Learning Dance Movements by Imitation: A Multiple Model Approach

Authors:
Axel Tidemann;Pinar Öztürk
Affiliations:
IDI, Norwegian University of Science and Technology,;IDI, Norwegian University of Science and Technology,
Venue:
KI '08 Proceedings of the 31st annual German conference on Advances in Artificial Intelligence
Year:
2008

Citing 4
Cited 0

The correspondence problem

Imitation in animals and artifacts
The mirror system, imitation, and the evolution of language

Imitation in animals and artifacts
Imitation as a dual-route process featuring predictive and learning components: a biologically plausible computational model

Imitation in animals and artifacts
Self-organizing multiple models for imitation: teaching a robot to dance the YMCA

IEA/AIE'07 Proceedings of the 20th international conference on Industrial, engineering, and other applications of applied intelligent systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Imitation learning is an intuitive and easy way of programming robots. Instead of specifying motor commands, you simply show the robot what to do. This paper presents a modular connectionist architecture that enables imitation learning in a simulated robot. The robot imitates human dance movements, and the architecture self-organizes the decomposition of movements into submovements, which are controlled by different modules. Modules both dominate and collaborate during control of the robot. Low-level examination of the inverse models (i.e. motor controllers) reveals a recurring pattern of neural activity during repetition of movements, indicating that the modules successfully capture specific parts of the trajectory to be imitated.