2007 | OriginalPaper | Chapter
Incremental Evolution of Stigmergy-Based Multi Robot Controllers Through Utility Functions
Authors : P. Caamaño, J. A. Becerra, R. J. Duro, F. Bellas
Published in: Knowledge-Based Intelligent Information and Engineering Systems
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
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.