Trajectory Reconstruction with NURBS Curves for Robot Programming by Demonstration

Abstract

Service robots require simple programming techniques allowing users with little or no technical expertise to integrate new tasks in a robotic platform. A promising solution for automatic acquisition of robot behaviors is the programming by demonstration (PbD) paradigm. Its aim is to let robot systems learn new behaviors from a human operator demonstration. This paper describes a virtual reality based PbD system for pick-and-place and manipulation tasks. The system recovers smooth robot trajectories from single or multiple user demonstrations, thereby overcoming sensor noise and human inconsistency problems. More specifically, we investigate the benefits of the human hand trajectory reconstruction with NURBS curves by means of a best-fit data smoothing algorithm. Some experiments involving object transportation while avoiding obstacles in the workspace show the viability and effectiveness of the approach.