Seamless multi-skill learning: learning and transitioning non-similar skills in quadruped robots with limited data.

IF 2.9 Q2 ROBOTICS
Frontiers in Robotics and AI Pub Date : 2025-04-30 eCollection Date: 2025-01-01 DOI:10.3389/frobt.2025.1542692
Jiaxin Tu, Peng Zhai, Yueqi Zhang, Xiaoyi Wei, Zhiyan Dong, Lihua Zhang
{"title":"Seamless multi-skill learning: learning and transitioning non-similar skills in quadruped robots with limited data.","authors":"Jiaxin Tu, Peng Zhai, Yueqi Zhang, Xiaoyi Wei, Zhiyan Dong, Lihua Zhang","doi":"10.3389/frobt.2025.1542692","DOIUrl":null,"url":null,"abstract":"<p><p>In multi-skill imitation learning for robots, expert datasets with complete motion features are crucial for enabling robots to learn and transition between different skills. However, such datasets are often difficult to obtain. As an alternative, datasets constructed using only joint positions are more accessible, but they are incomplete and lack details, making it challenging for existing methods to effectively learn and model skill transitions. To address these challenges, this study introduces the Seamless Multi-Skill Learning (SMSL) framework. Integrated within the Adversarial Motion Priors framework and incorporating self-trajectory augmentation techniques, SMSL effectively utilizes high-quality historical experiences to guide agents in learning skills and generating smooth, natural transitions between them, addressing the learning difficulties caused by incomplete expert datasets. Additionally, the research incorporates an adaptive command sampling mechanism to balance the training opportunities for skills of various difficulties and prevent catastrophic forgetting. Our experiments highlight potential issues with baseline methods when imitating incomplete expert datasets and demonstrate the superior performance of the SMSL framework. Sim-to-real experiments on real Solo8 robots further validate the effectiveness of SMSL. Overall, this study confirms the SMSL framework's capability in real robotic applications and underscores its potential for autonomous skill learning and generation from minimal data.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"12 ","pages":"1542692"},"PeriodicalIF":2.9000,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12075956/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Robotics and AI","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3389/frobt.2025.1542692","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"ROBOTICS","Score":null,"Total":0}
引用次数: 0

Abstract

In multi-skill imitation learning for robots, expert datasets with complete motion features are crucial for enabling robots to learn and transition between different skills. However, such datasets are often difficult to obtain. As an alternative, datasets constructed using only joint positions are more accessible, but they are incomplete and lack details, making it challenging for existing methods to effectively learn and model skill transitions. To address these challenges, this study introduces the Seamless Multi-Skill Learning (SMSL) framework. Integrated within the Adversarial Motion Priors framework and incorporating self-trajectory augmentation techniques, SMSL effectively utilizes high-quality historical experiences to guide agents in learning skills and generating smooth, natural transitions between them, addressing the learning difficulties caused by incomplete expert datasets. Additionally, the research incorporates an adaptive command sampling mechanism to balance the training opportunities for skills of various difficulties and prevent catastrophic forgetting. Our experiments highlight potential issues with baseline methods when imitating incomplete expert datasets and demonstrate the superior performance of the SMSL framework. Sim-to-real experiments on real Solo8 robots further validate the effectiveness of SMSL. Overall, this study confirms the SMSL framework's capability in real robotic applications and underscores its potential for autonomous skill learning and generation from minimal data.

无缝多技能学习:有限数据下四足机器人非相似技能的学习与转换。
在机器人多技能模仿学习中,具有完整运动特征的专家数据集对于机器人在不同技能之间学习和转换至关重要。然而,这样的数据集往往很难获得。作为替代方案,仅使用关节位置构建的数据集更容易访问,但它们不完整且缺乏细节,这使得现有方法难以有效地学习和建模技能转换。为了应对这些挑战,本研究引入了无缝多技能学习(SMSL)框架。SMSL集成在对抗运动先验框架内,并结合自轨迹增强技术,有效地利用高质量的历史经验来指导智能体学习技能,并在它们之间产生平滑、自然的过渡,解决了不完整的专家数据集造成的学习困难。此外,研究还引入了自适应指令抽样机制,以平衡不同难度技能的训练机会,防止灾难性遗忘。我们的实验突出了基线方法在模仿不完整专家数据集时的潜在问题,并展示了SMSL框架的优越性能。在真实的Solo8机器人上进行仿真实验,进一步验证了SMSL的有效性。总的来说,这项研究证实了SMSL框架在实际机器人应用中的能力,并强调了其自主技能学习和从最小数据生成的潜力。
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
CiteScore
6.50
自引率
5.90%
发文量
355
审稿时长
14 weeks
期刊介绍: Frontiers in Robotics and AI publishes rigorously peer-reviewed research covering all theory and applications of robotics, technology, and artificial intelligence, from biomedical to space robotics.
×
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