arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2412.09466cs.RO
收藏

基于分布强化学习的自主水面车辆集成决策与控制

Distributional Reinforcement Learning based Integrated Decision Making and Control for Autonomous Surface Vehicles

Stevens Institute of Technology(史蒂文斯理工学院)

Xi Lin, Paul Szenher, Yewei Huang, Brendan Englot

AI总结:

针对自主水面车辆在拥挤水道遵守避碰规则导航的难题,提出基于分布强化学习的连续动作空间导航系统,仿真验证其在安全与效率上优于现有方法。

摘要:

近年来,随着自主水面车辆(ASV)需求的不断增长,预计在不久的将来,用于各类海上任务的ASV部署数量将迅速增加。然而,ASV在充满障碍物的拥挤水道中执行基于传感器的自主导航仍具挑战性:感知误差、密集分布的船只以及浮标附近有限的操纵空间,可能会给遵守《国际海上避碰规则》(COLREGs)带来困难。为解决这些问题,我们提出了一种新颖的基于分布强化学习的导航系统,该系统可配合车载激光雷达(LiDAR)和里程计传感器,在连续动作空间中生成任意推力指令。在高保真Gazebo仿真中对所提系统进行的综合评估表明,它能够根据遇到的场景决定是遵守COLREGs还是采取其他有利行动,与采用最先进的分布强化学习、非分布强化学习及经典方法的系统相比,在导航安全性和效率方面表现更优。

英文摘要:

With the growing demands for Autonomous Surface Vehicles (ASVs) in recent years, the number of ASVs being deployed for various maritime missions is expected to increase rapidly in the near future. However, it is still challenging for ASVs to perform sensor-based autonomous navigation in obstacle-filled and congested waterways, where perception errors, closely gathered vehicles and limited maneuvering space near buoys may cause difficulties in following the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs). To address these issues, we propose a novel Distributional Reinforcement Learning based navigation system that can work with onboard LiDAR and odometry sensors to generate arbitrary thrust commands in continuous action space. Comprehensive evaluations of the proposed system in high-fidelity Gazebo simulations show its ability to decide whether to follow COLREGs or take other beneficial actions based on the scenarios encountered, offering superior performance in navigation safety and efficiency compared to systems using state-of-the-art Distributional RL, non-Distributional RL and classical methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑