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
Hi-index | 0.00 |
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.