Robotic Assembly of Deformable Linear Objects via Curriculum Reinforcement Learning

IF 4.6 2区计算机科学 Q2 ROBOTICS

IEEE Robotics and Automation Letters Pub Date : 2025-03-21 DOI:10.1109/LRA.2025.3553676

Kai Wu;Rongkang Chen;Qi Chen;Weihua Li

{"title":"Robotic Assembly of Deformable Linear Objects via Curriculum Reinforcement Learning","authors":"Kai Wu;Rongkang Chen;Qi Chen;Weihua Li","doi":"10.1109/LRA.2025.3553676","DOIUrl":null,"url":null,"abstract":"The automated assembly of flexible objects presents significant challenges. Although significant progress has been made in the assembly of rigid objects, the methods used for rigid objects cannot be directly applied to flexible objects due to their infinite degrees of freedom. This study proposes a reinforcement learning (RL) based method for deformable cable insertion tasks executed with a universal 2-finger gripper. Firstly, a vision-based detection method is employed to monitor the cable's state in real time, while a state classifier is introduced to provide real-time reward feedback for RL training. Secondly, an adaptive curriculum learning (CL) method is proposed to adjust the initial degree of cable bending through the success rate in the training process, allowing the RL agent to learn progressively from easier to more difficult tasks. The validation experiments were conducted on a type-C cable insertion task, where the robot grips the cable portion of the electrical connector. The results indicate that our method is capable of adapting to various degrees of cable bending, successfully handling cable configurations bent up to a maximum of 40° from its straight, unbent state, with an assembly success rate of over 90%.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 5","pages":"4770-4777"},"PeriodicalIF":4.6000,"publicationDate":"2025-03-21","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/10936981/","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

Abstract

The automated assembly of flexible objects presents significant challenges. Although significant progress has been made in the assembly of rigid objects, the methods used for rigid objects cannot be directly applied to flexible objects due to their infinite degrees of freedom. This study proposes a reinforcement learning (RL) based method for deformable cable insertion tasks executed with a universal 2-finger gripper. Firstly, a vision-based detection method is employed to monitor the cable's state in real time, while a state classifier is introduced to provide real-time reward feedback for RL training. Secondly, an adaptive curriculum learning (CL) method is proposed to adjust the initial degree of cable bending through the success rate in the training process, allowing the RL agent to learn progressively from easier to more difficult tasks. The validation experiments were conducted on a type-C cable insertion task, where the robot grips the cable portion of the electrical connector. The results indicate that our method is capable of adapting to various degrees of cable bending, successfully handling cable configurations bent up to a maximum of 40° from its straight, unbent state, with an assembly success rate of over 90%.

查看原文本刊更多论文

基于课程强化学习的可变形线性物体机器人装配

柔性物体的自动化装配提出了重大挑战。尽管在刚体装配方面已经取得了重大进展，但由于刚体具有无限自由度，所以用于刚体装配的方法不能直接应用于柔性物体。本研究提出了一种基于强化学习（RL）的方法，用于通用两指夹持器执行的可变形电缆插入任务。首先，采用基于视觉的检测方法实时监测电缆的状态，同时引入状态分类器为强化学习训练提供实时奖励反馈。其次，提出了一种自适应课程学习（CL）方法，通过训练过程中的成功率来调整电缆弯曲的初始程度，使RL智能体从较容易的任务逐步学习到较困难的任务。验证实验是在c型电缆插入任务中进行的，机器人抓住电连接器的电缆部分。结果表明，我们的方法能够适应不同程度的电缆弯曲，成功地处理电缆结构，从其直，不弯曲状态弯曲最多40°，装配成功率超过90%。

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

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.