Adaptive Autopilot: Constrained DRL for Diverse Driving Behaviors
This work addresses the need for safer and more natural autonomous driving to reduce driver intervention, though it is incremental as it builds on existing methods like C-DRL and focuses on a specific scenario.
This study tackled the problem of achieving human-like driving behavior in autonomous vehicles by introducing an adaptive autopilot framework using constrained deep reinforcement learning, which effectively learned safe driving policies across different driving styles in car-following scenarios.
In pursuit of autonomous vehicles, achieving human-like driving behavior is vital. This study introduces adaptive autopilot (AA), a unique framework utilizing constrained-deep reinforcement learning (C-DRL). AA aims to safely emulate human driving to reduce the necessity for driver intervention. Focusing on the car-following scenario, the process involves (i) extracting data from the highD natural driving study and categorizing it into three driving styles using a rule-based classifier; (ii) employing deep neural network (DNN) regressors to predict human-like acceleration across styles; and (iii) using C-DRL, specifically the soft actor-critic Lagrangian technique, to learn human-like safe driving policies. Results indicate effectiveness in each step, with the rule-based classifier distinguishing driving styles, the regressor model accurately predicting acceleration, outperforming traditional car-following models, and C-DRL agents learning optimal policies for humanlike driving across styles.