A neural network based framework for variable impedance skills learning from demonstrations

Zhang, Yu; Cheng, Long; Cao, Ran; Li, Houcheng; Yang, Chenguang

Abstract

Robots are becoming standard collaborators not only in factories, hospitals, and offices, but also in people's homes, where they can play an important role in situations where a human cannot complete a task alone or needs the help of another person (i.e., collaborative tasks). Variable impedance control with contact forces is critical for robots to successfully perform such manipulation tasks, and robots should be equipped with adaptive capabilities because conditions vary significantly for different robotic tasks in dynamic environments. This can be achieved by learning human motion capabilities and variable impedance skills. In this paper, a neural-network-based framework for learning variable impedance skills is proposed. The proposed approach builds the full stiffness function with the acquired forces and position learned from demonstrations, and then is used together with the sensed data to achieve the variable impedance control. The proposed algorithm can adapt to unknown situations that change the learned motion skill as needed (e.g., adapt to intermediate via-points or avoid obstacles). The proposed framework consists of two parts: Learning motion features and learning impedance features. The motion features learning is validated by reproducing, generalizing, and adapting to transit points and avoiding obstacles in the LASA dataset. Impedance features learning is validated based on a virtual variable stiffness system that achieves higher accuracy (approximately 90%) compared to traditional methods in a manual dataset, and the whole framework is validated through a co-manipulation task between a person and the Franka Emika robot.

• Journal Article Type: Article
• Acceptance Date: Nov 11, 2022
• Online Publication Date: Nov 19, 2022
• Publication Date: Feb 1, 2023
• Deposit Date: Nov 25, 2022
• Publicly Available Date: Nov 20, 2024
• Journal: Robotics and Autonomous Systems
• Print ISSN: 0921-8890
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 160
• Pages: 104312
• DOI: https://doi.org/10.1016/j.robot.2022.104312
• Keywords: Computer Science Applications; General Mathematics; Software; Control and Systems Engineering, Variable impedance skill, Learning from demonstrations, Skills learning, Human–robot interaction
• Public URL: https://uwe-repository.worktribe.com/output/10190852
• Publisher URL: https://www.sciencedirect.com/science/article/pii/S0921889022002019?via%3Dihub
• Additional Information: This article is maintained by: Elsevier; Article Title: A neural network based framework for variable impedance skills learning from demonstrations; Journal Title: Robotics and Autonomous Systems; CrossRef DOI link to publisher maintained version: https://doi.org/10.1016/j.robot.2022.104312; Content Type: article; Copyright: © 2022 Elsevier B.V. All rights reserved.