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

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.

arXiv commentICRA 2021

References in corpus (8)

• Playing Atari with Deep Reinforcement Learning
• Inductive Representation Learning on Large Graphs
• Trust Region Policy Optimization
• Reinforcement Learning with Unsupervised Auxiliary Tasks
• Comparison of Deep Reinforcement Learning and Model Predictive Control for Adaptive Cruise Control
• Playing FPS Games with Deep Reinforcement Learning
• Social-WaGDAT: Interaction-aware Trajectory Prediction via Wasserstein Graph Double-Attention Network
• CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning