Jindan Huang, Isaac Sheidlower, Reuben M. Aronson, Elaine Schaertl Short
{"title":"论机器人错误对人类教学动力的影响","authors":"Jindan Huang, Isaac Sheidlower, Reuben M. Aronson, Elaine Schaertl Short","doi":"arxiv-2409.09827","DOIUrl":null,"url":null,"abstract":"Human-in-the-loop learning is gaining popularity, particularly in the field\nof robotics, because it leverages human knowledge about real-world tasks to\nfacilitate agent learning. When people instruct robots, they naturally adapt\ntheir teaching behavior in response to changes in robot performance. While\ncurrent research predominantly focuses on integrating human teaching dynamics\nfrom an algorithmic perspective, understanding these dynamics from a\nhuman-centered standpoint is an under-explored, yet fundamental problem.\nAddressing this issue will enhance both robot learning and user experience.\nTherefore, this paper explores one potential factor contributing to the dynamic\nnature of human teaching: robot errors. We conducted a user study to\ninvestigate how the presence and severity of robot errors affect three\ndimensions of human teaching dynamics: feedback granularity, feedback richness,\nand teaching time, in both forced-choice and open-ended teaching contexts. The\nresults show that people tend to spend more time teaching robots with errors,\nprovide more detailed feedback over specific segments of a robot's trajectory,\nand that robot error can influence a teacher's choice of feedback modality. Our\nfindings offer valuable insights for designing effective interfaces for\ninteractive learning and optimizing algorithms to better understand human\nintentions.","PeriodicalId":501541,"journal":{"name":"arXiv - CS - Human-Computer Interaction","volume":"110 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"On the Effect of Robot Errors on Human Teaching Dynamics\",\"authors\":\"Jindan Huang, Isaac Sheidlower, Reuben M. Aronson, Elaine Schaertl Short\",\"doi\":\"arxiv-2409.09827\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Human-in-the-loop learning is gaining popularity, particularly in the field\\nof robotics, because it leverages human knowledge about real-world tasks to\\nfacilitate agent learning. When people instruct robots, they naturally adapt\\ntheir teaching behavior in response to changes in robot performance. While\\ncurrent research predominantly focuses on integrating human teaching dynamics\\nfrom an algorithmic perspective, understanding these dynamics from a\\nhuman-centered standpoint is an under-explored, yet fundamental problem.\\nAddressing this issue will enhance both robot learning and user experience.\\nTherefore, this paper explores one potential factor contributing to the dynamic\\nnature of human teaching: robot errors. We conducted a user study to\\ninvestigate how the presence and severity of robot errors affect three\\ndimensions of human teaching dynamics: feedback granularity, feedback richness,\\nand teaching time, in both forced-choice and open-ended teaching contexts. The\\nresults show that people tend to spend more time teaching robots with errors,\\nprovide more detailed feedback over specific segments of a robot's trajectory,\\nand that robot error can influence a teacher's choice of feedback modality. Our\\nfindings offer valuable insights for designing effective interfaces for\\ninteractive learning and optimizing algorithms to better understand human\\nintentions.\",\"PeriodicalId\":501541,\"journal\":{\"name\":\"arXiv - CS - Human-Computer Interaction\",\"volume\":\"110 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Human-Computer Interaction\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.09827\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Human-Computer Interaction","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.09827","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
On the Effect of Robot Errors on Human Teaching Dynamics
Human-in-the-loop learning is gaining popularity, particularly in the field
of robotics, because it leverages human knowledge about real-world tasks to
facilitate agent learning. When people instruct robots, they naturally adapt
their teaching behavior in response to changes in robot performance. While
current research predominantly focuses on integrating human teaching dynamics
from an algorithmic perspective, understanding these dynamics from a
human-centered standpoint is an under-explored, yet fundamental problem.
Addressing this issue will enhance both robot learning and user experience.
Therefore, this paper explores one potential factor contributing to the dynamic
nature of human teaching: robot errors. We conducted a user study to
investigate how the presence and severity of robot errors affect three
dimensions of human teaching dynamics: feedback granularity, feedback richness,
and teaching time, in both forced-choice and open-ended teaching contexts. The
results show that people tend to spend more time teaching robots with errors,
provide more detailed feedback over specific segments of a robot's trajectory,
and that robot error can influence a teacher's choice of feedback modality. Our
findings offer valuable insights for designing effective interfaces for
interactive learning and optimizing algorithms to better understand human
intentions.