In this paper, we investigate the mechanics of dance for humans that can be applied to
robots, in an attempt to make dancing robots learn the fundamentals of dance, and improve their
dancing. We provide a conceptual definition of ‘dance’ and ‘movement’ to make robot dancers
form their own movements to music. We used a virtual robot dog to experiment on our conceptual
definitions, and human subjects to give their feedback on the robot’s dancing. Experimental results
show that the robot learns (using reinforcement learning) our conceptual definition of ‘dance’ and
that a dance that has structure and fundamental joint movements, improves the dancing.
History
School
Science
Department
Computer Science
Citation
THOLLEY, I.S., MENG, Q. and CHUNG, P.W.H., 2012. Robot dancing: What makes a dance. Advanced Materials Research, 403-408, pp. 4901 - 4909.
This article is closed access. It was published in the journal Advanced Materials Research: http://www.scientific.net/AMR It was originally presented as a conference paper and published in the Proceedings of IEEE International Conference on Control, Robotics and Cybernetics, 2011, pp. 53 - 58.