WrightEagle and UT Austin Villa: RoboCup 2011 Simulation League Champions

Abstract

The RoboCup simulation league is traditionally the league with the largest number of teams participating, both at the international competitions and worldwide. 2011 was no exception, with a total of 39 teams entering the 2D and 3D simulation competitions. This paper presents the champions of the competitions, WrightEagle from the University of Science and Technology of China in the 2D competition, and UT Austin Villa from the University of Texas at Austin in the 3D competition.

RoboCup 2D Soccer Simulation League: Evaluation Challenges

“…Tracing such advances is especially important because different champion teams usually employ different approaches, often achieving a high degree of specialisation in a sub-field of AI, for example, automated hierarchical planning developed by WrightEagle [23,24,26,21,28], opponent modelling studied by HELIOS [27], and human-based evolutionary computation adopted by Gliders [11,12]. Many more research areas are likely to contribute towards improving the League, and several general research directions are recognised as particularly promising: nature-inspired collective intelligence [29,30,31], embodied intelligence [32,33,34,35], information theory of distributed cognitive systems [36,37,38,39,40,41], guided self-organisation [42,43,44], and deep learning [45,46,47].…”

“…In order to trace the progress of the League over time it is interesting to compare performance of several previous champions, directly competing against each other in a round-robin tournament. For example, we evaluated relative performance of six champions of RoboCup-2011 to RoboCup-2016: WrightEagle (WE2011 [22,23], WE2013 [24,25], WE2014 [26], WE2015 [21]), HELIOS2012 [27] and Gliders2016 [11,12]. The round-robin results over 1000 games, presented in Table 4, confirmed the progress of the League over the last six years, with the resultant ranking r l completely concurring with the chronological ranking r t , i.e., d 1 (r l , r t ) = 0.…”

Keyframe Sampling, Optimization, and Behavior Integration: Towards Long-Distance Kicking in the RoboCup 3D Simulation League

“…In recent years, the RoboCup 3D Simulation League has been won primarily by creating fast and robust walks ( [5], [6]). However, teams are now developing their own kicks ( [7], [8], [9]).…”

RoboCup Simulation Leagues: Enabling Replicable and Robust Investigation of Complex Robotic Systems

“…The RoboCup simulation league consists of both 2D and 3D competitions, which exhibit many similarities [10]: -The world model, including player and ball dynamics and kinematics, are simulated by a central soccer server [6]. -Participants develop a team of fully autonomous agents, each of which interacts with the soccer server:…”

“…-Turn body or neck by a specified angle -Dash forward or backward with a specified "power" -Slide tackle in a specified direction -Kick the ball in a specified direction with a specified angle, if near -Catch the ball if near (goalkeeper only) -Communicate with other players, either "verbally" or by "pointing" at a specified position Each team consists of 11 players and a "coach", which is a non-playing agent responsible for the allocation of players to each position given a number of randomly generated physical profiles (including characteristics such as speed and stamina). The 2D simulation league does model the dynamics or kinematics of any given human or robot; instead, it encourages development of complex player behaviours and team strategies [7,8,10]. It is also a powerful framework for evaluating the emergent downstream effects (e.g.…”