Learning Force‐Relevant Skills from Human Demonstration

Abstract

Many human manipulation skills are force relevant, such as opening a bottle cap and assembling furniture. However, it is still a difficult task to endow a robot with these skills, which largely is due to the complexity of the representation and planning of these skills. This paper presents a learning-based approach of transferring force-relevant skills from human demonstration to a robot. First, the force-relevant skill is encapsulated as a statistical model where the key parameters are learned from the demonstrated data (motion, force). Second, based on the learned skill model, a task planner is devised which specifies the motion and/or the force profile for a given manipulation task. Finally, the learned skill model is further integrated with an adaptive controller that offers task-consistent force adaptation during online executions. The effectiveness of the proposed approach is validated with two experiments, i.e., an object polishing task and a peg-in-hole assembly.

Simultaneously Encoding Movement and sEMG-Based Stiffness for Robotic Skill Learning

“…One of the challenges is to enable a robot to learn human-like behaviours with flexibility and impedance adaptation [6][7][8][9]. Especially for force-dominant tasks [10], this challenge needs to be addressed urgently.…”

Learning Ultrasound Scanning Skills from Human Demonstrations

“…For the learning of force-relevant skills, a great variety of previous studies in robotic manipulation focused on learning the relation between force information and other task-related variables, such as the position and velocity [45], the surface electromyography [46], the task states and constraints [47], and the desired impedance [48]- [50]. A multi-modal representation method for contact-rich tasks has been proposed in [51] to encode the concurrent feedback information from vision and touch.…”

Planning for Multi-stage Forceful Manipulation

“…Several recent works have characterized types of forcebased motions. Gao et al defined "force-relevant skills" as a desired position and velocity in task space, along with an interaction wrench and task constraint [13]. Mahschitz et al termed "sequential forceful interaction tasks" as those characterized by point-to-point movements and an interaction where the robot must actively apply a wrench [14].…”