environment. Through several experiments, we demonstrate that the proposed model outperforms existing models in predicting underwater image quality.

The stability criterion is critical for the design of legged robots' motion planning and control algorithms. If these algorithms cannot theoretically ensure legged robots' stability, we need many trials to identify suitable parameters for stable locomotion. However, most existing stability criteria are tailored to robots driven solely by legs and cannot be applied to thruster-assisted legged robots. Here, we propose a stability criterion for a thruster-assisted underwater hexapod robot by finding maximum and minimum allowable thruster forces and comparing them with the current thrusts to check its stability. On this basis, we propose a method to increase the robot's stability margin by adjusting the value of thrusts. This process is called stability enhancement. The criterion uses the optimization method to transform multiple variables such as attitude, velocity, acceleration of the robot body, and the angle and angular velocity of leg joints into one kind of variable (thrust) to judge the stability directly. In addition, the stability enhancement method is straightforward to implement because it only needs to adjust the thrusts. These provide insights into how multiclass forces such as inertia force, fluid force, thrust, gravity, and buoyancy affect the robot's stability.

This paper proposes a hybrid long short-term motor (HLSM) optimization and control approach for a walking exoskeleton. It consists of long-term global optimization, short-term local optimization, human-in-the-loop trajectory adaptation, and hybrid cerebellar model articulation controller (HCMAC). In the long-term global optimization, a graphic Spiking Neural Network (SNN) is utilized for an optimal global path. Along the path, the short-term motor optimization includes footstep optimization and obtains a sequence of footsteps. While in response to the unexpected obstacles along the footstep sequence, a human-in-the-loop planning strategy is designed by a virtual impedance model between the Centers of Mass (COMs) of the human and the exoskeleton, regulating the COM of the exoskeleton and generating footstep adaptation of the exoskeleton such that the exoskeleton can avoid obstacles and maintain its original global trajectory. Moreover, considering the unmodeled dynamics, we propose an HCMAC based on an integral Lyapunov function, which is exploited to counteract the system's nonlinear uncertainties, external disturbances, and reduces a relatively high computational cost. We validate the effectiveness of the HLSM planner and controller in a practical indoor setting. The results demonstrate the effectiveness of HLSM planning and control in a real scenario for a walking exoskeleton.

In this work, pursuit-evasion (PE) games with marine surface vessels (MSVs) as pursuers are solved while considering velocity constraints and unknown dynamics simultaneously. Differentiable performance index functions are designed for PE games based on minimum and maximum approximation functions. Then, we can obtain the desired pursuit velocities for MSVs satisfying velocity constraints and evasion strategies by applying game theory. NN are established to approximate unknown dynamics, which is suitable to design neural network (NN)-based control to ensure that all velocities of MSVs converge to their desired ones. Through rigorous Lyapunov analyses, it can be guaranteed that all convergence and weight errors are uniformly ultimately boundedUUB. Simulation results and comparison with known dynamics are provided and analyzed, which show that the proposed NN-based PE game is effective for MSVs with velocity constraints and unknown dynamics.

In this article, we investigate the problem of capturing a noncooperative target with deception behavior using reinforcement learning (RL) under incomplete information. The pursuer copes not only with its maneuverability constraint but also with the target’s deception behavior, in which the target deliberately conceals its private preference information. The target capture game involving deception behavior is formulated as a nonlinear differential game framework where the information structure is incomplete and asymmetric. The solution to this differential game is proposed based on an RL policy that incorporates critic, actor, and virtual actor neural networks (NNs), when taking into consideration the maneuverability constraint and information structure of the pursuer. Moreover, the states of the constrained adversarial system and the weight errors are proven to be ultimately uniformly bounded (UUB). To counter the deception of the target, we adopt unscented Kalman filter (UKF) to obtain the target intention on energy preference, and integrate it into the pursuer strategy. The feasibility of the proposed strategy and its superiority are verified through comparisons with recent works.

In this study, we present a coordinated protocol for a multiagent system (MAS) in competitive and cooperative manners for moving target defense with dynamic task-switching. The protocol comprises three components. First, we design a distance-based competitive distributed decision algorithm within an improvedk-Winner-Take-All (k-WTA) framework. This algorithm generates dynamic binary task-driven signals for each agent, enabling near-optimal online grouping of MAS with arbitrary proportions. Second, we introduce a cooperative strategy that employs a shared decision-making mechanism and utilizes feedback linearization without global position information. This strategy generates motion planning signals to coordinate the agents’ actions, achieving overall cooperative behaviors such as tracking, capturing, and intercepting. Finally, we incorporate an adaptive sliding mode technique based on second-order nonlinear dynamics to enhance robustness against disturbances, ensuring uniformly ultimately boundedness (UUB) of the closed-loop system. In addition, simulations and experiments with wheeled mobile robots (WMRs) validate the effectiveness of our method.

Path planning in unpredictable dynamic environments remains a challenging problem due to the unpredictable appearance, disappearance, and movement of dynamic obstacles during navigation. To address this problem, we propose a reverse tree guided rapid exploration random tree (RTRRT) algorithm that can efficiently perform navigation tasks in dynamic environments. The method first constructs a reverse tree rooted as goal state to search for an initial path. If a collision occurs on the path, The RT-RRT constructs a forward tree rooted as the current robot state in the same configuration space, until it connects with the reverse tree to find a new path. Furthermore, The RT-RRT improves the tree construction method and designs a path optimization strategy to reduce the path cost. The method is validated in different scenarios and has excellent navigation capabilities in unpredictable dynamic environments. In the same scenarios, the RT-RRT algorithm improves the success rate by 16.7%, reduces the path length by 20.54% and reduces the travel time by 10X compared to the RRTXalgorithm with the same number of samples.

This article presents an improved guidance law for underactuated marine vessels that compensates cross-track error caused by external disturbances through its sideslip. The proposed guidance law demonstrates improved path-following performance regardless of disturbances, such as waves, winds, and ocean currents. This article also presents an adaptive neural-network (NN) control law for the partially known vessel dynamics with state constraints. For satisfying the state constraints, this control scheme adopts an integral barrier Lyapunov function (iBLF)-based backstepping control technique. It is shown that the closed-loop system remains bounded, and state constraints are always satisfied. Finally, the efficacy of the improved guidance law and iBLF-based adaptive control strategy was verified in simulation and experiments using an autonomous surface vessel.

Broad learning systems (BLSs) have attracted considerable attention due to their powerful ability in efficient discriminative learning. In this article, a modified BLS with reinforcement learning signal feedback (BLRLF) is proposed as an efficient method for improving the performance of standard BLS. The main differences between our research and BLS are as follows. First, we add weight optimization after adding additional nodes or new training samples. Motivated by the weight iterative optimization in the convolution neural network (CNN), we use the output of the network as feedback while employing value iteration (VI)-based adaptive dynamic programming (ADP) to facilitate calculation of near-optimal increments of connection weights. Second, different from the homogeneous incremental algorithms in standard BLS, we integrate those broad expansion methods, and the heuristic search method is used to enable the proposed BLRLF to optimize the network structure autonomously. Although the training time is affected to a certain extent compared with BLS, the newly proposed BLRLF still retains a fast computational nature. Finally, the proposed BLRLF is evaluated using popular benchmarks from the UC Irvine Machine Learning Repository and many other challenging data sets. These results show that BLRLF outperforms many state-of-the-art deep learning algorithms and shallow networks proposed in recent years.

This article develops a self-triggered adaptive neural network (NN) tracking controller for a class of continuous-time nonlinear systems, that is, input constrained and with unknown drift and input dynamics. Since the drift and input dynamics are both unknown, an NN is built within a self-triggered update paradigm to approximate the unknown tracking control. The error derivative used in the weight update algorithm is derived using a robust exact differentiator technique. To address input constraints, an auxiliary compensator is designed for the unimplemented control effort. Through rigorous Lyapunov analyses, we can guarantee that all the tracking and weight errors are uniformly ultimately bounded. Finally, to show the effectiveness of the proposed control performance, simulation results of a two-link robot are provided and analyzed.

In this paper, event-triggered reinforcement learning-based adaptive tracking control is developed for the continuous-time nonlinear system with unknown dynamics and external disturbances. The critic and action neural networks are designed to approximate an unknown long-term performance index and controller, respectively. The dead-zone event-triggered condition is developed to reduce communication and computational costs. Rigorous theoretical analysis is provided to show that the closed-loop system can be stabilized. The weight errors and the filtered tracking error are all uniformly ultimately bounded. Finally, to demonstrate the developed controller, the simulation results are provided using an autonomous underwater vehicle model.

In this article, a synchronous reinforcement-learning-based algorithm is developed for input-constrained partially unknown systems. The proposed control also alleviates the need for an initial stabilizing control. A first-order robust exact differentiator is employed to approximate unknown drift dynamics. Critic, actor, and disturbance neural networks (NNs) are established to approximate the value function, the control policy, and the disturbance policy, respectively. The Hamilton-Jacobi-Isaacs equation is solved by applying the value function approximation technique. The stability of the closed-loop system can be ensured. The state and weight errors of the three NNs are all uniformly ultimately bounded. Finally, the simulation results are provided to verify the effectiveness of the proposed method.

In this paper, an integral reinforcement learning-based adaptive neural network (NN) tracking control is developed for the continuous-time (CT) nonlinear system with unknown control directions. The long-term performance index in the CT domain is prescribed. Critic and action NNs are designed to approximate the unavailable long-term performance index and the unknown dynamics, respectively. The reinforcement signal is explicitly embedded in the updated law of the action NN and then the estimated long-term performance index can be minimized. Rigorous theoretical analysis is provided to show that the closed-loop system is stabilized and all closed-loop signals are semiglobally uniformly ultimately bounded. Finally, to demonstrate the control performance, simulation results are provided to verify the tacking control performance of an autonomous underwater vehicle model.

In this paper, an admittance adaptation method has been developed for robots to interact with unknown environments. The environment to be interacted with is modeled as a linear system. In the presence of the unknown dynamics of environments, an observer in robot joint space is employed to estimate the interaction torque, and admittance control is adopted to regulate the robot behavior at interaction points. An adaptive neural controller using the radial basis function is employed to guarantee trajectory tracking. A cost function that defines the interaction performance of torque regulation and trajectory tracking is minimized by admittance adaptation. To verify the proposed method, simulation studies on a robot manipulator are conducted.

This paper proposes a novel adaptive control methodology based on the admittance model for multiple manipulators transporting a rigid object cooperatively along a predefined desired trajectory. First, an admittance model is creatively applied to generate reference trajectory online for each manipulator according to the desired path of the rigid object, which is the reference input of the controller. Then, an innovative integral barrier Lyapunov function is utilized to tackle the constraints due to the physical and environmental limits. Adaptive neural networks (NNs) are also employed to approximate the uncertainties of the manipulator dynamics. Different from the conventional NN approximation method, which is usually semiglobally uniformly ultimately bounded, a switching function is presented to guarantee the global stability of the closed loop. Finally, the simulation studies are conducted on planar two-link robot manipulators to validate the efficacy of the proposed approach.

This paper proposes an enhanced robot skill learning system considering both motion generation and trajectory tracking. During robot learning demonstrations, dynamic movement primitives (DMPs) are used to model robotic motion. Each DMP consists of a set of dynamic systems that enhances the stability of the generated motion toward the goal. A Gaussian mixture model and Gaussian mixture regression are integrated to improve the learning performance of the DMP, such that more features of the skill can be extracted from multiple demonstrations. The motion generated from the learned model can be scaled in space and time. Besides, a neural-network-based controller is designed for the robot to track the trajectories generated from the motion model. In this controller, a radial basis function neural network is used to compensate for the effect caused by the dynamic environments. The experiments have been performed using a Baxter robot and the results have confirmed the validity of the proposed methods.

This paper presents a cooperative multiagent search algorithm to solve the problem of searching for a target on a 2-D plane under multiple constraints. A Bayesian framework is used to update the local probability density functions (PDFs) of the target when the agents obtain observation information. To obtain the global PDF used for decision making, a sampling-based logarithmic opinion pool algorithm is proposed to fuse the local PDFs, and a particle sampling approach is used to represent the continuous PDF. Then the Gaussian mixture model (GMM) is applied to reconstitute the global PDF from the particles, and a weighted expectation maximization algorithm is presented to estimate the parameters of the GMM. Furthermore, we propose an optimization objective which aims to guide agents to find the target with less resource consumptions, and to keep the resource consumption of each agent balanced simultaneously. To this end, a utility function-based optimization problem is put forward, and it is solved by a gradient-based approach. Several contrastive simulations demonstrate that compared with other existing approaches, the proposed one uses less overall resources and shows a better performance of balancing the resource consumption.

In this paper, we investigate the trajectory tracking problem for a fully actuated autonomous underwater vehicle (AUV) that moves in the horizontal plane. External disturbances, control input nonlinearities and model uncertainties are considered in our control design. Based on the dynamics model derived in the discrete-time domain, two neural networks (NNs), including a critic and an action NN, are integrated into our adaptive control design. The critic NN is introduced to evaluate the long-time performance of the designed control in the current time step, and the action NN is used to compensate for the unknown dynamics. To eliminate the AUV's control input nonlinearities, a compensation item is also designed in the adaptive control. Rigorous theoretical analysis is performed to prove the stability and performance of the proposed control law. Moreover, the robustness and effectiveness of the proposed control method are tested and validated through extensive numerical simulation results.

Autonomous underwater vehicles (AUVs) have been widely employed in ocean survey, monitoring, and search and rescue tasks for both civil and military applications. It is beneficial to use multiple AUVs that perform environmental sampling and sensing tasks for the purposes of efficiency and cost effectiveness. In this paper, an adaptive path planning algorithm is proposed for multiple AUVs to estimate the scalar field over a region of interest. In the proposed method, a measurable model composed of multiple basis functions is defined to represent the scalar field. A selective basis function Kalman filter is developed to achieve model estimation through the information collected by multiple AUVs. In addition, a path planning method, the multidimensional rapidly exploring random trees star algorithm, which uses mutual information, is proposed for the multi-AUV system. Employing the path planning algorithm, the sampling positions of the AUVs are determined to improve the quality of future samples by maximizing the mutual information between the scalar field model and observations. Extensive simulation results are provided to demonstrate the effectiveness of the proposed algorithm. Additionally, an indoor experiment using four robotic fishes is carried out to validate the algorithms presented.

In this paper, automatic motion control is investigated for one of wheeled inverted pendulum (WIP) models, which have been widely applied for modeling of a large range of two wheeled modern vehicles. First, the underactuated WIP model is decomposed into a fully actuated second order subsystem Σa consisting of planar movement of vehicle forward and yaw angular motions, and a nonactuated first order subsystem Σb of pendulum motion. Due to the unknown dynamics of subsystem Σa and the universal approximation ability of neural network (NN), an adaptive NN scheme has been employed for motion control of subsystem Σa . The model reference approach has been used whereas the reference model is optimized by the finite time linear quadratic regulation technique. The pendulum motion in the passive subsystem Σb is indirectly controlled using the dynamic coupling with planar forward motion of subsystem Σa , such that satisfactory tracking of a set pendulum tilt angle can be guaranteed. Rigours theoretic analysis has been established, and simulation studies have been performed to demonstrate the developed method.

In this paper, we investigate the leader-follower formation control of underactuated Autonomous Underwater Vehicles (AUVs). By using position measurements from the leader, we design a virtual vehicle such that the trajectory of the virtual vehicle converges to the reference trajectory of the follower. A position tracking control is designed for the follower to track the virtual vehicle using Lyapunov and backstepping synthesis. Simulation results demonstrated the effectiveness of the proposed scheme.