Arquitectura Basada en Roles Aplicada en Equipos de Fútbol de Robots con Control Centralizado

José G. Guarnizo, Martín Mellado

Resumen

El fútbol de robots ofrece un entorno adecuado para el diseño y la validación de arquitecturas de sistemas multi-robot. Al clasificar las ligas de fútbol de robots existentes se encuentran ligas con arquitecturas centralizadas que poseen percepción global del entorno y donde los robots son controlados desde un ordenador a través de un único sistema de toma de decisiones. En este artículo se presenta una arquitectura basada en roles para equipos de fútbol de robots con percepción global y control centralizado. En esta arquitectura un rol es seleccionado para cada jugador por medio de una función. A partir de este rol y de las condiciones de juego presentes se selecciona un comportamiento que el jugador deberá ejecutar. La función que es utilizada para la asignación de roles es activada cuando el balón cambia de cuadrante en el campo de juego. La estrategia presentada es comparada en simulación realizando partidos contra un equipo que posee una estrategia de roles constantes y un equipo con una estrategia jerárquica basada en selección de tácticas y posteriormente asignación de roles a partir de la táctica seleccionada. Los resultados mostraron no solo un mejor rendimiento del equipo con la estrategia basada en roles, sino también uniformidad en los comportamientos realizados por los jugadores del equipo durante las transiciones de roles y comportamientos.

Palabras clave

Agentes; toma de decisiones; robots móviles autónomos; control centralizado; arquitecturas

Texto completo:

PDF

Referencias

Abeyruwan, S., Seekircher, A., Visser, U., 2012. Dynamic Roles Assigment Using General Value Functions. 7th Workshop on Humanoid Soccer Robots, IEEE-RAS International Conference on Humanoid Robots. Osaka.

Abreu, P.H., Castro, D., Almeida, F., Mendes-Moreira, J., 2014. Improving a Simulated Soccer Team`s Performance Through a Memory-Based Collaborative Filtering Approach. Applied Soft Computing, 23, 180-193. DOI: 10.1016/j.asoc.2014.06.021

Acosta Calderon, C. A., Mohan, R. E., Zhou, C., 2010. Distributed Architecture for Dynamic Role Behaviour in Humanoid Soccer Robots. En: V. Papi, Robot Soccer. Intech, pp. 121-138. DOI: 10.5772/7344

Agüero, C. E., Matellán, V., Cañas, J. M., Gómez, V. M., 2006. SWITCH! Dynamic roles exchange among cooperative robots. Second International Workshop on Multi-Agent Robotic Systems (MARS 2006). Setúbal.

Arias, M., Ramirez, J., 2008. Team Agent Behavior Architecture in Robot Soccer. Robotic Symp., 2008. LARS`2008. IEEE Latin American, 20-25.

Atkinson, J., Rojas, D., 2009. On-the-fly generation of multi-ropbot team formation strategies based in game conditions. Expert Systems with Applications, 3(2), 6082-6090. DOI: 10.1016/j.eswa.2008.07.039

Baldoni, M., Boella, G., Dorni, N., Mugnaini, A., Grenna, R., 2008. Organizations and roles as primitives in the JADE framework. Workshop on Objects and Agents. 89-92.

Bayindir, L., 2016. A review of swarm robotics tasks. Neurocomputing, 172, 292-231. DOI: 10.1016/j.neucom.2015.05.116.

Bravo, C., Aguilar-Castro, J., Ríos, A., Aguilar-Martin, J., Rivas, F., 2011. Arquitectura Basada en Inteligencia Artificial Distribuida para la Gerencia Integrada de Producción Industrial. Revista Iberoamericana de Automática e Informática Industrial RIAI, 8(4), 405-417. DOI: 10.1007/978-3-662-43645-5_2

Campbell, A., Wu, A. S., 2011. Multi-agent rolle allocation: issues, approaches and multiple perspective. Autonomous Agents and Multi-Agent Systems, 22(2), 317-355. DOI: 10.1007/s10458-010-9127-4

Chen, B., Zhang, A., Cao, L., 2014. Autonomous intelligent decision-making system based on Bayesian SOM neural network for robot soccer. Neurocomputing, 128, 447-458. DOI:10.1016/j.neucom.2013.08.021

Cravo, J., Almeida, F., Abreu, P. H., Reis, L.P., Lau, N., Mota, L., 2014. Strategy planner: Graphical definition of soccer set-plays. Data & Knowledge Engineering, 9, 110-131. DOI:10.1016/j.datak.2014.10.001

Cardoso, P., Molina, L., Freire, E.O., Carvalho, E.A.N., 2012,. A Methodology to Designing Strategies for Robot Soccer Based on Discrete Event Systems Fornalism. Robotics Symposium and Latin American Robotics Symposium (SBR-LARS), 2012 Brazilian. 143-149.

El Barachi, M., Rabah, S., Kara, N., Dssouli, R., Paquet, J., 2013,. A MultiService Multi-role Integrated Information Model for Dynamic Resource Discovery in Virtual Networks. Wireless Communications and Networking Conference (WCNC), 2013 IEEE. 4777-4782.

Esquivel-Flores, O., Benítez-Pérez, H., 2012. Reconfiguración Dinámica de Sistemas Distribuidos en Tiempo-Real Basada en Agentes. Revista Iberoamericana de Automática e Informática Industrial RIAI, 9(3), 300- 313. DOI:10.1016/j.riai.2012.05.014

Fernandes, M., Bianchi, R.A.C., Heuristically-Acelerated Reinforcement Learning: A Comparative Analysis of Performance. 14th Annual Conference, TAROS 2013, Oxford, UK, August 28--30, 2013. 15-27.

Fira. May. 2015. Fira SimuroSot League. http://www.fira.net/contents/sub03/sub03_7.asp

Garcia, P., Balmaceda, J. M., Schiaffino, S., Amandi, A., 2013. Automatic Detection of Team Roles in Computer Supported Collaborative Work. IEEE Latin America Transactions, 11(4), 1066-1074. DOI: 10.1109/TLA.2013.6601751.

Guarnizo, J.G., Mellado, M., Low, C., Blanes, F., 2015. Architecting centralized coordination of soccer robots based on principle solution. Advanced Robotics, 29(5), 989-1004. DOI:10.1080/01691864.2015.1017534

Hernández, L., Balandrón, C., Aguiar, J.M., Carro, B., Sánchez-Esguevillas, A., Llorent, J., Chinaro, D., Gomez-Sanz, J.J., Cook, D., 2013. A MultiAgent System Architecture for Smart Grid Management and Forecasting of Energy Demand in Virtual Power Plants. IEEE Communications Magazine, 51(1), 106-113. DOI: 10.1109/MCOM.2013.6400446

Hilaire, V., Lauri, F., Gruer, P., Koukam, A., Rodriguez, S., 2008. An Adaptative Agent Architecture for Holonic Multi-Agent Systems. ACM Transactions on Autonomous and Adaptive Systems, 3(1), 1-24. DOI: 10.1145/1342171.1342173

Hwang, K.S., Tan, S.W., Chen, Y.J., Lee. C.H., 2007. Reinforcement Learning in Strategy Selection for a Coordinated Multirobot System. Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on, 37(6), 1151-1157. DOI: 10.1109/TSMCA.2007.904823

Hwang, K.S., Jiang, W.C., Yu, H.S., Lin. S.Y., 2011. Cooperative Reinforcement Learning Based on Zero-Sum Games. En: Mobile Robots – Control Architectures, Bio-Interfacing, Navigation, Multi Robot Motion Planning and Operator. Intech, pp. 289-308. DOI: 10.5772/26620

Hwang, K.S., Tan, S.W., Chen, C.C., 2014. Cooperative strategy based on adaptive Q-learning for robot soccer systems. Fuzzy Systems, IEEE Transactions on, 12(4), 569-576. DOI: 10.1109/TFUZZ.2004.832523

Jolly, K., Sreerama Kumar, R., Vijayakumar, R., 2010. Intelligent task planning and action selection of a mobile robot in a multi-agent system through a fuzzy neural network approach. Engineering Applications of Artificial Intelligence, 23(6), 923-933. DOI:10.1016/j.engappai.2010.04.001

Kendall, E.A., 2000. Role modeling for agent systems analysis, design and implementation. Concurrency, IEEE, 8(2), 34-41. DOI:10.1016/j.simpat.2007.02.002

Kim, J.H., Shim, H.S.; Kim, H.S.; Jung, M.J.; Choi, I.H.; Kim, J.O., 1997. A cooperative multi-agent system and its real time application to robot soccer. Robotics and Automation, 1997. Proceedings. 1997 IEEE International Conference on, (1), 20-25.

Klanþar, G., Zupanþiþ, B., Karba, R., 2007. Modelling and simulation of a group of mobile robots. Simulation Modelling Practice and Theory, 15(6), 647-658. DOI: 10.1109/4434.846192

Kontes, G., Lagoudakis, M., 2007. Coordinated Team Play in the FourLegged RoboCup League. Tools with Artificial Intelligence, 2007. ICTAI 2007. 19th IEEE International Conference on. 109-116.

Lau, N., Lopes, L. S., Corrente, G., Filipe, N., 2009. Multi-robot team coordination through roles, positionings and coordinated procedures. Intelligent Robots and Systems, 2009. IROS 2009. 5841-5848.

Lauer, M., Hafner, R., Lange, S., Riedmiller, M., 2010. Cognitive Concepts in Autonomous Soccer Playing Robots. Cognitive Systems Research, 11(3), 287-309. DOI: 10.1016/j.cogsys.2009.12.003

Lou, Y., Chen, B., Shi, H., 2012. Decision making model based on state assessment and hierarchical FSM in robot soccer. Automatic Control and Artificial Intelligence (ACAI 2012), International Conference on. 756-759. DOI:10.1049/cp.2012.1087

McMillen, C., Veloso, M., 2006. Distributed, Play-Based Role Assignment for Robot Teams in Dynamic Environments. Distributed Autonomous Robotic Systems 7. Ed. Springer, pp. 145–154. DOI: 10.1007/4-431-35881-7

Palamar, P. F., Ziparo, V., Locchi, L., Nardi, D., Lima, P., 2009. Teamwork Design Based on Petri Net Plans. RoboCup 2008: Robot Soccer World Cup XII. 200-211.

Riley, P., Veloso, M., 2002. Recognizing Probabilistic Opponent Movement Models. RoboCup 2001: Robot Soccer World Cup V. 453-458.

Shi, H., Xu, L., Zhang, L., Pan, W., Xu, G., 2015. Research on self-adaptive decision-making mechanism for competition strategies in robot soccer. Frontiers of Computer Science, 9(3), 485-494. DOI: 10.1007/s11704-014-4210-7

Stone, P., Veloso, M., 1999. Task decomposition, dynamic role assignment, and low-bandwidth communication for real-time strategic teamwork. Journal of Artificial Intelligence, 110, 241-273.

Stulp, F., Utz, H., Isik, M., Mayer, G., 2010. Implicit Coordination with Shared Belief: A Heterogeneous Robot Soccer Team Case Study. Advanced Robotics, 24(7), 1017–1036. DOI: 10.1163/016918610X496964

Testart, J., Ruiz del Solar, J., Schulz, R., Guerrero, P., Palma-Amestoy, R., 2011. A Real-Time Hybrid Architecture for Biped Humanoids with Active Vision Mechanisms. Journal of Intelligent and Robotic Systems, 63(2), 233-255. DOI: 10.1007/s10846-010-9515-7

Wang, J., Wang, T., Wang, X., Meng, X., 2009,. Multi-robot decision making based on coordination graphs. Mechatronics and Automation, 2009. ICMA 2009. International Conference on. 2393-2398.

Wu, C.-J., Lee, T.-L., 2004. A Fuzzy Mechanism for Action Selection of Soccer Robots. Journal of Intelligent & Robotic Systems, 39(1), 57-70. DOI: 10.1023/B:JINT.0000010795.04819.90

Wu, J., Snášel, V., Ochodková, E., Martinoviþ, J., SvatoĖ, V., Abraham, A., 2013. Analysis of strategy in robot soccer game. Neurocomputing, 109, 66-75. DOI:10.1016/j.neucom.2012.03.021

Yang, M., Jia, Y., 2012, Action Utility Prediction and Role Task Allocation in Robot Soccer System. Control Automation Robotics & Vision (ICARCV), 2012 12th International Conference on. 112-117.

Yu, W.Y., Soo, V.W., Tsai, M.S., 2015. Power distribution system service restoration bases on a committee-based intelligent agent architecture. Engineering Applications of Artificial Intelligence, 41, 92-102.

Zhou, L., Varadharajan, V, Hitchens, M., 2015. Trust Enhanced Cryptographic Role-Based Access Control for Secure Cloud data Storage. Information Forensics and Security, IEEE Transactions on. 10(11), 2381- 2395. DOI: 10.1109/TIFS.2015.2455952

Zhu, H., 2006. A role-Based Architecture for intelligent Agent Systems. Distributed Intelligent Systems: Collective Intelligence and Its Applications, 2006. DIS 2006. IEEE Workshop on, 354-362.

Abstract Views

520
Metrics Loading ...

Metrics powered by PLOS ALM




Creative Commons License

Esta revista se publica bajo una Licencia Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)

Universitat Politècnica de València     https://doi.org/10.4995/riai

e-ISSN: 1697-7920     ISSN: 1697-7912