This article addresses the problem of prescribed-time fault-tolerant tracking control for a class of nonlinear multiagent systems (MASs) subject to parameter uncertainties and external disturbances. To improve tracking precision, the trajectory reconstruction approach based on cubic spline interpolation is proposed, which effectively reconstructs the discrete reference signals. Then, a class of prescribed-time regulators is meticulously designed to formulate the fault-tolerant tracking controller, ensuring that the outputs of the controlled system converge to the reconstructed trajectory with arbitrary accuracy within the prescribed tracking time. Finally, stability analyses and a simulation example are presented to demonstrate the effectiveness of the proposed prescribed-time fault-tolerant tracking control strategy, validating its theoretical significance and practical applicability in engineering systems.

This article investigates the problem of observer-based prescribed-time tracking control (OPTC) for a class of nonlinear systems with uncertain nonvanishing disturbances. First, a prescribed-time observer (PTO) with a well-designed time-varying high gain is constructed to achieve zero-error observation of the uncertain nonvanishing disturbances within the prescribed observation time. Subsequently, a two-stage controller design framework is proposed to construct the desired control input, which consists of two distinct components: the first-stage controller and the second-stage controller. The first-stage controller is established to compensate for the effects of the system’s nonlinear dynamics, thereby providing a relatively satisfactory tracking performance. The second-stage controller, on the other hand, is constructed based on a sophisticated switching mechanism of the control gains, which not only ensures that the tracking error converges to zero within the prescribed tracking time but also guarantees a smooth transition between the two-stage controllers. Finally, the simulation example involving a disturbed single-link flexible-joint robotic manipulator is presented to demonstrate the effectiveness of the proposed control strategy.

Global control problem for uncertain nonlinear systems with unknown high-order odd-rational powers, additive sensor faults and fully unknown nonlinearities is investigated. By introducing a novel prescribed-performance transformation, the initial error of each subsystem can be confined in the constrained area for arbitrary system initialization. Then, the designed controller can guarantee global stability of the studied system for all initial system states, and can allow the system nonlinearities to be completely unknown. The odd-rational-power terms are divided into two parts appropriately by using mathematical tools, which facilitates the control design under sensor faults and odd-rational powers while the odd-rational powers are allowed to be unknown. It is proved that the proposed controller can guarantee the global stability of nonlinear systems with unknown system nonlinearities under odd-rational powers and sensor faults. Finally, the advantages and effectiveness of the proposed method are highlighted by both numerical and semi-physical simulations.

In long-horizon tasks, leveraging prior knowledge to streamline task execution is essential. However, navigating complex environments to achieve long-term objectives poses a significant challenge due to the vast exploration space involved. To address this issue, we propose a skill-based hierarchical reinforcement learning (RL) framework, termed LeSkill. This framework utilizes a conditional generative model to pretrain a comprehensive and generalizable skill repository from heterogeneous datasets, facilitating skill inference across diverse contexts. This strategy enhances transferability to novel tasks, thereby minimizing the need for extensive, task-specific training. Subsequently, a concise set of task-specific demonstrations is employed to guide the selection process, allowing the model to efficiently sample relevant skills from the pre-existing skill repository, which effectively reduces the exploration space. This approach accelerates the acquisition of highly effective policies tailored for task completion. Our framework undergoes rigorous evaluation on two challenging long horizon, multistep tasks: a standard task and a distribution mismatch task. The results highlight the framework’s superior performance in mastering intricate tasks and its remarkable generalization capabilities.

Visual-based robot pose estimation is a fundamental challenge, involving the determination of the camera’s pose with respect to a robot. Conventional methods for camera-to-robot pose calibration rely on fiducial markers to establish keypoint correspondences. However, these approaches exhibit significant variability in accuracy and robustness, particularly in 2D keypoint detection. In this work, we present an end-to-end pose estimation approach that achieves camera-to-robot calibration using monocular images and keypoint information. Our method employs a two-level nested U-shaped architecture, featuring a bottom-level residual U-block to extract richer contextual information from diverse receptive fields to enhance keypoint refinement. By incorporating the perspective-n-point (PnP) algorithm and leveraging 3D robot joint keypoints, we establish correspondence of 3D coordinate points between the robot’s coordinate system and the camera’s coordinate system, facilitating accurate pose estimation. Experimental evaluations encompass real-world and synthetic datasets, demonstrating competitive results across three distinct robot manipulators.

Reinforcement Learning (RL) based methods have been increasingly explored for robot learning. However, RL based methods often suffer from low sampling efficiency in the exploration phase, especially for long-horizon manipulation tasks, and generally neglect the semantic information from the task level, resulted in a delayed convergence or even tasks failure. To tackle these challenges, we propose a Temporal-Logic-guided Hybrid policy framework (HyTL) which leverages three-level decision layers to improve the agent’s performance. Specifically, the task specifications are encoded via linear temporal logic (LTL) to improve performance and offer interpretability. And a waypoints planning module is designed with the feedback from the LTL-encoded task level as a high-level policy to improve the exploration efficiency. The middle-level policy selects which behavior primitives to execute, and the low-level policy specifies the corresponding parameters to interact with the environment. We evaluate HyTL on four challenging manipulation tasks, which demonstrate its effectiveness and interpretability. Our project is available at: https://sites.google.com/view/hytl-0257/.

This article addresses the synchronization tracking problem for high-order uncertain nonlinear multiagent systems via intermittent feedback under a directed graph. By resorting to a novel storer-based triggering transmission strategy in the state channels, we propose an event-triggered neuroadaptive control method with quantitative state feedback that exhibits several salient features: 1) avoiding continuous control updates by making the parameter estimations updated intermittently at the trigger instants; 2) resulting in lower-frequency triggering transmissions by using one event detector to monitor the triggering condition such that each agent only needs to broadcast information at its own trigger times; and 3) saving communication and computation resources by designing the intermittent updating of neural network weights using a dual-phase technique during the triggering period. Besides, it is shown that the proposed scheme is capable of steering the tracking/disagreement errors into an adjustable neighborhood close to the origin, and the existence of a strictly positive dwell time is proved to circumvent Zeno behavior. Both theoretical analysis and numerical simulation authenticate and validate the efficiency of the proposed protocols.

In this article, we investigate the distributed tracking control problem for networked uncertain nonlinear strict-feedback systems with unknown time-varying gains under a directed interaction topology. A dual phase performance-guaranteed approach is established. In the first phase, a fully distributed robust filter is constructed for each agent to estimate the desired trajectory with prescribed performance such that the control directions of all agents are allowed to be nonidentical. In the second phase, by establishing a novel lemma regarding Nussbaum function, a new adaptive control protocol is developed for each agent based on backstepping technique, which not only steers the output to track the corresponding estimated signal asymptotically with arbitrarily prescribed transient response but also extends the application scope of the proposed control scheme largely since the unknown control gains are allowed to be time-varying and even state-dependent. In such a way, the underlying problem is tackled with the output tracking error converging into an arbitrarily preassigned residual set exhibiting an arbitrarily predefined convergence rate. Besides, all the internal signals are ensured to be semi-globally ultimately uniformly bounded (SGUUB). Finally, two examples are provided to illustrate the effectiveness of the co-designed scheme.

This article presents a novel dual-phase based approach for distributed event-triggered control of uncertain Euler-Lagrange (EL) multiagent systems (MASs) with guaranteed performance under a directed topology. First, a fully distributed robust filter is designed to estimate the reference signal for each agent with guaranteed observation performance under continuous state feedback, which transforms the distributed event-triggered control problem into a centralized one for multiple single systems. Second, an event-triggered controller is constructed via intermittent state feedback, making the output of each agent follow the corresponding estimated signal with guaranteed tracking performance. The proposed co-design scheme is of relatively low complexity in structure and cheap in computation since a priori knowledge of system nonlinearities or estimation of their bounds is not required in building the control scheme, and yet neither approximating structures nor adaptive online updating algorithms are needed. It is shown that the output tracking error of each agent is ensured to shrink into a prescribed precision set at an arbitrarily assignable convergence rate, although the plant states and the actuation signal are triggered simultaneously. All the internal signals are uniformly bounded and the occurrence of Zeno behavior is precluded. The efficiency of the proposed method is verified via numerical simulation.

It is nontrivial to achieve asymptotic tracking control for uncertain nonlinear strict-feedback systems with unknown time-varying delays. This problem becomes even more challenging if the control direction is unknown. To address such problem, the Lyapunov-Krasovskii functional (LKF) is used to deal with the time delays, and the neural network (NN) is applied to compensate for the time-delay-free yet unknown terms arising from the derivative of LKF, and then an NN-based adaptive control scheme is constructed on the basis of backstepping technique, which enables the output tracking error to converge to zero asymptotically. Besides, with a milder condition on time delay functions, the notorious singularity issue commonly encountered in coping with time delay problems is subtly settled, which makes the proposed scheme simple in structure and inexpensive in computation. Moreover, all the signals in the closed-loop system are ensured to be semiglobally uniformly ultimately bounded, and the transient performance can be improved with proper choice of design parameters. Both the theoretical analysis and numerical simulation are carried out to validate the relevance of the proposed method.

It is still an open problem to achieve asymptotic tracking meanwhile maintaining specific performance for nonlinear systems with structurally mismatched uncertainties and strictly constrained inputs. In this work, we present a solution to this problem by using neural network (NN)-based adaptive control embedded with the robust integral of the sign of the error (RISE) technique. Most existing prescribed performance control (PPC) can only ensure uniformly ultimately bounded stability, and the RISE-based control, although capable of achieving asymptotic stability, does not guarantee transient behavior (especially, when the system is in strict-feedback form with saturated input). Here, in this study, we make use of NNs to accommodate the unknown nonlinearities, where the NN approximation error, together with other uncertainties, is fully compensated by using a RISE unit. The constraints imposed on the inputs are addressed by the hyperbolic tangent function, resulting in a solution capable of guaranteeing asymptotic tracking with prescribed transient performance, in the presence of mismatched modeling uncertainties and actuation saturation. A numerical simulation is carried out to verify the effectiveness of the proposed method.

This paper investigates the attitude trajectory tracking control problem for quadrotor UAVs. An uncertain nonlinear affine state system is modeled from the quadrotor with unknown external disturbances. By checking the existence of certain auxiliary matrix, a milder controllability condition for the quadrotor model is introduced building upon which a robust adaptive attitude trajectory tracking controller is proposed, which guarantees that all signals in the closed loop quadrotor system are globally ultimately uniformly bounded (GUUB) and the trajectory tracking errors converge to zero asymptotically. Finally, the effectiveness of our method is verified by simulations.

In this paper, we investigate the tracking control problem for a class of strict feedback systems with pregiven performance specifications as well as full-state constraints. Our focus is on developing a feasible neural network (NN)-based control method that is able to, under full-state constraints, force the tracking error to converge into a prescribed region within preset finite time and further reduce the error to a smaller and adjustable residual set, while confining the overshoot within predefined small level. Based on two consecutive error transformations governed by two auxiliary functions, named with behavior-shaping function and asymmetric scaling function, respectively, a novel approach to achieve given performance specifications is developed under certain bound condition on the transformed error, such condition, along with the full-stated constraints, is guaranteed by imbedding barrier Lyapunov function (BLF) into the back-stepping design. Furthermore, asymmetric output constraints are maintained with a single symmetric BLF, simplifying the procedure of stability analysis. All internal signals including the stimulating inputs to the NN unit are ensured to be bounded. Both theoretical analysis and numerical simulation verify the effectiveness and the benefits of the design.

In this paper, we present a neuroadaptive control for a class of uncertain nonlinear strict-feedback systems with full-state constraints and unknown actuation characteristics where the break points of the dead-zone model are considered as time-variant. In order to deal with the modeling uncertainties and the impact of the nonsmooth actuation characteristics, neural networks are utilized at each step of the backstepping design. By using barrier Lyapunov function, together with the concept of virtual parameter, we develop a neuroadaptive control scheme ensuring tracking stability and at the same time maintaining full-state constraints. The proposed control strategy bears the structure of proportional-integral (PI) control, with the PI gains being automatically and adaptively determined, making its design less demanding and its implementation less costly. Both theoretical analysis and numerical simulation validate the benefits and the effectiveness of the proposed method.

This paper considers the tracking control problem for a class of multi-input multi-output nonlinear systems subject to unknown actuation characteristics and external disturbances. Neuroadaptive proportional-integral (PI) control with self-tuning gains is proposed, which is structurally simple and computationally inexpensive. Different from traditional PI control, the proposed one is able to online adjust its PI gains using stability-guaranteed analytic algorithms without involving manual tuning or trial and error process. It is shown that the proposed neuroadaptive PI control is continuous and smooth everywhere and ensures the uniformly ultimately boundedness of all the signals of the closed-loop system. Furthermore, the crucial compact set precondition for a neural network (NN) to function properly is guaranteed with the barrier Lyapunov function, allowing the NN unit to play its learning/approximating role during the entire system operation. The salient feature also lies in its low complexity in computation and effectiveness in dealing with modeling uncertainties and nonlinearities. Both square and nonsquare nonlinear systems are addressed. The benefits and the feasibility of the developed control are also confirmed by simulations.

The "universal" approximating/learning feature of neural network (NN), widely and extensively used for control design, is contingent upon some critical conditions, either of which, if not satisfied, would render such feature vanished. In this paper, we show that these conditions are literally linked with several fundamental issues that have been overlooked in most existing NN-based control designs, either unconsciously or deliberately. We further propose a collective approach to explicitly address these issues, establishing a strategy enabling the NN unit to be fully functional in the control loop during the entire process of system operation and ensuring the more reliable and more effective NN-associated control performance. This is achieved by incorporating the control with a new structural NN unit, consisting of a group of diversified neurons with self-adjusting subneurons, each being driven/stimulated by input signals confined within a compact set. Meanwhile, the continuity of the control signal and the boundedness of all the closed-loop signals are ensured. Both the theoretical analysis and numerical simulation validate the effectiveness of the proposed method.The "universal" approximating/learning feature of neural network (NN), widely and extensively used for control design, is contingent upon some critical conditions, either of which, if not satisfied, would render such feature vanished. In this paper, we show that these conditions are literally linked with several fundamental issues that have been overlooked in most existing NN-based control designs, either unconsciously or deliberately. We further propose a collective approach to explicitly address these issues, establishing a strategy enabling the NN unit to be fully functional in the control loop during the entire process of system operation and ensuring the more reliable and more effective NN-associated control performance. This is achieved by incorporating the control with a new structural NN unit, consisting of a group of diversified neurons with self-adjusting subneurons, each being driven/stimulated by input signals confined within a compact set. Meanwhile, the continuity of the control signal and the boundedness of all the closed-loop signals are ensured. Both the theoretical analysis and numerical simulation validate the effectiveness of the proposed method.