Lateral and longitudinal human–machine co-driving of intelligent vehicle based on driving authorities game

Due to the current limitations of autonomous driving technology, human–machine co-driving is viewed as a viable and practical intermediary solution to bridge the gap between assisted driving and fully automated driving. To address challenges related to the allocation of lateral and longitudinal driving authority, as well as the interaction between the driver and the autonomous system, this paper proposes a game-sharing control strategy that operates at both the decision-making and control levels. At the decision level, a bargaining game-based approach is employed to allocate lateral and longitudinal driving authority dynamically, adjusting the distribution in accordance with a benefit function. At the control level, a lateral controller based on an extended game is developed to compute the optimal control manoeuvres by combining the driver’s inputs and reference tracking commands. This controller smoothly combines control inputs from both the driver and the automated system to ensure vehicle stability and minimize human–machine conflict. Simulation results show that, under a double lane-change scenario, the proposed strategy reduces yaw rate, lateral velocity, and lateral deviation by 0.35 rad/s, 0.6 m/s, and 0.6 m, respectively, compared with the fuzzy authority allocation method. Additionally, under cornering conditions, lateral deviation is reduced by 0.7 m. Finally, the proposed human–machine co-driving control strategy is verified by the experiment. The results indicate that the proposed strategy not only enhances trajectory tracking accuracy but also improves vehicle stability. Furthermore, by comparing the lateral and longitudinal authority allocation between the proposed and fuzzy strategies, it is evident that the approach significantly alleviates human–machine conflict, especially by reducing the frequent transfer of authority.