Soccer 2D Simulation

This study analysed the influence of field dimension and players’ skill level on collective tactical behaviours during small- sided and conditioned games (SSCGs). Positioning and displacement data were collected using global positioning systems (15 Hz) during SSCGs (Gk+4 v. 4+Gk) played by two groups of participants (NLP- national-level and RLP-regional-level players) on different field dimensions (small: 36.8 × 23.8 m; intermediate: 47.3 × 30.6 and large: 57.8 × 37.4 m). Team tactical performance was assessed through established dynamic team variables (effective playing space, playing length per width ratio and team separateness) and nonlinear signal processing techniques (sample entropy of distances to nearest opponents and the teams’ centroids’ mutual information). Results showed that the effective playing space and team separateness increased significantly with pitch size regardless of participant skill level (P < 0.001, η2 = 0.78 and P < 0.001, η2 = 0.65, respectively). Playing length per width ratio increased with pitch size for the NLP but was maintained at a relatively constant level by RLP across treatments indicating different playing shapes. There was significantly more irregularity in distances to nearest opponents for the NLP in small (P = 0.003) and intermediate fields (P = 0.01). Findings suggest that tactical behaviours in SSCGs are constrained by field size and skill level, which need to be considered by coaches when designing training practices.

RoboCup is an international research aimed at improving artificial intelligence and robotics. It is a standard issue to get a wide range of technologies together and obtain new achievements. In 2D simulation league, after each game, server saves a log that contains all information about the game. By using data mining techniques knowledge can be discovered from this massive data. In this research we aimed to extract ball and player positions from log files and pre-process this data to specify some information including the action that have been taken place, start point, and involving players, etc. We mined this data to predict own and opponent action using C4.5 algorithm. The result showed that after applying our method the goal scoring was increased 251.39% with 64.13% confidence interval (with alpha = 0.1).

This article presents the UaiSoccer2D team, a simulation
team of robots soccer simulated at UFSJ - Federal University of São João del-Rei, MG, Brazil. Will be present a modeling strategy for use of reinforcement learning algorithm Q-learning.

This paper describes a research about fuzzy controllers for the positioning of the goalkeeper without the ball in the 2d simulated robot soccer. The goal of this research was to improve the behavior of the goalkeeper, raising the number of catches and decreasing the number of goals, improving its positioning to catch the ball. To validate the research, 30 matches were simulated against some of the best teams of the world that participate of the RoboCup. The achieved results are presented, the conclusions are discussed and future works are suggested.

Este artigo apresenta os resultados iniciais do grupo de pesquisa Bahia Robotics Team. Neste trabalho, controladores fuzzy são usados para melhorar algumas habilidades dos jogadores. Para os atacantes, o chute e o posicionamento foram aperfeiçoados. Os meiocampistas tiveram seu posicinamento e tomada de decisões abordados. Goleiro e defensores tiveram o posicionamento tratado. O passe de bola melhorou para todos os jogadores. O time gerado Bahia2D foi testado em partidas contra algumas equipes vitoriosas no Ropocup Brasil Open 2006 e em edições anteriores da competição mundial da Robocup. Apresenta também os resultados positivos obtidos até o momento, bem como os trabalhos em andamento para solucionar problemas que ainda são encontrados.

Dribbling an opponent player in digital soccer environment is an important practical problem in motion planning. It has special complexities, which can be generalized to the most important problems in other similar multi-agent systems. In this paper, we propose a hybrid computational geometry and evolutionary computation approach for generating motion trajectories to avoid a mobile obstacle. In this case, an opponent agent is not only an obstacle but also one who tries to harden the dribbling procedure. One characteristic of this approach is reducing the process cost of online stage by transferring it to an offline stage, which causes increment in agents’ performance. This approach breaks the problem into two offline and online stages. During the offline stage the goal is to find the desired trajectory using evolutionary computation and saving it as a trajectory plan. A trajectory plan consists of nodes, which approximate information of each trajectory plan. In the online stage a linear interpolation along with Delaunay Triangulation in a xy-plan is applied to the trajectory plan to retrieve the desired action.