使用等变模型和把握分数优化的推抓策略学习

IF 5.3 2区 计算机科学 Q2 ROBOTICS
Boce Hu;Heng Tian;Dian Wang;Haojie Huang;Xupeng Zhu;Robin Walters;Robert Platt
{"title":"使用等变模型和把握分数优化的推抓策略学习","authors":"Boce Hu;Heng Tian;Dian Wang;Haojie Huang;Xupeng Zhu;Robin Walters;Robert Platt","doi":"10.1109/LRA.2025.3606392","DOIUrl":null,"url":null,"abstract":"Goal-conditioned robotic grasping in cluttered environments remains a challenging problem due to occlusions caused by surrounding objects, which prevent direct access to the target object. A promising solution to mitigate this issue is combining pushing and grasping policies, enabling active rearrangement of the scene to facilitate target retrieval. However, existing methods often overlook the rich geometric structures inherent in such tasks, thus limiting their effectiveness in complex, heavily cluttered scenarios. To address this, we propose the Equivariant Push-Grasp Network, a novel framework for joint pushing and grasping policy learning. Our contributions are twofold: (1) leveraging <inline-formula><tex-math>$\\text{SE}(2)$</tex-math></inline-formula>-equivariance to improve both pushing and grasping performance and (2) a grasp score optimization-based training strategy that simplifies the joint learning process. Experimental results show that our method improves grasp success rates by 45% in simulation and by 35% in real-world scenarios compared to strong baselines, representing a significant advancement in push-grasp policy learning.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 11","pages":"11180-11187"},"PeriodicalIF":5.3000,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Push-Grasp Policy Learning Using Equivariant Models and Grasp Score Optimization\",\"authors\":\"Boce Hu;Heng Tian;Dian Wang;Haojie Huang;Xupeng Zhu;Robin Walters;Robert Platt\",\"doi\":\"10.1109/LRA.2025.3606392\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Goal-conditioned robotic grasping in cluttered environments remains a challenging problem due to occlusions caused by surrounding objects, which prevent direct access to the target object. A promising solution to mitigate this issue is combining pushing and grasping policies, enabling active rearrangement of the scene to facilitate target retrieval. However, existing methods often overlook the rich geometric structures inherent in such tasks, thus limiting their effectiveness in complex, heavily cluttered scenarios. To address this, we propose the Equivariant Push-Grasp Network, a novel framework for joint pushing and grasping policy learning. Our contributions are twofold: (1) leveraging <inline-formula><tex-math>$\\\\text{SE}(2)$</tex-math></inline-formula>-equivariance to improve both pushing and grasping performance and (2) a grasp score optimization-based training strategy that simplifies the joint learning process. Experimental results show that our method improves grasp success rates by 45% in simulation and by 35% in real-world scenarios compared to strong baselines, representing a significant advancement in push-grasp policy learning.\",\"PeriodicalId\":13241,\"journal\":{\"name\":\"IEEE Robotics and Automation Letters\",\"volume\":\"10 11\",\"pages\":\"11180-11187\"},\"PeriodicalIF\":5.3000,\"publicationDate\":\"2025-09-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Robotics and Automation Letters\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/11150764/\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ROBOTICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Robotics and Automation Letters","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/11150764/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ROBOTICS","Score":null,"Total":0}
引用次数: 0

摘要

在混乱的环境中,目标条件机器人的抓取仍然是一个具有挑战性的问题,因为周围物体造成的遮挡会阻止机器人直接接触目标物体。缓解这个问题的一个有希望的解决方案是结合推送和抓取策略,使场景的主动重排,以促进目标检索。然而,现有的方法往往忽略了这些任务中固有的丰富几何结构,从而限制了它们在复杂,严重混乱的场景中的有效性。为了解决这个问题,我们提出了等变推抓网络,这是一个用于联合推抓策略学习的新框架。我们的贡献有两方面:(1)利用$\text{SE}(2)$-equivariance来提高推送和抓取性能;(2)基于抓取分数优化的训练策略,简化了联合学习过程。实验结果表明,与强基线相比,我们的方法在模拟中的抓取成功率提高了45%,在现实场景中的抓取成功率提高了35%,这代表了推抓取策略学习的重大进步。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Push-Grasp Policy Learning Using Equivariant Models and Grasp Score Optimization
Goal-conditioned robotic grasping in cluttered environments remains a challenging problem due to occlusions caused by surrounding objects, which prevent direct access to the target object. A promising solution to mitigate this issue is combining pushing and grasping policies, enabling active rearrangement of the scene to facilitate target retrieval. However, existing methods often overlook the rich geometric structures inherent in such tasks, thus limiting their effectiveness in complex, heavily cluttered scenarios. To address this, we propose the Equivariant Push-Grasp Network, a novel framework for joint pushing and grasping policy learning. Our contributions are twofold: (1) leveraging $\text{SE}(2)$-equivariance to improve both pushing and grasping performance and (2) a grasp score optimization-based training strategy that simplifies the joint learning process. Experimental results show that our method improves grasp success rates by 45% in simulation and by 35% in real-world scenarios compared to strong baselines, representing a significant advancement in push-grasp policy learning.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
IEEE Robotics and Automation Letters
IEEE Robotics and Automation Letters Computer Science-Computer Science Applications
CiteScore
9.60
自引率
15.40%
发文量
1428
期刊介绍: The scope of this journal is to publish peer-reviewed articles that provide a timely and concise account of innovative research ideas and application results, reporting significant theoretical findings and application case studies in areas of robotics and automation.
×
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:604180095
Book学术官方微信