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 2302.03385cs.RO
收藏

NeuronsGym: 面向机器人任务Sim2Real策略学习的混合框架与基准

NeuronsGym: A Hybrid Framework and Benchmark for Robot Tasks with Sim2Real Policy Learning

Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学)

Haoran Li, Shasha Liu, Mingjun Ma, Guangzheng Hu, Yaran Chen, Dongbin Zhao

AI总结:

本研究提出面向机器人任务Sim2Real策略学习的混合框架NeuronsGym,含仿真训练与实物验证系统,提出SFPL安全评估指标,构建导航与对抗任务基准并举办挑战赛,推动通用移动智能体算法发展。

摘要:

具身AI的兴起极大提升了通用移动智能体系统的发展可能性。目前已有众多场景丰富、视觉保真度高、应用场景多样的评估平台被开发出来。本文提出了一个名为NeuronsGym的混合框架,可用于机器人任务的策略学习,涵盖用于训练策略的仿真平台,以及用于研究sim2real问题的实物系统。与当前多数单任务、移动缓慢的机器人平台不同,本框架提供了速度范围更广的敏捷实物机器人,可用于训练机器人导航与对抗策略。同时,为评估机器人导航的安全性,我们提出了安全加权路径长度(SFPL),以改进当前移动机器人导航中的安全评估。基于该平台,我们通过对比当前主流的sim2real方法,构建了该平台下导航与对抗任务的全新基准,并举办了2022 IEEE Conference on Games(CoG,IEEE游戏大会)RoboMaster sim2real挑战赛。我们已开源该框架的代码(https://github.com/DRL-CASIA/NeuronsGym),希望该平台能推动更灵活敏捷的通用移动智能体算法的发展。

英文摘要:

The rise of embodied AI has greatly improved the possibility of general mobile agent systems. At present, many evaluation platforms with rich scenes, high visual fidelity and various application scenarios have been developed. In this paper, we present a hybrid framework named NeuronsGym that can be used for policy learning of robot tasks, covering a simulation platform for training policy, and a physical system for studying sim2real problems. Unlike most current single-task, slow-moving robotic platforms, our framework provides agile physical robots with a wider range of speeds, and can be employed to train robotic navigation and confrontation policies. At the same time, in order to evaluate the safety of robot navigation, we propose a safety-weighted path length (SFPL) to improve the safety evaluation in the current mobile robot navigation. Based on this platform, we build a new benchmark for navigation and confrontation tasks under this platform by comparing the current mainstream sim2real methods, and hold the 2022 IEEE Conference on Games (CoG) RoboMaster sim2real challenge. We release the codes of this framework\footnote{\url{https://github.com/DRL-CASIA/NeuronsGym}} and hope that this platform can promote the development of more flexible and agile general mobile agent algorithms.

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。

↑