基于神经网络的双手机器人控制方法

Q4 Computer Science

International Journal of Automation and Smart Technology Pub Date : 2017-03-01 DOI:10.5875/AUSMT.VXIX.XX

T. Kalganova, M. Mukhtar, E. Akyürek, N. Lesne

{"title":"基于神经网络的双手机器人控制方法","authors":"T. Kalganova, M. Mukhtar, E. Akyürek, N. Lesne","doi":"10.5875/AUSMT.VXIX.XX","DOIUrl":null,"url":null,"abstract":"Human hands can precisely perform a wide range of tasks. This paper investigates key performance differences when conventional robotic hand controllers are combined with Neural Networks (NN). Tests are performed on a novel 3D printed multi-finger ambidextrous robot hand. The ambidextrous hand is actuated using pneumatic artificial muscles (PAMs) and can bend its fingers both left and right, offering full ambidextrous functionality. Force sensors are placed on the fingertips. In our control method, the grasping trajectory of each finger combines its data with that of the neighboring fingers to obtain accurate results.","PeriodicalId":38109,"journal":{"name":"International Journal of Automation and Smart Technology","volume":"7 1","pages":"27-32"},"PeriodicalIF":0.0000,"publicationDate":"2017-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Neural Network based Control Method Implemented on Ambidextrous Robot Hand\",\"authors\":\"T. Kalganova, M. Mukhtar, E. Akyürek, N. Lesne\",\"doi\":\"10.5875/AUSMT.VXIX.XX\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Human hands can precisely perform a wide range of tasks. This paper investigates key performance differences when conventional robotic hand controllers are combined with Neural Networks (NN). Tests are performed on a novel 3D printed multi-finger ambidextrous robot hand. The ambidextrous hand is actuated using pneumatic artificial muscles (PAMs) and can bend its fingers both left and right, offering full ambidextrous functionality. Force sensors are placed on the fingertips. In our control method, the grasping trajectory of each finger combines its data with that of the neighboring fingers to obtain accurate results.\",\"PeriodicalId\":38109,\"journal\":{\"name\":\"International Journal of Automation and Smart Technology\",\"volume\":\"7 1\",\"pages\":\"27-32\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Automation and Smart Technology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.5875/AUSMT.VXIX.XX\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"Computer Science\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Automation and Smart Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5875/AUSMT.VXIX.XX","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Computer Science","Score":null,"Total":0}

引用次数: 3

摘要

人手可以精确地执行各种任务。本文研究了传统机械手控制器与神经网络（NN）相结合时的关键性能差异。对一种新型的3D打印多指双手灵巧机器人手进行了测试。双手灵巧的手由气动人造肌肉（PAM）驱动，可以左右弯曲手指，提供完全的双手灵巧功能。力传感器放置在指尖。在我们的控制方法中，每个手指的抓取轨迹将其数据与相邻手指的数据相结合，以获得准确的结果。

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

Neural Network based Control Method Implemented on Ambidextrous Robot Hand

Human hands can precisely perform a wide range of tasks. This paper investigates key performance differences when conventional robotic hand controllers are combined with Neural Networks (NN). Tests are performed on a novel 3D printed multi-finger ambidextrous robot hand. The ambidextrous hand is actuated using pneumatic artificial muscles (PAMs) and can bend its fingers both left and right, offering full ambidextrous functionality. Force sensors are placed on the fingertips. In our control method, the grasping trajectory of each finger combines its data with that of the neighboring fingers to obtain accurate results.

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

International Journal of Automation and Smart Technology Engineering-Electrical and Electronic Engineering

CiteScore

0.70

自引率

0.00%

发文量

审稿时长

16 weeks

期刊介绍： International Journal of Automation and Smart Technology (AUSMT) is a peer-reviewed, open-access journal devoted to publishing research papers in the fields of automation and smart technology. Currently, the journal is abstracted in Scopus, INSPEC and DOAJ (Directory of Open Access Journals). The research areas of the journal include but are not limited to the fields of mechatronics, automation, ambient Intelligence, sensor networks, human-computer interfaces, and robotics. These technologies should be developed with the major purpose to increase the quality of life as well as to work towards environmental, economic and social sustainability for future generations. AUSMT endeavors to provide a worldwide forum for the dynamic exchange of ideas and findings from research of different disciplines from around the world. Also, AUSMT actively seeks to encourage interaction and cooperation between academia and industry along the fields of automation and smart technology. For the aforementioned purposes, AUSMT maps out 5 areas of interests. Each of them represents a pillar for better future life: - Intelligent Automation Technology. - Ambient Intelligence, Context Awareness, and Sensor Networks. - Human-Computer Interface. - Optomechatronic Modules and Systems. - Robotics, Intelligent Devices and Systems.