Evolving a Behavioral Repertoire for a Walking Robot

Antoine Cully 1 Jean-Baptiste Mouret 2, 1, *
* Auteur correspondant
2 LARSEN - Lifelong Autonomy and interaction skills for Robots in a Sensing ENvironment
Inria Nancy - Grand Est, LORIA - AIS - Department of Complex Systems, Artificial Intelligence & Robotics
Abstract : Numerous algorithms have been proposed to allow legged robots to learn to walk. However, the vast majority of these algorithms is devised to learn to walk in a straight line, which is not sufficient to accomplish any real-world mission. Here we introduce the Transferability-based Behavioral Repertoire Evolution algorithm (TBR-Evolution), a novel evolutionary algorithm that simultaneously discovers several hundreds of sim-ple walking controllers, one for each possible direction. By taking advantage of so-lutions that are usually discarded by evolutionary processes, TBR-Evolution is sub-stantially faster than independently evolving each controller. Our technique relies on two methods: (1) novelty search with local competition, which searches for both high-performing and diverse solutions, and (2) the transferability approach, which com-bines simulations and real tests to evolve controllers for a physical robot. We evaluate this new technique on a hexapod robot. Results show that with only a few dozen short experiments performed on the robot, the algorithm learns a repertoire of con-trollers that allows the robot to reach every point in its reachable space. Overall, TBR-Evolution opens a new kind of learning algorithm that simultaneously optimizes all the achievable behaviors of a robot.
Type de document :
Article dans une revue
Evolutionary Computation, Massachusetts Institute of Technology Press (MIT Press), 2016, 24 (1), pp.33. 〈10.1162/EVCO_a_00143〉
Liste complète des métadonnées

Littérature citée [61 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01095543
Contributeur : Antoine Cully <>
Soumis le : lundi 15 décembre 2014 - 17:32:15
Dernière modification le : mercredi 21 mars 2018 - 18:57:41
Document(s) archivé(s) le : lundi 16 mars 2015 - 12:30:35

Fichier

tbr_evolution.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Antoine Cully, Jean-Baptiste Mouret. Evolving a Behavioral Repertoire for a Walking Robot. Evolutionary Computation, Massachusetts Institute of Technology Press (MIT Press), 2016, 24 (1), pp.33. 〈10.1162/EVCO_a_00143〉. 〈hal-01095543〉

Partager

Métriques

Consultations de la notice

198

Téléchargements de fichiers

282