Skip to main content
SpringerLink
Log in

Online identification of time-varying dynamical systems for industrial robots based on sparse Bayesian learning

  • Article
  • Published:
Science China Technological Sciences Aims and scope Submit manuscript

Abstract

Nowadays, industrial robots have been widely used in manufacturing, healthcare, packaging, and more. Choosing robots in these applications mainly attributes to their repeatability and precision. However, prolonged and loaded operations can deteriorate the accuracy and efficiency of industrial robots due to the unavoidable accumulated kinematical and dynamical errors. This paper resolves these aforementioned issues by proposing an online time-varying sparse Bayesian learning (SBL) method to identify dynamical systems of robots in real-time. The identification of dynamical systems for industrial robots is cast as a sparse linear regression problem. By constructing the dictionary matrix, the parameters of the robot dynamics are effectively estimated via a re-weighted ℓ1-minimization algorithm. Online recursive methods are integrated into SBL to achieve real-time system identification. By including sparsity and promoting online learning, the proposed method can handle time-varying dynamical systems and therefore improve operational stability and accuracy. Experimental results on both simulated and real selective compliance assembly robot arm (SCARA) robots have demonstrated the effectiveness of the proposed method for industrial robots.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Dauth W, Findeisen S, Südekum J, et al. German robots—The impact of industrial robots on workers. CEPR Discussion Paper No. DP12306, 2017

  2. Tang T, Lin H C, Zhao Y, et al. Teach industrial robots peg-hole-insertion by human demonstration. In: Proceedings of IEEE International Conference on Advanced Intelligent Mechatronics (AIM). Banff, 2016. 488–494

  3. Rahmatizadeh R, Abolghasemi P, Bölöni L, et al. Vision-based multitask manipulation for inexpensive robots using end-to-end learning from demonstration. In: Proceedings of IEEE International Conference on Robotics and Automation (ICRA). Brisbane, 2018. 3758–3765

  4. Wu J, Zhang D, Liu J, et al. A moment approach to positioning accuracy reliability analysis for industrial robots. IEEE Trans Rel, 2019, 69: 699–714

    Article  Google Scholar 

  5. Murray R M, Li Z, Sastry S S, et al. A Mathematical Introduction to Robotic Manipulation. Boca Raton: CRC Press, 1994

    MATH  Google Scholar 

  6. Klančar G, Škrjanc I. Tracking-error model-based predictive control for mobile robots in real time. Robot Auton Syst, 2007, 55: 460–469

    Article  Google Scholar 

  7. Boaventura T, Buchli J, Semini C, et al. Model-based hydraulic impedance control for dynamic robots. IEEE Trans Robot, 2015, 31: 1324–1336

    Article  Google Scholar 

  8. Gautier M. Identification of robots dynamics. IFAC Proc Volumes, 1986, 19: 125–130

    Article  Google Scholar 

  9. Khalil W, Gautier M, Lemoine P. Identification of the payload inertial parameters of industrial manipulators. In: Proceedings of IEEE International Conference on Robotics and Automation (ICRA). Rome, 2007. 4943–4948

  10. Sinha S K, Nagaraja T. Extended Kalman filter algorithm for continuous system parameter identification. Comput Electrical Eng, 1990, 16: 51–64

    Article  Google Scholar 

  11. Gautier M, Poignet P. Extended kalman filtering and weighted least squares dynamic identification of robot. Control Eng Practice, 2001, 9: 1361–1372

    Article  Google Scholar 

  12. Poignet P, Gautier M. Comparison of weighted least squares and extended kalman filtering methods for dynamic identification of robots. In: Proceedings of IEEE International Conference on Robotics and Automation (ICRA). San Francisco, 2000, 4: 3622–3627

    Google Scholar 

  13. Wu J, Wang J, You Z. An overview of dynamic parameter identification of robots. Robot Comput-Integrated Manuf, 2010, 26: 414–419

    Article  Google Scholar 

  14. Urrea C, Pascal J. Design, simulation, comparison and evaluation of parameter identification methods for an industrial robot. Comput Electrical Eng, 2018, 67: 791–806

    Article  Google Scholar 

  15. Haykin S. Adaptive Filter Theory: International Edition. San Antonio: Pearson Education, 2013. 515

    Google Scholar 

  16. Jiang Z H, Ishida T, Sunawada M. Neural network aided dynamic parameter identification of robot manipulators. In: Proceedings of IEEE International Conference on Systems, Man and Cybernetics. Taipei, 2006, 4: 3298–3303

    Google Scholar 

  17. Su H, Qi W, Yang C, et al. Deep neural network approach in robot tool dynamics identification for bilateral teleoperation. IEEE Robot Autom Lett, 2020, 5: 2943–2949

    Article  Google Scholar 

  18. Zhou J, Kang H J. A hybrid least-squares genetic algorithm-based algorithm for simultaneous identification of geometric and compliance errors in industrial robots. Adv Mech Eng, 2015, 7: 168781401559028

    Article  Google Scholar 

  19. Zhang Z, Qian K, Schuller B W, et al. An online robot collision detection and identification scheme by supervised learning and bayesian decision theory. IEEE Trans Automat Sci Eng, 2021, 18: 1144–1156

    Article  Google Scholar 

  20. Bruder D, Remy C D, Vasudevan R. Nonlinear system identification of soft robot dynamics using Koopman operator theory. In: Proceedings of IEEE International Conference on Robotics and Automation (ICRA). Montreal, 2019. 6244–6250

  21. Brunton S L, Proctor J L, Kutz J N. Discovering governing equations from data by sparse identification of nonlinear dynamical systems. Proc Natl Acad Sci USA, 2016, 113: 3932–3937

    Article  MathSciNet  Google Scholar 

  22. Yuan Y, Tang X, Zhou W, et al. Data driven discovery of cyber physical systems. Nature Commun, 2019, 10: 1–9

    Article  Google Scholar 

  23. Pan W, Yuan Y, Gonçalves J, et al, Reconstruction of arbitrary biochemical reaction networks: A compressive sensing approach. In: Proceedings of IEEE Conference on Decision and Control (CDC). Maui, 2012. 2334–2339

  24. Tipping M E. Sparse Bayesian learning and the relevance vector machine. J Mach Learn Res, 2001, 1: 211–224

    MathSciNet  MATH  Google Scholar 

  25. Pan W, Yuan Y, Goncalves J, et al. A sparse bayesian approach to the identification of nonlinear state-space systems. IEEE Trans Automat Contr, 2015, 61: 182–187

    Article  MathSciNet  Google Scholar 

  26. Siciliano B, Sciavicco L, Villani L, et al. Robotics: Modelling, Planning and Control. Berlin: Springer International Publishing, 2010. 281

    Google Scholar 

  27. Yang C, Jiang Y, He W, et al. Adaptive parameter estimation and control design for robot manipulators with finite-time convergence. IEEE Trans Ind Electron, 2018, 65: 8112–8123

    Article  Google Scholar 

  28. Yuan Y, Zhang H T, Wu Y, et al. Bayesian learning-based model-predictive vibration control for thin-walled workpiece machining processes. IEEE/ASME Trans Mechatron, 2017, 22: 509–520

    Article  Google Scholar 

  29. Cao L, Zhang X M, Huang T, et al. Online monitoring machining errors of thin-walled workpiece: A knowledge embedded sparse Bayesian regression approach. IEEE/ASME Trans Mechatron, 2019, 24: 1259–1270

    Article  Google Scholar 

  30. Palmer J A, Wipf D P, Kreutz-Delgado K, et al. Variational EM algorithms for non-Gaussian latent variable models. In: Proceedings of Advances in Neural Information Processing Systems (NIPS). Cambridge: MIT Press, 2006, 18: 1059

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, 430074, China

    Tan Shen, YunLong Dong, DingXin He & Ye Yuan

Authors
  1. Tan Shen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. YunLong Dong
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. DingXin He
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ye Yuan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ye Yuan.

Additional information

Data and code availability

The data and the code that support the findings of this study are available on request via E-mail upon reasonable request.

This work was supported by the National Key R&D Program of China (Grant No. 2018YFB1701202).

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Shen, T., Dong, Y., He, D. et al. Online identification of time-varying dynamical systems for industrial robots based on sparse Bayesian learning. Sci. China Technol. Sci. 65, 386–395 (2022). https://doi.org/10.1007/s11431-021-1947-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11431-021-1947-5

Search

Navigation