Transferring human skills to telerobotic manipulators

Abstract

Communicating human expertise to a machine is a critically important issue particularly for telerobots operated under human supervision. The goal of this paper is to develop a new method for representing human skills in assembly tasks and transferring the skills to telerobotic systems. By monitoring communication signals between master and slave manipulators, we acquire data from which control strategies of the human operator are extracted. Two levels of control strategies are extracted from the data: one is a high-level sequence of motion with regard to discrete state transitions of the contact state, and the other is compliant motion strategies with which the human operator manipulates parts. Based on a priori knowledge of the geometry of parts, we first generate a state network representing possible transitions of contact states using the method developed by Hirai and Asada [12]. The human control data are interpreted with reference to this network and a motion sequence of motion is extracted from the data. The complaint motion control strategy necessary for each state transition is then identified by processing the force and velocity profiles of the acquired data. The identified control strategies in individual steps of the operation are then compiled in order to simplify the representation of the strategies as well as to obtain smooth state transitions.