Safe and Human-Like Autonomous Driving: A Predictor–Corrector Potential Game Approach

This article proposes a novel decision-making framework for autonomous vehicles (AVs), called predictor–corrector potential game (PCPG), composed of a predictor and a corrector. To enable human-like reasoning and characterize agent interactions, a receding-horizon multiplayer game is formulated. To address the challenges caused by the complexity of solving a multiplayer game and by the requirement of real-time operation, a potential game (PG)-based decision-making framework is developed in the PG predictor, where the agents’ cost functions are heuristically predefined. We acknowledge that the behaviors of other traffic agents, for example, human-driven vehicles and pedestrians, may not necessarily be consistent with the predefined cost functions. To address this issue, a best response-based PG corrector is designed. In the corrector, the action deviation between the ego vehicle prediction and the surrounding agents’ actual behaviors are measured and are fed back to the ego vehicle decision-making, to correct the prediction errors caused by the inaccurate predefined cost functions and to improve the ego vehicle strategies. Distinguished from most existing game-theoretic approaches, this PCPG: 1) deals with multiplayer games and guarantees the existence of a pure-strategy Nash equilibrium (PSNE) and the convergence of the PSNE-seeking algorithm; 2) is computationally scalable in a multiagent scenario; 3) guarantees the ego vehicle safety under suitable conditions; and 4) approximates the actual PSNE of the system despite the unknown cost functions of others. Comparative studies between the PG, the PCPG, and the control barrier function (CBF)-based approaches are conducted in diverse traffic scenarios, including oncoming traffic scenarios and multivehicle intersection-crossing scenarios. The results from validation case studies based on a naturalistic dataset are reported.