Hostname: page-component-6bf8c574d5-8gtf8 Total loading time: 0 Render date: 2025-02-22T20:35:35.308Z Has data issue: false hasContentIssue false
  • English
  • Français

A novel joint external torque estimate model of the lightweight robot’s joint based on a BP neural network

Published online by Cambridge University Press:  04 February 2025

Tao Zhang Open the ORCID record for Tao Zhang [Opens in a new window] ,
Haochong Li ,
Yongping Shi ,
Lei Wang ,
Xuanchen Zhang ,
Jun Zhang  and
Huapeng Wu
Tao Zhang
Affiliation:
School of Mechanical Engineering, Hefei University of Technology, Hefei, China
Haochong Li*
Affiliation:
School of Mechanical Engineering, Hefei University of Technology, Hefei, China
Yongping Shi*
Affiliation:
School of Mechanical Engineering, Hefei University of Technology, Hefei, China Lappeenranta University of Technology (LUT), Lappeenranta, Finland
Lei Wang
Affiliation:
School of Mechanical Engineering, Hefei University of Technology, Hefei, China
Xuanchen Zhang
Affiliation:
Institute of Plasma Physics Chinese Academy of Sciences (ASIPP), Chinese Academy of Sciences, Hefei, China
Jun Zhang
Affiliation:
Institute of Plasma Physics Chinese Academy of Sciences (ASIPP), Chinese Academy of Sciences, Hefei, China
Huapeng Wu
Affiliation:
Lappeenranta University of Technology (LUT), Lappeenranta, Finland
*
Corresponding authors: Haochong Li; Email: [email protected], Yongping Shi; Email: [email protected]
Corresponding authors: Haochong Li; Email: [email protected], Yongping Shi; Email: [email protected]
Get access Rights & Permissions [Opens in a new window]

Abstract

The safety of human-collaborative operations with robots depends on monitoring the external torque of the robot, in which there are toque sensor-based and torque sensor-free methods. Economically, the classic method for estimating joint external torque is the first-order momentum observer (MOB) based on a physic model without torque sensors. However, uncertainties in the dynamic model, which encompasses parameters identification error and joint friction, affect the torque estimation accuracy. To address this issue, this paper proposes using the backpropagation neural network (BPNN) method to estimate joint external torque without the delicate physical model by utilizing the powerful machine learning ability to handle the uncertainties of the MOB method and improve the accuracy of torque estimation. Using data obtained from the torque sensor to train the BPNN to build up a digital torque model, the trained BPNN can perceive force in practical applications without relying on the torque sensor. In the end, by contrast to the classic first-order MOB, the result demonstrates that BPNN achieves higher estimation accuracy compared to the MOB.

Keywords

robot joint external torquemomentum observerbackpropagation neural network
Type
Research Article
Information
Robotica , First View , pp. 1 - 16
Copyright
© The Author(s), 2025. 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

Metzner, M., Leurer, S., Handwerker, A., Karlidag, E., Blank, A., Hefner, F. and Franke, J., “High-precision assembly of electronic devices with lightweight robots through sensor-guided insertion,” Proc. CIRP 97, 337–341 (2021).CrossRefGoogle Scholar
Husmann, S., Stemmler, S., Hähnel, S., Vogelgesang, S., Abel, D. and Bergs, T., “Model predictive force control in grinding based on a lightweight robot,” IFAC-PapersOnLine 52(13), 1779–1784 (2019).CrossRefGoogle Scholar
Liu, Y., Li, X., Zhu, A., Zheng, Z. and Zhu, H., “Design and evaluation of a surface electromyography-controlled lightweight upper arm exoskeleton rehabilitation robot,” Int. J. Adv. Robot. Syst. 18(3) (2021).CrossRefGoogle Scholar
Li, W., Liu, K., Li, C., Sun, Z., Liu, S. and Gu, J., “Development and evaluation of a wearable lower limb rehabilitation robot,” J. Bionic Eng. 19(3), 688–699 (2022).CrossRefGoogle Scholar
Cao, M. Y., Laws, S. and Baena, F. R.y, “Six-axis force/torque sensors for robotics applications: A review,” IEEE Sensors J. 21(24), 27238–27251 (2021).CrossRefGoogle Scholar
Kim, U., Lee, D.-H., Kim, Y. B., Seok, D.-Y. and Choi, H. R., “A novel six-axis force/torque sensor for robotic applications,” IEEE-ASME Trans. Mech. 22(3), 1381–1391 (2017).CrossRefGoogle Scholar
Kim, Y. B., Seok, D.-Y., Lee, S. Y., Kim, J., Kang, G., Kim, U. and Choi, H. R., “6-axis force/torque sensor with a novel autonomous weight compensating capability for robotic applications,” IEEE Robot. Autom. Lett. 5(4), 6686–6693 (2020).CrossRefGoogle Scholar
Wang, Z., Liu, L., Yan, W., He, J., Cui, B. and Li, Z., “Research on collision point identification based on six-axis force/torque sensor,” J. Sensors 2020, 1–13 (2020).Google Scholar
Cheng, G., Dean-Leon, E., Bergner, F., Olvera, J. R. G., Leboutet, Q. and Mittendorfer, P., “A comprehensive realization of robot skin: Sensors, sensing, control, and applications,” Proc. IEEE 107(10), 2034–2051 (2019).CrossRefGoogle Scholar
Ye, Z., Pang, G., Xu, K., Hou, Z., Lv, H., Shen, Y. and Yang, G., “Soft robot skin with conformal adaptability for on-body tactile perception of collaborative robots,” IEEE Robot. Autom. Lett. 7(2), 5127–5134 (2022).CrossRefGoogle Scholar
Zhong, C., Zhao, S., Liu, Y., Li, Z., Kan, Z. and Feng, Y., “A flexible wearable e-skin sensing system for robotic teleoperation,” Robotica 41(3), 1025–1038 (2023).CrossRefGoogle Scholar
Han, L., Xu, W., Li, B. and Kang, P., “Collision detection and coordinated compliance control for a dual-arm robot without force/torque sensing based on momentum observer,” IEEE-ASME Trans. Mech. 24(5), 2261–2272 (2019).CrossRefGoogle Scholar
De Luca, A. and Mattone, R.. Sensorless Robot Collision Detection and Hybrid Force/Motion Control. In: Proceedings of the 2005 IEEE International Conference on Robotics and Automation (IEEE, 2005), pp. 999–1004.Google Scholar
Lee, S.-D. and Song, J.-B., “Sensorless collision detection based on friction model for a robot manipulator,” Int. J. Precis. Eng. Manuf. 17(1), 11–17 (2016).CrossRefGoogle Scholar
Briquet-Kerestedjian, N., Makarov, M., Rodriguez-Ayerbe, P. and Grossard, M., Quantifying the uncertainties-induced errors in robot impact detection methods (2016).CrossRefGoogle Scholar
Park, K. M., Kim, J., Park, J. and Park, F. C., “Learning-based real-time detection of robot collisions without joint torque sensors,” IEEE Robot. Autom. Lett. 6(1), 103–110 (2021).CrossRefGoogle Scholar
Parvaresh, A. and Moosavian, S. A. A., “Dynamics and path tracking of continuum robotic arms using data-driven identification tools,” Robotica 40(4), 1098–1124 (2022).CrossRefGoogle Scholar
Haddadin, S., De Luca, A. and Albu-Schaeffer, A., “Robot collisions: A survey on detection, isolation, and identification,” IEEE Trans. Robot. 33(6), 1292–1312 (2017).CrossRefGoogle Scholar
Garofalo, G., Mansfeld, N., Jankowski, J. and Ott, C., Sliding mode momentum observers for estimation of external torques and joint acceleration (2019).CrossRefGoogle Scholar
Liu, K., Wei, C., Ni, D., Lu, Z., Zhang, Z. and Li, Y., Stribeck friction model identification based on genetic algorithm (2022).CrossRefGoogle Scholar
Swevers, J., Ganseman, C., Tukel, D. B., d. Schutter, J. and Brussel, H. V., “Optimal robot excitation and identification,” IEEE Trans. Robot. Autom. 13(5), 730–740 (1997).CrossRefGoogle Scholar
Park, K.-J., “Fourier-based optimal excitation trajectories for the dynamic identification of robots,” Robotica 24(5), 625–633 (2006).CrossRefGoogle Scholar
Karsoliya, S., “Approximating number of hidden layer neurons in multiple hidden layer BPNN architecture,” Int. J. Eng. Trends Technol. 3(6), 714–717 (2012).Google Scholar
Hagan, M. T. and Menhaj, M. B., “Training feedforward networks with the Marquardt algorithm,” IEEE Trans. Neural Netw. 5(6), 989–993 (1994).CrossRefGoogle ScholarPubMed
Hagan, M. T., Demuth, H. B. and Beale, M., Neural Network Design (PWS Publishing Co, 1997).Google Scholar
Proakis, J. G., “Digital Signal Processing: Principles,” In: Algorithms, and Applications. vol. 4 (Pearson Education India, 2007).Google Scholar
MathWorks. MathWorks Documentation [EB/OL]. [2024-11-08]. https://ww2.mathworks.cn/help/dsp/ref/butter.html?searchHighlight=butter&s_tid=srchtitle_support_results_2_butter.Google Scholar