Hostname: page-component-848d4c4894-x5gtn Total loading time: 0 Render date: 2024-06-06T11:10:49.762Z Has data issue: false hasContentIssue false
  • English
  • Français

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

Published online by Cambridge University Press:  24 April 2023

Donghao Shi Open the ORCID record for Donghao Shi [Opens in a new window] ,
Qinchuan Li ,
Chenguang Yang  and
Zhenyu Lu
Donghao Shi
Affiliation:
School of Mechanical Engineering, Zhejiang Sci-Tech University, Hangzhou, China
Qinchuan Li*
Affiliation:
School of Mechanical Engineering, Zhejiang Sci-Tech University, Hangzhou, China
Chenguang Yang
Affiliation:
Bristol Robotics Laboratory, University of the West of England, Bristol, UK
Zhenyu Lu
Affiliation:
Bristol Robotics Laboratory, University of the West of England, Bristol, UK
*
Corresponding author: Qinchuan Li; Email: lqchuan@zstu.edu.cn
Get access Rights & Permissions [Opens in a new window]

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.

Keywords

dynamic movement primitivesrobotic skill learningintegral barrier Lyapunov function
Type
Research Article
Information
Robotica , Volume 41 , Issue 8 , August 2023 , pp. 2451 - 2463
Copyright
© The Author(s), 2023. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Atkeson, C. G., Schaal, C. G. and Systems, A., “Learning from demonstration,” Robot. Auton. Syst. 47(2-3), 65–67 (2004).Google Scholar
Schaal, S., Mohajerian, P. and Ijspeert, A. J. P. I. B. R., “Dynamics systems vs. optimal control - a unifying view,” Prog. Brain Res. 165, 425–445 (2007).CrossRefGoogle ScholarPubMed
Tang, T., Lin, H. C., Zhao, Y., Fan, Y. and Tomizuka, M., “Teach Industrial Robots Peg-Hole-Insertion by Human Demonstration,” IEEE International Conference on Advanced Intelligent Mechatronics, (2016).CrossRefGoogle Scholar
Vogt, D., Stepputtis, S., Grehl, S., Jung, B. and Amor, H. B., A System for Learning Continuous Human-Robot Interactions from Human-Human Demonstrations, 2017 IEEE International Conference on Robotics and Automation (ICRA), (2017).CrossRefGoogle Scholar
Lioutikov, R., Neumann, G., Maeda, G., Peters, J. and IEEE, Probabilistic Segmentation Applied to an Assembly Task, 2015 IEEE-RAS 15th International Conference on Humanoid Robots (IEEE-RAS International Conference on Humanoid Robots), (2015) pp. 533–540.Google Scholar
Moro, C., Nejat, G. and Mihailidis, A., “Learning and personalizing socially assistive robot behaviors to aid with activities of daily living,” ACM Trans. Human-Robot Interact. 7(2), 1–25 (2018).CrossRefGoogle Scholar
Xu, W., Chen, J., Lau, H. Y. K. and Ren, H., “Automate surgical tasks for a flexible serpentine manipulator via learning actuation space trajectory from demonstration,” IEEE Int. Conf. Robot. Autom., 4406–4413 (2016).Google Scholar
Osa, T., Harada, K., Sugita, N., Mitsuishi, M. and IEEE, Trajectory Planning under Different Initial Conditions for Surgical Task Automation by Learning from Demonstration, 2014 IEEE International Conference on Robotics and Automation (IEEE International Conference on Robotics and Automation ICRA), (2014) pp. 6507–6513.Google Scholar
Gams, A., Nemec, B., Ijspeert, A. J. and Ude, A., “Coupling movement primitives: Interaction with the environment and bimanual tasks,” IEEE Trans. Robot. 30(4), 816–830 (2014).CrossRefGoogle Scholar
Argall, B. D., Chernova, S., Veloso, M. and Browning, B., “A survey of robot learning from demonstration,” Robot. Auton. Syst. 57(5), 469–483 (2009).CrossRefGoogle Scholar
Losey, D. P. and O’Malley, M. K.. Learning the Correct Robot Trajectory in Real-Time From Physical Human Interactions, vol. 27. ACM, New York, NY, USA, (2019).Google Scholar
Nemec, B., Zlajpah, L., Slajpa, S., Piskur, J. and Ude, A., An Efficient PBD Framework for Fast Deployment of Bi-Manual Assembly Tasks, 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids), (2018).CrossRefGoogle Scholar
Hagenow, M., Senft, E., Radwin, R., Gleicher, M. and Zinn, M., “Corrective shared autonomy for addressing task variability,” IEEE Robot. Autom. Lett. 6(2), 1–1 (2021).CrossRefGoogle ScholarPubMed
Sheridan, T. B. J. M. P., Telerobotics, automation, and human supervisory control, (1992).Google Scholar
Si, W. Y., Guan, Y. and Wang, N., “Adaptive compliant skill learning for contact-rich manipulation with human in the loop,” IEEE Robot. Autom. Lett. 7(3), 5834–5841 (2022).CrossRefGoogle Scholar
Yang, C., Huang, D., He, W., Cheng, L. J. I. T. O. N. N. and Systems, L., “Neural control of robot manipulators with trajectory tracking constraints and input saturation,” IEEE Trans. Neural Netw. Learn. Syst. 99, 1–12 (2020).Google Scholar
Tee, K. P., Ge, S. S. and Tay, E. H., “Barrier Lyapunov functions for the control of output-constrained nonlinear systems,” Automatica 45(4), 918–927 (2009).CrossRefGoogle Scholar
Jin, X., “Fault tolerant finite-time leader follower formation control for autonomous surface vessels with LOS range and angle constraints,” Automatica 68, 228–236 (2016).CrossRefGoogle Scholar
Wei, H., Shuang, Z. and Ge, S. S. J. I. T. O. I. E., “Adaptive control of a flexible crane system with the boundary output constraint,” IEEE Trans. Ind. Electron. 61(8), 4126–4133 (2014).Google Scholar
He, W., Xue, C., Yu, X., Li, Z. and Yang, C. J. I. T. O. A. S., “Admittance-based controller design for physical human-robot interaction in the constrained task space,” IEEE Trans. Autom. Sci. Eng. 99, 1–13 (2020).Google Scholar
Calinon, S., D’Halluin, F., Sauser, E. L., Caldwell, D. G., Billard, A. G. J. R. and A. M. IEEE, “Learning and reproduction of gestures by imitation,” IEEE Robot. Autom. Mag. 17(2), 44–54 (2010).CrossRefGoogle Scholar
Lu, Z., Wang, N. and Yang, C. J. I. A. T. o. M., “A constrained DMPs framework for robot skills learning and generalization from human demonstrations,” IEEE/ASME Trans. Mech. 99, 1 (2021).Google Scholar
Si, W., Wang, N. and Yang, C. J. N. C., “Composite dynamic movement primitives based on neural networks for human-robot skill transfer,” Neural Comput. Appl. 5, 1–11 (2021).Google Scholar
Chen, Z., Huang, F., Sun, W., Gu, J. and Yao, B. J. I. A. T. o. M., “RBF neural network based adaptive robust control for nonlinear bilateral teleoperation manipulators with uncertainty and time delay,” IEEE/ASME Trans. Mech. 99, 1 (2019).Google Scholar