Saltar apartados
  • UA
  • i3a
  • TIN2009-10581 Adaptation and self-assembling morphological swarm intelligent systems (AAMORE)

TIN2009-10581 Adaptation and self-assembling morphological swarm intelligent systems (AAMORE)

[TIN2009-10581] Adaptation and self-assembling morphological swarm intelligent systems (AAMORE)

 

Summary

This project represents a substantial contribution to the State of the art current systems of swarm providing an extensive analysis on the link between microscopic and macroscopic behavior and morphology of agents in a robotic swarm. This project will advance from multiple perspectives.

On the one hand an oriented model of intelligent agents will bring to formalize systems Robotics swarming, totally focused on its fundamental features: the large number of agents, the existence of few homogeneous groups of robots, the definition of simple agents (relatively incapable or inefficient), local perception of the agents, the ability of local communication between agents, the robustness of the system the flexibility in their configuration or the same scalability. Most of the current research focus in the development of behaviours for a given hardware platform or on the contrary in the development of a unique morphology on which will be investigated tasks and behaviors to study. On the other hand, this project focuses on the study of the morphology of an individual agent and affects how this morphology to the individual agent behaviors and the global behavior of the swarm to a given task.

In addition, using this model of agents, swarm robot Simulator and physical robots requested in the project, will take place several experiments that establishing different swarm behaviors aimed at the detection of leaks, tasks of rescue, signage of agents or mapped in inaccessible environments, such as caves or grottos. It is essential to analyze these different behaviors, both microscopic how macroscopic and social, evaluating them from the point of view of the morphology of the agents and self-Assembly of these capabilities.

The benefits of the study of behaviour from the point of view of morphology are obvious, since they will allow the scientific community to establish a mechanism allowing to quantitatively assess morphology more suitable for certain behavior, and can therefore determine which capabilities are interested in highlight an agent depending on their tasks and problems to solve. Therefore, arises as a priority objective, the achievement by evolutionary computation, intelligent and technical agents of Bayesian inference, of a system capable of evaluating the goodness of a particular morphology taking into account the development of behaviors, both as a macroscopic and social microcopicos for these agents.

Industrial Computing and Artificial Intelligence (i3a)


Universidad de Alicante
Dpto.Ciencia de la Computación e Inteligencia Artificial
Grupo Informática Industrial e Inteligencia Artificial

Carretera San Vicente s/n
03690 San Vicente del Raspeig
Alicante (Spain)

Tel: (+34) 96 590 3400

Fax: (+34) 96 590 3464

For further information: informacio@ua.es, and for enquiries on this web server: webmaster@ua.es

Carretera San Vicente del Raspeig s/n - 03690 San Vicente del Raspeig - Alicante - Tel. 96 590 3400 - Fax 96 590 3464