Self-Awareness Safety of Deep Reinforcement Learning in Road Traffic Junction Driving

TL;DR

This paper assesses safety in deep reinforcement learning for autonomous driving at junctions, introducing a self-awareness module that significantly enhances safety metrics over baseline models.

Contribution

It proposes a novel self-awareness attention mechanism for DRL to improve safety evaluation in complex traffic scenarios, addressing limitations of traditional reward-based safety considerations.

Findings

Baseline DRL models show poor safety performance.

Self-awareness attention-DQN significantly reduces collision rate.

Improved safety metrics in intersection and roundabout scenarios.

Abstract

Autonomous driving has been at the forefront of public interest, and a pivotal debate to widespread concerns is safety in the transportation system. Deep reinforcement learning (DRL) has been applied to autonomous driving to provide solutions for obstacle avoidance. However, in a road traffic junction scenario, the vehicle typically receives partial observations from the transportation environment, while DRL needs to rely on long-term rewards to train a reliable model by maximising the cumulative rewards, which may take the risk when exploring new actions and returning either a positive reward or a penalty in the case of collisions. Although safety concerns are usually considered in the design of a reward function, they are not fully considered as the critical metric to directly evaluate the effectiveness of DRL algorithms in autonomous driving. In this study, we evaluated the safety performance of three baseline DRL models (DQN, A2C, and PPO) and proposed a self-awareness module from an attention mechanism for DRL to improve the safety evaluation for an anomalous vehicle in a complex road traffic junction environment, such as intersection and roundabout scenarios, based on four metrics: collision rate, success rate, freezing rate, and total reward. Our two experimental results in the training and testing phases revealed the baseline DRL with poor safety performance, while our proposed self-awareness attention-DQN can significantly improve the safety performance in intersection and roundabout scenarios.