---
_id: '61327'
abstract:
- lang: eng
  text: "Robot learning from humans has been proposed and researched for several decades
    as a means to enable robots to learn new skills or\r\nadapt existing ones to new
    situations. Recent advances in artificial intelligence, including learning approaches
    like reinforcement\r\nlearning and architectures like transformers and foundation
    models, combined with access to massive datasets, has created attractive\r\nopportunities
    to apply those data-hungry techniques to this problem. We argue that the focus
    on massive amounts of pre-collected\r\ndata, and the resulting learning paradigm,
    where humans demonstrate and robots learn in isolation, is overshadowing a specialized\r\narea
    of work we term Human-Interactive-Robot-Learning (HIRL). This paradigm, wherein
    robots and humans interact during the\r\nlearning process, is at the intersection
    of multiple fields (artificial intelligence, robotics, human-computer interaction,
    design and others)\r\nand holds unique promise. Using HIRL, robots can achieve
    greater sample efficiency (as humans can provide task knowledge through\r\ninteraction),
    align with human preferences (as humans can guide the robot behavior towards their
    expectations), and explore more\r\nmeaningfully and safely (as humans can utilize
    domain knowledge to guide learning and prevent catastrophic failures). This can
    result\r\nin robotic systems that can more quickly and easily adapt to new tasks
    in human environments. The objective of this paper is to\r\nprovide a broad and
    consistent overview of HIRL research and to guide researchers toward understanding
    the scope of HIRL, and\r\ncurrent open or underexplored challenges related to
    four themes — namely, human, robot learning, interaction, and broader context.\r\nThe
    paper includes concrete use cases to illustrate the interaction between these
    challenges and inspire further research according to\r\nbroad recommendations
    and a call for action for the growing HIRL community"
article_type: original
author:
- first_name: 'Kim '
  full_name: 'Baraka, Kim '
  last_name: Baraka
- first_name: Ifrah
  full_name: Idrees, Ifrah
  last_name: Idrees
- first_name: Taylor Kessler
  full_name: Faulkner, Taylor Kessler
  last_name: Faulkner
- first_name: Erdem
  full_name: Biyik, Erdem
  last_name: Biyik
- first_name: Serena
  full_name: Booth, Serena
  last_name: Booth
- first_name: Mohamed
  full_name: Chetouani, Mohamed
  last_name: Chetouani
- first_name: Daniel H.
  full_name: Grollman, Daniel H.
  last_name: Grollman
- first_name: Akanksha
  full_name: Saran, Akanksha
  last_name: Saran
- first_name: Emmanuel
  full_name: Senft, Emmanuel
  last_name: Senft
- first_name: Silvia
  full_name: Tulli, Silvia
  last_name: Tulli
- first_name: Anna-Lisa
  full_name: Vollmer, Anna-Lisa
  last_name: Vollmer
- first_name: Antonio
  full_name: Andriella, Antonio
  last_name: Andriella
- first_name: Helen
  full_name: Beierling, Helen
  last_name: Beierling
- first_name: Tiffany
  full_name: Horter, Tiffany
  last_name: Horter
- first_name: Jens
  full_name: Kober, Jens
  last_name: Kober
- first_name: Isaac
  full_name: Sheidlower, Isaac
  last_name: Sheidlower
- first_name: Matthew E.
  full_name: Taylor, Matthew E.
  last_name: Taylor
- first_name: Sanne
  full_name: van Waveren, Sanne
  last_name: van Waveren
- first_name: Xuesu
  full_name: Xiao, Xuesu
  last_name: Xiao
citation:
  ama: 'Baraka K, Idrees I, Faulkner TK, et al. Human-Interactive Robot Learning:
    Definition, Challenges, and Recommendations. <i>Transactions on Human-Robot Interaction</i>.'
  apa: 'Baraka, K., Idrees, I., Faulkner, T. K., Biyik, E., Booth, S., Chetouani,
    M., Grollman, D. H., Saran, A., Senft, E., Tulli, S., Vollmer, A.-L., Andriella,
    A., Beierling, H., Horter, T., Kober, J., Sheidlower, I., Taylor, M. E., van Waveren,
    S., &#38; Xiao, X. (n.d.). Human-Interactive Robot Learning: Definition, Challenges,
    and Recommendations. <i>Transactions on Human-Robot Interaction</i>.'
  bibtex: '@article{Baraka_Idrees_Faulkner_Biyik_Booth_Chetouani_Grollman_Saran_Senft_Tulli_et
    al., title={Human-Interactive Robot Learning: Definition, Challenges, and Recommendations},
    journal={Transactions on Human-Robot Interaction}, author={Baraka, Kim  and Idrees,
    Ifrah and Faulkner, Taylor Kessler and Biyik, Erdem and Booth, Serena and Chetouani,
    Mohamed and Grollman, Daniel H. and Saran, Akanksha and Senft, Emmanuel and Tulli,
    Silvia and et al.} }'
  chicago: 'Baraka, Kim , Ifrah Idrees, Taylor Kessler Faulkner, Erdem Biyik, Serena
    Booth, Mohamed Chetouani, Daniel H. Grollman, et al. “Human-Interactive Robot
    Learning: Definition, Challenges, and Recommendations.” <i>Transactions on Human-Robot
    Interaction</i>, n.d.'
  ieee: 'K. Baraka <i>et al.</i>, “Human-Interactive Robot Learning: Definition, Challenges,
    and Recommendations,” <i>Transactions on Human-Robot Interaction</i>.'
  mla: 'Baraka, Kim, et al. “Human-Interactive Robot Learning: Definition, Challenges,
    and Recommendations.” <i>Transactions on Human-Robot Interaction</i>.'
  short: K. Baraka, I. Idrees, T.K. Faulkner, E. Biyik, S. Booth, M. Chetouani, D.H.
    Grollman, A. Saran, E. Senft, S. Tulli, A.-L. Vollmer, A. Andriella, H. Beierling,
    T. Horter, J. Kober, I. Sheidlower, M.E. Taylor, S. van Waveren, X. Xiao, Transactions
    on Human-Robot Interaction (n.d.).
date_created: 2025-09-17T12:42:45Z
date_updated: 2025-09-17T13:40:16Z
keyword:
- Robot learning
- Interactive learning systems
- Human-robot interaction
- Human-in-the-loop machine learning
- Teaching and learning
language:
- iso: eng
project:
- _id: '123'
  name: TRR 318 - Subproject B5
publication: Transactions on Human-Robot Interaction
publication_status: submitted
status: public
title: 'Human-Interactive Robot Learning: Definition, Challenges, and Recommendations'
type: journal_article
user_id: '50995'
year: '2025'
...