A Real-Time Generalized Nash Equilibrium Framework for Interaction-Aware Autonomous Driving in Mixed Traffic
This work addresses the safety and efficiency challenges faced by autonomous vehicles in mixed traffic, where the unpredictable behavior of human drivers complicates interaction. To tackle this issue, the paper formulates driving interactions as a generalized Nash equilibrium problem—a framework introduced here for the first time in a real-time autonomous driving system. By jointly optimizing vehicle strategies while explicitly coupling safety and geometric constraints, the approach enables dynamic coordination between autonomous policies and human behaviors. To solve the resulting non-convex equilibrium problem efficiently, the authors develop a dedicated particle swarm optimization (PSO)-based solver capable of millisecond-level decision-making. Real-world vehicle tests demonstrate that the system converges within 50 milliseconds, generating smooth, human-like trajectories that effectively handle critical interactive scenarios.