Robust Tracking of Multiple Soccer Robots Using Random Finite Sets

  • Pablo CanoEmail author
  • Javier Ruiz-del-Solar
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9776)


Having a good estimation of the robot-players positions is becoming imperative to accomplish high level tasks in any RoboCup League. Classical approaches use a vector representation of the robot positions and Bayesian filters to propagate them over time. However, these approaches have data association problems in real game situations. In order to tackle this issue, this paper presents a new method for building robot maps using Random Finite Sets (RFS). The method is applied to the problem of estimating the position of the teammates and opponents in the SPL league. Considering the computational capabilities of Nao robots, the GM-PHD implementation of RFS is used. In this implementation, the estimations of the robot positions and the robot observations are represented using Mixture of Gaussians, but instead of associating a robot or an observation to a given Gaussian, the weight of each Gaussian maintains an estimation of the number of robots that it represents. The proposed method is validated in several real game situations and compared with a classical EKF based approach. The proposed GM-PHD method shows a much better performance, being able to deal with most of the data association problems, even being able to manage complex situations such as robot kidnappings.


World modeling Multi-target tracking Robot position estimation Random Finite Sets 



The authors thank Constanza Villegas for her contributions to the development of this publication and the UChile Robotics Team for their general support. We also thank the B-Human SPL Team for sharing their code release, contributing the development of the Standard Platform League. This work was partially funded by FONDECYT Project 1161500.


  1. 1.
    Mendoza, J.P., Biswas, J., Cooksey, P., Wang, R., Klee, S., Zhu, D., Veloso, M.: Selectively reactive coordination for a team of robot soccer champions. In: Proceedings of AAAI-2016 (2016)Google Scholar
  2. 2.
    Trevizan, F.W.F., Veloso, M.M.M.: Learning opponent’s strategies in the RoboCup small size league. In: Proceedings of AAMAS 2010 Workshop on Agents in Real-Time and Dynamic Environments, pp. 45–52, Toronto (2010)Google Scholar
  3. 3.
    Yasui, K., Kobayashi, K., Murakami, K., Naruse, T.: Analyzing and learning an opponent’s strategies in the RoboCup small size league. In: Behnke, S., Veloso, M., Visser, A., Xiong, R. (eds.) RoboCup 2013. LNCS, vol. 8371, pp. 159–170. Springer, Heidelberg (2014). doi: 10.1007/978-3-662-44468-9_15CrossRefGoogle Scholar
  4. 4.
    Laue, T., Röfer, T.: Integrating simple unreliable perceptions for accurate robot modeling in the four-legged league. In: Lakemeyer, G., Sklar, E., Sorrenti, D.G., Takahashi, T. (eds.) RoboCup 2006. LNCS, vol. 4434, pp. 474–482. Springer, Heidelberg (2007). doi: 10.1007/978-3-540-74024-7_48CrossRefGoogle Scholar
  5. 5.
    Fabisch, A., Laue, T., Röfer, T.: Robot recognition and modeling in the RoboCup standard platform league. In: Pagello, E., Zhou, C., Behnke, S., Menegatti, E., Röfer, T., Stone, P. (eds.) Proceedings of the Fifth Workshop on Humanoid Soccer Robots in Conjunction with the 2010 IEEE-RAS International Conference on Humanoid Robots, pp. 65–70, Nashville, TN, USA (2010)Google Scholar
  6. 6.
    Goodman, I.R., Mahler, R.P.S., Nguyen, H.T.: Mathematics of Data Fusion. Springer, Dordrecht (1997). doi: 10.1007/978-94-015-8929-1CrossRefzbMATHGoogle Scholar
  7. 7.
    Mahler, R.P.S.: A theoretical foundation for the stein-winter “probability hypothesis density (PHD)” multitarget tracking approach. In: Sensor and Data Fusion (2000)Google Scholar
  8. 8.
    Mahler, R.: A brief survey of advances in random-set fusion. In: 2015 International Conference on Control, Automation and Information Sciences (ICCAIS), pp. 62–67. IEEE (2015)Google Scholar
  9. 9.
    Mahler, R.P.S.: Statistical Multisource-Multitarget Information Fusion. Artech House, Inc., Norwood (2007)zbMATHGoogle Scholar
  10. 10.
    Mahler, R.P.S.: Multitarget Bayes filtering via first-order multitarget moments. IEEE Trans. Aerosp. Electron. Syst. 39, 1152–1178 (2003)CrossRefGoogle Scholar
  11. 11.
    Vo, B.N., Singh, S., Doucet, A.: Sequential Monte Carlo methods for multi-target filtering with random finite sets. In: IEEE Transactions on Aerospace and Electronic Systems, pp. 1224–1245 (2005)Google Scholar
  12. 12.
    Vo, B.-N., Ma, W.-K.: The Gaussian mixture probability hypothesis density filter. IEEE Trans. Signal Process. 54, 4091–4104 (2006)CrossRefGoogle Scholar
  13. 13.
    Mullane, J.S., Vo, B.-N., Adams, M.D., Vo, B.-T.: Random Finite Sets for Robot Mapping & SLAM - New Concepts in Autonomous Robotic Map Representations. Springer, Heidelberg (2011). doi: 10.1007/978-3-642-21390-8CrossRefzbMATHGoogle Scholar
  14. 14.
    Thomas, R., Laue, T., Judith, M., Bartsch, M., Batram, M.J., Arne, B., Martin, B., Kroker, M., Maaß, F., Thomas, M., Steinbeck, M., Stolpmann, A., Taddiken, S.: Team Report and Code Release 2013, pp. 1–194 (2014)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Department of Electrical Engineering, Advanced Mining Technology CenterUniversidad de ChileSantiagoChile

Personalised recommendations