A Cooperative Steering Control Strategy for Human–Machine Co-Driving Based on Stackelberg Game and Reinforcement Learning
提出一种基于Stackelberg博弈和深度确定性策略梯度的人机共驾转向控制策略，通过动态分配驾驶权来平衡安全与舒适，实验显示在避障场景中驾驶稳定性提升31.49%，控制稳定性提升48.11%，驾驶员负担降低42.87%。
Human–machine co-driving is expected to be a long-term driving mode. However, existing cooperative steering control strategies often struggle to effectively handle human–machine interaction conflicts and dynamically allocate driving authority, making it difficult to balance safety and driver’s comfort. To address these issues, this article establishes a Stackelberg game-based model predictive control (MPC) framework and derives a human–machine optimal control strategy under the equilibrium conditions. Furthermore, a two-layer adaptive authority allocation model is developed using the deep deterministic policy gradient (DDPG) method, which comprehensively considers environmental risks, human–machine conflict, and driver’s states. This model prevents a vehicle from entering an unstable state by dynamically allocating the driving authority to both the human driver and the autonomous driving system. Results from driver-in-the-loop experiments indicate that, in obstacle avoidance scenarios, the proposed control strategy enhances vehicle driving stability by 31.49%, improves control stability by 48.11%, and reduces the driver’s burden by 42.87%, demonstrating that the proposed strategy can assist the driver in completing obstacle avoidance tasks and ensure driving safety in high-risk scenarios. In low-risk scenarios, it maintains the driver’s freedom, prevents excessive intervention from the autonomous driving system that could lead to significant human–machine conflicts, and alleviates the driver’s operational burden.