Combining Learning and Programming for High-Performance Robot Controllers

Abstract : The implementation of high-performance robot controllers for complex control tasks such as playing autonomous robot soccer is tedious, error-prone, and a never ending programming task. In this paper we propose programmers to write autonomous controllers that optimize and automatically adapt themselves to changing circumstances of task execution using explicit perception , dynamics and action models. To this end we develop ROLL (Robot Learning Language), a control language allowing for model-based robot programming. ROLL provides language constructs for specifying executable code pieces of how to learn and update these models. We are currently using ROLL's mechanisms for implementing a rational reconstruction of our soccer robot controllers.
Type de document :
Communication dans un congrès
Tagungsband Autonome Mobile Systeme, 2005, Stuttgart, France. Autonome Mobile Systeme 2005 19. Fachgespräch Stuttgart, 8./9. Dezember 2005, 2005, 〈10.1007/3-540-30292-1_39〉
Liste complète des métadonnées

Littérature citée [4 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01329007
Contributeur : Alexandra Kirsch <>
Soumis le : mercredi 8 juin 2016 - 16:10:25
Dernière modification le : vendredi 10 juin 2016 - 10:47:12

Fichier

kirsch05combining.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Alexandra Kirsch, Michael Beetz. Combining Learning and Programming for High-Performance Robot Controllers. Tagungsband Autonome Mobile Systeme, 2005, Stuttgart, France. Autonome Mobile Systeme 2005 19. Fachgespräch Stuttgart, 8./9. Dezember 2005, 2005, 〈10.1007/3-540-30292-1_39〉. 〈hal-01329007〉

Partager

Métriques

Consultations de la notice

19

Téléchargements de fichiers

17