Temporal Alignment and Demonstration Selection as Pre-Processing Phase for Learning by Demonstration

International audience Robots can benefit from users’ demonstrations to learnmotions. To be efficient, a pre-processing phase needsto be performed on data recorded from demonstrations.This paper presents pre-processing methods developedfor Learning By Demonstration (LbD). Thepre-processing phase con...

Full description

Bibliographic Details
Published in:The International FLAIRS Conference Proceedings
Main Authors: Donjat, Jérémie, Legeleux, Amélie, Buche, Cédric, Duhaut, Dominique
Other Authors: École Nationale d'Ingénieurs de Brest (ENIB), Université de Bretagne Sud (UBS), FrenCh austRalian labOratory for humanS/autonomouS agents teamING (CROSSING), University of South Australia Adelaide -University of Adelaide-Flinders University Adelaide, Australia -Centre National de la Recherche Scientifique (CNRS)-Naval Group, Equipe Robot interaction, Ambient system, Machine learning, Behaviour, Optimization (Lab-STICC_RAMBO), Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Lab-STICC), École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom Paris (IMT)-Centre National de la Recherche Scientifique (CNRS)-Université Bretagne Loire (UBL)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom Paris (IMT)-École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom Paris (IMT)-Centre National de la Recherche Scientifique (CNRS)-Université Bretagne Loire (UBL)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom Paris (IMT)
Format: Conference Object
Language:English
Published: HAL CCSD 2022
Subjects:
[INFO]Computer Science [cs]
Hutchinson Island
Online Access:https://hal.science/hal-03670974
https://doi.org/10.32473/flairs.v35i.130649
Description
Summary:International audience Robots can benefit from users’ demonstrations to learnmotions. To be efficient, a pre-processing phase needsto be performed on data recorded from demonstrations.This paper presents pre-processing methods developedfor Learning By Demonstration (LbD). Thepre-processing phase consists in methods composedof alignment algorithms and algorithms that select thegood demonstrations. In this paper we propose sixmethods and compare them to select the best one.

Similar Items