Perceptive Pedipulation with Local Obstacle Avoidance

Jonas Stolle, Philip Arm, Mayank Mittal, Marco Hutter
{"title":"Perceptive Pedipulation with Local Obstacle Avoidance","authors":"Jonas Stolle, Philip Arm, Mayank Mittal, Marco Hutter","doi":"arxiv-2409.07195","DOIUrl":null,"url":null,"abstract":"Pedipulation leverages the feet of legged robots for mobile manipulation,\neliminating the need for dedicated robotic arms. While previous works have\nshowcased blind and task-specific pedipulation skills, they fail to account for\nstatic and dynamic obstacles in the environment. To address this limitation, we\nintroduce a reinforcement learning-based approach to train a whole-body\nobstacle-aware policy that tracks foot position commands while simultaneously\navoiding obstacles. Despite training the policy in only five different static\nscenarios in simulation, we show that it generalizes to unknown environments\nwith different numbers and types of obstacles. We analyze the performance of\nour method through a set of simulation experiments and successfully deploy the\nlearned policy on the ANYmal quadruped, demonstrating its capability to follow\nfoot commands while navigating around static and dynamic obstacles.","PeriodicalId":501031,"journal":{"name":"arXiv - CS - Robotics","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Robotics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.07195","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Pedipulation leverages the feet of legged robots for mobile manipulation, eliminating the need for dedicated robotic arms. While previous works have showcased blind and task-specific pedipulation skills, they fail to account for static and dynamic obstacles in the environment. To address this limitation, we introduce a reinforcement learning-based approach to train a whole-body obstacle-aware policy that tracks foot position commands while simultaneously avoiding obstacles. Despite training the policy in only five different static scenarios in simulation, we show that it generalizes to unknown environments with different numbers and types of obstacles. We analyze the performance of our method through a set of simulation experiments and successfully deploy the learned policy on the ANYmal quadruped, demonstrating its capability to follow foot commands while navigating around static and dynamic obstacles.
具有局部障碍物规避功能的感知脚踏装置
脚踏机器人利用腿部机器人的脚进行移动操纵,无需专用机械臂。虽然之前的研究已经展示了盲人和特定任务的脚踏技能,但它们未能考虑到环境中的静态和动态障碍。为了解决这一局限性,我们引入了一种基于强化学习的方法来训练全身障碍感知策略,该策略可在避开障碍的同时跟踪脚的位置指令。尽管只在五个不同的模拟场景中训练了该策略,但我们发现它可以泛化到具有不同数量和类型障碍物的未知环境中。我们通过一系列模拟实验分析了该方法的性能,并成功地在 ANYmal 四足动物上部署了学习到的策略,证明了它能够在绕过静态和动态障碍物的同时遵循脚部指令。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信