Treffer: Robustness in the long run: Auto-teaching vs anticipation in Evolutionary Robotics

Title:
Robustness in the long run: Auto-teaching vs anticipation in Evolutionary Robotics
Authors:
GODZIK, Nicolas, SCHOENAUER, Marc, SEBAG, Michèle
Source:
PPSN VIII : parallel problem solving from nature (Birmingham, 18-22 September 2004)Lecture notes in computer science. :932-941
Publisher Information:
Berlin: Springer, 2004.
Publication Year:
2004
Physical Description:
print, 13 ref
Original Material:
INIST-CNRS
Subject Terms:
Computer science, Informatique, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Informatique théorique, Theoretical computing, Algorithmique. Calculabilité. Arithmétique ordinateur, Algorithmics. Computability. Computer arithmetics, Intelligence artificielle, Artificial intelligence, Apprentissage et systèmes adaptatifs, Learning and adaptive systems, Algorithme rétropropagation, Backpropagation algorithm, Algoritmo retropropagación, Algorithme évolutionniste, Evolutionary algorithm, Algoritmo evoluciónista, Anticipation, Anticipación, Biomimétique, Biomimetics, Capteur mesure, Measurement sensor, Captador medida, Commande adaptative, Adaptive control, Control adaptativo, Enseignement, Teaching, Enseñanza, Long terme, Long term, Largo plazo, Parallélisme, Parallelism, Paralelismo, Robotique, Robotics, Robótica, Robustesse, Robustness, Robustez, Réseau neuronal, Neural network, Red neuronal, Résolution problème, Problem solving, Resolución problema
Document Type:
Konferenz Conference Paper
File Description:
text
Language:
English
Author Affiliations:
TAO team, INRIA Futurs and LRI, UMR CNRS 8623 bat. 490, Université Paris-Sud, 91405 Orsay, France
ISSN:
0302-9743
Access URL:
http://pascal-francis.inist.fr/vibad/index.php?action=search&terms=16176926
Rights:
Copyright 2004 INIST-CNRS
CC BY 4.0
Sauf mention contraire ci-dessus, le contenu de cette notice bibliographique peut être utilisé dans le cadre d’une licence CC BY 4.0 Inist-CNRS / Unless otherwise stated above, the content of this bibliographic record may be used under a CC BY 4.0 licence by Inist-CNRS / A menos que se haya señalado antes, el contenido de este registro bibliográfico puede ser utilizado al amparo de una licencia CC BY 4.0 Inist-CNRS
Notes:
Computer science; theoretical automation; systems
Accession Number:
edscal.16176926
Database:
PASCAL Archive

Weitere Informationen

In Evolutionary Robotics, auto-teaching networks, neural networks that modify their own weights during the life-time of the robot, have been shown to be powerful architectures to develop adaptive controllers. Unfortunately, when run for a longer period of time than that used during evolution, the long-term behavior of such networks can become unpredictable. This paper gives an example of such dangerous behavior, and proposes an alternative solution based on anticipation: as in auto-teaching networks, a secondary network is evolved, but its outputs try to predict the next state of the robot sensors. The weights of the action network are adjusted using some back-propagation procedure based on the errors made by the anticipatory network. First results - in simulated environments - show a tremendous increase in robustness of the long-term behavior of the controller.