Lin Chen

In the automated sorting and processing of agricultural products, the nonlinear mechanical degradation induced by lipid oxidation severely restricts the grasping reliability of high‐fat fragile targets. To address the resulting damage and slip issues, this study proposes a damage‐less grasping strategy driven by an oxidation prior, integrating variable impedance control and quadratic programming‐based control barrier functions (QP‐CBF). By fusing multimodal optical and tactile information, the proposed strategy utilizes hyperspectral imaging to predict the degree of oxidative deterioration, mapping this prior into a dynamic safety threshold for the normal gripping force. Furthermore, fractional‐order calculus is introduced to reconstruct the viscoelastic mechanical response of the targets, effectively suppressing the normal force overshoot during the initial contact phase. To mitigate the spatial slippage risks exacerbated by strict underlying force constraints, the framework employs a QP‐CBF module to dynamically constrain hazardous spatial accelerations, thereby achieving active anti‐slip intervention. Experiments conducted on multi‐gradient oxidized samples demonstrate that under severe oxidation‐induced embrittlement, the proposed intervention mechanism effectively compensates for the friction deficit. Compared to conventional feedforward perception strategies that frequently fail due to insufficient normal gripping force, our approach improves the intact handling success rate by 37%, achieving an overall success rate exceeding 93%. These results indicate that the integrated control framework successfully resolves the physical contradiction between preventing breakage and avoiding slippage, providing a highly robust algorithmic reference for the compliant robotic manipulation of fragile objects.

An online adaptive reinforcement learning (RL) algorithm is proposed to solve the infinite-horizon optimal tracking control problem for unmanned surface vehicles (USVs), in the presence of modeling uncertainties and external disturbances. A novel identifier-critic neural network (NN) architecture is developed to obtain the approximate solution of the Hamilton-Jacobi-Bellman (HJB) equations, in which the identifier and critic network weight adaptive laws are designed by gradient descent algorithm. The improved critic network adaptive law can relax the traditional persistence of excitation condition, which facilitates the implementation of the algorithm in practical applications. The time-varying and asymmetric constraint requirement on tracking errors is provided to ensure the satisfaction of transient and steady-state performance. Furthermore, the presented control scheme also works for the unconstrained systems. Through Lyapunov analysis, tracking errors are proved to converge into a small neighborhood of zero. Finally, both numerical simulations and virtual-reality experiments are performed to demonstrate the effectiveness of the proposed control scheme.

This article presents an online reinforcement learning (RL) algorithm to learn the distributed optimal containment control solution for underactuated surface vehicles subject to modeling uncertainties and unknown ocean disturbances. First, the request of exact knowledge of vehicle system dynamics is avoided by constructing an adaptive neural network identifier. The unknown lumped disturbances are estimated by disturbance observers. Second, an actor-critic-based RL algorithm is developed to release the persistence of excitation condition. Third, based on RL algorithm and backstepping procedure, we design adaptive finite-time optimal containment controllers such that the containment errors converge into a small neighborhood around zero in finite time and satisfy the predefined performance specifications. Finally, simulation studies on underactuated surface vehicles are provided to verify the effectiveness of the presented optimal control algorithm.

This article develops a reinforcement learning (RL) strategy to address the robust optimal tracking control problem for an intelligent surface vehicle (ISV) with modeling uncertainties and unknown ocean disturbances. A neural network (NN) identifier is constructed to learn uncertain nonlinear dynamics. Unlike the typical architecture of actor-critic networks, a single-critic network is employed to obtain the approximate solution of Hamilton-Jacobi-Bellman (HJB) equation. By introducing an additional stability term and experience replay (ER) technique, we present a novel critic weight update rule, such that (i) the traditional persistent excitation (PE) condition is relaxed, and (ii) the request of an initial admissible control is alleviated. Subsequently, a performance-guaranteed adaptive optimal tracking control algorithm is developed to guarantee the prescribed transient behavior of tracking errors and minimize the cost function simultaneously. A rigorous theoretical analysis indicates that the developed controller guarantees semi-globally uniformly ultimate boundedness of the closed-loop adaptive system with prescribed performance. Simulation studies demonstrate the effectiveness and robustness of the presented control algorithm.

An adaptive optimal consensus control design technique is presented for uncertain multiagent systems with prescribed performance guarantees using reinforcement learning (RL) algorithm. Firstly, an adaptive neural network identifier is employed to learn the knowledge of uncertain system dynamics and a disturbance observer is developed to compensate for time-varying disturbances. Secondly, a critic-network learning structure is established to obtain the approximate solution of Hamilton-Jacobi-Bellman (HJB) equations of multiagent systems. Then, an experience replay method is applied to update the critic network weights without requiring persistence of excitation condition. Thirdly, RL-based optimized consensus controllers are developed such that (i) the cost function is minimized, (ii) transient and steady-state performances of consensus error systems are guaranteed, and (iii) uniform ultimate boundedness of the closed-loop systems is achieved. Finally, application to consensus control of unmanned surface vehicles with uncertain hydrodynamic dampings is given to demonstrate the effectiveness of the optimal control design technique.

The environmental disturbances acting on marine surface vessels are naturally stochastic. The control performance may be seriously deteriorated if the stochastic components are ignored in control design. In this paper, we aim to address the trajectory tracking control problem for uncertain underactuated surface vessels exposed to stochastic disturbances under prescribed performance constraints. The environmental disturbances are divided into a deterministic part and a stochastic component modeled as standard Wiener process. Subsequently, a novel tan-type quartic barrier Lyapunov function (BLF) is incorporated into the control design to handle the Hessian terms induced by stochastic differentiation rule and simultaneously guarantee prescribed performance of tracking errors in probability. Meanwhile, a transverse function control method is developed to introduce an additional control input so as to deal with the difficulties caused by underactuation and nonzero off-diagonal terms. Based on transverse function control, backstepping procedure, neural networks (NNs), and quartic barrier Lyapunov function, an adaptive NN-based trajectory tracking control protocol is finally developed, whose advantage is that prescribed performance of tracking errors is guaranteed in probability despite the presence of stochastic environmental disturbances. Simulations are carried out to validate the effectiveness of the proposed control protocol.

Summary: In this article, an optimized formation control algorithm is presented for unmanned surface vehicles (USVs) with collision avoidance and prescribed performance. The prescribed formation geometry is designed in the leader‐follower formation architecture, in which each vehicle tracks its intermediary leader with preserving a desired separation. A prescribed performance control design technique is introduced to guarantee the transient and steady‐state performance specifications on formation errors. Radial basis function neural networks (NNs) are employed to approximate modeling uncertainties including damping terms and unmodeled dynamics. Based on an actor‐critic learning strategy, a reinforcement learning (RL) algorithm is proposed to ensure the optimality of formation control and the specified tracking accuracy simultaneously, in which actor NNs take appropriate control behaviors by interacting with the external environment, and critic NNs evaluate the control performance and generate a reinforcement signal to actor NNs for facilitating the improvement of subsequent behaviors. Stability analysis shows that the proposed optimal formation controller achieves semi‐global uniform ultimate boundedness of closed‐loop adaptive systems with prescribed performance. Comparative simulation results illustrate the effectiveness and superiority of the presented control algorithm.

In this article, we present an adaptive reinforcement learning optimal tracking control (RLOTC) algorithm for an underactuated surface vessel subject to modeling uncertainties and time-varying external disturbances. By integrating backstepping technique with the optimized control design, we show that the desired optimal tracking performance of vessel control is guaranteed due to the fact that the virtual and actual control inputs are designed as optimized solutions of every subsystem. To enhance the robustness of vessel control systems, we employ neural network (NN) approximators to approximate uncertain vessel dynamics and present adaptive control technique to estimate the upper boundedness of external disturbances. Under the reinforcement learning framework, we construct actor–critic networks to solve the Hamilton–Jacobi–Bellman equations corresponding to subsystems of surface vessel to achieve the optimized control. The optimized control algorithm can synchronously train the adaptive parameters not only for actor–critic networks but also for NN approximators and adaptive control. By Lyapunov stability theorem, we show that the RLOTC algorithm can ensure the semiglobal uniform ultimate boundedness of the closed-loop systems. Compared with the existing reinforcement learning control results, the presented RLOTC algorithm can compensate for uncertain vessel dynamics and unknown disturbances, and obtain the optimized control performance by considering optimization in every backstepping design. Simulation studies on an underactuated surface vessel are given to illustrate the effectiveness of the RLOTC algorithm.