Dynamic Event-Triggered Critic Neural Network Optimal Control of Euler–Lagrange Systems With Full-State Constraints

This paper presents an optimal control strategy for Euler–Lagrange systems subject to full-state constraints, based on a dynamic event-triggered critic neural network. To handle the constraints, an error transformation technique is introduced to convert the constrained error dynamics into an unconstrained form. Leveraging the transformed system, a critic neural network is utilized to approximate the performance index and derive the corresponding optimal control law. The specific update mechanism is formulated for the weight matrix of the neural network. To alleviate computational load, a dynamic event-triggered condition is designed to limit the frequency of weight updates, thereby mitigating unnecessary computations while effectively eliminating Zeno behavior. Comprehensive stability analysis proves the proposed approach is feasible and ensures that the approximation error of the critic neural network remains uniformly ultimately bounded. Numerical simulations on a robotic manipulator demonstrate the effectiveness of the proposed method and further verify its disturbance rejection capability under parametric perturbations and external disturbances.