Adaptive categorization of ART networks in robot behavior learning using game-theoretic formulation

Wai Keung Fung*, Yun Hui Liu

*Awdur cyfatebol y gwaith hwn

Allbwn ymchwil: Cyfraniad at gyfnodolynErthygladolygiad gan gymheiriaid

16 Dyfyniadau (Scopus)

Crynodeb

Adaptive Resonance Theory (ART) networks are employed in robot behavior learning. Two of the difficulties in online robot behavior learning, namely, (1) exponential memory increases with time, (2) difficulty for operators to specify learning tasks accuracy and control learning attention before learning. In order to remedy the aforementioned difficulties, an adaptive categorization mechanism is introduced in ART networks for perceptual and action patterns categorization in this paper. A game-theoretic formulation of adaptive categorization for ART networks is proposed for vigilance parameter adaptation for category size control on the categories formed. The proposed vigilance parameter update rule can help improving categorization performance in the aspect of category number stability and solve the problem of selecting initial vigilance parameter prior to pattern categorization in traditional ART networks. Behavior learning using physical robot is conducted to demonstrate the effectiveness of the proposed adaptive categorization mechanism in ART networks.

Iaith wreiddiolSaesneg
Tudalennau (o-i)1403-1420
Nifer y tudalennau18
CyfnodolynNeural Networks
Cyfrol16
Rhif cyhoeddi10
Dynodwyr Gwrthrych Digidol (DOIs)
StatwsCyhoeddwyd - 31 Mai 2003
Cyhoeddwyd yn allanolIe

Dyfynnu hyn