Platoon Control
Platoon control focuses on coordinating the movement of multiple vehicles, typically autonomous, to improve traffic flow, fuel efficiency, and safety. Current research emphasizes developing robust and safe control algorithms, often employing reinforcement learning (including multi-agent and federated approaches), model predictive control, and graph neural networks to handle complex interactions and uncertainties in mixed-autonomy traffic. These advancements aim to address challenges like communication delays, heterogeneous vehicle dynamics, and unpredictable human driver behavior, ultimately contributing to more efficient and safer transportation systems.
Papers
Multi-Timescale Control and Communications with Deep Reinforcement Learning -- Part I: Communication-Aware Vehicle Control
Tong Liu, Lei Lei, Kan Zheng, Xuemin, Shen
Multi-Timescale Control and Communications with Deep Reinforcement Learning -- Part II: Control-Aware Radio Resource Allocation
Lei Lei, Tong Liu, Kan Zheng, Xuemin, Shen