Ant Intelligence in Robotic Soccer

Abstract

Robotic Soccer is a multi-agent test bed, which requires the designer to address most of the issues of multi-agent research. Social insect behaviors observed in nature when adopted to solve problems they are giving promissing results. The domains like computers, electronics, electrical, mechanical etc., are inspired in adopting these behaviors. This paper addresses the ant intelligence in robotic soccer to evolve the best team of players. The simulation team evolved (PUTeam) was tested with teams of soccerbots in teambots (a simulation tool for Robotic Soccer) and the experimental results clearly shows the performance of the evolved team against the opponent teams are more effective.

Formations of Robotic Swarm: An Artificial Force Based Approach

“…With recent advances in communication, networking and computing, multi-agent systems have generated a renewed interest among researchers across the world (Chaimowicz, Michael et al 2005;Chao-xia, Bing-rong et al 2007;De Gennaro, Iannelli et al 2005;Desai, Ostrowski et al 1998;Gazi and Passino 2002;Kwok, Ha et al 2007;Ramani, Viswanath et al 2008;Suzuki and Yamashita 1999;Xin and Yangmin 2008). Although swarm or multiagent dynamic system concept, in general, is used in several disciplines, this work considers a multi-agent system as a collection of loosely coupled dynamic units moving in 2 or 3 dimensional space.…”

“…Many researchers studied group behavior of animals such as organization of work in ant colonies (Gordon 2003), social foraging models in fish (Hamilton and Dill 2003), navigation and signaling methods used by ants (Robinson, Jackson et al 2005) and shoaling behavior of fish (Brown and Warburton 1999) with respect to performing an escape mechanism. Mathematical models for the group behavior developed by Inada in (Inada 2001) and algorithms governing schooling behavior of fish presented by Grunbaum et al (Grünbaum 2004) etc, have inspired the robotics researchers into more refined approaches in swarming techniques (Krieger, Billeter et al 2000;Kwok, Ha et al 2007;Ramani, Viswanath et al 2008). Aggregation and formation are among the most important behaviors exhibited by biological swarms which enable them to protect against natural threats, strengthen them with sensing capabilities to locate food, resources, escape routes, etc (Brown and Warburton 1999).…”

Formations of Robotic Swarm: An Artificial Force Based Approach

“…With recent advances in communication, networking and computing, multi-agent systems have generated a renewed interest among researchers across the world (Chaimowicz, Michael et al 2005;Chao-xia, Bing-rong et al 2007;De Gennaro, Iannelli et al 2005;Desai, Ostrowski et al 1998;Gazi & Passino 2002;Kwok, Ha et al 2007;Ramani, Viswanath et al 2008;Suzuki & Yamashita 1999;Xin & Yangmin 2008). Although swarm or multi-agent dynamic system concept, in general, is used in several disciplines, this work considers a multi-agent system as a collection of loosely coupled dynamic units moving in 2 or 3 dimensional space.…”

“…Many researchers studied group behavior of animals such as organization of work in ant colonies (Gordon 2003), social foraging models in fish (Hamilton & Dill 2003), navigation and signaling methods used by ants (Robinson, Jackson et al 2005) and shoaling behavior of fish (Brown & Warburton 1999) with respect to performing an escape mechanism. Mathematical models for the group behavior developed by Inada in (Inada 2001) and algorithms governing schooling behavior of fish presented by Grunbaum et al (Grünbaum 2004) etc, have inspired the robotics researchers into more refined approaches in swarming techniques (Krieger, Billeter et al 2000;Kwok, Ha et al 2007;Ramani, Viswanath et al 2008). Aggregation and formation are among the most important behaviors exhibited by biological swarms which enable them to protect against natural threats, strengthen them with sensing capabilities to locate food, resources, escape routes, etc (Brown & Warburton 1999).…”

Arquitecturas Centralizadas de Coordinación. Extrapolación del Fútbol de Robots al Control de Modo de Operaciones de Micro-Redes

“…La selección de comportamientos es realizada por Máquinas de Estado Finito basadas en sistemas de inferencia difusos. En [85] utilizan algoritmos evolutivos Ant Intelligence para la asignación de posiciones a los jugadores para equipos de la RoboCup 2D Simulation League, otros conceptos de coordinación no son trabajados. Una arquitectura de equipo para la Standard Platform League utilizando robots AIBO es presentada en [86], basado en las experiencias de un entrenador humano se diseña una Red Neuronal para la selección de roles dependiendo de las actuales condiciones de juego como posiciones de los jugadores y el balón, y el historial de las distintas acciones seleccionadas a lo largo del juego.…”