Reactive Stepping for Humanoid Robots using Reinforcement Learning: Application to Standing Push Recovery on the Exoskeleton Atalante

Author:

Duburcq Alexis1,Schramm Fabian1,Boeris Guilhem1,Bredeche Nicolas2,Chevaleyre Yann3

Affiliation:

1. Wandercraft,Paris,France

2. Sorbonne Université, CNRS, Institut des Systèmes Intelligents et de Robotique, ISIR,Paris,France,F-75005

3. Université Paris-Dauphine, PSL, CNRS, Laboratoire d'analyse et modélisation de systèmes pour l,Paris,France

Publisher

IEEE

Reference41 articles.

1. Decoding Motor Skills of Artificial Intelligence and Human Policies: A Study on Humanoid and Human Balance Control

2. Push Recovery Strategies through Deep Reinforcement Learning

3. High-dimensional continuous control using generalized advantage estimation;schulman;International Conference on Learning Representations (ICLR),2016

4. Dynamic Balance Force Control for compliant humanoid robots

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Push and Pull Robot with Reinforcement Learning Algorithms;2024 9th International Conference on Integrated Circuits, Design, and Verification (ICDV);2024-06-06

2. ExoRecovery: Push Recovery with a Lower-Limb Exoskeleton Based on Stepping Strategy;2024 IEEE International Conference on Robotics and Automation (ICRA);2024-05-13

3. Biomimetic Viscoelastic Compliance Control for Self-Balancing Lower Limb Exoskeleton;IEEE Transactions on Industrial Informatics;2024

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3