Chen, Mingyang; Li, Bingbing; Zhang, Sunan; Zhang, Hao; Zhuang, Weichao; Yin, Guodong; Chen, Boli; (2025) A Game-Theoretical Framework for Safe Decision Making and Control of Mixed Autonomy Vehicles. IEEE Transactions on Intelligent Transportation Systems (In press).

Preview

Text Manuscrit.pdf - Accepted Version Download (11MB) | Preview

Abstract

To improve the safety and efficiency of the intelligent transportation system, especially in mixed autonomy, where human-driven vehicles (HDVs) and connected autonomous vehicles (CAVs) coexist, a two-layer learning-and-game-based coalitional decision-making and control strategy for multi-vehicle lane-changing is proposed in this paper. In particular, a gamebased coalition formation is proposed in the upper layer, which could facilitate real-time control in the lower layer, and can significantly improve computation efficiency compared with the benchmark method that optimizes the trajectories of all vehicles involved in lane-changing as a whole. In the lower layer, a Stackelberg game-based framework is utilized to model the interaction between CAVs and HDVs, where both types of vehicles can change lanes. To enhance robustness against human uncertainty, a data-enabled predictive control is applied to CAVs. Numerical simulations and human-in-the-loop (HIL) experiments are conducted based on data representing different driving behaviors, whose results demonstrate the effectiveness of our proposed framework in various lane-changing scenarios involving HDVs with different aggressiveness.

Download activity - last month

Export as JSONXMLCSV

Download activity - last 12 months

Export as CSVXMLJSON

Downloads by country - last 12 months

Export as JSONXMLCSV

Archive Staff Only

View Item