Humanoid robot behavior learning based on ART neural network and cross-modality learning

Authors:
Lizhong Gu;Jianbo Su
Affiliations:
Department of Automation & Research Center of Intelligent Robotics, Shanghai Jiaotong University, Shanghai, China;Department of Automation & Research Center of Intelligent Robotics, Shanghai Jiaotong University, Shanghai, China
Venue:
ICNC'06 Proceedings of the Second international conference on Advances in Natural Computation - Volume Part I
Year:
2006

Citing 3
Cited 1

The ART of Adaptive Pattern Recognition by a Self-Organizing Neural Network

Computer
Challenges in building robots that imitate people

Imitation in animals and artifacts
Learning Movement Sequences from Demonstration

ICDL '02 Proceedings of the 2nd International Conference on Development and Learning

Hierarchical behavior categorization using correlation based adaptive resonance theory

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a novel robot behavior learning method based on Adaptive Resonance Theory (ART) neural network and cross-modality learning. We introduce the concept of classification learning and propose a new representation of observed behavior. Compared with previous robot behavior learning methods, this method has the property of learning a new behavior while at the same time preserving prior learned behaviors. Moreover, visual information and audio information are integrated to form a unified percept of the observed behavior, which facilitates robot behavior learning. We implement this learning method on a humanoid robot head for behavior learning and experimental results demonstrate the effectiveness of this method.