Event-Triggered Robust Hierarchical Synchronization Control of Unmanned Surface Vehicles via Reinforcement Learning

In this paper, the event-triggered robust hierarchical synchronization (ETRHS) control of unmanned surface vehicles (USVs) is investigated via reinforcement learning. In the ETRHS control problem, there exists one dominant USV and many following USVs. The dominant USV chooses a motion control policy based on the responses of all following USVs, and then each following USV takes corresponding optimal responses to the dominant USV’s policy. This paper converts the ETRHS control problem to an event-triggered optimal synchronization control problem by designing novel value functions for the dominant and following USVs. Subsequently, critic-only structures are established and the ETRHS control laws of all USVs are obtained to form the Stackelberg equilibrium. In order to reduce the computing and communication burden, a novel event-triggering condition is designed for each USV, and the corresponding control law is updated when the condition is triggered. Theoretical analysis demonstrates that the developed reinforcement learning-based ETRHS controllers guarantee all following USVs synchronize with the dominant USV even when dynamic uncertainties exist. Finally, simulation results verify the effectiveness of the developed reinforcement learning-based ETRHS control scheme.