Reinforcement Learning for Autonomous Driving with Latent State Inference and Spatial-Temporal Relationships
This work addresses the challenge of subtle cue identification in autonomous driving for safer navigation in human environments, though it appears incremental as it builds on existing reinforcement learning methods.
The paper tackles the problem of autonomous driving navigation by inferring latent states of other drivers and modeling spatial-temporal relationships, resulting in significant performance improvements at T-intersections compared to state-of-the-art baselines.
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.