Multi Vehicle Pursuit
Multi-vehicle pursuit (MVP) research focuses on developing algorithms enabling multiple autonomous vehicles to cooperatively track and capture a moving target, often in complex environments like urban areas. Current research heavily utilizes reinforcement learning, employing architectures like deep Q-networks and transformers, often incorporating elements of hierarchical control and opponent modeling to improve pursuit efficiency and success rates in dynamic scenarios. These advancements have significant implications for applications such as autonomous law enforcement, search and rescue operations, and traffic management, improving the effectiveness and safety of multi-agent systems in real-world settings.
Papers
Graded-Q Reinforcement Learning with Information-Enhanced State Encoder for Hierarchical Collaborative Multi-Vehicle Pursuit
Yiying Yang, Xinhang Li, Zheng Yuan, Qinwen Wang, Chen Xu, Lin Zhang
An Opponent-Aware Reinforcement Learning Method for Team-to-Team Multi-Vehicle Pursuit via Maximizing Mutual Information Indicator
Qinwen Wang, Xinhang Li, Zheng Yuan, Yiying Yang, Chen Xu, Lin Zhang