Motion Learning and Adaptive Impedance for Robot Control during Physical Interaction with Humans

Elena Gribovskaya 1 Abderrahmane Kheddar 2, 3 Aude Billard 1
1 LASA - Learning Algorithms and Systems Laboratory
EPFL - Ecole Polytechnique Fédérale de Lausanne
2 IDH - Interactive Digital Humans
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
Abstract : This article combines programming by demonstration and adaptive control for teaching a robot to physically interact with a human in a collaborative task requiring sharing of a load by the two partners. Learning a task model allows the robot to anticipate the partner's intentions and adapt its motion according to perceived forces. As the human represents a highly complex contact environment, direct reproduction of the learned model may lead to sub-optimal results. To compensate for unmodelled uncertainties, in addition to learning we propose an adaptive control algorithm that tunes the impedance parameters, so as to ensure accurate reproduction. To facilitate the illustration of the concepts introduced in this paper and provide a systematic evaluation, we present experimental results obtained with simulation of a dyad of two planar 2-DOF robots.
Document type :
Conference papers
Complete list of metadatas

https://hal-lirmm.ccsd.cnrs.fr/lirmm-00781272
Contributor : François Keith <>
Submitted on : Friday, January 25, 2013 - 6:01:01 PM
Last modification on : Tuesday, June 18, 2019 - 12:06:37 PM

Identifiers

  • HAL Id : lirmm-00781272, version 1

Collections

Citation

Elena Gribovskaya, Abderrahmane Kheddar, Aude Billard. Motion Learning and Adaptive Impedance for Robot Control during Physical Interaction with Humans. ICRA: International Conference on Robotics and Automation, May 2011, Shanghai, China. pp.4326-4332. ⟨lirmm-00781272⟩

Share

Metrics

Record views

516