Autonomous and Human-Driven Vehicles Interacting in a Roundabout: A Quantitative and Qualitative Evaluation

arXiv:2309.08254v2 Announce Type: replace-cross
Abstract: Optimizing traffic dynamics in an evolving transportation landscape is crucial, particularly in scenarios where autonomous vehicles (AVs) with varying levels of autonomy coexist with human-driven cars. While optimizing Reinforcement Learning (RL) policies for such scenarios is becoming more and more common, little has been said about realistic evaluations of such trained policies. This paper presents an evaluation of the effects of AVs penetration among human drivers in a roundabout scenario, considering both quantitative and qualitative …

abstract arxiv autonomous autonomous vehicles autonomy cars cs.ai cs.lg cs.ro dynamics evaluation human landscape quantitative reinforcement reinforcement learning traffic transportation type vehicles