Hierarchical Program-Triggered Reinforcement Learning Agents for Automated Driving

Recent advances in Reinforcement Learning (RL) combined with Deep Learning (DL) have demonstrated impressive performance in complex tasks, including autonomous driving. The use of RL agents in autonomous driving leads to a smooth human-like driving experience, but the limited interpretability of Deep Reinforcement Learning (DRL) creates a verification and certification bottleneck. Instead of relying on RL agents to learn complex tasks, we propose HPRL - Hierarchical Program-triggered Reinforcement Learning, which uses a hierarchy consisting of a structured program along with multiple RL agents, each trained to perform a relatively simple task. The focus of verification shifts to the master program under simple guarantees from the RL agents, leading to a significantly more interpretable and verifiable implementation as compared to a complex RL agent. The evaluation of the framework is demonstrated on different driving tasks, and National Highway Traffic Safety Administration (NHTSA) pre-crash scenarios using CARLA, an open-source dynamic urban simulation environment.

I. Introduction

There has been a steady increase in the development of self-driving cars as they possess the potential to radically change the future of mobility. Deriving safe driving policies remains a key challenge in achieving deployable autonomous driving systems. The formulation of driving strategies has been studied by three schools of work, namely rule-based methods, imitation based learning, and reinforcement learning.