Multi-task Safe Reinforcement Learning for Navigating Intersections in Dense Traffic

TL;DR

This paper introduces a multi-task safe reinforcement learning framework with social attention and safety layers to improve autonomous vehicle navigation at intersections, balancing safety and efficiency in dense traffic.

Contribution

It proposes a novel multi-task safe reinforcement learning approach incorporating social attention and safety layers for intersection navigation.

Findings

Improves safety in dense traffic scenarios.

Maintains high traffic efficiency.

Validated in SUMO and CARLA simulators.

Abstract

Multi-task intersection navigation including the unprotected turning left, turning right, and going straight in dense traffic is still a challenging task for autonomous driving. For the human driver, the negotiation skill with other interactive vehicles is the key to guarantee safety and efficiency. However, it is hard to balance the safety and efficiency of the autonomous vehicle for multi-task intersection navigation. In this paper, we formulate a multi-task safe reinforcement learning with social attention to improve the safety and efficiency when interacting with other traffic participants. Specifically, the social attention module is used to focus on the states of negotiation vehicles. In addition, a safety layer is added to the multi-task reinforcement learning framework to guarantee safe negotiation. We compare the experiments in the simulator SUMO with abundant traffic flows and CARLA with high-fidelity vehicle models, which both show that the proposed algorithm can improve safety with consistent traffic efficiency for multi-task intersection navigation.