Learning Agile Hybrid Whole-body Motor Skills for Thruster-Aided Humanoid Robots

Learning Agile Hybrid Whole-body Motor Skills for Thruster-Aided Humanoid Robots
复制标题

学习推进器辅助人形机器人的敏捷混合全身运动技能

DOI:
10.1109/iros47612.2022.9981974
复制
发表时间:
2022
期刊:
in Proceedings of The 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems,
影响因子:
--
通讯作者:
Inaba Masayuki
Inaba Masayuki
中科院分区:
--
文献类型:
--
作者:
Shi Fan;Anzai Tomoki;Kojio Yuta;Okada Kei;Inaba Masayuki

文献摘要

参考文献

被引文献

相似文献

人形机器人是具有多种运动技能潜力的多功能平台。然而,这种只有两个接触脚的接触开关系统在许多情况下很难保持平衡。受到鸟类结合腿和翅膀的启发,我们提出了借助推进器套装的人形机器人的新颖混合运动行为。为了充分利用它们的敏捷性,同时保证高效计算,我们结合了基于强化学习的神经控制器来处理高度非线性系统的复杂性和基于优化的控制器来显式处理安全关键推进器模块的约束条件。我们的学习框架在几个具有混合步行甚至动态运动技能的推进器辅助人形平台上进行了演示。据我们所知,这是第一个工作,1.在推进器辅助的人形机器人上展示了敏捷的混合全身运动技能; 2.在强化学习设置下实现混合运动。
Humanoid robots are versatile platforms with the potential for multiple locomotion skills. However, this contact-switched system with only two contact feet is fragile to keep balance in many scenarios. Inspired by birds combining legs and wings, we propose the novel hybrid locomotion behavior for the humanoid robots with the aid of a thruster suit. To fully leverage their agility while guaranteeing efficient computation, we combine the neural controller based on reinforcement learning to handle the complexity of the highly non-linear system and the optimization-based controller to explicitly handle the constraint conditions of the safety-critical thruster module. Our learning framework is demonstrated on several thruster-aided humanoid platforms with hybrid walking and even dynamic locomotion skills. To our best knowledge, it is the first work that, 1. demonstrates agile hybrid whole-body locomotion skills on the thruster-aided humanoid robot; 2. achieves hybrid locomotion under the reinforcement learning settings.
Jet-HR1:基于涵道风扇推进系统的二维双足机器人跨过大型障碍物
DOI: 10.1109/humanoids.2017.8246905
发表时间: 2017
期刊: 2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids)
影响因子: --
作者:
Zhifeng Huang;Biao Liu;Jiapeng Wei;Qingsheng Lin;J. Ota;Yun Zhang
通讯作者: Yun Zhang
喷气动力机器人模型喷气发动机的建模、识别和控制
DOI: 10.1109/lra.2020.2970572
发表时间: 2019
影响因子: 5.2
作者:
Giuseppe L’Erario;Luca Fiorio;Gabriele Nava;Fabio Bergonti;Hosameldin Awadalla Omer Mohamed;Silvio Traversaro;D. Pucci
通讯作者: D. Pucci
基于降阶模型的推进器辅助腿式运动反馈设计
DOI: --
发表时间: 2021
期刊: arXiv.org
影响因子: --
作者:
Pravin Dangol;A. Ramezani
通讯作者: A. Ramezani
DOI: 10.1109/lra.2018.2792536
发表时间: 2018-04-01
影响因子: 5.2
作者:
Hwangbo, Jemin;Lee, Joonho;Hutter, Marco
通讯作者: Hutter, Marco