Robot Variable Impedance Skill Transfer and Learning Framework Based on a Simplified Human Arm Impedance Model

Abstract

A variable impedance skill transfer framework is introduced and experimentally evaluated in this article. This framework mainly includes the following: 1. a real-time estimation algorithm of arm endpoint stiffness based on the human arm endpoint impedance model, and 2. the tele-impedance demonstration (tele-demonstration) method and Gaussian mixture model (GMM)-based learning from demonstration (LfD) method, which are designed according to the impedance model and the variable impedance skill transfer process. The modelling of the human arm endpoint impedance is inspired by human operation habits. The model can modify the task stiffness in three Cartesian directions based on the arm configuration and muscle co-contraction effect. The model parameters and their values are identified by performing a perturbation-based arm endpoint impedance identification experiment. The real-time impedance model is used for tele-demonstration and obtaining multimodality learning data, including human arm position and impedance information. These multimodality learning data are used for the variable impedance skill learning and generalization, and an electrical switch skill is learned and generalized by a compliant robotic arm in the experiments to execute a variable impedance interaction task in a dynamic uncertain environment.