Learning CPG sensory feedback with policy gradient for biped locomotion for a full-body humanoid

Gen Endo, Jun Morimoto, Takamitsu Matsubara, Jun Nakanishi, Gordon Cheng

Publikation: KonferenzbeitragPapierBegutachtung

27 Zitate (Scopus)

Abstract

This paper describes a learning framework for a central pattern generator based biped locomotion controller using a policy gradient method. Our goals in this study are to achieve biped walking with a 3D hardware humanoid, and to develop an efficient learning algorithm with CPG by reducing the dimensionality of the state space used for learning. We demonstrate that an appropriate feed-back controller can be acquired within a thousand trials by numerical simulations and the obtained controller in numerical simulation achieves stable walking with a physical robot in the real world. Numerical simulations and hardware experiments evaluated walking velocity and stability. Furthermore, we present the possibility of an additional online learning using a hardware robot to improve the controller within 200 iterations.

OriginalspracheEnglisch
Seiten1267-1273
Seitenumfang7
PublikationsstatusVeröffentlicht - 2005
Extern publiziertJa
Veranstaltung20th National Conference on Artificial Intelligence and the 17th Innovative Applications of Artificial Intelligence Conference, AAAI-05/IAAI-05 - Pittsburgh, PA, USA/Vereinigte Staaten
Dauer: 9 Juli 200513 Juli 2005

Konferenz

Konferenz20th National Conference on Artificial Intelligence and the 17th Innovative Applications of Artificial Intelligence Conference, AAAI-05/IAAI-05
Land/GebietUSA/Vereinigte Staaten
OrtPittsburgh, PA
Zeitraum9/07/0513/07/05

Fingerprint

Untersuchen Sie die Forschungsthemen von „Learning CPG sensory feedback with policy gradient for biped locomotion for a full-body humanoid“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren