Selectively Reactive Coordination for a Team of Robot Soccer Champions

Abstract

CMDragons 2015 is the champion of the RoboCup Small Size League of autonomous robot soccer. The team won all of its six games, scoring a total of 48 goals and conceding 0. This unprecedented dominant performance is the result of various features, but we particularly credit our novel offense multi-robot coordination. This paper thus presents our Selectively Reactive Coordination (SRC) algorithm, consisting of two layers: A coordinated opponent-agnostic layer enables the team to create its own plans, setting the pace of the game in offense. An individual opponent-reactive action selection layer enables the robots to maintain reactivity to different opponents. We demonstrate the effectiveness of our coordination through results from RoboCup 2015, and through controlled experiments using a physics-based simulator and an automated referee.

Online Learning of Robot Soccer Free Kick Plans Using a Bandit Approach

“…In fact, during RoboCup 2015, our team did perform such adaptation during real games, and it won the SSL tournament. However, it is very difficult to accurately evaluate the amount of credit that the online learning of free kicks deserves in that victory due to (i) lack of ground truth, (ii) small number of games, and (iii) the large proportion of the games that does not involve free kicks, such as offense coordination during regular gameplay (Mendoza et al 2016a). Thus, we instead present a controlled experimental evaluation of our algorithm.…”