Performance analysis in soccer: a Cartesian coordinates based approach using RoboCup data

Abreu, Pedro Henriques; Moura, José J. G.; Silva, Daniel Castro; Reis, Luís Paulo; Garganta, Júlio

doi:10.1007/s00500-011-0733-0

Cited by 18 publications

(13 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Simulation: It consists of developing a tool that automatically calculates the final game statistics through a log file selection as described in [2]. It is important to note that, for this approach, all log files of the 2D simulation league between 2006 and 2009 were used.…”

Section: Project Architecture Detailsmentioning

confidence: 99%

Using model-based collaborative filtering techniques to recommend the expected best strategy to defeat a simulated soccer opponent

Abreu

Silva

Portela

et al. 2014

IDA

Self Cite

View full text Add to dashboard Cite

How to improve the performance of a simulated soccer team using final game statistics? This is the question this research aims to answer using model-based collaborative techniques and a robotic team -FC Portugal -as a case study. After developing a framework capable of automatically calculating the final game statistics through the RoboCup log files, a feature selection algorithm was used to select the variables that most influence the final game result. In the next stage, given the statistics of the current game, we rank the strategies that obtained the maximum average of goal difference in similar past games. This is done by splitting offline past games into different k-clusters. Then, for each cluster, the expected best strategy was assigned. The online phase consists in the selection of the expected best strategy for the cluster in which the current game best fits. Regarding the final results, our approach proved that it is possible to improve the performance of a robotic team by more than 35%, even in a competitive environment such as the RoboCup 2D simulation league. 974 P.H. Abreu et al. / Model-based CF techniques to recommend the best strategy in simulated soccerDespite the difference in competitiveness among soccer teams developed for the 2D simulation league compared to the human soccer teams, the importance of preparing a simulated soccer team for the next opponent occupies a similar role in achieving a game victory. Normally, as part of the preparation for a match, a soccer coach tries to adapt his strategy in order to increase the possibility of defeating the opponent. In consequence of that, in this research, we have used data from the RoboCup Soccer group, more precisely the log files produced in the 2009 2D simulation league. In this league two teams of eleven virtual agents try to attain the best possible final result, which means scoring more goals than their opponent. In each game the agents need to connect to a soccer server, which is responsible for supporting the entire competition (simulating the match between the virtual teams) and, at the end, generating a log file. This file contains information relating to 1 :

show abstract

Section: Project Architecture Detailsmentioning

confidence: 99%

Using model-based collaborative filtering techniques to recommend the expected best strategy to defeat a simulated soccer opponent

Abreu

Silva

Portela

et al. 2014

IDA

Self Cite

View full text Add to dashboard Cite

show abstract

“…A criação de u ma interface natural para permit ir u m jogo mais fácil [27][28][29] e a utilização de metodologias de aprendizage m [30][31][32][33] para a criação de perfis do utilizador [34][35] são também melhorias possíveis. Outras melhorias futuras seriam a ap licação de metodologias de desenvolvimento de software educativo [36][37][38] A curto prazo pretende-se a exploração da cooperação entre os jogadores que sejam v izinhos no FarmVille, desenvolvendo um sistema mu ltiagente em que exista cooperação entre os vários agentes do tipo Farm para se atingir objet ivos comuns.…”

Section: Conclusões E Trabalho Futurounclassified

Sistema Inteligente para Auxílio na Seleção e Execução de Tarefas num Jogo Social

Reis

Neves²,

Abreu³

et al. 2012

COMPUTER

View full text Add to dashboard Cite

Nowadays social networks are used for various recreational purposes. It is believed that every day a user spend, on average, two hours playing this type of networkgames. Farmville is a social game availab le at one of the most successful social networks: Facebook.Farmv ille game allows each user to use a diverse set of actions in order to manage a virtual farm. However, this management quickly becomes a boring and time consuming process and often the user quitsplaying this game. In this context this project main objective was related with the development of an intelligent system able to effect ively assist the player when playing Farmv ille. The system will help the user in most of his management tasks on the farm such as seeding and harvesting, receiv ing and sending gifts and managing the farm animals. The use of the implemented system ensures greater progress in the game, because there is a decrease in the time spent in performing the tasks enabling the user to focus on the strategies for advancingin the game. Keywords Social Networks, Social Games, Farmv ille, Intelligent Systems IntroduçãoA Rede Social Facebook tem sido desde o seu lançamento um dos sites mais visitados do mundo. Em 2011 foi o líder mundial de sites visitados com cerca de 880 milhões de utilizadores ativos e 1 bilião de páginas visitadas [1]. Os jogos são aplicativos muito usados no Facebook, sendo frequentemente usados pelos utilizadores como forma de entretenimento e de interação com outros utilizadores. O FarmVille consiste num jogo de gestão de uma quinta virtual onde cada utilizador de forma cooperativa, ou não, pode realizar u m conjunto diversificado de tarefas que lhe permit irão progredir no jogo. Este tem regras mu ito simples, é de fácil aprendizagem e as suas actividades básicas são o preparo da terra, a p lantação de sementes, a colheita de diversos produtos, a criação de animais e a co lheita dos frutos de vários tipos de árvores. Co m vista à evolução no jogo, o utilizador interage com o amb iente através de cliques do rato. Contudo, estas ações tornam-se rapidamente fastidiosas e cansativas. Um exemp lo desta problemát ica éum jogador que possui na sua quinta um número elevado de O FarmVille exige mu ita d isponibilidade por ser u m jogo que se desenrola em tempo real, e muita responsabilidade no cumprimento dos horários das colheitas dos produtos. O não cumprimento destes horários leva à perda dos produtos plantados e do dinheiro investido na sua plantação, prejudicando assim o avanço do jogo.No FarmVille existem várias tarefas, várias sementes que podem ser plantadas, vários tipos de árvores e animais, cada um deles com custos de aquisição e lucro diferentes. Alguns itens são mais rentáveis e/ou fornecem mais pontos de experiência do que outros, e contribuem de forma diferente para o avanço do jogo. Portanto, o estudo de estratégias de jogo que facilitem o avanço no jogo é importante para os jogadores do FarmVille.Neste trabalho foi criado um sistema mu lti agente que permit indo ao utilizador a utilização de dife...

show abstract

“…Ponnuthurai N. Suganthan is an associate professor at the school of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798, email: epnsugan@ntu.edu.sg R. G. Reynolds is a professor at the Computer Science Department, Wayne State University, MI, 48202, USA, e-mail: reynolds@cs.wayne.edu handling, shoot and interception) [6]- [10] when competing in simulated soccer as an important application for evolving group behaviors between agents and coordinating their movement through the problem-solving process.…”

Section: Introductionmentioning

confidence: 99%

“…Robocup [6]- [10] is the leading competition in this field as an international robotics competition to promote robotics and AI research. This international competition has many types of leagues; Humanoid, Standard size, Middle size, small size, and simulation league (2D, 3D).…”

Section: Introductionmentioning

confidence: 99%

Cultural Algorithms applied to the evolution of robotic soccer team tactics: A novel perspective

Ali

Morghem

Albadarneh

et al. 2014

2014 IEEE Congress on Evolutionary Computation (CEC)

View full text Add to dashboard Cite

Cultural Algorithms have been previously employed to model the emergence of cooperative behaviors of agents in different multi-agent systems. In this paper, a simplified and adaptive version will be used as the basis to generate cooperative behaviors within a team of soccer players using different team formations and effective plays. This system can be used as a tutorial for the application of Cultural Algorithms for the coordination of groups of agents in complex multi-agent dynamic environments. Simplified Cultural Algorithms were successful in effectively learning different types of plays, including active and passive protagonists, within a small number of generations. Successful learning includes the coordination of adjustments of the team members to develop the most suitable team formations for every scenario. Experimental results enable us to conclude that Cultural Algorithms, when configured properly, in order to produce significant results, can perform very competitively when compared to other types of learning strategies and case-based game plays.

show abstract

Performance analysis in soccer: a Cartesian coordinates based approach using RoboCup data

Cited by 18 publications

References 27 publications

Using model-based collaborative filtering techniques to recommend the expected best strategy to defeat a simulated soccer opponent

Using model-based collaborative filtering techniques to recommend the expected best strategy to defeat a simulated soccer opponent

Sistema Inteligente para Auxílio na Seleção e Execução de Tarefas num Jogo Social

Cultural Algorithms applied to the evolution of robotic soccer team tactics: A novel perspective

Contact Info

Product

Resources

About