Skip to Main content Skip to Navigation
Theses

Apprentissage et correction des imperfections des robots humanoïdes de petite taille : application à l'odométrie et à la synthèse de mouvements

Abstract : Small humanoid robots are often affected by many flaws : mechanical wraps and backlashes, electrical issues and motor control problems. This work is aimed at applying machine learning methods to deal with the flaws of the real robot. More precisely, improving the odometry accuracy and generated motion stability is studied. This thesis is highly guided and inspired by the participation of the Rhoban team (Rhoban Football Club) to the international RoboCup competition. Since 2011, the team has been competing each year in a soccer tournament within the fully autonomous small humanoid robots (Kid-Size) league. Proprioceptive odometry estimates the robot displacements from its internal sensors (no camera is used) whereas predictive odometry simulates the displacements created from a sequence of walk orders. Two corrective methods are proposed for the two kinds of odometries. The first one is based on a non parametric regression (LWPR) and a motion capture setup. The second one optimizes (CMA-ES) a linear corrective model without needing any external measure system. The proprioceptive odometry is essential to the localization of the robot on the soccer field. The predictive odometry is used to train a control policy for the walk motion. The generation of very dynamic motions like walking or kicking the ball is difficult due to the biped balance constraint and the many servomotor flaws. To start, kick motions are generated by optimization (CMA-ES) and evaluated based on the inverse dynamic model of the robot. The implementation of a physics simulator has been started. The objective is make the real behaviour of the robot to catch up the target trajectory by correcting the motion within the simulator.
Document type :
Theses
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-01691707
Contributor : Abes Star :  Contact
Submitted on : Wednesday, January 24, 2018 - 11:56:08 AM
Last modification on : Thursday, July 23, 2020 - 3:50:26 PM
Long-term archiving on: : Thursday, May 24, 2018 - 6:53:36 PM

File

ROUXEL_QUENTIN_2017.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01691707, version 1

Collections

Citation

Quentin Rouxel. Apprentissage et correction des imperfections des robots humanoïdes de petite taille : application à l'odométrie et à la synthèse de mouvements. Autre [cs.OH]. Université de Bordeaux, 2017. Français. ⟨NNT : 2017BORD0816⟩. ⟨tel-01691707⟩

Share

Metrics

Record views

744

Files downloads

158