Weakly Supervised Reinforcement Learning for Autonomous Highway Driving via Virtual Safety Cages

TL;DR

This paper introduces a reinforcement learning approach for autonomous highway driving that uses rule-based safety cages as weak supervision, improving safety, convergence speed, and interpretability of the control policies.

Contribution

It proposes a novel weak supervision method using safety cages to guide reinforcement learning in autonomous driving, enhancing safety and interpretability.

Findings

Safety cages improve exploration safety.

Weak supervision accelerates training convergence.

Models with safety cages perform better under sub-optimal parameters.

Abstract

The use of neural networks and reinforcement learning has become increasingly popular in autonomous vehicle control. However, the opaqueness of the resulting control policies presents a significant barrier to deploying neural network-based control in autonomous vehicles. In this paper, we present a reinforcement learning based approach to autonomous vehicle longitudinal control, where the rule-based safety cages provide enhanced safety for the vehicle as well as weak supervision to the reinforcement learning agent. By guiding the agent to meaningful states and actions, this weak supervision improves the convergence during training and enhances the safety of the final trained policy. This rule-based supervisory controller has the further advantage of being fully interpretable, thereby enabling traditional validation and verification approaches to ensure the safety of the vehicle. We compare models with and without safety cages, as well as models with optimal and constrained model parameters, and show that the weak supervision consistently improves the safety of exploration, speed of convergence, and model performance. Additionally, we show that when the model parameters are constrained or sub-optimal, the safety cages can enable a model to learn a safe driving policy even when the model could not be trained to drive through reinforcement learning alone.