Mandatory lane changes at intersections, where vehicles must switch lanes mid-block to enter the correct turning lane, are a critical contributor to traffic delay, fuel waste, and driving instability. These effects become even more serious in mixed traffic, where connected and autonomous vehicles (CAVs) must interact with unpredictable human drivers.
The team published their study in Communications in Transportation Research ( https://doi.org/10.26599/COMMTR.2026.9640011 ).
To address this challenge, researchers have developed a new artificial intelligence framework called SS-MA-PPO (Simulation-Supervised Multi-Agent Proximal Policy Optimization). Rather than treating acceleration and lane-switching as isolated tasks, the SS-MA-PPO framework treats mandatory lane-change control as a coordinated multi-agent problem. This enables CAVs to effectively coordinate with surrounding vehicles, thereby mitigating lane-changing conflicts.
A core feature is the Simulation-Guided Supervisory Module (SGSM). Its primary purpose is to act as a "safety net" during the AI's learning process. By using human-driver behavioral models to pre-evaluate decisions, it prevents the system from making risky maneuvers, ensuring that the AI remains reliable even during early training phases. The framework integrates surrounding vehicle information to shift the focus from individual vehicle speed to collective efficiency, allowing CAVs to cooperate to create gaps and smooth out traffic flow.
The team evaluated SS-MA-PPO using a real-world traffic dataset from Langfang, China. In tests varying from 20% to 100% CAV penetration, SS-MA-PPO consistently delivered the best performance in terms of delay, waiting time, fuel consumption, and stop-and-go frequency. It outperformed both rule-based methods, such as IDM + LC2013, and advanced multi-agent reinforcement learning baselines including SS-MADDPG and SS-MAA2C.
"Our framework shows that handling acceleration and lane-changing in one unified decision process, combined with supervision and cooperation, can significantly improve real traffic performance." the researchers explain.
According to the team, SS-MA-PPO provides a practical and scalable solution for CAV control in mixed traffic environments. Future research will integrate adaptive traffic signal control, extend the method to corridor- and network-scale applications, and explore more advanced data-driven human-driver models to enhance realism.
About Communications in Transportation Research
Communications in Transportation Research was launched in 2021, with academic support provided by Tsinghua University and China Intelligent Transportation Systems Association. The Editors-in-Chief are Professor Xiaobo Qu, a member of the Academia Europaea from Tsinghua University and Professor Xiaopeng (Shaw) Li from University of Wisconsin–Madison. The journal mainly publishes high-quality, original research and review articles that are of significant importance to emerging transportation systems, aiming to serve as an international platform for showcasing and exchanging innovative achievements in transportation and related fields, fostering academic exchange and development between China and the global community.
It has been indexed in SCIE, SSCI, Ei Compendex, Scopus, CSTPCD, CSCD, OAJ, DOAJ, TRID and other databases. It was selected as Q1 Top Journal in the Engineering and Technology category of the Chinese Academy of Sciences (CAS) Journal Ranking List. In 2022, it was selected as a High-Starting-Point new journal project of the "China Science and Technology Journal Excellence Action Plan". In 2024, it was selected as the Support the Development Project of "High-Level International Scientific and Technological Journals". The same year, it was also chosen as an English Journal Tier Project of the "China Science and Technology Journal Excellence Action Plan PhaseⅡ". In 2024, it received the first impact factor (2023 IF) of 12.5, ranking Top1 (1/58, Q1) among all journals in "TRANSPORTATION" category. In 2025, its 2024 IF was announced as 14.5, maintaining the Top1 position (1/62, Q1) in the same category.
From Volume 6 (2026), Communications in Transportation Research will be published by Tsinghua University Press on the SciOpen platform with the official journal website at https://www.sciopen.com/journal/2097-5023 . We kindly request that all new manuscript submissions be made through the journal's submission system at https://mc03.manuscriptcentral.com/commtr
