TY - JOUR
T1 - A Human-Centered View of Continual Learning: Understanding Interactions, Teaching Patterns, and Perceptions of Human Users Towards a Continual Learning Robot in Repeated Interactions
AU - Ayub, Ali
AU - De Francesco, Zachary
AU - Mehta, Jainish
AU - Agha, Khaled Yaakoub
AU - Holthaus, Patrick
AU - Nehaniv, Chrystopher L.
AU - Dautenhahn, Kerstin
N1 - © 2024 Copyright held by the owner/author(s). This work is licensed under a Creative Commons Attribution International 4.0 License. https://creativecommons.org/licenses/by/4.0/
PY - 2024/10/23
Y1 - 2024/10/23
N2 - Continual learning (CL) has emerged as an important avenue of research in recent years, at the intersection of Machine Learning (ML) and Human-Robot Interaction (HRI), to allow robots to continually learn in their environments over long-term interactions with humans. Most research in continual learning, however, has been robot-centered to develop continual learning algorithms that can quickly learn new information on systematically collected static datasets. In this paper, we take a human-centered approach to continual learning, to understand how humans interact with, teach, and perceive continual learning robots over the long term, and if there are variations in their teaching styles. We developed a socially guided continual learning system that integrates CL models for object recognition with a mobile manipulator robot and allows humans to directly teach and test the robot in real time over multiple sessions. We conducted an in-person study with 60 participants who interacted with the continual learning robot in 300 sessions with 5 sessions per participant. In this between-participant study, we used three different CL models deployed on a mobile manipulator robot. An extensive qualitative and quantitative analysis of the data collected in the study shows that there is significant variation among the teaching styles of individual users indicating the need for personalized adaptation to their distinct teaching styles. Our analysis shows that the constrained experimental setups that have been widely used to test most CL models are not adequate, as real users interact with and teach continual learning robots in a variety of ways. Finally, our analysis shows that although users have concerns about continual learning robots being deployed in our daily lives, they mention that with further improvements continual learning robots could assist older adults and people with disabilities in their homes.
AB - Continual learning (CL) has emerged as an important avenue of research in recent years, at the intersection of Machine Learning (ML) and Human-Robot Interaction (HRI), to allow robots to continually learn in their environments over long-term interactions with humans. Most research in continual learning, however, has been robot-centered to develop continual learning algorithms that can quickly learn new information on systematically collected static datasets. In this paper, we take a human-centered approach to continual learning, to understand how humans interact with, teach, and perceive continual learning robots over the long term, and if there are variations in their teaching styles. We developed a socially guided continual learning system that integrates CL models for object recognition with a mobile manipulator robot and allows humans to directly teach and test the robot in real time over multiple sessions. We conducted an in-person study with 60 participants who interacted with the continual learning robot in 300 sessions with 5 sessions per participant. In this between-participant study, we used three different CL models deployed on a mobile manipulator robot. An extensive qualitative and quantitative analysis of the data collected in the study shows that there is significant variation among the teaching styles of individual users indicating the need for personalized adaptation to their distinct teaching styles. Our analysis shows that the constrained experimental setups that have been widely used to test most CL models are not adequate, as real users interact with and teach continual learning robots in a variety of ways. Finally, our analysis shows that although users have concerns about continual learning robots being deployed in our daily lives, they mention that with further improvements continual learning robots could assist older adults and people with disabilities in their homes.
U2 - 10.1145/3659110
DO - 10.1145/3659110
M3 - Article
SN - 2573-9522
VL - 13
SP - 1
EP - 39
JO - ACM Transactions on Human-Robot Interaction (THRI)
JF - ACM Transactions on Human-Robot Interaction (THRI)
IS - 4
M1 - 52
ER -