Safe, Efficient, and Comfortable Reinforcement-Learning-Based Car-Following for AVs with an Analytic Safety Guarantee and Dynamic Target Speed

Abstract

Over the last decade, there has been rising interest in automated driving systems and adaptive cruise control (ACC). Controllers based on reinforcement learning (RL) are particularly promising for autonomous driving, being able to optimize a combination of criteria such as efficiency, stability, and comfort. However, RL-based controllers typically offer no safety guarantees. In this paper, we propose SECRM (the Safe, Efficient, and Comfortable RL-based car-following Model) for autonomous car-following that balances traffic efficiency maximization and jerk minimization, subject to a hard analytic safety constraint on acceleration. The acceleration constraint is derived from the criterion that the follower vehicle must have sufficient headway to be able to avoid a crash if the leader vehicle brakes suddenly. We critique safety criteria based on the time-to-collision (TTC) threshold (commonly used for RL controllers), and confirm in simulator experiments that a representative previous TTC-threshold-based RL autonomous-vehicle controller may crash (in both training and testing). In contrast, we verify that our controller SECRM is safe, in training scenarios with a wide range of leader behaviors, and in both regular-driving and emergency-braking test scenarios. We find that SECRM compares favorably in efficiency, comfort, and speed-following to both classical (non-learned) car-following controllers (intelligent driver model, Shladover, Gipps) and a representative RL-based car-following controller.

A Heterogeneity-Aware Car-Following Model: Based on the XGBoost Method

“…To validate our research, we sought out the widely recognized HighD dataset, which is an open-source dataset widely used in the field. The dataset has been extensively utilized for various studies, including car-following [29,30], lane-changing [31], and trajectory prediction [32]. One of the key advantages of the HighD dataset is its high-quality data and diverse range of scenarios.…”