EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Human-robot planar co-manipulation of extended objects: data-driven models and control from human-human dyads

Erich Mielke, Eric Townsend, David Wingate, John L Salmon, Marc D Killpack

Frontiers in Neurorobotics · 12.02.2024 · 18

DOI: 10.3389/fnbot.2024.1291694 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Neurorobotics, online erschienen am 12.02.2024. Verfasst von Erich Mielke und 4 weiteren Autor:innen. Beteiligte Einrichtung: Robotics and Dynamics Laboratory, Brigham Young University, Mechanical Engineering, Provo, UT, United States. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation, U.S. Army.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human teams are able to easily perform collaborative manipulation tasks. However, simultaneously manipulating a large extended object for a robot and human is a difficult task due to the inherent ambiguity in the desired motion. Our approach in this paper is to leverage data from human-human dyad experiments to determine motion intent for a physical human-robot co-manipulation task. We do this by showing that the human-human dyad data exhibits distinct torque triggers for a lateral movement. As an alternative intent estimation method, we also develop a deep neural network based on motion data from human-human trials to predict future trajectories based on past object motion. We then show how force and motion data can be used to determine robot control in a human-robot dyad. Finally, we compare human-human dyad performance to the performance of two controllers that we developed for human-robot co-manipulation. We evaluate these controllers in three-degree-of-freedom planar motion where determining if the task involves rotation or translation is ambiguous.

Schlagwörter

Stichwörter der Autor:innen

cooperative manipulationforce controlhuman-robot interactionlearning and adaptive systemsneural networkphysical human-robot interactionvariable impedance

Autor:innen und Institutionen

  • Robotics and Dynamics Laboratory, Brigham Young University, Mechanical Engineering, Provo, UT, United States.

Förderung

  • National Science Foundation
  • U.S. Army

Zitieren

APA

Mielke, E., Townsend, E., Wingate, D., Salmon, J. L., & Killpack, M. D. (2024). Human-robot planar co-manipulation of extended objects: data-driven models and control from human-human dyads. Frontiers in Neurorobotics, 18. https://doi.org/10.3389/fnbot.2024.1291694

Vancouver

Mielke E, Townsend E, Wingate D, Salmon JL, Killpack MD. Human-robot planar co-manipulation of extended objects: data-driven models and control from human-human dyads. Frontiers in Neurorobotics. 2024;18. doi:10.3389/fnbot.2024.1291694

BibTeX
@article{Mielke2024,
  author = {Mielke, Erich and Townsend, Eric and Wingate, David and Salmon, John L and Killpack, Marc D},
  title = {Human-robot planar co-manipulation of extended objects: data-driven models and control from human-human dyads},
  journal = {Frontiers in Neurorobotics},
  year = {2024},
  volume = {18},
  doi = {10.3389/fnbot.2024.1291694}
}
Kostenlos starten →