Advertisement

A Boosted Decision Tree Approach for a Safe Human-Robot Collaboration in Quasi-static Impact Situations

  • Nemanja Kovincic
  • Hubert Gattringer
  • Andreas MüllerEmail author
  • Mathias Brandstötter
Conference paper
  • 59 Downloads
Part of the Mechanisms and Machine Science book series (Mechan. Machine Science, volume 84)

Abstract

According to the ISO/TS 15066, human safety in quasi-static impact situations in human-robot collaboration is assessed first by identifying all high-risk impact situations and then by measuring maximal and steady-state values the impact force and pressure at these possibly critical situations. This means that if something is changed in a collaborative application, the ISO/TS 15066 requires that the risk analysis and the force measurements must be redone, which severely limits the flexibility of a robotic system. In this paper, a physics guided boosted decision tree is proposed as a tool to assess human safety. The basic hypothesis is that a physics guided boosted decision tree can be trained to estimates the peak impact force for a given impact velocity, robot configuration, an impact point on the robot and a human body part. Based on experimental measurements done with the Universal Robots UR10e and on a simple mathematical model of an impact between a point on a robot and a point on a human body part, a feature vector is generated as an input to the boosted decision tree. After the training using Matlab’s Least-squares boosting algorithm, the boosted decision tree can predict the measured peak impact force with a relative error of less than 9% thus supporting the basic hypothesis. However, the predictions of the trained boosted decision tree are valid only for the case of a quasi-static impact in a vertical direction between a robot’s end-effector and a back of human’s non-dominant hand.

Keywords

Human-robot collaboration Safety Robotics Machine learning Boosted decision tree ISO/TS 15066 

References

  1. 1.
    Technical Specification: ISO/TS 15066:2016, Robots and robotic devices: collaborative robots. Technical report, The International Organization for Standardization (2016)Google Scholar
  2. 2.
    Ajoudani, A., Zanchettin, A.M., Ivaldi, S., Albu-Schäffer, A., Kosuge, K., Khatib, O.: Progress and prospects of the human-robot collaboration. Auton. Robots 42(5), 957–975 (2018)CrossRefGoogle Scholar
  3. 3.
    Echávarri, J., Ceccarelli, M., Carbone, G., Alén, C., Muñoz, J.L., Díaz, A., Munoz-Guijosa, J.M.: Towards a safety index for assessing head injury potential in service robotics. Adv. Robot. 27(11), 831–844 (2013)CrossRefGoogle Scholar
  4. 4.
    Forssell, U., Lindskog, P.: Combining semi-physical and neural network modeling: an example of its usefulness. IFAC Proc. Vol. 30(11), 767–770 (1997)CrossRefGoogle Scholar
  5. 5.
    Garofalo, G., Mansfeld, N., Jankowski, J., Ott, C.: Sliding mode momentum observers for estimation of external torques and joint acceleration. In: IEEE International Conference on Robotics and Automation (ICRA) (2019)Google Scholar
  6. 6.
    Géron, A.: Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems. O’Reilly Media, Sebastopol (2019)Google Scholar
  7. 7.
    Haddadin, S., Albu-Schäffer, A., Hirzinger, G.: Safety evaluation of physical human-robot interaction via crash-testing. In: Robotics: Science and Systems, vol. 3, pp. 217–224. Citeseer (2007)Google Scholar
  8. 8.
    Haddadin, S., De Luca, A., Albu-Schäffer, A.: Robot collisions: a survey on detection, isolation, and identification. IEEE Trans. Rob. 33(6), 1292–1312 (2017)CrossRefGoogle Scholar
  9. 9.
    Haddadin, S., Haddadin, S., Khoury, A., Rokahr, T., Parusel, S., Burgkart, R., Bicchi, A., Albu-Schäffer, A.: On making robots understand safety: embedding injury knowledge into control. Int. J. Robot. Res. 31(13), 1578–1602 (2012)CrossRefGoogle Scholar
  10. 10.
    Hoo, K.A., Sinzinger, E.D., Piovoso, M.J.: Improvements in the predictive capability of neural networks. J. Process Control 12(1), 193–202 (2002)CrossRefGoogle Scholar
  11. 11.
    Jia, X., Willard, J., Karpatne, A., Read, J., Zwart, J., Steinbach, M., Kumar, V.: Physics guided RNNs for modeling dynamical systems: a case study in simulating lake temperature profiles. In: Proceedings of the 2019 SIAM International Conference on Data Mining, pp. 558–566. SIAM (2019)Google Scholar
  12. 12.
    Karpatne, A., Atluri, G., Faghmous, J.H., Steinbach, M., Banerjee, A., Ganguly, A., Shekhar, S., Samatova, N., Kumar, V.: Theory-guided data science: a new paradigm for scientific discovery from data. IEEE Trans. Knowl. Data Eng. 29(10), 2318–2331 (2017)CrossRefGoogle Scholar
  13. 13.
    Karpatne, A., Watkins, W., Read, J., Kumar, V.: Physics-guided neural networks (PGNN): an application in lake temperature modeling. arXiv preprint arXiv:1710.11431 (2017)
  14. 14.
    Kovincic, N., Gattringer, H., Müller, A., Weyrer, M., Schlotzhauer, A., Kaiser, L., Brandstötter, M.: A model-based strategy for safety assessment of a robot arm interacting with humans. PAMM 19(1), e201900247 (2019)CrossRefGoogle Scholar
  15. 15.
    Mansfeld, N., Hamad, M., Becker, M., Marin, A.G., Haddadin, S.: Safety map: a unified representation for biomechanics impact data and robot instantaneous dynamic properties. IEEE Robot. Autom. Lett. 3(3), 1880–1887 (2018)CrossRefGoogle Scholar
  16. 16.
    Ren, H., Stewart, R., Song, J., Kuleshov, V., Ermon, S.: Learning with weak supervision from physics and data-driven constraints. AI Mag. 39(1), 27–38 (2018)CrossRefGoogle Scholar
  17. 17.
    Schlotzhauer, A., Kaiser, L., Wachter, J., Brandstotter, M., Hofbaur, M.: On the trustability of the safety measures of collaborative robots: 2D Collision-force-map of a sensitive manipulator for safe HRC. In: IEEE International Conference on Automation Science and Engineering (CASE) (2019)Google Scholar
  18. 18.
    Stewart, R., Ermon, S.: Label-free supervision of neural networks with physics and domain knowledge. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)Google Scholar

Copyright information

© The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Nemanja Kovincic
    • 1
  • Hubert Gattringer
    • 1
  • Andreas Müller
    • 1
    Email author
  • Mathias Brandstötter
    • 2
  1. 1.Institute for RoboticsJohannes Kepler UniversityLinzAustria
  2. 2.JOANNEUM RESEARCHKlagenfurtAustria

Personalised recommendations