Skip to Main content Skip to Navigation

Apprentissage ouvert de representations et de fonctionnalites en robotique : anayse, modeles et implementation

Abstract : Autonomous acquisition of representations and functionalities by a machine address several theoretical questions. Today's autonomous robots are developed around a set of functionalities. Their representations of the world are deduced from the analysis and modeling of a given problem, and are initially given by the developers. This limits the learning capabilities of robots. In this thesis, we propose an approach and a system able to build open-ended representation and functionalities. This system learns through its experimentations of the environment and aims to augment a value function. Its objective consists in acting to reactivate the representations it has already learnt to connote positively. An analysis of the generalization capabilities to produce appropriate actions enable define a minimal set of properties needed by such a system. The open-ended representation system is composed of a network of homogeneous processing units and is based on position coding. The meaning of a processing unit depends on its position in the global network. This representation system presents similarities with the principle of numeration by position. A representation is given by a set of active units. This system is implemented in a suite of software called NeuSter, which is able to simulate million unit networks with billions of connections on heterogeneous clusters of POSIX machines. The first results permit to validate the constraints provided by the analysis. Such a system is able to learn hierarchically and without supervision, within a unique network, various feature extractors such as borders and lines, corners, end stops, view dependant faces, directions of motion, optical flow patterns such as rotation, expansions, contractions, and phonemes. NeuSter learns online using the data given by its sensors. It has been tested on mobile robots for learning and tracking of objects.
Document type :
Complete list of metadata

Cited literature [87 references]  Display  Hide  Download
Contributor : Emilie Marchand <>
Submitted on : Friday, May 27, 2005 - 10:32:49 AM
Last modification on : Friday, January 10, 2020 - 9:08:09 PM
Long-term archiving on: : Friday, April 2, 2010 - 9:44:17 PM


  • HAL Id : tel-00009324, version 1


Williams Paquier. Apprentissage ouvert de representations et de fonctionnalites en robotique : anayse, modeles et implementation. Automatique / Robotique. Université Paul Sabatier - Toulouse III, 2004. Français. ⟨tel-00009324⟩



Record views


Files downloads