Robot Impedance Iterative Learning With Sparse Online Gaussian Process

Yongping Pan; Tian Shi; Wei Li; Bin Xu; Choon Ki Ahn

doi:10.1109/JAS.2025.125195

IEEE/CAA Journal of Automatica Sinica

JCR Impact Factor: 15.3, Top 1 (SCI Q1)

CiteScore: 23.5, Top 2% (Q1)
Google Scholar h5-index: 77， TOP 5

Turn off MathJax

Article Contents

Article Navigation > IEEE/CAA Journal of Automatica Sinica > 2025 > In Press, Accepted Manuscript

Y. Pan, T. Shi, W. Li, B. Xu, and C. Ahn, “Robot impedance iterative learning with sparse online Gaussian process,” IEEE/CAA J. Autom. Sinica, 2025. doi: 10.1109/JAS.2025.125195

Citation:

Y. Pan, T. Shi, W. Li, B. Xu, and C. Ahn, “Robot impedance iterative learning with sparse online Gaussian process,” IEEE/CAA J. Autom. Sinica, 2025. doi: 10.1109/JAS.2025.125195

Y. Pan, T. Shi, W. Li, B. Xu, and C. Ahn, “Robot impedance iterative learning with sparse online Gaussian process,” IEEE/CAA J. Autom. Sinica, 2025. doi: 10.1109/JAS.2025.125195

Citation:

Y. Pan, T. Shi, W. Li, B. Xu, and C. Ahn, “Robot impedance iterative learning with sparse online Gaussian process,” IEEE/CAA J. Autom. Sinica, 2025. doi: 10.1109/JAS.2025.125195

PDF( 1494 KB)

Robot Impedance Iterative Learning With Sparse Online Gaussian Process

doi: 10.1109/JAS.2025.125195

Funds: This work was supported in part by the Major Key Project of PCL, China (PCL2024A04), and in part by the National Research Foundation of Korea, funded by the Ministry of Science and ICT, Korea (NRF-2020R1A2C1005449)

More Information

Author Bio:
Yongping Pan (Senior Member, IEEE) received the Ph.D. degree in control theory and control engineering from the South China University of Technology, in 2011.He spent one year as a Control Systems Engineer in the industry in Shenzhen and Guangzhou, China. From 2011, has over ten years of research experience with the Nanyang Technological University, Singapore, the National University of Singapore, Singapore, and the University of Tokyo, Japan. In 2019, he joined the Sun Yat-sen University in Guangzhou and Shenzhen as a Professor who led the Intelligent Robotics Lab. Currently, he is a Professor with the Peng Cheng National Laboratory in Shenzhen. His research interests include automatic control and machine learning for robotics, such as compliant actuation, interaction control, visual servoing, motion planning, and dexterous manipulation. He has authored or co-authored over 200 peer-reviewed academic papers, including more than 130 papers in refereed journals.Dr. Pan serves as the Founding Chair of the IEEE Robotics and Automation Society Guangzhou Chapter and as an Associate Editor of several top-tier journals, such as the IEEE Transactions on Control Systems Technology, IEEE Transactions on Automation Science and Engineering, and IEEE Robotics and Automation Letters. He has served as various chairs of over 10 international conferences, the Lead Guest Editor of 4 special issues in reputable refereed journals, and the Lead Workshop Organizer of the IEEE Conference on Decision and Control (2023). He received the Best Automation Paper Finalist at the International Conference on Robotics and Automation (2024), the Best Conference Paper Award at the International Conference on Control and Robotics (2022), and the Best Conference Paper Finalist at the IEEE International Conference on Advanced Robotics and Mechatronics (2018). Furthermore, he has been recognized as a Global Highly Cited Researcher by Clarivate (2019) and a Most Cited Chinese Researcher by Elsevier (2021–2023)

Tian Shi (Student Member, IEEE) received the M.S. degree in control engineering from Jilin University, in 2021. He is currently pursuing the Ph.D. degree in computer science and technology at Sun Yat-sen University.His research interests include adaptive and interaction control for compliant actuation robots

Wei Li received received the B.S. degree in electronic information engineering from Guangdong University of Technology, in 2017, and the M.S. degree in computer technology from Sun Yat-sen University, in 2022.His research interests include Gaussian process and physical robot interaction

Bin Xu received the B.S. degree in measurement and control from Northwestern Polytechnical University, in 2006, and the Ph.D. degree in computer science from Tsinghua University, in 2012.He is currently a Professor with the School of Automation, Northwestern Polytechnical University. His research interests include intelligent control and adaptive control with applications

Choon Ki Ahn (Senior Member, IEEE) received the Ph.D. degree in the School of Electrical Engineering and Computer Science from Seoul National University, Korea, in 2006.He is currently a Crimson Professor of Excellence with the College of Engineering and a Full Professor with the School of Electrical Engineering, Korea University, Korea. In 2017, he received the Presidential Young Scientist Award from the President of South Korea. In 2020, 2021, and 2023, he received the Best (Outstanding) Associate Editor Award for IEEE Transactions on Neural Networks and Learning Systems; IEEE Transactions on Systems, Man, and Cybernetics: Systems; and IEEE Transactions on Circuits and Systems I: Regular Papers, respectively. In 2019-2024, he received the Korea University Research Excellence Award. In 2023, he was inducted into the Korea University Hall of Fame as the world’s top researcher.He has been a Senior Editor of IEEE Transactions on Neural Networks and Learning Systems; IEEE Transactions on Systems, Man, and Cybernetics: Systems; IEEE Systems Journal. He has also been an Associate Editor of IEEE Transactions on Fuzzy Systems; IEEE Transactions on Automation Science and Engineering; IEEE Transactions on Intelligent Transportation Systems; IEEE Transactions on Circuits and Systems I: Regular Papers; IEEE Systems, Man, and Cybernetics Magazine; and other flagship journals. He is the recipient of the 2019-2024 Highly Cited Researcher Award in Engineering by Clarivate Analytics (formerly, Thomson Reuters)
Corresponding author: Yongping Pan, e-mail: panyp@pcl.ac.cn
Received Date: 2024-07-03
Revised Date: 2024-11-08
Accepted Date: 2024-11-08

Available Online: 2025-05-23

Abstract

Abstract

Robot interaction control with variable impedance parameters may conform to task requirements during continuous interaction with dynamic environments. Iterative learning (IL) is effective to learn desired impedance parameters for robots under unknown environments, and Gaussian process (GP) is a nonparametric Bayesian approach that models complicated functions with providable confidence using limited data. In this paper, we propose an impedance IL method enhanced by a sparse online Gaussian process (SOGP) to speed up learning convergence and improve generalization. The SOGP is used to model a variable impedance strategy and is updated in the same iteration by removing similar data points from previous iterations while learning impedance parameters in multiple iterations. The proposed IL-SOGP method is verified by high-fidelity simulations of a collaborative robot with 7 degrees of freedom based on the admittance control framework. Numerical results have shown that the proposed method accelerates iterative convergence and improves generalization compared to the classical IL-based impedance learning method.
- Gaussian process,
- impedance variation,
- iterative learning,
- physical robot interaction,
- robot learning

FullText(HTML)

References(40)

References

[1]	E. Matheson, R. Minto, E. G. Zampieri, M. Faccio, and G. Rosati, “Human-robot collaboration in manufacturing applications: A review,” Robot., vol. 8, no. 4, p. 100, Dec. 2019. doi: 10.3390/robotics8040100
[2]	G. Kang, H. S. Oh, J. K. Seo, U. Kim, and H. R. Choi, “Variable admittance control of robot manipulators based on human intention,” IEEE/ASME Trans. Mechatronics, vol. 24, no. 3, pp. 1023–1032, Jun. 2019. doi: 10.1109/TMECH.2019.2910237
[3]	C. Ott, R. Mukherjee, and Y. Nakamura, “A hybrid system framework for unified impedance and admittance control,” J. Intell. Robot. Syst., vol. 78, no. 3–4, pp. 359–375, Jul. 2015. doi: 10.1007/s10846-014-0082-1
[4]	M. Sharifi, A. Zakerimanesh, J. K. Mehr, A. Torabi, V. K. Mushahwar, and M. Tavakoli, “Impedance variation and learning strategies in human-robot interaction,” IEEE Trans. Cybern., vol. 52, no. 7, pp. 6462–6475, Jul. 2022. doi: 10.1109/TCYB.2020.3043798
[5]	N. Nikooienejad, M. Maroufi, and S. O. Reza Moheimani, “A survey of iterative learning control: A learning-based method for high-performance tracking control,” IEEE Control Syst. Mag., vol. 26, no. 3, pp. 96–114, Jun. 2006. doi: 10.1109/MCS.2006.1636313
[6]	Y. Li and S. S. Ge, “Impedance learning for robots interacting with unknown environments,” IEEE Trans. Control Syst. Technol., vol. 22, no. 4, pp. 1422–1432, Jul. 2014. doi: 10.1109/TCST.2013.2286194
[7]	S. Riaz, L. Hui, M. S. Aldemir, and F. Afzal, “A future concern of iterative learning control: A survey,” J. Stat. Manag. Syst., vol. 24, no. 6, pp. 1301–1322, Apr. 2021.
[8]	D. Zhang, Z. Wang, and T. Masayoshi, “Neural-network-based iterative learning control for multiple tasks,” IEEE Trans. Neural Netw. Learn. Syst., vol. 32, no. 9, pp. 4178–4190, Sep. 2020.
[9]	L. Rath, A. R. Geist, and S. Trimpe, “Using physics knowledge for learning rigid-body forward dynamics with Gaussian process force priors,” in Proc. Conf. Robot Learn., London, UK, 2021, pp. 101–111.
[10]	J. Lee, J. Feng, M. Humt, M. G. Müller, and R. Triebel, “Trust your robots! predictive uncertainty estimation of neural networks with sparse Gaussian processes,” in Proc. Conf. Robot Learn., London, UK, 2021, pp. 1168–1179.
[11]	H. Liu, Y.-S. Ong, X. Shen, and J. Cai, “When Gaussian process meets big data: A review of scalable GPs,” IEEE Trans. Neural Netw. Learn. Syst., vol. 31, no. 11, pp. 4405–4423, Nov. 2020. doi: 10.1109/TNNLS.2019.2957109
[12]	L. Csato and M. Opper, “Sparse on-line Gaussian processes,” Neural Comput., vol. 14, no. 3, pp. 641–668, Mar. 2002. doi: 10.1162/089976602317250933
[13]	J. S. De La Cruz, W. Owen, and D. Kulic, “Online learning of inverse dynamics via Gaussian process regression,” in Proc. IEEE/RSJ Int. Conf. Intell. Robot. Syst., Vilamoura, Algarve, Portugal, 2012, pp. 3583–3590.
[14]	L. Deng, W. Li, and Y. Pan, “Data-efficient Gaussian process online learning for adaptive control of multi-DoF robotic arms,” IFAC-PapersOnLine, vol. 55, no. 2, pp. 84–89, 2022. doi: 10.1016/j.ifacol.2022.04.174
[15]	R.-E. Precup, S. Preitl, J. K. Tar, M. L. Tomescu, M. Takacs, P. Korondi, x and P. Baranyi, “Fuzzy control system performance enhancement by iterative learning control,” IEEE Trans. Ind. Electron., vol. 55, no. 9, pp. 3461–3475, Sep. 2008. doi: 10.1109/TIE.2008.925322
[16]	J. Wang, Y. Gao, Y. Gao, J. Liu, G. Sun, and L. Wu, “Intelligent dynamic practical-sliding-mode control for singular markovian jump systems,” Inf. Sci., vol. 607, pp. 153–172, Aug. 2022. doi: 10.1016/j.ins.2022.05.059
[17]	I. A. Zamfirache, R.-E. Precup, R.-C. Roman, and E. M. Petriu, “Neural network-based control using actor-critic reinforcement learning and grey Wolf optimizer with experimental servo system validation,” Expert Syst. Appl., vol. 225, Art. no. 120112, Sep. 2023.
[18]	F. Dimeas and N. Aspragathos, “Fuzzy learning variable admittance control for human-robot cooperation,” in Proc. IEEE/RSJ Int. Conf. Intell. Robot. Syst., Chicago, IL, USA, 2014, pp. 4770–4775.
[19]	A.-N. Sharkawy, P. N. Koustournpardis, and N. Aspragathos, “Variable admittance control for human-robot collaboration based on online neural network training,” in Proc. IEEE/RSJ Int. Conf. Intell. Robot. Syst., Madrid, Spain, 2018, pp. 1334–1339.
[20]	A.-N. Sharkawy, P. Koustoumpardis, and N. Aspragathos, “A neural network-based approach for variable admittance control in human-robot cooperation: online adjustment of the virtual inertia,” Intel. Serv. Robotics, vol. 13, pp. 495–519, Aug. 2020. doi: 10.1007/s11370-020-00337-4
[21]	X. Yu, W. He, Y. Li, C. Xue, J. Li, J. Zou, and C. Yang, “Bayesian estimation of human impedance and motion intention for human-robot collaboration,” IEEE Trans. Cybern., vol. 51, no. 4, pp. 1822–1834, Apr. 2021. doi: 10.1109/TCYB.2019.2940276
[22]	C. Li, Z. Zhang, G. Xia, X. Xie, and Q. Zhu, “Efficient learning variable impedance control for industrial robots,” Bull. Pol. Acad. Sci. Tech. Sci., vol. 67, p. 2, Apr. 2019.
[23]	L. Deng, Z. Li, and Y. Pan, “Sparse online Gaussian process impedance learning for multi-DoF robotic arms,” in Proc. IEEE Int. Conf. Adv. Robot. Mechatron., Chongqing, China, 2021, pp. 199–206.
[24]	C. Wang, Y. Li, S. S. Ge, and T. H. Lee, “Reference adaptation for robots in physical interactions with unknown environments,” IEEE Trans. Cybern., vol. 47, no. 11, pp. 3504–3515, Nov. 2017. doi: 10.1109/TCYB.2016.2562698
[25]	T. Yamawaki, H. Ishikawa, and M. Yashima, “Iterative learning of variable impedance control for human-robot cooperation,” in Proc. IEEE/RSJ Int. Conf. Intell. Robot. Syst., Daejeon, South Korea, 2016, pp. 839–844.
[26]	A. Kramberger, E. Shahriari, A. Gams, B. Nemec, A. Ude, and S. Haddadin, “Passivity based iterative learning of admittance-coupled dynamic movement primitives for interaction with changing environments,” in Proc. IEEE/RSJ Int. Conf. Intell. Robot. Syst., Madrid, Spain, 2018, pp. 6023–6028.
[27]	X. Li, Y.-H. Liu, and H. Yu, “Iterative learning impedance control for rehabilitation robots driven by series elastic actuators,” Automatica, vol. 90, pp. 1–7, Apr. 2018. doi: 10.1016/j.automatica.2017.12.031
[28]	K. Dupree, C.-H. Liang, G. Hu, and W. E. Dixon, “Adaptive lyapunov-based control of a robot and mass-spring system undergoing an impact collision,” IEEE Trans. Syst. Man Cybern. B, vol. 38, no. 4, pp. 1050–1061, Aug. 2008. doi: 10.1109/TSMCB.2008.923154
[29]	J. E. Colgate and N. Hogan, “Robust control of dynamically interacting systems,” Int. J. Control, vol. 48, no. 1, pp. 65–88, Oct. 1988. doi: 10.1080/00207178808906161
[30]	F. Ficuciello, L. Villani, and B. Siciliano, “Variable impedance control of redundant manipulators for intuitive human-robot physical interaction,” IEEE Trans. Robot., vol. 31, no. 4, pp. 850–863, Aug. 2015. doi: 10.1109/TRO.2015.2430053
[31]	C. E. Rasmussen and C. K. I. Williams, Gaussian Processes for Machine Learning. Cambridge, MA, USA: MIT press, 2006.
[32]	B. Wilcox and M. C. Yip, “SOLAR-GP: Sparse online locally adaptive regression using Gaussian processes for Bayesian robot model learning and control,” IEEE Robot. Autom. Lett., vol. 5, no. 2, pp. 2832–2839, Apr. 2020. doi: 10.1109/LRA.2020.2974432
[33]	X. Li, Y. Pan, G. Chen, and H. Yu, “Adaptive human-robot interaction control for robots driven by series elastic actuators,” IEEE Trans. Robot., vol. 33, no. 1, pp. 169–182, Feb. 2017. doi: 10.1109/TRO.2016.2626479
[34]	T. Sun, L. Peng, L. Cheng, Z.-G. Hou, and Y. Pan, “Stability-guaranteed variable impedance control of robots based on approximate dynamic inversion,” IEEE Trans. Syst. Man, Cybern. Syst., vol. 51, no. 7, pp. 4193–4200, Jul. 2019.
[35]	F. J. Abu-Dakka and M. Saveriano, “Variable impedance control and learning-A review,” Front. Robot. AI, vol. 7, p. 177, Dec. 2020.
[36]	W. Li, Z. Li, Y. Liu, and Y. Pan, “Learning inverse robot dynamics using sparse online Gaussian process with forgetting mechanism,” in Proc. IEEE Int. Conf. Adv. Intell. Mechatronics, Sapporo, Japan, 2022, pp. 638–643.
[37]	C. Gaz, M. Cognetti, A. Oliva, P. R. Giordano, and A. De Luca, “Dynamic identification of the Franka Emika Panda robot with retrieval of feasible parameters using penalty-based optimization,” IEEE Robot. Autom. Lett., vol. 4, no. 4, pp. 4147–4154, Oct. 2019. doi: 10.1109/LRA.2019.2931248
[38]	Y. Xie, X. Zhang, S. Zheng, C. K. Ahn, and S. Wang, “Asynchronous H_∞ continuous stabilization of mode-dependent wwitched mobile robot,” IEEE Trans. Syst. Man, Cybern. Syst., vol. 52, pp. 6906–6920, Nov. 2022. doi: 10.1109/TSMC.2021.3119054
[39]	S.-K. Kim, C. K. Ahn, and R. K. Agarwal, “Position-tracking controller for two-wheeled balancing robot applications using invariant dynamic surface,” IEEE Trans. Syst. Man, Cybern. Syst., vol. 51, no. 2, pp. 705–711, Feb. 2021. doi: 10.1109/TSMC.2018.2882868
[40]	M.-G. Unguritu and T.-C. Nichiţelea, “Design and assessment of an anti-lock braking system controller,” Roman. J. Inf. Sci. Technol., vol. 26, no. 1, pp. 21–32, 2023.

Supplements(0)

Cited By

Proportional views

Proportional views

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Figures(8) / Tables(2)

Get Citation

PDF

XML

Article Metrics

Article views (13) PDF downloads(4)

Robot Impedance Iterative Learning With Sparse Online Gaussian Process

doi: 10.1109/JAS.2025.125195

Abstract

References

Proportional views

Catalog

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Export File

Citation

Format

Content