Spatial-Temporal-Aware Safe Multi-Agent Reinforcement Learning of Connected Autonomous Vehicles in Challenging Scenarios

@article{Zhang2022SpatialTemporalAwareSM,
  title={Spatial-Temporal-Aware Safe Multi-Agent Reinforcement Learning of Connected Autonomous Vehicles in Challenging Scenarios},
  author={Zhili Zhang and Songyang Han and Jiangwei Wang and Fei Miao},
  journal={ArXiv},
  year={2022},
  volume={abs/2210.02300}
}
—Communication technologies enable coordination among connected and autonomous vehicles (CAVs). However, it remains unclear how to utilize shared information to improve the safety and efficiency of the CAV system. In this work, we propose a framework of constrained multi-agent reinforcement learning (MARL) with a parallel safety shield for CAVs in challenging driving scenarios. The coordination mechanisms of the proposed MARL include information sharing and cooperative policy learning, with… 

Figures and Tables from this paper