Especificando Comportamentos para Futebol de Robôs da Abordagem DDM
Abstract
Robot soccer is often used as a test bed for Multi-Agent Systems (MAS). In a soccer team, each player is an agent, and his actions should be coordinated with other agents to reach a goal. In this context, coordinated plans, called Setplays, are used to simulate and plan real game situations. Tools for defining Setplays usually have a limited set of behaviors available for use, e.g. kicking, and new behaviors have to be hand-coded. This work proposes a solution to support the implementation of behaviors for simulation and execution of cooperative MASs, in the context of robot soccer. The solution uses Model Driven Development (MDD), which allows the definition of behaviors at a high abstraction level and subsequent (semi) automatic transformation into source code for specific tools. Experiments with robot soccer teams demonstrated the viability of the solution in defining behaviors and generating source code for the FCPortugal Framework and SPlanner tools used by several robot soccer teams.
References
Brambilla, M., Cabot, J., and Wimmer, M. (2012). Model-driven software engineering in practice.
Cravo, J., Almeida, F., Abreu, P. H., Reis, L. P., Lau, N., and Mota, L. (2014). Strategy planner: Graphical definition of soccer set-plays. Data & Knowledge Engineering, 94:110–131.
Cravo, J. G. B. (2011). Splanner uma aplicação gráfica de definição flexível de jogadas estudadas no robocup. Master degree dessertation in Informatics and Computing Engineering. [link]. Acesso em: 15 de novembro de 2021.
Hogg, T. and Sretavan, D. W. (2005). Controlling tiny multi-scale robots for nerve repair.
INFORMATIK (2011). Simrobot. [link] Accessed 15 November 2022.
Jung, C. et al. (2019). Computação embarcada: Projeto e implementação de veículos autônomos inteligentes.
Konolige, K. and Nilsson, N. J. (1980). Multiple-agent planning systems. In Proceedings of the First AAAI Conference on Artificial Intelligence, AAAI’80, page 138–142. AAAI Press.
Magalhães Mascarenhas, A., Maciel, R., and Andrade, A. (2015). Towards a metamodel design methodology: Experiences from a model transformation metamodel design. International Conference on Software Engineering and Knowledge Engineering.
Marques, F. T. (2010). Generic coordination methodologies applied to the robocup simulation leagues. Master degree dessertation in Informatics and Computing Engineering. [link]. Accessed 15 November 2022.
Meessen, K. (2011). Turtle simulator. [link] Acesso em: 15 dez. 2021.
Mota, L. et al. (2015). Collaborative behavior in soccer: The setplay free software framework. Lecture Notes in Computer Science, 8992:709–716.
OMG (2008). Mof model to text transformation language, v1.0. Object Management Group. [link]. Accessed 24 October 2022.
Paraschos, A., Spanoudakis, N. I., and Lagoudakis, M. G. (2012). Model-driven behavior specification for robotic teams. In Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems Volume 1, AAMAS ’12, page 171–178, Richland, SC. International Foundation for Autonomous Agents and Multiagent Systems.
Pessin, G. et al. (2007). Simulação virtual de agentes autônomos para a identificação e controle de incêndios em reservas naturais.
Reis, L. P. et al. (2010). Playmaker: Graphical definition of formations and setplays. In 5th Iberian Conference on Information Systems and Technologies, pages 1–6. [link].
Robocup. Objective. [link]. Accessed 23 October 2022.
Russell, S. J. and Norvig, P. (2020). Artificial Intelligence: A Modern Approach (4th Edition). Pearson, Berkeley.
Solingen, R., Basili, V., and Caldiera, G.and Rombach, H. (2002). Goal Question Metric (GQM) Approach. John Wiley & Sons, Hoboken.
