A Hierarchical Control Algorithm for a Pursuit–Evasion Game Based on Fuzzy Actor–Critic Learning and Model Predictive Control

In this paper, we adopt the fuzzy actor–critic learning (FACL) and model predictive control (MPC) algorithms to solve the pursuit–evasion game (PEG) of quadrotors. FACL is used for perception, decision-making, and predicting the trajectories of agents, while MPC is utilized to address the flight control and target optimization of quadrotors. Specifically, based on the information of the opponent, the agent obtains its own game strategy by using the FACL algorithm. Based on the reference input from the FACL algorithm, the MPC algorithm is used to develop altitude, translation, and attitude controllers for the quadrotor. In the proposed hierarchical framework, the FACL algorithm provides real-time reference inputs for the MPC controller, enhancing the robustness of quadrotor control. The simulation and experimental results show that the proposed hierarchical control algorithm effectively realizes the PEG of quadrotors.