Adaptive Autopilot: Constrained DRL for Diverse Driving Behaviors

作     者：Selvaraj, Dinesh Cyril Vitale, Christian Panayiotou, Tania Kolios, Panayiotis Chiasserini, Carla Fabiana Ellinas, Georgios 

作者机构：CARS@Polito Politecnico di Torino Torino Italy The KIOS Research and Innovation Center of Excellence The Department of Electrical and Computer Engineering University of Cyprus Nicosia Cyprus The KIOS Research and Innovation Center of Excellence The Department of Computer Science University of Cyprus Nicosia Cyprus 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2024年

核心收录：

主　　题：Reinforcement learning 

摘      要：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 human-like driving across styles. Copyright © 2024, The Authors. All rights reserved.