Event-based automated refereeing for robot soccer
The RoboCup Small Size League (SSL) is a robot soccer game with robots that play on a customized field with overhead cameras. The majority of the research effort to date has been on the performance of the autonomous teams in aspects of motion planning and team strategy. However, another critical component of a robot game is the referee. In current SSL games, refereeing is done by humans, who use a “referee box” that passes their calls to the robots. In this work, we contribute an automated referee (autoref) for SSL games, towards enabling games to proceed with little or no human supervision. The goal is to move closer to the eventual full automation of complete games with real robots. The technical challenges include the clear definition of the rules of the game in terms of features to be extracted from the visual perception, temporal sequencing, and corresponding calls and game management. We provide a description of a game of SSL as it is relevant to an autoref, by categorizing the rules of the game and presenting the structure of a game as a hybrid automaton. We then describe the complete autoref using a modular event-based architecture, following up on the automaton as a guideline, to keep track of the state of a game and issue referee commands accordingly. We present the results of using our autoref to referee games on real robots, as well as a comparison of the events detected by the autoref to the calls made by a human referee during the real SSL games at RoboCup 2014.
KeywordsRoboCup SSL Hybrid automata Event detection Game formalization
- Alur, R., Courcoubetis, C., Henzinger, T. A., & Ho, P. H. (1993). Hybrid automata: An algorithmic approach to the specification and verification of hybrid systems. In R. L. Grossman, A. Nerode, A. P. Ravn, & H. Rischel (Eds.), Hybrid systems, Lecture notes in computer science (pp. 209–229). Berlin: Springer.Google Scholar
- Arenas, M., Ruiz-del Solar, J., Norambuena, S., & Cubillos, S. (2009). A robot referee for robot soccer. In L. Iocchi, H. Matsubara, A. Weitzenfeld, & C. Zhou (Eds.), RoboCup 2008: Robot Soccer 10 1371 World Cup XII (pp. 426–438). Berlin: Springer.Google Scholar
- Bruce, J., & Veloso, M. (2003). Fast and accurate vision-based pattern detection and identification. In Proceedings of the 2003 IEEE international conference on robotics and automation (Vol 1, pp. 1277–1282). IEEE.Google Scholar
- Bruce, J., Balch, T., & Veloso, M. (2000). Fast and inexpensive color image segmentation for interactive robots. In Proceedings of the 2000 IEEE/RSJ conference on intelligent robots and systems (pp. 2061–2066). IEEE/RSJ.Google Scholar
- Chen, M., Dorer, K., Foroughi, E., Heintz, F., Huang, Z., Kapetanakis, S., Kostiadis, K., Kummenje, J., Murray, J., Noda, I., Obst, O., Riley, P., Steffens, T., Wang, Y., & Yin, X. (2003). RoboCup soccer server users manual. http://sourceforge.net/projects/sserver/files/rcssmanual/9-20030211/.
- Egerstedt, M. (2000). Behavior based robotics using hybrid automata. In N. Lynch & B. Krogh (Eds.), Hybrid systems: Computation and control. Lecture notes in computer science (Vol. 1790, pp. 103–116). Berlin: Springer.Google Scholar
- Fierro, R., Das, A.K., Kumar, V., & Ostrowski, J.P. (2001). Hybrid control of formations of robots. In Proceedings of the IEEE international conference on robotics and automation (Vol 1, pp. 157–162), IEEE.Google Scholar
- Käppeler, U.P., Zweigle, O., Häußermann, K., Rajaie, H., Tamke, A., Koch, A., Eckstein, B., Aichele, F., DiMarco, D., Berthelot, A., Walter, T., & Levi, P. (2010). RFC Stuttgart team description 2010. ftp://ftp.informatik.uni-stuttgart.de/pub/library/ncstrl.ustuttgart_fi/INPROC-2010-97/INPROC-2010-97.pdf.
- Klavins, E., & Koditschek, D.E. (2000). A formalism for the composition of concurrent robot behaviors. In Proceedings of the IEEE international conference on robotics and automation (Vol 4, pp. 3395–3402). IEEE.Google Scholar
- Mosterman, P. J. (1999). An overview of hybrid simulation phenomena and their support by simulation packages. In Hybrid systems: Computation and control (pp. 165–177). Berlin: SpringerGoogle Scholar
- Niemüller, T., Lakemeyer, G., Ferrein, A., Reuter, S., Ewert, D., Jeschke, S., Pensky, D., & Karras, U. (2013). RoboCup Logistics League sponored by Festo: A competitive factory automation testbed. In Proceedings of the 16th international conference on advanced robotics—1st workshop on developments in RoboCup leagues.Google Scholar
- Schoenmakers, F., Koudijs, G., Martinez, C.L., Briegel, M., van Wesel, H., Groenen, J., Hendriks, O., Klooster, O., Soetens, R., & van de Molengraft, M. (2013). Tech United Eindhoven team description 2013: Middle size league. http://www.techunited.nl/media/files/TDP2013.pdf.
- SSL Technical Committee (2015). Laws of the RoboCup Small Size League 2015. http://wiki.robocup.org/wiki/File:Small_Size_League_-_Rules_2015.pdf.
- Tanaka, K., Nakashima, H., Noda, I., Hasida, K., Frank, I., & Matsubara, H. (1998). MIKE: An automatic commentary system for soccer. In Proceedings of the international conference on multi agent systems (pp. 285–292), IEEE.Google Scholar
- Vail, D., Veloso, M., & Lafferty, J. (2007). Conditional random fields for activity recognition. In Proceedings of the 6th international joint conference on autonomous agents and multiagent systems (p. 235). ACM.Google Scholar
- Veloso, M., Biswas, J., Cooksey, P., Klee, S., Mendoza, J.P., Wang, R., & Zhu, D. (2015). CMDragons 2015 extended team description. http://robocup2015.oss-cn-shenzhen.aliyuncs.com/TeamDescriptionPapers/SmallSize/RoboCup_Symposium_2015_submission_81.pdf.
- Voelz, D., André, E., Herzog, G., & Rist, T. (1999). Rocco: A RoboCup soccer commentator system. In M. Asada, & H. Kitano (Eds.), RoboCup-98: Robot SoccerWorld 12 Cup II (pp. 50–60). Berlin: Springer.Google Scholar
- Zhu, D., Biswas, J., & Veloso, M. (2015). AutoRef: Towards real-robot soccer complete automated refereeing. In R. A. C. Bianchi, H. L. Akin, S. Ramamoorthy, K. Sugiura (Eds.), RoboCup 2014: Robot World Cup XVIII (pp. 419–430), Berlin: Springer.Google Scholar
- Zickler, S. (2010). Physics-based robot motion planning in dynamic multi-body environments. PhD thesis, Carnegie Mellon University, Thesis Number: CMU-CS-10-115.Google Scholar
- Zickler, S., Laue, T., Birbach, O., Wongphati, M., & Veloso, M. (2009). SSL-Vision: The shared vision system for the RoboCup Small Size League. In J. Baltes, M. G. Lagoudakis, T. Naruse, S. S. Ghidary (Eds.), RoboCup 2009: Robot Soccer World Cup XII (pp. 425–436). Berlin: Springer.Google Scholar