• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于符号的装配技能学习中接触状态识别

Symbolic-Based Recognition of Contact States for Learning Assembly Skills.

作者信息

Al-Yacoub Ali, Zhao Yuchen, Lohse Niels, Goh Mey, Kinnell Peter, Ferreira Pedro, Hubbard Ella-Mae

机构信息

Intelligent Automation Centre, Loughborough University, Loughborough, United Kingdom.

Beijing Ewaybot Technology LLC, Beijing, China.

出版信息

Front Robot AI. 2019 Oct 17;6:99. doi: 10.3389/frobt.2019.00099. eCollection 2019.

DOI:10.3389/frobt.2019.00099
PMID:33501114
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC7805827/
Abstract

Imitation learning is gaining more attention because it enables robots to learn skills from human demonstrations. One of the major industrial activities that can benefit from imitation learning is the learning of new assembly processes. An essential characteristic of an assembly skill is its different contact states (CS). They determine how to adjust movements in order to perform the assembly task successfully. Humans can recognize CSs through haptic feedback. They execute complex assembly tasks accordingly. Hence, CSs are generally recognized using force and torque information. This process is not straightforward due to the variations in assembly tasks, signal noise and ambiguity in interpreting force/torque (F/T) information. In this research, an investigation has been conducted to recognize the CSs during an assembly process with a geometrical variation on the mating parts. The F/T data collected from several human trials were pre-processed, segmented and represented as symbols. Those symbols were used to train a probabilistic model. Then, the trained model was validated using unseen datasets. The primary goal of the proposed approach aims to improve recognition accuracy and reduce the computational effort by employing symbolic and probabilistic approaches. The model successfully recognized CS based only on force information. This shows that such models can assist in imitation learning.

摘要

模仿学习正受到越来越多的关注，因为它能使机器人从人类示范中学习技能。能从模仿学习中受益的主要工业活动之一是新装配工艺的学习。装配技能的一个基本特征是其不同的接触状态（CS）。它们决定了如何调整动作以便成功执行装配任务。人类可以通过触觉反馈识别接触状态。他们据此执行复杂的装配任务。因此，通常使用力和扭矩信息来识别接触状态。由于装配任务的变化、信号噪声以及在解释力/扭矩（F/T）信息时的模糊性，这个过程并不简单。在这项研究中，已经进行了一项调查，以识别在配合零件存在几何变化的装配过程中的接触状态。从几次人类试验中收集的F/T数据经过预处理、分段并表示为符号。这些符号被用来训练一个概率模型。然后，使用未见过的数据集对训练好的模型进行验证。所提出方法的主要目标旨在通过采用符号和概率方法提高识别准确率并减少计算量。该模型仅基于力信息就成功识别了接触状态。这表明这样的模型可以协助模仿学习。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/7016422f2b45/frobt-06-00099-g0015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/7f3e1be31fac/frobt-06-00099-g0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/16b3cbaeb8dc/frobt-06-00099-g0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/2758cc96ed7b/frobt-06-00099-g0003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/2fe54cb14319/frobt-06-00099-g0004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/15044103a485/frobt-06-00099-g0005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/ecaf226b7797/frobt-06-00099-g0006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/35e40bf1902e/frobt-06-00099-g0007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/3d3df18615dc/frobt-06-00099-g0008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/6649aa84c64f/frobt-06-00099-g0009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/cadda8aaef18/frobt-06-00099-g0010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/b30b03962a4f/frobt-06-00099-g0011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/1810546e3f36/frobt-06-00099-g0012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/b82d57ec2211/frobt-06-00099-g0013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/81a8d813f771/frobt-06-00099-g0014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/7016422f2b45/frobt-06-00099-g0015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/7f3e1be31fac/frobt-06-00099-g0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/16b3cbaeb8dc/frobt-06-00099-g0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/2758cc96ed7b/frobt-06-00099-g0003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/2fe54cb14319/frobt-06-00099-g0004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/15044103a485/frobt-06-00099-g0005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/ecaf226b7797/frobt-06-00099-g0006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/35e40bf1902e/frobt-06-00099-g0007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/3d3df18615dc/frobt-06-00099-g0008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/6649aa84c64f/frobt-06-00099-g0009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/cadda8aaef18/frobt-06-00099-g0010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/b30b03962a4f/frobt-06-00099-g0011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/1810546e3f36/frobt-06-00099-g0012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/b82d57ec2211/frobt-06-00099-g0013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/81a8d813f771/frobt-06-00099-g0014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c6ee/7805827/7016422f2b45/frobt-06-00099-g0015.jpg

相似文献

1
Symbolic-Based Recognition of Contact States for Learning Assembly Skills.基于符号的装配技能学习中接触状态识别
Front Robot AI. 2019 Oct 17;6:99. doi: 10.3389/frobt.2019.00099. eCollection 2019.
2
Peg-in-hole assembly skill imitation learning method based on ProMPs under task geometric representation.基于任务几何表示的ProMPs的插销入孔装配技能模仿学习方法
Front Neurorobot. 2023 Nov 9;17:1320251. doi: 10.3389/fnbot.2023.1320251. eCollection 2023.
3
Objective laparoscopic skills assessments of surgical residents using Hidden Markov Models based on haptic information and tool/tissue interactions.基于触觉信息和工具/组织相互作用，使用隐马尔可夫模型对外科住院医师进行客观的腹腔镜技能评估。
Stud Health Technol Inform. 2001;81:417-23.
4
An Adaptive Imitation Learning Framework for Robotic Complex Contact-Rich Insertion Tasks.用于机器人复杂的富含接触的插入任务的自适应模仿学习框架
Front Robot AI. 2022 Jan 11;8:777363. doi: 10.3389/frobt.2021.777363. eCollection 2021.
5
Deep imitation learning for 3D navigation tasks.用于3D导航任务的深度模仿学习
Neural Comput Appl. 2018;29(7):389-404. doi: 10.1007/s00521-017-3241-z. Epub 2017 Dec 4.
6
Leveraging Haptic Feedback to Improve Data Quality and Quantity for Deep Imitation Learning Models.利用触觉反馈提高深度模仿学习模型的数据质量和数量。
IEEE Trans Haptics. 2024 Oct-Dec;17(4):984-991. doi: 10.1109/TOH.2024.3384482. Epub 2024 Dec 19.
7
Hidden Markov model approach to skill learning and its application to telerobotics.
IEEE Trans Rob Autom. 1994 Oct;10(5):621-31. doi: 10.1109/70.326567.
8
A Bayesian Developmental Approach to Robotic Goal-Based Imitation Learning.一种基于贝叶斯发展方法的机器人目标导向模仿学习
PLoS One. 2015 Nov 4;10(11):e0141965. doi: 10.1371/journal.pone.0141965. eCollection 2015.
9
Extended residual learning with one-shot imitation learning for robotic assembly in semi-structured environment.半结构化环境下用于机器人装配的基于一次性模仿学习的扩展残差学习
Front Neurorobot. 2024 Apr 29;18:1355170. doi: 10.3389/fnbot.2024.1355170. eCollection 2024.
10
Development and validation of a surgical training simulator with haptic feedback for learning bone-sawing skill.开发并验证一种具有触觉反馈的外科手术训练模拟器，用于学习骨锯技能。
J Biomed Inform. 2014 Apr;48:122-9. doi: 10.1016/j.jbi.2013.12.010. Epub 2013 Dec 28.

本文引用的文献

1
A double-loop structure in the adaptive generalized predictive control algorithm for control of robot end-point contact force.用于控制机器人端点接触力的自适应广义预测控制算法中的双环结构。
ISA Trans. 2014 Sep;53(5):1603-8. doi: 10.1016/j.isatra.2014.05.024. Epub 2014 Jun 24.
2
Humans integrate visual and haptic information in a statistically optimal fashion.人类以统计上最优的方式整合视觉和触觉信息。
Nature. 2002 Jan 24;415(6870):429-33. doi: 10.1038/415429a.