LAUSR

This paper proposes a novel coordination control strategy through reinforcement learning approach for human-machine cooperative steering of intelligent vehicles, so as to realize a more flexible and efficient way for the human driver and the automated driving system to jointly complete the path-following. Firstly, the human-machine cooperative steering is modeled by the optimal preview driver model with adaptive preview time and the MPC lateral tracking model with adaptive prediction horizon and step, as well as the steering system with a realistic dual-motor steering-by-wire structure is also built into the human-machine cooperative steering system. Then, the human-machine coordination control strategy is designed and trained based on two reinforcement learning agents to further optimize the allocation of cooperative steering weights. Finally, the strategy is fully verified in lane departure simulation scenarios and also in real-world Steering-in-the-Loop experiments with real-time controller, which shows that both agents can effectively keep the vehicle with the small lateral and yaw errors in the simulation scenarios, and also can be successfully applied in the realistic human-machine cooperative system to maintain the lateral and yaw errors within a safe range during path-following.