Imitation of walking paths with a low-cost humanoid robot

Abstract

The ability to follow specific and task-relevant paths is an essential feature for legged humanoid robots. In this paper, we describe a technique for programming walking paths for humanoid robots based on imitation. Demonstrated paths are synthesized as NURBS (Non Uniform Rational B-Spline), and can be adapted by the robot based on local and dynamic information. We report simple experiments performed with a Robosapien V2 low-cost humanoid toy which has been suitably enhanced to support imitation-based programming. We show that despite robot limitations rather complex navigational tasks can be achieved through visual guidance. The system combines inputs from multiple sensory devices, including a motion tracker and a monocular vision system for landmark recognition. © 2008 Springer-Verlag Berlin Heidelberg.