A constrained framework based on IBLF for robot learning with human supervision

Shi, Donghao; Li, Qinchuan; Yang, Chenguang; Lu, Zhenyu

Abstract

Dynamical movement primitives (DMPs) method is a useful tool for efficient robotic skills learning from human demonstrations. However, the DMPs method should know the specified constraints of tasks in advance. One flexible solution is to introduce the human superior experience as part of input. In this paper, we propose a framework for robot learning based on demonstration and supervision. Superior experience supplied by teleoperation is introduced to deal with unknown environment constrains and correct the demonstration for next execution. DMPs model with integral barrier Lyapunov function is used to deal with the constrains in robot learning. Additionally, a radial basis function neural network based controller is developed for teleoperation and the robot to track the generated motions. Then, we prove convergence of the generated path and controller. Finally, we deploy the novel framework with two touch robots to certify its effectiveness.

Citation

Shi, D., Li, Q., Yang, C., & Lu, Z. (2023). A constrained framework based on IBLF for robot learning with human supervision. Robotica, 41(8), 2451-2463. https://doi.org/10.1017/S0263574723000462

• Journal Article Type: Article
• Acceptance Date: Mar 28, 2023
• Online Publication Date: Apr 24, 2023
• Publication Date: Aug 31, 2023
• Deposit Date: May 3, 2023
• Publicly Available Date: Oct 25, 2023
• Journal: Robotica
• Print ISSN: 0263-5747
• Electronic ISSN: 1469-8668
• Publisher: Cambridge University Press (CUP)
• Peer Reviewed: Peer Reviewed
• Volume: 41
• Issue: 8
• Pages: 2451-2463
• DOI: https://doi.org/10.1017/S0263574723000462
• Keywords: Computer Science Applications; General Mathematics; Software; Control and Systems Engineering; Control and Optimization; Mechanical Engineering; Modeling and Simulation; dynamic movement primitives; robotic skill learning; integral barrier Lyapunov functi
• Public URL: https://uwe-repository.worktribe.com/output/10732041
• Publisher URL: https://www.cambridge.org/core/journals/robotica/article/constrained-framework-based-on-iblf-for-robot-learning-with-human-supervision/EC77418C0AA18A59CDC630C6BDF69FE7