EUVIMEDEUVIMED entdecken
Crossref

Learning contact-rich whole-body manipulation with example-guided reinforcement learning

Jose A Barreiros iD, Aykut Özgün Önol iD, Mengchao Zhang iD, Sam Creasey, Aimee Goncalves, Andrew Beaulieu iD, Aditya Bhat, Kate M Tsui, Alex Alspach iD

Science Robotics · 2025

DOI: 10.1126/scirobotics.ads6790 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Robotics, 2025. Verfasst von Jose A Barreiros und 8 weiteren Autor:innen. Beteiligte Einrichtung: Toyota Research Institute, Cambridge, MA, USA. Hauptthemen laut MEDLINE: Robotics, Reinforcement, Psychology, Learning. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 84 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Humans use diverse skills and strategies to effectively manipulate various objects, ranging from dexterous in-hand manipulation (fine motor skills) to complex whole-body manipulation (gross motor skills). The latter involves full-body engagement and extensive contact with various body parts beyond just the hands, where the compliance of our skin and muscles plays a crucial role in increasing contact stability and mitigating uncertainty. For robots, synthesizing these contact-rich behaviors has fundamental challenges because of the rapidly growing combinatorics inherent to this amount of contact, making explicit reasoning about all contact interactions intractable. We explore the use of example-guided reinforcement learning to generate robust whole-body skills for the manipulation of large and unwieldy objects. Our method’s effectiveness is demonstrated on Toyota Research Institute’s Punyo robot, a humanoid upper body with highly deformable, pressure-sensing skin. Training was conducted in simulation with only a single example motion per object manipulation task, and policies were easily transferred to hardware owing to domain randomization and the robot’s compliance. The resulting agent can manipulate various everyday objects, such as a water jug and large boxes, in a similar fashion to the example motion. In addition, we show blind dexterous whole-body manipulation, relying solely on proprioceptive and tactile feedback without object pose tracking. Our analysis highlights the critical role of compliance in facilitating whole-body manipulation with humanoid robots.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RoboticsReinforcement, PsychologyLearningHumansMotor SkillsEquipment DesignComputer SimulationTouchBiomechanical Phenomena

Autor:innen und Institutionen

  • Toyota Research Institute, Cambridge, MA, USA.

ORCID-Profile: Jose A Barreiros, Aykut Özgün Önol, Mengchao Zhang, Andrew Beaulieu, Alex Alspach

Zitieren

APA

Barreiros, J. A., Önol, A. Ö., Zhang, M., Creasey, S., Goncalves, A., Beaulieu, A., Bhat, A., Tsui, K. M., & Alspach, A. (2025). Learning contact-rich whole-body manipulation with example-guided reinforcement learning. Science Robotics. https://doi.org/10.1126/scirobotics.ads6790

Vancouver

Barreiros JA, Önol AÖ, Zhang M, Creasey S, Goncalves A, Beaulieu A, et al. Learning contact-rich whole-body manipulation with example-guided reinforcement learning. Science Robotics. 2025. doi:10.1126/scirobotics.ads6790

BibTeX
@article{Barreiros2025,
  author = {Barreiros, Jose A and Önol, Aykut Özgün and Zhang, Mengchao and Creasey, Sam and Goncalves, Aimee and Beaulieu, Andrew and Bhat, Aditya and Tsui, Kate M and Alspach, Alex},
  title = {Learning contact-rich whole-body manipulation with example-guided reinforcement learning},
  journal = {Science Robotics},
  year = {2025},
  doi = {10.1126/scirobotics.ads6790}
}
Kostenlos starten →