EUVIMEDEUVIMED entdecken
Crossref

Demonstrate once, execute on many: Kinematic intelligence for cross-robot skill transfer

Sthithpragya Gupta iD, Durgesh Haribhau Salunkhe iD, Aude Billard iD

Science Robotics · 15.04.2026 · 11 (113)

DOI: 10.1126/scirobotics.aea1995 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Robotics, erschienen am 15.04.2026. Verfasst von Sthithpragya Gupta und 2 weiteren Autor:innen. Beteiligte Einrichtung: Learning Algorithms and Systems Laboratory, École Polytechnique Fédérale de Lausanne, Lausanne 1015, Switzerland. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: Horizon Europe, EU project DARKO.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Teaching robots new skills should be as natural as showing rather than programming. Learning from demonstration (LfD) moves toward this goal by allowing users to guide a robot or sketch a desired motion, enabling learning without writing a line of code. However, most LfD methods remain tied to the robot they were trained on. Changes in morphology, different link lengths, joint orientations, or limits often break the learned behavior, making retraining unavoidable. Here, we introduce a framework that endows robots with kinematic intelligence: an internal understanding of their own joint limits, singularities, and connectivity. Instead of correcting for these constraints after learning, we embedded them directly into the control policy from the outset. The approach takes one or multiple demonstrations, extracts a globally stable dynamical system, and produces behaviors that remain valid across robots with different kinematic structures. Our method is grounded in a comprehensive analytical classification of noncuspidal three-revolute (3R) robots, which form the building blocks of many commercial robots. This classification enables a joint space policy that preserves user intent and adapts to robot-specific constraints. We validated the framework on diverse simulated and real robots, both redundant and nonredundant, with varied link geometries and joint configurations. The demonstrated skill executes safely and consistently across robots without retuning, thereby achieving cross-robot skill transfer.

Autor:innen und Institutionen

  • Learning Algorithms and Systems Laboratory, École Polytechnique Fédérale de Lausanne, Lausanne 1015, Switzerland.

ORCID-Profile: Sthithpragya Gupta, Durgesh Haribhau Salunkhe, Aude Billard

Förderung

  • Horizon Europe
  • EU project DARKO

Zitieren

APA

Gupta, S., Salunkhe, D. H., & Billard, A. (2026). Demonstrate once, execute on many: Kinematic intelligence for cross-robot skill transfer. Science Robotics, 11(113). https://doi.org/10.1126/scirobotics.aea1995

Vancouver

Gupta S, Salunkhe DH, Billard A. Demonstrate once, execute on many: Kinematic intelligence for cross-robot skill transfer. Science Robotics. 2026;11(113). doi:10.1126/scirobotics.aea1995

BibTeX
@article{Gupta2026,
  author = {Gupta, Sthithpragya and Salunkhe, Durgesh Haribhau and Billard, Aude},
  title = {Demonstrate once, execute on many: Kinematic intelligence for cross-robot skill transfer},
  journal = {Science Robotics},
  year = {2026},
  volume = {11},
  number = {113},
  doi = {10.1126/scirobotics.aea1995}
}
Kostenlos starten →