EUVIMEDEUVIMED entdecken
Übersichtsarbeit

On human-in-the-loop optimization of human–robot interaction

Patrick Slade iD, Christopher Atkeson, J Maxwell Donelan iD, Han Houdijk, Kimberly A Ingraham, Myunghee Kim iD, Kyoungchul Kong iD, Katherine L Poggensee iD, Robert Riener, Martin Steinert, Juanjuan Zhang iD, Steven H Collins iD

Nature · 26.09.2024 · 633 (8031) · 779-788

DOI: 10.1038/s41586-024-07697-2 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Nature, online erschienen am 25.09.2024. Verfasst von Patrick Slade und 11 weiteren Autor:innen. Beteiligte Einrichtung: Harvard John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA. slade@seas.harvard.edu. Hauptthemen laut MEDLINE: Man-Machine Systems, Robotics, User-Computer Interface. Die Arbeit wurde bisher 152-mal zitiert (Crossref) und nennt 123 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

From industrial exoskeletons to implantable medical devices, robots that interact closely with people are poised to improve every aspect of our lives. Yet designing these systems is very challenging; humans are incredibly complex and, in many cases, we respond to robotic devices in ways that cannot be modelled or predicted with sufficient accuracy. A new approach, human-in-the-loop optimization, can overcome these challenges by systematically and empirically identifying the device characteristics that result in the best objective performance for a specific user and application. This approach has enabled substantial improvements in human-robot performance in research settings and has the potential to speed development and enhance products. In this Perspective, we describe methods for applying human-in-the-loop optimization to new human-robot interaction problems, addressing each key decision in a variety of contexts. We also identify opportunities to develop new optimization techniques and answer underlying scientific questions. We anticipate that our readers will advance human-in-the-loop optimization and use it to design robotic devices that truly enhance the human experience.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Man-Machine SystemsRoboticsUser-Computer InterfaceHumans

Autor:innen und Institutionen

  • Harvard John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA. slade@seas.harvard.edu.
  • The Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA.
  • WearTech Labs, Simon Fraser University, Burnaby, British Columbia, Canada.
  • Department of Human Movement Sciences, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands.
  • Department of Electrical and Computer Engineering, University of Washington, Seattle, WA, USA.
  • Mechanical and Industrial Engineering, University of Illinois Chicago, Chicago, IL, USA.

ORCID-Profile: Patrick Slade, J Maxwell Donelan, Myunghee Kim, Kyoungchul Kong, Katherine L Poggensee, Juanjuan Zhang, Steven H Collins

Zitieren

APA

Slade, P., Atkeson, C., Donelan, J. M., Houdijk, H., Ingraham, K. A., Kim, M., Kong, K., Poggensee, K. L., Riener, R., Steinert, M., Zhang, J., & Collins, S. H. (2024). On human-in-the-loop optimization of human–robot interaction. Nature, 633(8031), 779-788. https://doi.org/10.1038/s41586-024-07697-2

Vancouver

Slade P, Atkeson C, Donelan JM, Houdijk H, Ingraham KA, Kim M, et al. On human-in-the-loop optimization of human–robot interaction. Nature. 2024;633(8031):779-788. doi:10.1038/s41586-024-07697-2

BibTeX
@article{Slade2024,
  author = {Slade, Patrick and Atkeson, Christopher and Donelan, J Maxwell and Houdijk, Han and Ingraham, Kimberly A and Kim, Myunghee and Kong, Kyoungchul and Poggensee, Katherine L and Riener, Robert and Steinert, Martin and Zhang, Juanjuan and Collins, Steven H},
  title = {On human-in-the-loop optimization of human–robot interaction},
  journal = {Nature},
  year = {2024},
  volume = {633},
  number = {8031},
  pages = {779--788},
  doi = {10.1038/s41586-024-07697-2}
}
Kostenlos starten →