Generalizing Cooperative Eco-driving via Multi-residual Task Learning

arXiv:2403.04232v1 Announce Type: cross
Abstract: Conventional control, such as model-based control, is commonly utilized in autonomous driving due to its efficiency and reliability. However, real-world autonomous driving contends with a multitude of diverse traffic scenarios that are challenging for these planning algorithms. Model-free Deep Reinforcement Learning (DRL) presents a promising avenue in this direction, but learning DRL control policies that generalize to multiple traffic scenarios is still a challenge. To address this, we introduce Multi-residual Task Learning (MRTL), a generic …

abstract algorithms arxiv autonomous autonomous driving control cs.ai cs.lg cs.ma cs.ro cs.sy diverse driving eess.sy efficiency free however planning reinforcement reinforcement learning reliability residual traffic type via world