Multiobjectivity and complexity in embodied cognition

We propose a novel perspective on the use of evolutionary multiobjective optimization (EMO) as a paradigm for evolving embodied organisms and as a framework for characterizing complexity. The paper demonstrates novel experiments that show the power of EMO in generating robots with different morpholo...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on evolutionary computation 2005-08, Vol.9 (4), p.337-360
Main Authors: Teo, J., Abbass, H.A.
Format: Article
Language:English
Subjects:
Applied sciences
Artificial intelligence
Artificial life
Cognition
Cognitive robotics
complexity
Computer science
control theory
systems
embodied cognition
evolutionary multiobjective optimization (EMO)
evolutionary robotics
Exact sciences and technology
Information technology
Intelligent agent
Intelligent robots
Learning and adaptive systems
Morphology
Organisms
Power generation
Citations: Items that this one cites
Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose a novel perspective on the use of evolutionary multiobjective optimization (EMO) as a paradigm for evolving embodied organisms and as a framework for characterizing complexity. The paper demonstrates novel experiments that show the power of EMO in generating robots with different morphologies, yet with very similar locomotion abilities. The proposed framework for comparing the complexity of an object across different complexity measures allowed meaningful and quantifiable comparisons between the evolved organisms. We show empirically that the partial order feature inherited in the Pareto concept exhibits characteristics which are suitable for comparing between the complexities of artificially evolved embodied organisms.
ISSN:1089-778X
1941-0026
DOI:10.1109/TEVC.2005.846902