An integration planning and control method of intelligent vehicles based on the iterative linear quadratic regulator

This paper proposes an integrated strategy of planning and control to address the poor quality of the generated trajectory by intelligent vehicles. The trajectory planner is designed based on the iterative linear quadratic regulator (ILQR) theory, taking into account the nonlinear dynamics of the vehicle in the trajectory planning layer. The planner directly outputs the control commands that act on the actuator, achieving the integration of planning and control. To improve the control performance of the trajectory planner under extreme operating conditions, a stability controller is developed using the sliding mode control method (SMC). Additionally, a torque distributor is designed to coordinate the control requirements of the trajectory planner and the stability controller, with the optimization goal of minimizing the tire loading rate. Finally, complex scenario tests are carried out under various working conditions to evaluate the performance of the integrated strategy. The results indicate that the integrated strategy outperforms the decoupled strategy in terms of control performance and exhibits better adaptability across various working conditions and sce-narios. Even if the reference trajectory is unreasonable, the vehicle can still perform smooth, efficient, and comfortable obstacle avoidance and lane-changing maneuvers. By working in tandem, the stability controller and the trajectory planner can expand the planning and control boundaries of the system, thereby significantly enhancing the system's ability to respond to extreme working conditions.