Deng, Ning (Tsinghua University), Cai, Mengchi (Tsinghua University), Liu, Qingquan (Tsinghua University), Chen, Chaoyi (Tsinghua University), Xu, Qing (Tsinghua University), Li, Shen (Tsinghua University), Li, Meng (Tsinghua University), Li, Keqiang (Tsinghua University)

Multi-Lane Coordinated Lane Change Based on Monte Carlo Tree Search in Mixed Traffic Environments

Scheduled for presentation during the Regular Session "S10b-Cooperative and Connected Autonomous Systems" (WE-EA-T10), Wednesday, November 19, 2025, 14:50−15:30, Cooleangata 4

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 19, 2025

Abstract

Coordinated decision-making and control can help Connected and Automated Vehicles (CAVs) effectively handle the uncertainty of human-driven vehicles (HDVs) and improve overall traffic throughput. This paper presents a Monte Carlo Tree Search (MCTS)-based coordinated decision-making and control framework for CAVs in mixed traffic environments. A probabilistic modeling approach is developed to capture HDV lane-change behavior under three different motivations: free, active, and mandatory. Leveraging this model, CAVs execute safe and smooth coordinated lane changes in lane bottleneck merging scenarios. To reduce computational burden under uncertainty, a rolling horizon optimization strategy is integrated with MCTS. Simulation results demonstrate the effectiveness of the proposed method in enhancing coordination and improving traffic efficiency.