Configuration Depending Crosstalk Torque Calibration for Robotic Manipulators with Deep Neural Regression Models

  • Adrian ZwienerEmail author
  • Sebastian Otte
  • Richard Hanten
  • Andreas Zell
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 867)


In this paper, an approach for articulated robotic manipulator which minimizes configuration depending crosstalk torques is presented. In particular, these crosstalk torques are an issue for the Kinova Jaco 2 manipulator. We can experimentally show that the presented approach leads to crosstalk minimization for the Kinova Jaco 2 manipulator. Crosstalk leads to a significant difference between sensor output and inverse dynamic models using CAD rigid body parameters. As a consequence, these disturbances lead to a hindered torque control and perception. Different machine learning techniques, namely Random Forests and various neural network architectures, are evaluated on this task. We show that particularly deep neural regression networks are able to learn the influence of the cross torques which improves perception.


Crosstalk torques Calibration Machine learning 


  1. 1.
    Camoriano, R., Traversaro, S., Rosasco, L., Metta, G., Nori, F.: Incremental semiparametric inverse dynamics learning. In: 2016 IEEE International Conference on Robotics and Automation (ICRA), pp. 544–550. IEEE (2016)Google Scholar
  2. 2.
    Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016)Google Scholar
  3. 3.
    Haddadin, S., De Luca, A., Albu-Schäffer, A.: Robot collisions: a survey on detection, isolation, and identification. IEEE Trans. Robot. 33(6), 1292–1312 (2017)CrossRefGoogle Scholar
  4. 4.
    Ishiguro, A., Furuhashi, T., Okuma, S., Uchikawa, Y.: A neural network compensator for uncertainties of robotics manipulators. IEEE Trans. Ind. Electron. 39(6), 565–570 (1992)CrossRefGoogle Scholar
  5. 5.
    Jain, A., Killpack, M.D., Edsinger, A., Kemp, C.C.: Reaching in clutter with whole-arm tactile sensing. Int. J. Robot. Res. 32(4), 458–482 (2013)CrossRefGoogle Scholar
  6. 6.
    Kim, Y.L., Park, J.J., Song, J.B.: Crosstalk calibration for torque sensor using actual sensing frame. J. Mech. Sci. Technol. 24(8), 1729–1735 (2010)CrossRefGoogle Scholar
  7. 7.
    Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. ArXiv e-prints abs/1412.6980 (2014)
  8. 8.
    Lee, S.H., Kim, Y.L., Song, J.B.: Torque sensor calibration using virtual load for a manipulator. Int. J. Precis. Eng. Manuf. 11(2), 219–225 (2010)CrossRefGoogle Scholar
  9. 9.
    Likar, N., Zlajpah, L.: External joint torque-based estimation of contact information. Int. J. Adv. Robot. Syst. 11(1), 107 (2014)CrossRefGoogle Scholar
  10. 10.
    de Luca, A., Mattone, R.: Sensorless robot collision detection and hybrid force/motion control. In: Proceedings of the 2005 IEEE International Conference on Robotics and Automation, pp. 999–1004, April 2005Google Scholar
  11. 11.
    Marco, A., Hennig, P., Bohg, J., Schaal, S., Trimpe, S.: Automatic LQR tuning based on Gaussian process global optimization. In: 2016 IEEE International Conference on Robotics and Automation (ICRA), pp. 270–277 (2016)Google Scholar
  12. 12.
    Mohammadi, A., Tavakoli, M., Marquez, H., Hashemzadeh, F.: Nonlinear disturbance observer design for robotic manipulators. Control Eng. Pract. 21(3), 253–267 (2013)CrossRefGoogle Scholar
  13. 13.
    Otte, S., Krechel, D., Liwicki, M.: JANNLab Neural Network Framework for Java. In: Poster Proceedings of MLDM 2013, pp. 39–46. ibai-publishing, New York (2013)Google Scholar
  14. 14.
    Pastor, P., Righetti, L., Kalakrishnan, M., Schaal, S.: Online movement adaptation based on previous sensor experiences. In: 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 365–371. IEEE (2011)Google Scholar
  15. 15.
    Rasmussen, C.E., Williams, C.K.: Gaussian Processes for Machine Learning, vol. 1. MIT press, Cambridge (2006)zbMATHGoogle Scholar
  16. 16.
    Shahriari, B., Swersky, K., Wang, Z., Adams, R.P., de Freitas, N.: Taking the human out of the loop: A review of bayesian optimization. Proc. IEEE 104(1), 148–175 (2016)CrossRefGoogle Scholar
  17. 17.
    Siciliano, B., Khatib, O.: Springer Handbook of Robotics. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  18. 18.
    Vorndamme, J., Schappler, M., Haddadin, S.: Collision detection, isolation and identification for humanoids. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 4754–4761. IEEE (2017)Google Scholar
  19. 19.
    Zelenak, A., Pryor, M., Schroeder, K.: An extended Kalman filter for collision detection during manipulator contact tasks. In: ASME 2014 Dynamic Systems and Control Conference, p. V001T11A005. American Society of Mechanical Engineers (2014)Google Scholar
  20. 20.
    Zwiener, A., Geckeler, C., Zell, A.: contact point localization for articulated manipulators with proprioceptive sensors and machine learning. In: 2018 IEEE International Conference on Robotics and Automation (ICRA) (2018, accepted)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Adrian Zwiener
    • 1
    Email author
  • Sebastian Otte
    • 2
  • Richard Hanten
    • 1
  • Andreas Zell
    • 1
  1. 1.Cognitive Systems GroupUniversity of TübingenTübingenGermany
  2. 2.Cognitive Modeling GroupUniversity of TübingenTübingenGermany

Personalised recommendations