Publication:
Generalization capabilities of co-evolution in learning robot behavior

Thumbnail Image
Identifiers
URI: https://hdl.handle.net/10016/5829
ISSN: 0741-2223
DOI: 10.1002/rob.10054
UXXI: AR/0000004509
Files
generalization_isasi_JRS_2002_ps.pdf (696.07 KB)
Publication date
2002-09-18
Defense date
Authors
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Wiley-Blackwell
Impact
Google Scholar
Export
Research Projects
Organizational Units
Journal Issue
Abstract
In this article, a co-evolutive method is used to evolve neural controllers for general obstacle-avoidance of a Braitenberg vehicle. During a first evolutionary process, Evolution Strategies were applied to generate neural controllers; the generality of the obtained behaviors was quite poor. During a second evolutionary process, a new co-evolutive method, called Uniform Co-evolution, is introduced to co-evolve both the controllers and the environment. A comparison of both methods shows that the co-evolutive approach improves the generality of controllers.
Description
Keywords
Bibliographic citation
Journal of Robotic Systems, 2002, vol. 19, n. 10, p. 455-467
Collections
DI - GCERN - Artículos de revistas científicas