A unified parametric representation for robotic compliant skills with adaptation of impedance and force

Zeng, Chao; Li, Yanan; Guo, Jing; Huang, Zhifeng; Wang, Ning; Yang, Chenguang

Abstract

Robotic compliant manipulation is a very challenging but urgent research spot in the domain of robotics. One difficulty lies in the lack of a unified representation for encoding and learning of compliant profiles. This article aims to introduce a novel learning and control framework to address this problem: 1) we provide a parametric representation that enables a compliant skill to be encoded in a parametric space and allows a robot to learn compliant manipulation skills based on motion and force information collected from human demonstrations; and 2) the updating laws of the compliant profiles, including impedance and force profiles, are derived from a biomimetic control strategy based on the human motor learning principles. Our approach enables the simultaneous adaptation of impedance and feedforward force online during robot's reproduction of the demonstrated tasks to deal with task dynamics and external interferences. The proposed approach is verified based on both simulation and real-world task scenarios.

• Journal Article Type: Article
• Acceptance Date: Aug 26, 2021
• Online Publication Date: Sep 27, 2021
• Publication Date: 2022-04
• Deposit Date: Sep 29, 2021
• Publicly Available Date: Sep 30, 2021
• Journal: IEEE/ASME Transactions on Mechatronics
• Print ISSN: 1083-4435
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• Volume: 27
• Issue: 2
• Pages: 623-633
• DOI: https://doi.org/10.1109/tmech.2021.3109160
• Keywords: Electrical and Electronic Engineering; Computer Science Applications; Control and Systems Engineering
• Public URL: https://uwe-repository.worktribe.com/output/7860486