Incremental Evolution of Stigmergy-Based Multi Robot Controllers Through Utility Functions

Authors:
P. Caamaño;J. A. Becerra;R. J. Duro;F. Bellas
Affiliations:
Integrated Group for Engineering Research, Universidade da Coruña, Spain;Integrated Group for Engineering Research, Universidade da Coruña, Spain;Integrated Group for Engineering Research, Universidade da Coruña, Spain;Integrated Group for Engineering Research, Universidade da Coruña, Spain
Venue:
KES '07 Knowledge-Based Intelligent Information and Engineering Systems and the XVII Italian Workshop on Neural Networks on Proceedings of the 11th International Conference
Year:
2007

Citing 6
Cited 1

Towards collaborative and adversarial learning:: a case study in robotic soccer

International Journal of Human-Computer Studies - Evolution and learning in multiagent systems
An Behavior-based Robotics

An Behavior-based Robotics
Artificial Life: An Overview

Artificial Life: An Overview
Emergence of Cooperation: State of the Art

Artificial Life
Swarm Robotics: SAB 2004 International Workshop, Santa Monica, CA, USA, July 17, 2004, Revised Selected Papers (Lecture Notes in Computer Science)

Swarm Robotics: SAB 2004 International Workshop, Santa Monica, CA, USA, July 17, 2004, Revised Selected Papers (Lecture Notes in Computer Science)
Directed stigmergy-based control for multi-robot systems

Proceedings of the ACM/IEEE international conference on Human-robot interaction

On the potential contributions of hybrid intelligent approaches to Multicomponent Robotic System development

Information Sciences: an International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper deals with the problem of jointly designing the behaviors of a group of robots so as to produce a particular desired collaborative behavior in stigmergy-based settings. In this line, the approach followed has its roots on traditional evolutionary behavior based robotics techniques, but instead of trying to evolve the whole controller for a particular complex behavior in one step, an incremental approach is used by combining the results from different evolutionary/learning processes in different settings for the construction of a complete controller architecture. The key aspects when trying to generalize the process of obtaining the controllers from single robots to multi robot systems are discussed in the framework of a set of simple collaborative tasks, focusing the discussion on the utility functions that guide the evolution.