Learning movement synchronization in multi-component robotic systems

Imitation learning of tasks in multi-component robotic systems requires capturing concurrency and synchronization requirements in addition to task structure. Learning time-critical tasks depends furthermore on the ability to model temporal elements in demonstrations. This paper proposes a modeling framework based on Petri nets capable of modeling these aspects in a programming by demonstration context. In the proposed approach, models of tasks are constructed from segmented demonstrations as task Petri nets, which can be executed as discrete controllers for reproduction. We present algorithms that automatically construct models from demonstrations, showing how elements of time-critical tasks can be mapped into task Petri net elements. The approach is validated by an experiment in which a robot plays a musical passage on a keyboard.

I. Introduction

Programming by demonstration (PbD), also called imitation learning or learning from demonstration, is a recent approach that promises a rapid and efficient way to impart skills to robots [1]. In PbD, robots are taught new skills or tasks simply by having a human teacher (or possibly another robotic agent) perform demonstrations, which they capture using various sensors. The robot then utilizes learning algorithms to learn the task and reproduce it with a measure of adaptability.