Adaptive Decision-making for Autonomous Driving Vehicles

For autonomous driving vehicles (ADVs), decision-making is crucial for safe and efficient driving. However, ADVs face significant challenges in coexisting with human road users, making fast and optimal driving decisions, and operating in unknown traffic environments with only incomplete information. Unsignalized intersection and lane-changing scenarios are particularly representative of such challenges, which involves complex dynamic interactions. ADVs need to assess and predict the driving preferences of nearby vehicles to optimize and adaptively adjust their own driving policies while considering uncertainties arising from incomplete observations. In this talk, recent developments on adaptive decision-making based on game-theory and learning-based methods will be presented.