Skip to Main content Skip to Navigation
Poster communications

Learning-based modelling of physical interaction for assistive robots

Abstract : Deploying companion robots for assisting humans requires safe and robust interaction with the environment, both in terms of mobility and object manipulation. To extend a robot's workspace, we are here concerned with multifloor operation and staircase traversal, as a building block for the development of object fetching services. In this article, we advocate a lifelong learning treatment of this problem within a reinforcement learning (RL) framework. In view of sparse earlier work for the scenario of interest, we hereby identify relevant methodological aspects and report our preliminary developments.
Complete list of metadatas

Cited literature [33 references]  Display  Hide  Download

https://hal-imt-atlantique.archives-ouvertes.fr/hal-02341202
Contributor : Andrei Mitriakov <>
Submitted on : Thursday, October 31, 2019 - 11:39:48 AM
Last modification on : Wednesday, June 24, 2020 - 4:19:50 PM
Long-term archiving on: : Saturday, February 1, 2020 - 2:48:18 PM

File

JFPDA_2019_paper_17.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02341202, version 1

Citation

Andrei Mitriakov, Panagiotis Papadakis, Sao Mai Nguyen, Serge Garlatti. Learning-based modelling of physical interaction for assistive robots. Journées Francophones sur la Planification, la Décision et l'Apprentissage pour la conduite de systèmes (JFPDA), Jul 2019, Toulouse, France. ⟨hal-02341202⟩

Share

Metrics

Record views

88

Files downloads

82