A Human-Centered View of Continual Learning
Understanding Interactions, Teaching Patterns, and Perceptions of Human Users Toward a Continual Learning Robot in Repeated Interactions
Bibliographic Data
| ID | 22190866 |
|---|---|
| Authors | Ali Ayub (0000-0001-9458-477X, University of Waterloo), Zachary De Francesco (0009-0000-4964-7452, University of Waterloo), Jainish Mehta (0009-0004-8222-0716, University of Waterloo), Khaled Yaakoub Agha (0009-0009-0334-3176, University of Waterloo), Patrick Holthaus (0000-0001-8450-9362, University of Hertfordshire), Chrystopher L Nehaniv (0000-0002-7807-1875, University of Waterloo), Kerstin Dautenhahn (0000-0002-9263-3897, University of Waterloo) |
| Year | 2024 |
| Volume | 13 |
| Issue | 4 |
| Pages | 1-39 |
| Publication date | 2024-12-31 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | ACM Transactions on Human-Robot Interaction (JOURNAL) |
| Journal identifiers | ISSN: 2573-9522 • E-ISSN: 2573-9522 |
| Publisher | Association for Computing Machinery (ACM) (PUBLISHER) |
| DOI | 10.1145/3659110 |
| OpenAlex | W4398236206 |
| Language | EN |
| References cited | 53 |
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 CL, however, has been robot-centered to develop CL algorithms that can quickly learn new information on systematically collected static datasets. In this article, we take a human-centered approach to CL, to understand how humans interact with, teach, and perceive CL robots over the long term, and if there are variations in their teaching styles. We developed a socially guided CL 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 CL 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 CL robots in a variety of ways. Finally, our analysis shows that although users have concerns about CL robots being deployed in our daily lives, they mention that with further improvements CL robots could assist older adults and people with disabilities in their homes
Cognitive science · Human–computer interaction · Human–robot interaction · Knowledge management · Perception · Robot · AI in Service Interactions · Computer Science · Neuroscience · Psychology · Social Robot Interaction and HRI · Teaching and Learning Programming · Artificial Intelligence
Socially intelligent robots
Why there are complementary learning systems in the hippocampus and neocortex
ImageNet Large Scale Visual Recognition Challenge
Individual Comparisons by Ranking Methods
You Only Look Once
Calculating and reporting effect sizes to facilitate cumulative science
Controlling the False Discovery Rate
Using thematic analysis in psychology
| Highly cited | No |
|---|