This article presents an adaptive prescribed-time dynamic surface control approach for a differential-driven unmanned surface vehicle (USV) with fully unknown parameters, which is a cascaded control system consisting of kinematic, kinetic, and motor-driven propeller layers. First, the control design of the kinematic layer determines the virtual surge and yaw velocities, which are filtered as the pseudocommands for the kinetic layer. By imposing a performance function for the position error of the USV, it can be driven into the preset precision region within the prescribed time. Second, the virtual force control laws designed in the kinetic layer give the desired motor angular speed commands, which are filtered as the pseudocommands for the propeller layer. Then, in the control design of the propeller layer, the actual command duty cycles are proposed to make the actual motor angular speed follow these pseudospeed commands of motors to apply in practice directly. By employing the fuzzy logic system to approximate the nonlinearities, we can establish a simpler control structure than the existing disturbance-observer-based controller due to the avoidance of virtual control laws and the adaptive compensations of modeling uncertainties. Finally, experimental results show that the proposed method makes the tacking task successful with user-defined performance.

Accurate performance and low energy consumption are essential for trajectory tracking control of an underactuated surface vessel (USV) to satisfy marine operation requirements. This paper studies the user-specified optimal tracking control problem for the USV in the presence of modeling uncertainties. A fuzzy weights-based adaptive reinforcement learning (RL) control scheme is developed to achieve the tracking control with the predefined convergence time and steady-state accuracy while minimizing the performance index function. The constructed performance index function includes the surge velocity control law and the constrained position tracking error. Following that, an optimal backstepping design frame is proposed to derive the controllers with unknown gradient terms by constructing the error subsystems at the kinematic and kinetic levels of the USV. Then, a fuzzy reinforcement learning algorithm (FRLA) is presented to derive the optimal control solutions of corresponding error subsystems. Since the fuzzy basis function vectors derived from measured states of the USV system may be zero vectors, the persistence excitation condition may not always be satisfied. Thus, in the design of fuzzy RL updating laws of critics and actors, a positive parameter compensation technique is proposed to make the matrixes consist of fuzzy basis functions strictly positive definite. It releases the need for assumption of persistence excitation, and the convergence of the critic weight estimate and the boundedness of closed-loop systems can be guaranteed. Finally, the effectiveness of the presented method is demonstrated by numerical simulations and real-world experiments.

This article addresses the event-based adaptive optimal fault-tolerant consensus control problem for a class of nonlinear multiagent systems (MASs) under a directed graph. It can be solved that both control gains and actuator failure parameters are unknown in considered MASs, which enhances the practicability of optimal consensus control. First, a reinforcement learning-based distributed optimal control law is designed by constructing the identifier-critic-actor learning networks. Furthermore, by utilizing the distributed optimal control law as an auxiliary variable, an adaptive fault-tolerant controller is proposed to effectively compensate for actuator failures. Meanwhile, a co-design scheme is proposed for the construction of an event-triggered control input with the fault-tolerant property. It is proven that the designed control input ensures the boundedness of closed-loop systems through rigorous stability analysis. Finally, the effectiveness of the developed approach can be illustrated via simulations of numerical nonlinear MASs and a group of autonomous underwater vehicles.

This article studies the optimized backstepping consensus control problem for uncertain nonstrict-feedback nonlinear multiagent systems with intermittent actuator faults and input quantization. A fuzzy approximation-based optimal consensus control scheme is proposed via the reinforcement learning algorithm. Meanwhile, a time-varying constraint function is embedded into the optimized backstepping consensus design to guarantee the consensus errors converge to a preassigned residual set within the prescribed time. To overcome the difficulty of the virtual optimized controller design caused by unknown virtual control coefficients, a class of intermediate variables is designed. A modified variable separation technique is proposed to circumvent the problem of algebraic loop caused by the construction of virtual optimized controllers. Then, based on the reconstruction of unknown bounds, a fault-tolerant controller under the quantization action is developed to compensate for the impact of unknown actuator faults automatically, and achieve semiglobally ultimately uniformly bounded results. In the end, a practical example of a group of single-link manipulators is given to illustrate the validity of the presented method.

This article addresses the problem of prescribed-time optimal consensus control for a class of uncertain nonlinear multiagent systems (MASs) subject to denial-of-service (DoS) attacks over resilient event-triggered communication (RETC). First, a novel performance index function is devised to balance the convergence of consensus error and the cost of control energy, thereby achieving the optimal consensus with the preassigned steady-state precision and convergence time. Subsequently, a set of intermediate variables is established within the framework of reinforcement learning (RL)-based optimized backstepping to solve the problem of unknown control gains, which facilitates the implementation of optimal controllers. Furthermore, the designed actual optimal control law is transmitted through RETC, which provides two advanced advantages: 1) a resilient switching control protocol to avoid the impact of DoS attacks and 2) a flexible switching threshold event-triggered mechanism to conserve communication resources and balance system performance. Finally, the effectiveness of the presented approach is verified by a simulation example.