Efficiently Learning and Generalizing Variable Impedance Manipulation Skills from Human Demonstrations

Learning Variable Impedance Control(VIC) policy can help robot assistants to intelligently adapt their manipulation compliance to ensure both safe interaction and proper task completion when operating in human-robot interaction environments. In this paper, we propose a DMP-based framework that learns and generalizes variable impedance manipulation skills from human demonstrations. This framework improves robots' adaptability to environment changes(i.e. the weight and shape changes of the robot end-effector) and inherits the efficiency of demonstration variance-based stiffness estimation method. Besides, with our stiffness estimation method, we generate not only translational stiffness profiles, but also rotational stiffness profiles that are ignored or incomplete in most learning VIC papers. Real-world experiments on a 7 DoF runduant robot manipulator haven been conducted to validate the effectiveness of our framework.