An uncertainty cognition-based game model for lane-changing process in mixed driving environment

Abstract

The non-instantaneous nature of lane-changing demands real-time adaptability for autonomous vehicles (AVs) to respond continuously changing traffic conditions. In the mixed environment where AVs coexist with human-driven vehicles (HVs), the lack of inter-vehicle information exchange necessitates the Nash Equilibrium as best response. In addition, the unpredictable intentions of HV introduce uncertainty, posing a challenge for the solution of equilibrium. This paper introduces an aggressiveness parameter reflecting human drivers' yielding tendencies to autonomous vehicles and enables human-like uncertainty cognition during lane changes. To meet the practical solution requirements of the uncertainty cognition-based game model, we propose Proactive Equilibrium Strategy Algorithm (PESA) based on two-stage Nash equilibrium and anticipation of the opponent's next-stage strategy. Utilising Next Generation Simulation (NGSIM) as environmental data, PESA shows safer and more efficient lane-changing behaviour and leads to more favourable post-lane-changing traffic conditions compared to actual data outcomes.