Shared Steering Torque Control for Lane Change Assistance: A Stochastic Game-Theoretic Approach

The challenging issue of "human-machine copilot" opens up a new frontier to enhancing driving safety. However, driver-machine conflicts and uncertain driver/external disturbances are significant problems in cooperative steering systems, which degrade the system's path-tracking ability and reduce driving safety. This paper proposes a novel stochastic game-based shared control framework to model the steering torque interaction between the driver and the intelligent electric power steering (IEPS) system. A six-order driver-vehicle dynamic system, including driver/external uncertainty, is established for path-tracking. Then, the affine linear-quadratic-based path-tracking problem is proposed to model the maneuvers of the driver and IEPS. Particularly, the feedback Nash and Stackelberg frameworks to the affine-quadratic problem are derived by stochastic dynamic programming. Two cases of copilot lane change driving scenarios are studied via computer simulation. The intrinsic relation between the stochastic Nash and Stackelberg strategies is investigated based on the results. And the steering-in-the-loop experiment reveals the potential of the proposed shared control framework in handling driver-IEPS conflicts and uncertain driver/external turbulence. Finally, the copiloting experiments with a human driver further demonstrate the rationality of the game-based pattern between both the agents.