Human-Interactive Robot Learning: Definition, Challenges, and Recommendations

Robot learning from humans has been proposed and researched for several decades as a means to enable robots to learn new skills or adapt existing ones to new situations. Recent advances in AI, including learning approaches like reinforcement learning and architectures like transformers and foundation models, combined with access to massive datasets, have created attractive opportunities to apply those data-hungry techniques to this problem. We argue that the focus on massive amounts of pre-collected data, and the resulting learning paradigm, where humans demonstrate and robots learn in isolation, is overshadowing a specialized area of work we term Human-Interactive Robot Learning (HIRL). This paradigm, wherein robots and humans interact during the learning process , is at the intersection of multiple fields (AI, robotics, human–computer interaction, design and others) and holds unique promise. Using HIRL, robots can achieve greater sample efficiency (as humans can provide task knowledge through interaction), align with human preferences (as humans can guide the robot behavior toward their expectations), and explore more meaningfully and safely (as humans can utilize domain knowledge to guide learning and prevent catastrophic failures). This can result in robotic systems that can more quickly and easily adapt to new tasks in human environments. The objective of this article is to provide a broad and consistent overview of HIRL research and to guide researchers toward understanding the scope of HIRL, and current open or underexplored challenges related to four themes—namely, human, robot learning, interaction, and broader context. The article includes concrete use cases to illustrate the interaction between these challenges and inspire further research according to broad recommendations and a call for action for the growing HIRL community.

Authors

Institutions

Publication Details

Journal
ACM Transactions on Human-Robot Interaction
Published
2025-12-09
DOI
https://doi.org/10.1145/3779297
Citations
1
Primary Topic
Social Robot Interaction and HRI
Type
article
Field-Weighted Citation Impact
2.44
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Human-Interactive Robot Learning: Definition, Challenges, and Recommendations

Silvia Tulli, Xuesu Xiao, Kim Baraka, Erdem Bıyık et al.
1 citations
ACM Transactions on Human-Robot Interaction
Social Robot Interaction and HRI
2.44
article

Human-Interactive Robot Learning: Definition, Challenges, and Recommendations

Silvia Tulli, Xuesu Xiao, Kim Baraka, Erdem Bıyık, Helen Beierling, Jens Kober, Anna-Lisa Vollmer, Antonio Andriella, Mohamed Chétouani, Taylor Kessler Faulkner, Akanksha Saran, Emmanuel Senft, Isaac Sheidlower, Matthew E. Taylor, Ifrah Idrees, Serena Booth, Daniel H. Grollman, Sanne van Waveren, Tiffany Horter
article en
1 citations

Abstract

Robot learning from humans has been proposed and researched for several decades as a means to enable robots to learn new skills or adapt existing ones to new situations. Recent advances in AI, including learning approaches like reinforcement learning and architectures like transformers and foundation models, combined with access to massive datasets, have created attractive opportunities to apply those data-hungry techniques to this problem. We argue that the focus on massive amounts of pre-collected data, and the resulting learning paradigm, where humans demonstrate and robots learn in isolation, is overshadowing a specialized area of work we term Human-Interactive Robot Learning (HIRL). This paradigm, wherein robots and humans interact during the learning process , is at the intersection of multiple fields (AI, robotics, human–computer interaction, design and others) and holds unique promise. Using HIRL, robots can achieve greater sample efficiency (as humans can provide task knowledge through interaction), align with human preferences (as humans can guide the robot behavior toward their expectations), and explore more meaningfully and safely (as humans can utilize domain knowledge to guide learning and prevent catastrophic failures). This can result in robotic systems that can more quickly and easily adapt to new tasks in human environments. The objective of this article is to provide a broad and consistent overview of HIRL research and to guide researchers toward understanding the scope of HIRL, and current open or underexplored challenges related to four themes—namely, human, robot learning, interaction, and broader context. The article includes concrete use cases to illustrate the interaction between these challenges and inspire further research according to broad recommendations and a call for action for the growing HIRL community.

ACM Transactions on Human-Robot InteractionVol. 15(2)
University of Southern California (US), Tufts University (US), Centre National de la Recherche Scientifique (FR), Georgia Institute of Technology (US), University of Alberta (CA), George Mason University (US), John Brown University (US), Bielefeld University (DE), University of Washington (US), Brown University (US), Alberta Medical Association (CA), Sony Corporation (United States) (US), Sorbonne Université (FR), University of Oxford (GB), Robotics Research (United States) (US), Artificial Intelligence Research Institute (ES), Sorbonne University Abu Dhabi (AE), Institut Systèmes Intelligents et de Robotique (FR), Université Paris 1 Panthéon-Sorbonne (FR), Idiap Research Institute (CH), Vrije Universiteit Amsterdam (NL), Delft University of Technology (NL)
Openalex Percentile: Top 8%
Social Robot Interaction and HRI
2.44
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.