基于椭圆拟合的桌面目标抓取方法研究

Cobot Pub Date : 2023-09-29 DOI:10.12688/cobot.17497.2

Shaolin Zhang, Yueguang Ge, Wenkai Chang, Haitao Wang, Shuo Wang

{"title":"基于椭圆拟合的桌面目标抓取方法研究","authors":"Shaolin Zhang, Yueguang Ge, Wenkai Chang, Haitao Wang, Shuo Wang","doi":"10.12688/cobot.17497.2","DOIUrl":null,"url":null,"abstract":"<ns4:p>The grasping operation task in service scenes faces several problems including too many kinds of objects and a large amount of training data. This paper focuses on the grasping strategy and pose detection in desktop object grasping tasks. A grasping strategy is given based on the combination of desktop normal vector detection, object category detection, and grasping pose detection. The grasping pose is calculated by ellipse fitting on the depth map. An optimal function is designed to evaluate the possibility of the object sliding along the ellipse axis and the stability of the grasping height. The most reliable grasping pose is selected. Finally, experiments were carried out with a six-degree-of-freedom manipulator, and the proposed grasping method achieved effective grasping of desktop objects without prior knowledge of the object.</ns4:p>","PeriodicalId":29807,"journal":{"name":"Cobot","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Research on desktop object grasping based on ellipse fitting\",\"authors\":\"Shaolin Zhang, Yueguang Ge, Wenkai Chang, Haitao Wang, Shuo Wang\",\"doi\":\"10.12688/cobot.17497.2\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<ns4:p>The grasping operation task in service scenes faces several problems including too many kinds of objects and a large amount of training data. This paper focuses on the grasping strategy and pose detection in desktop object grasping tasks. A grasping strategy is given based on the combination of desktop normal vector detection, object category detection, and grasping pose detection. The grasping pose is calculated by ellipse fitting on the depth map. An optimal function is designed to evaluate the possibility of the object sliding along the ellipse axis and the stability of the grasping height. The most reliable grasping pose is selected. Finally, experiments were carried out with a six-degree-of-freedom manipulator, and the proposed grasping method achieved effective grasping of desktop objects without prior knowledge of the object.</ns4:p>\",\"PeriodicalId\":29807,\"journal\":{\"name\":\"Cobot\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-09-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Cobot\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.12688/cobot.17497.2\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cobot","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.12688/cobot.17497.2","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

服务场景抓取操作任务面临对象种类过多、训练数据量大等问题。本文主要研究桌面物体抓取任务中的抓取策略和姿态检测。提出了一种基于桌面法向量检测、目标类别检测和抓取姿态检测相结合的抓取策略。在深度图上通过椭圆拟合计算抓取姿态。设计了一个最优函数来评估物体沿椭圆轴滑动的可能性和抓取高度的稳定性。选择最可靠的抓握姿势。最后，在六自由度机械手上进行了实验，实验结果表明，所提出的抓取方法在不需要事先了解桌面物体的情况下实现了对桌面物体的有效抓取。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Research on desktop object grasping based on ellipse fitting

The grasping operation task in service scenes faces several problems including too many kinds of objects and a large amount of training data. This paper focuses on the grasping strategy and pose detection in desktop object grasping tasks. A grasping strategy is given based on the combination of desktop normal vector detection, object category detection, and grasping pose detection. The grasping pose is calculated by ellipse fitting on the depth map. An optimal function is designed to evaluate the possibility of the object sliding along the ellipse axis and the stability of the grasping height. The most reliable grasping pose is selected. Finally, experiments were carried out with a six-degree-of-freedom manipulator, and the proposed grasping method achieved effective grasping of desktop objects without prior knowledge of the object.

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

Cobot collaborative robots-

自引率

0.00%

发文量

期刊介绍： Cobot is a rapid multidisciplinary open access publishing platform for research focused on the interdisciplinary field of collaborative robots. The aim of Cobot is to enhance knowledge and share the results of the latest innovative technologies for the technicians, researchers and experts engaged in collaborative robot research. The platform will welcome submissions in all areas of scientific and technical research related to collaborative robots, and all articles will benefit from open peer review. The scope of Cobot includes, but is not limited to: ● Intelligent robots ● Artificial intelligence ● Human-machine collaboration and integration ● Machine vision ● Intelligent sensing ● Smart materials ● Design, development and testing of collaborative robots ● Software for cobots ● Industrial applications of cobots ● Service applications of cobots ● Medical and health applications of cobots ● Educational applications of cobots As well as research articles and case studies, Cobot accepts a variety of article types including method articles, study protocols, software tools, systematic reviews, data notes, brief reports, and opinion articles.