Dynamic Event-Triggered Optimal Control for Heterogeneous Vehicle Platoon Based on Integral Reinforcement Learning

This article investigates the issue of data-based distributed optimal control for third-order heterogeneous vehicle platoon system (HVPS) with input saturation under switching topology. In the control design, the integral reinforcement learning (IRL) algorithm is used to learn the online solution of the Hamilton-Jacobi-Bellman (HJB) equation with unknown dynamics. Combining IRL algorithm and critic neural network (CNN), a distributed adaptive optimal control approach is designed based on dynamic event-triggered (DET) mechanism. By the aid of topology-dependent Lyapunov function and the average dwell time method, the developed optimal control method demonstrates that all the signals in the considered system are uniformly ultimately bounded (UUB), the closed-loop system can achieve Nash equilibrium and string stability can be ensured. In addition, Zeno behavior can also be avoided. Finally, to illustrate the effectiveness of the developed optimal control approach, a simulation example is given.