A Neural Network Approach of the Control of Dynamic Biped Equilibrium - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 1993

A Neural Network Approach of the Control of Dynamic Biped Equilibrium

Résumé

In this paper, we propose a Neural Network learning architecture for the reflex-control of complex systems. The multi-layer-network is trained by a new learning algorithm which does not need a desired output, but directly minimizes a criterion which spezify the control objective. We propose two learning concepts: off-line learning and on-line learning (similar to adaptive control). We have tested our method for a simplified dynamic problem: the dynamic stability of a simulated planar biped. To obtain dynamic equilibrium during the single-support-phase, the robot trunk is controlled such that a zero-moment-point (ZMP) criterion is satisfied. We show that although no gait-specific knowledge is used during off-line learning, dynamic walking for different step lengths and heights could be realized and controled. The capability of the proposed learning algorithm to adapt the trunk control on-line to the actually performed leg trajectories allows further improvements and adaptation to real environment conditions or perturbations.
Fichier principal
Vignette du fichier
ISMCR1993.pdf (3.58 Mo) Télécharger le fichier
Origine Accord explicite pour ce dépôt

Dates et versions

hal-01348277 , version 1 (08-09-2016)

Identifiants

  • HAL Id : hal-01348277 , version 1

Citer

Patrick Henaff, Holger Schwenk, M. Milgram. A Neural Network Approach of the Control of Dynamic Biped Equilibrium. 3rd International Symposium on Measurement and Control in Robotics (ISMCR '93), Sep 1993, Turin, Italy. pp.AS.II-19. ⟨hal-01348277⟩
346 Consultations
29 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More