非专业人员如何通过多次课程对机器人进行运动学教学:教学风格的多样性及其对表现的影响

IF 3.8 2区 计算机科学 Q2 ROBOTICS
Pourya Aliasghari, Moojan Ghafurian, Chtystopher L. Nehaniv, Kerstin Dautenhahn
{"title":"非专业人员如何通过多次课程对机器人进行运动学教学:教学风格的多样性及其对表现的影响","authors":"Pourya Aliasghari, Moojan Ghafurian, Chtystopher L. Nehaniv, Kerstin Dautenhahn","doi":"10.1007/s12369-024-01164-8","DOIUrl":null,"url":null,"abstract":"<p>In real-world applications, robots should adapt to users and environments; however, users may not know how to teach new tasks to a robot. We studied whether participants without any experience in teaching a robot would become more proficient robot teachers through repeated kinesthetic human–robot teaching interactions. An experiment was conducted with twenty-eight participants who were asked to kinesthetically teach a humanoid robot different cleaning tasks in five repeated sessions, each session including four tasks. Throughout the sessions, participants’ gaze patterns, methods of manipulating the robot’s arm, their perceived workload, and some physical properties of the demonstrated actions were measured. Our data analyses revealed a diversity in non-experts’ human–robot teaching styles in repeated interactions. Three clusters of human teachers were identified based on participants’ performance in providing the demonstrations. The majority of participants significantly improved their success and speed of kinesthetic demonstrations by performing multiple rounds of teaching the robot. Overall, participants gazed less often at the robot’s hand and perceived less effort over repeated sessions. Our findings highlight how non-experts adapt to robot teaching by being exposed repeatedly to human–robot teaching tasks, without any formal training or external intervention, and we identify the characteristics of successful and improving human teachers.\n</p>","PeriodicalId":14361,"journal":{"name":"International Journal of Social Robotics","volume":"19 1","pages":""},"PeriodicalIF":3.8000,"publicationDate":"2024-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"How Non-experts Kinesthetically Teach a Robot over Multiple Sessions: Diversity in Teaching Styles and Effects on Performance\",\"authors\":\"Pourya Aliasghari, Moojan Ghafurian, Chtystopher L. Nehaniv, Kerstin Dautenhahn\",\"doi\":\"10.1007/s12369-024-01164-8\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>In real-world applications, robots should adapt to users and environments; however, users may not know how to teach new tasks to a robot. We studied whether participants without any experience in teaching a robot would become more proficient robot teachers through repeated kinesthetic human–robot teaching interactions. An experiment was conducted with twenty-eight participants who were asked to kinesthetically teach a humanoid robot different cleaning tasks in five repeated sessions, each session including four tasks. Throughout the sessions, participants’ gaze patterns, methods of manipulating the robot’s arm, their perceived workload, and some physical properties of the demonstrated actions were measured. Our data analyses revealed a diversity in non-experts’ human–robot teaching styles in repeated interactions. Three clusters of human teachers were identified based on participants’ performance in providing the demonstrations. The majority of participants significantly improved their success and speed of kinesthetic demonstrations by performing multiple rounds of teaching the robot. Overall, participants gazed less often at the robot’s hand and perceived less effort over repeated sessions. Our findings highlight how non-experts adapt to robot teaching by being exposed repeatedly to human–robot teaching tasks, without any formal training or external intervention, and we identify the characteristics of successful and improving human teachers.\\n</p>\",\"PeriodicalId\":14361,\"journal\":{\"name\":\"International Journal of Social Robotics\",\"volume\":\"19 1\",\"pages\":\"\"},\"PeriodicalIF\":3.8000,\"publicationDate\":\"2024-08-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Social Robotics\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1007/s12369-024-01164-8\",\"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}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Social Robotics","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s12369-024-01164-8","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

摘要

在实际应用中,机器人应适应用户和环境;然而,用户可能不知道如何向机器人教授新任务。我们研究了没有任何机器人教学经验的参与者是否会通过反复的人机教学互动,成为更熟练的机器人教师。我们对 28 名参与者进行了一项实验,要求他们在五个重复的环节中,以动觉方式向仿人机器人教授不同的清洁任务,每个环节包括四项任务。在整个过程中,我们测量了参与者的注视模式、操纵机器人手臂的方法、他们感知到的工作量以及演示动作的一些物理特性。我们的数据分析显示,在重复互动中,非专家的人类-机器人教学风格多种多样。根据参与者提供示范的表现,我们确定了三个人类教师集群。大多数参与者通过对机器人进行多轮教学,大大提高了动觉演示的成功率和速度。总体而言,参与者在多次教学过程中注视机器人手部的次数减少了,所付出的努力也减少了。我们的研究结果突显了非专业人员是如何在没有任何正规培训或外部干预的情况下,通过反复接触人机教学任务来适应机器人教学的。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

How Non-experts Kinesthetically Teach a Robot over Multiple Sessions: Diversity in Teaching Styles and Effects on Performance

How Non-experts Kinesthetically Teach a Robot over Multiple Sessions: Diversity in Teaching Styles and Effects on Performance

In real-world applications, robots should adapt to users and environments; however, users may not know how to teach new tasks to a robot. We studied whether participants without any experience in teaching a robot would become more proficient robot teachers through repeated kinesthetic human–robot teaching interactions. An experiment was conducted with twenty-eight participants who were asked to kinesthetically teach a humanoid robot different cleaning tasks in five repeated sessions, each session including four tasks. Throughout the sessions, participants’ gaze patterns, methods of manipulating the robot’s arm, their perceived workload, and some physical properties of the demonstrated actions were measured. Our data analyses revealed a diversity in non-experts’ human–robot teaching styles in repeated interactions. Three clusters of human teachers were identified based on participants’ performance in providing the demonstrations. The majority of participants significantly improved their success and speed of kinesthetic demonstrations by performing multiple rounds of teaching the robot. Overall, participants gazed less often at the robot’s hand and perceived less effort over repeated sessions. Our findings highlight how non-experts adapt to robot teaching by being exposed repeatedly to human–robot teaching tasks, without any formal training or external intervention, and we identify the characteristics of successful and improving human teachers.

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
CiteScore
9.80
自引率
8.50%
发文量
95
期刊介绍: Social Robotics is the study of robots that are able to interact and communicate among themselves, with humans, and with the environment, within the social and cultural structure attached to its role. The journal covers a broad spectrum of topics related to the latest technologies, new research results and developments in the area of social robotics on all levels, from developments in core enabling technologies to system integration, aesthetic design, applications and social implications. It provides a platform for like-minded researchers to present their findings and latest developments in social robotics, covering relevant advances in engineering, computing, arts and social sciences. The journal publishes original, peer reviewed articles and contributions on innovative ideas and concepts, new discoveries and improvements, as well as novel applications, by leading researchers and developers regarding the latest fundamental advances in the core technologies that form the backbone of social robotics, distinguished developmental projects in the area, as well as seminal works in aesthetic design, ethics and philosophy, studies on social impact and influence, pertaining to social robotics.
×
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