Advertisement

An Open Source Vision Pipeline Approach for RoboCup Humanoid Soccer

  • Niklas FiedlerEmail author
  • Hendrik Brandt
  • Jan Gutsche
  • Florian Vahl
  • Jonas Hagge
  • Marc Bestmann
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11531)

Abstract

We are proposing an Open Source ROS vision pipeline for the RoboCup Soccer context. It is written in Python and offers sufficient precision while running with an adequate frame rate on the hardware of kid-sized humanoid robots to allow a fluent course of the game. Fully Convolutional Neural Networks (FCNNs) are used to detect balls while conventional methods are applied to detect robots, obstacles, goalposts, the field boundary, and field markings. The system is evaluated using an integrated evaluator and debug framework. Due to the usage of standardized ROS messages, it can be easily integrated into other teams’ code bases.

Keywords

RoboCup Open Source Computer vision 

Notes

Acknowledgments

Thanks to the RoboCup team Hamburg Bit-Bots, especially Timon Engelke and Daniel Speck, as well as Norman Hendrich. This research was partially funded by the German Research Foundation (DFG) and the National Science Foundation of China (NSFC) in project Crossmodal Learning, TRR-169. We are grateful to the NVIDIA corporation for supporting our research through the NVIDIA GPU Grant Program (https://developer.nvidia.com/academic_gpu_seeding). We used the donated NVIDIA Titan X (Pascal) to train our models.

References

  1. 1.
    Allali, J., Gondry, L., Hofer, L., Laborde-Zubieta, P., Ly, O., et al.: Rhoban football club - team description paper. Technical report, CNRS, LaBRI, University of Bordeaux and Bordeaux INP (2019)Google Scholar
  2. 2.
    Baltes, J., Missoura, M., Seifert, D., Sadeghnejad, S.: Robocup soccer humanoid league. Technical report (2013)Google Scholar
  3. 3.
    Barry, D., Curtis-Black, A., Keijsers, M., Munir, S., Young, M.: Electric sheep team description paper. Technical report, University of Canterbury, Christchurch, New Zealand (2019)Google Scholar
  4. 4.
    Bestmann, M., et al.: Hamburg bit-bots and wf wolves team description for RoboCup 2019 humanoid KidSize. Technical report, Universität Hamburg, Germany and Ostfalia University of Applied Sciences, Wolfenbüttel, Germany (2019)Google Scholar
  5. 5.
    Bestmann, M., Hendrich, N., Wasserfall, F.: ROS for humanoid soccer robots (2017)Google Scholar
  6. 6.
    van Dijk, S.G., Scheunemann, M.M.: Deep learning for semantic segmentation on minimal hardware. In: Holz, D., Genter, K., Saad, M., von Stryk, O. (eds.) RoboCup 2018. LNCS (LNAI), vol. 11374, pp. 349–361. Springer, Cham (2019).  https://doi.org/10.1007/978-3-030-27544-0_29CrossRefGoogle Scholar
  7. 7.
    Dorer, K., Hochberg, U., Ülker, M.W.: The sweaty 2019 RoboCup humanoid adultsize team description. Technical report, University of Applied Sciences Offenburg (2019)Google Scholar
  8. 8.
    Fan, W., et al.: Zjudancer team description paper. Technical report, State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China (2019)Google Scholar
  9. 9.
    Fiedler, N., Bestmann, M., Hendrich, N.: Image tagger: an open source online platform for collaborative image labeling. In: Holz, D., Genter, K., Saad, M., von Stryk, O. (eds.) RoboCup 2018. LNCS (LNAI), vol. 11374, pp. 162–169. Springer, Cham (2019).  https://doi.org/10.1007/978-3-030-27544-0_13CrossRefGoogle Scholar
  10. 10.
    Houliston, T., Chalup, S.K.: Visual mesh: real-time object detection using constant sample density. In: Holz, D., Genter, K., Saad, M., von Stryk, O. (eds.) RoboCup 2018. LNCS (LNAI), vol. 11374, pp. 45–56. Springer, Cham (2019).  https://doi.org/10.1007/978-3-030-27544-0_4CrossRefGoogle Scholar
  11. 11.
    Leiva, F., Cruz, N., Bugueño, I., Ruiz-del-Solar, J.: Playing soccer without colors in the SPL: a convolutional neural network approach. In: Holz, D., Genter, K., Saad, M., von Stryk, O. (eds.) RoboCup 2018. LNCS (LNAI), vol. 11374, pp. 122–134. Springer, Cham (2019).  https://doi.org/10.1007/978-3-030-27544-0_10CrossRefGoogle Scholar
  12. 12.
    Luna, J.P.V., Vázquez, S.G.R., Martinez, I.J.C.J., Ramírez, I.D.N.: Eaglebots.mx team description paper. Technical report, Highest Institute of Technology of Tepeaca (2019)Google Scholar
  13. 13.
    Mahmoudi, H., Fatehi, A., Gholami, A., et al.: MRL team description paper for humanoid KidSize league of RoboCup 2019. Technical report, Mechatronics Research Lab, Department of Computer and Electrical Engineering, Qazvin Islamic Azad University, Qazvin, Iran (2019)Google Scholar
  14. 14.
    Philipps, J., Rumpe, B.: Refinement of pipe-and-filter architectures. In: Wing, J.M., Woodcock, J., Davies, J. (eds.) FM 1999. LNCS, vol. 1708, pp. 96–115. Springer, Heidelberg (1999).  https://doi.org/10.1007/3-540-48119-2_8CrossRefGoogle Scholar
  15. 15.
    Quigley, M., Conley, K., Gerkey, B., Faust, J., Foote, T., Leibs, J., et al.: ROS: an open-source robot operating system. In: ICRA Workshop on Open Source Software, Kobe, Japan, vol. 3, p. 5 (2009)Google Scholar
  16. 16.
    Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)Google Scholar
  17. 17.
    RoboCup Technical Committee: RoboCup soccer humanoid league laws of the game 2018/2019. Technical report (2019)Google Scholar
  18. 18.
    Scheunemann, M.M., van Dijk, S.G., Miko, R., Barry, D., Evans, G.M., et al.: Bold hearts team description for RoboCup 2019 (humanoid kid size league). Technical report, School of Computer Science, University of Hertfordshire (2019)Google Scholar
  19. 19.
    Schnekenburger, F., Scharffenberg, M., Wülker, M., Hochberg, U., Dorer, K.: Detection and localization of features on a soccer field with feedforward fully convolutional neural networks (FCNN) for the adult-size humanoid robot sweaty. In: Proceedings of the 12th Workshop on Humanoid Soccer Robots, IEEE-RAS International Conference on Humanoid Robots, Birmingham (2017)Google Scholar
  20. 20.
    Speck, D., Bestmann, M., Barros, P.: Towards real-time ball localization using CNNs. In: Holz, D., Genter, K., Saad, M., von Stryk, O. (eds.) RoboCup 2018. LNCS (LNAI), vol. 11374, pp. 337–348. Springer, Cham (2019).  https://doi.org/10.1007/978-3-030-27544-0_28CrossRefGoogle Scholar
  21. 21.
    Tan, P.N.: Introduction to Data Mining. Pearson Education India, Bengaluru (2006)Google Scholar
  22. 22.
    Tully Foote, R.B.R.: ROS Wiki: nodelet. https://wiki.ros.org/nodelet. Accessed 28 Mar 2019

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Niklas Fiedler
    • 1
    Email author
  • Hendrik Brandt
    • 1
  • Jan Gutsche
    • 1
  • Florian Vahl
    • 1
  • Jonas Hagge
    • 1
  • Marc Bestmann
    • 1
  1. 1.Hamburg Bit-Bots, Department of InformaticsUniversity of HamburgHamburgGermany

Personalised recommendations