English

Reinforcement Learning for Autonomous Driving with Latent State Inference and Spatial-Temporal Relationships

Machine Learning 2021-03-25 v2

Abstract

Deep reinforcement learning (DRL) provides a promising way for learning navigation in complex autonomous driving scenarios. However, identifying the subtle cues that can indicate drastically different outcomes remains an open problem with designing autonomous systems that operate in human environments. In this work, we show that explicitly inferring the latent state and encoding spatial-temporal relationships in a reinforcement learning framework can help address this difficulty. We encode prior knowledge on the latent states of other drivers through a framework that combines the reinforcement learner with a supervised learner. In addition, we model the influence passing between different vehicles through graph neural networks (GNNs). The proposed framework significantly improves performance in the context of navigating T-intersections compared with state-of-the-art baseline approaches.

Keywords

Cite

@article{arxiv.2011.04251,
  title  = {Reinforcement Learning for Autonomous Driving with Latent State Inference and Spatial-Temporal Relationships},
  author = {Xiaobai Ma and Jiachen Li and Mykel J. Kochenderfer and David Isele and Kikuo Fujimura},
  journal= {arXiv preprint arXiv:2011.04251},
  year   = {2021}
}

Comments

ICRA 2021

R2 v1 2026-06-23T20:00:17.323Z