Benchmarking robot cooperation without pre-coordination in the RoboCup Standard Platform League drop-in player competition

Abstract

Abstract-The Standard Platform League is one of the main competitions of the annual RoboCup world championships. In this competition, teams of five humanoid robots play soccer against each other. In 2014, the league added a new subcompetition which serves as a testbed for cooperation without pre-coordination: the Drop-in Player Competition. Instead of homogeneous robot teams that are each programmed by the same people and hence implicitly pre-coordinated, this competition features ad hoc teams, i. e. teams that consist of robots originating from different RoboCup teams and that are each running different software. In this paper, we provide an overview of this competition, including its motivation and rules. We then present and analyze the results of the 2014 competition, which gathered robots from 23 teams, involved at least 50 human participants, and consisted of fifteen 20-minute games for a total playing time of 300 minutes. We also suggest improvements for future iterations, many of which will be evaluated at RoboCup 2015.

Fear Learning for Flexible Decision Making in RoboCup: A Discussion

“…The drop-in competition, introduced in 2013 [5], encourages the creation of agents capable of coordinating and co-operating with other teammates in an ad-hoc manner. In this competition, robots of different RoboCup teams collaborate as a single team towards a common goal: win the match with the highest goal difference possible.…”

“…Doing so could mislead their robots towards engaging in a disadvantageous or non-intelligent behaviour, which would negatively affect their score in the competition. According to Genter et al [5], some RoboCup teams have developed strategies to determine the reliability of their teammates' messages and skills. Others, in turn, have solved the issue by simply not accepting any incoming messages, or even by not communicating at all with teammates.…”