B-Human 2017 – Team Tactics and Robot Skills in the Standard Platform League
The team B-Human won the main competition and, together with the team HULKs, the Mixed Team Competition in the RoboCup Standard Platform League 2017. In this paper, we argue that in the current state of the league, the development of sophisticated robot behaviors makes a difference between the top teams, while other abilities such as perception, modeling, and motion have been solved to a similar degree by the different top teams. We describe our general tactical approaches for the main competition as well as for the Mixed Team competition. In addition and as an example for a behavior-related robot skill, we present our approach to realtime path planning for humanoid robots with limited processing power.
- 2.LaValle, S.M.: Rapidly-exploring random trees: a new tool for path planning. Technical report TR 98–11, Computer Science Department, Iowa State University (1998)Google Scholar
- 3.Menashe, J., et al.: Fast and precise black and white ball detection for RoboCup soccer. In: RoboCup 2017: Robot World Cup XXI, Nagoya, Japan, July 2017Google Scholar
- 4.Müller, J., Laue, T., Röfer, T.: Kicking a ball – modeling complex dynamic motions for humanoid robots. In: Ruiz-del-Solar, J., Chown, E., Plöger, P.G. (eds.) RoboCup 2010. LNCS (LNAI), vol. 6556, pp. 109–120. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-20217-9_10CrossRefGoogle Scholar
- 5.Röfer, T.: CABSL – C-based agent behavior specification language. In: Akiyama et al. (eds.) RoboCup 2017. LNAI, vol. 11175, pp. 135–142. Springer, Cham (2018). http://www.informatik.uni-bremen.de/kogrob/papers/RC-Roefer-18.pdf
- 6.RoboCup Federation: Website RoboCup Standard Platform League (2017). http://spl.robocup.org
- 7.Röfer, T.: B-human team report and code release 2017 (2017). http://www.b-human.de/downloads/publications/2017/coderelease2017.pdf