基于kinect V2的多人与人形机器人同步运动

P. S. Akhil, A. M. Parimi
{"title":"基于kinect V2的多人与人形机器人同步运动","authors":"P. S. Akhil, A. M. Parimi","doi":"10.1109/ICIINFS.2016.8262973","DOIUrl":null,"url":null,"abstract":"Humanoid robots have evolved into a key technology required for many applications which are beyond the reach of humans. As these robots have high number degrees of freedom, a conventional control system is hard to develop. Tele-operation of these humanoid robots by humans is one area which has drawn a lot of interest from the researchers in recent times. This paper proposes a method to imitate the physical movements of multiple persons using Kinect V2 developed by Microsoft. Two main issues have been addressed in this paper. One is finding out the position of speaker when a verbal command is given and the other is to track the body of the speaker and mimic. Multi — microphone array in Kinect V2 has been used for speech recognition and to point the direction of the speaker. Once a mimic command is given by a person, the location of his/her body is obtained and the skeletal data of this person would be used to imitate. The skeletal data of the person being tracked will contain 25 three dimensional coordinates which are the positions of various joints in the body with respect to Kinect V2. Angles at various joints of the skeleton are extracted and given to the microcontroller which controls the humanoid robot. Humanoid robots are not very much stable, whenever the posture of the robot changes there is every chance that the robot may go out of balance. Hence a Zero Moment Point (ZMP) based balance algorithm is implemented for the balancing of the robot.","PeriodicalId":234609,"journal":{"name":"2016 11th International Conference on Industrial and Information Systems (ICIIS)","volume":"205 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Synchronization of motion from multiple humans and humanoid robot based on kinect V2\",\"authors\":\"P. S. Akhil, A. M. Parimi\",\"doi\":\"10.1109/ICIINFS.2016.8262973\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Humanoid robots have evolved into a key technology required for many applications which are beyond the reach of humans. As these robots have high number degrees of freedom, a conventional control system is hard to develop. Tele-operation of these humanoid robots by humans is one area which has drawn a lot of interest from the researchers in recent times. This paper proposes a method to imitate the physical movements of multiple persons using Kinect V2 developed by Microsoft. Two main issues have been addressed in this paper. One is finding out the position of speaker when a verbal command is given and the other is to track the body of the speaker and mimic. Multi — microphone array in Kinect V2 has been used for speech recognition and to point the direction of the speaker. Once a mimic command is given by a person, the location of his/her body is obtained and the skeletal data of this person would be used to imitate. The skeletal data of the person being tracked will contain 25 three dimensional coordinates which are the positions of various joints in the body with respect to Kinect V2. Angles at various joints of the skeleton are extracted and given to the microcontroller which controls the humanoid robot. Humanoid robots are not very much stable, whenever the posture of the robot changes there is every chance that the robot may go out of balance. Hence a Zero Moment Point (ZMP) based balance algorithm is implemented for the balancing of the robot.\",\"PeriodicalId\":234609,\"journal\":{\"name\":\"2016 11th International Conference on Industrial and Information Systems (ICIIS)\",\"volume\":\"205 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 11th International Conference on Industrial and Information Systems (ICIIS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICIINFS.2016.8262973\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 11th International Conference on Industrial and Information Systems (ICIIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICIINFS.2016.8262973","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

人形机器人已经发展成为许多人类无法企及的应用所需要的关键技术。由于这些机器人具有高自由度,传统的控制系统难以开发。人类对这些类人机器人的远程操作是近年来研究人员非常感兴趣的一个领域。本文提出了一种利用微软公司开发的Kinect V2来模拟多人物理动作的方法。本文主要讨论了两个问题。一种是在发出口头命令时找出说话人的位置,另一种是跟踪说话人的身体并模仿。Kinect V2中的多麦克风阵列已被用于语音识别和指向扬声器的方向。一旦一个人发出模仿命令,就会获得他/她身体的位置,并使用这个人的骨骼数据进行模仿。被跟踪的人的骨骼数据将包含25个三维坐标,这些坐标是相对于Kinect V2的身体中各种关节的位置。提取骨架各关节处的角度,并将其传递给控制仿人机器人的单片机。人形机器人的稳定性不是很好,每当机器人的姿势改变时,机器人就有可能失去平衡。为此,提出了一种基于零力矩点的平衡算法来实现机器人的平衡。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Synchronization of motion from multiple humans and humanoid robot based on kinect V2
Humanoid robots have evolved into a key technology required for many applications which are beyond the reach of humans. As these robots have high number degrees of freedom, a conventional control system is hard to develop. Tele-operation of these humanoid robots by humans is one area which has drawn a lot of interest from the researchers in recent times. This paper proposes a method to imitate the physical movements of multiple persons using Kinect V2 developed by Microsoft. Two main issues have been addressed in this paper. One is finding out the position of speaker when a verbal command is given and the other is to track the body of the speaker and mimic. Multi — microphone array in Kinect V2 has been used for speech recognition and to point the direction of the speaker. Once a mimic command is given by a person, the location of his/her body is obtained and the skeletal data of this person would be used to imitate. The skeletal data of the person being tracked will contain 25 three dimensional coordinates which are the positions of various joints in the body with respect to Kinect V2. Angles at various joints of the skeleton are extracted and given to the microcontroller which controls the humanoid robot. Humanoid robots are not very much stable, whenever the posture of the robot changes there is every chance that the robot may go out of balance. Hence a Zero Moment Point (ZMP) based balance algorithm is implemented for the balancing of the robot.
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
自引率
0.00%
发文量
0
×
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:481959085
Book学术官方微信