Attention-Based Distributional Reinforcement Learning for Safe and Efficient Autonomous Driving

Autonomous driving vehicles play a critical role in intelligent transportation systems and have garnered considerable attention. Currently, the popular approach in autonomous driving systems is to design separate optimal objectives for each independent module. Therefore, a major concern arises from the fact that these diverse optimal objectives may have an impact on the final driving policy. However, reinforcement learning provides a promising solution to tackle the challenge through joint training and its exploration ability. This letter aims to develop a safe and efficient reinforcement learning approach with advanced features for autonomous navigation in urban traffic scenarios. Firstly, we develop a novel distributional reinforcement learning method that integrates an implicit distribution model into an actor-critic framework. Subsequently, we introduce a spatial attention module to capture interaction features between the ego vehicle and other traffic vehicles, and design a temporal attention module to extract the long-term sequential feature. Finally, we utilize bird's-eye-view as a context-aware representation of traffic scenarios, fused by the above spatio-temporal features. To validate our approach, we conduct experiments on the NoCrash and CoRL benchmarks, especially on our closed-loop openDD scenarios. The experimental results demonstrate the impressive performance of our approach in terms of convergence and stability compared to the baselines.