Human-Like Decision Making: A Human–Machine Shared Steering Control System With Adaptive Authority Allocation

Aiming at the dynamic conflict and driving authority allocation problems in the human-automation shared steering control (SSC) system, this paper proposed a framework for decision-making and control integration that considering risk perception and game theory. Firstly, by introducing the risk perception field, the complex and variable driving risk is precisely quantified, and the drivers are divided into skilled, normal and unpracticed according to their driving skill. Taking the driving risk acceptance as the core element, combined with the driving skill, a two-layer architecture integrating decision-making and control is constructed. The upper path planning module efficiently generates candidate trajectories based on preview time and driving risk acceptance. The lower control module uses model predictive control (MPC) and non-cooperative Stackelberg game to realize steering interaction while ensuring the priority of driver’s intention. Meanwhile, a dynamic authority allocation strategy based on driving risk and driving skill is established. Finally, to fully verify the effectiveness of the proposed method, two double lane change (DLC) scenarios with the same and different reference trajectories were designed, and four evaluation indicators were proposed, including comfort and driving conflict. The experimental results show that compared with the Nash game, the Stackelberg-based method can guarantee the driver’s dominance, alleviate the human-automation conflict, reduce the driver’s workload and increase the driving smoothness.