Abstract
This paper presents a novel perspective to the use of multi-objective optimization and in particular evolutionary multi-objective optimization (EMO) as a measure of complexity. We show that the partial order feature that is being inherited in the Pareto concept exhibits characteristics which are suitable for studying and measuring the complexities of embodied organisms. We also show that multi-objectivity provides a suitable methodology for investigating complexity in artificially evolved creatures. Moreover, we present a first attempt at quantifying the morphological complexity of quadruped and hexapod robots as well as their locomotion behaviors.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Hussein A. Abbass. The self-adaptive pareto differential evolution algorithm. In Proceedings of the 2002 Congress on Evolutionary Computation (CEC2002), volume 1, pages 831–836. IEEE Press, Piscataway, NJ, 2002.
Josh C. Bongard. Evolving modular genetic regulatory networks. In Proceedings of the 2002 Congress on Evolutionary Computation (CEC2002), pages 1872–1877. IEEE Press, Piscataway, NJ, 2002.
Rodney A. Brooks. Intelligence without reason. In L. Steels and R. Brooks (Eds), The Artificial Life Route to Artificial Intelligence: Building Embodied, Situated Agents, pages 25–81. Lawrence Erlbaum Assoc. Publishers, Hillsdale, NJ, 1995.
Critical Mass Labs. Vortex [online]. http://www.cm-labs.com [cited — 25/1/2002].
Kalyanmoy Deb. Multi-objective Optimization using Evolutionary Algorithms. John Wiley & Sons, Chicester, UK, 2001.
Claus Emmeche. Garden in the Machine. Princeton University Press, Princeton, NJ, 1994.
David P. Feldman and James P. Crutchfield. Measures of statistical complexity: Why? Physics Letters A, 238:244–252, 1998.
Dario Floreano and Joseba Urzelai. Evolutionary robotics: The next generation. In T. Gomi, editor, Proceedings of Evolutionary Robotics III, pages 231–266. AAI Books, Ontario, 2000.
Simon Haykin. Neural networks — a comprehensive foundation. Prentice Hall, USA, 2 edition, 1999.
Gregory S. Hornby and Jordan B. Pollack. Body-brain coevolution using L-systems as a generative encoding. In L. Spector et al. (Eds), Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2001), pages 868–875. Morgan Kaufmann, San Francisco, 2001.
Andrei N. Kolmogorov. Three approaches to the quantitative definition of information. Problems of Information Transmission, 1:1–7, 1965.
Hod Lipson and Jordan B. Pollack. Automatic design and manufacture of robotic lifeforms. Nature, 406:974–978, 2000.
Henrik H. Lund and John Hallam. Evolving sufficient robot controllers. In Proceedings of the 4th IEEE International Conference on Evolutionary Computation, pages 495–499. IEEE Press, Piscataway, NJ, 1997.
Rolf Pfeifer and Christian Scheier. Understanding Intelligence. MIT Press, Cambridge, MA, 1999.
Jordan B. Pollack, Hod Lipson, Sevan G. Ficici, Pablo Funes, and Gregory S. Hornby. Evolutionary techniques in physical robotics. In Peter J. Bentley and David W. Corne (Eds), Creative Evolutionary Systems, chapter 21, pages 511–523. Morgan Kaufmann Publishers, San Francisco, 2002.
Cosma R. Shalizi. Causal Architecture, Complexity and Self-Organization in Time Series and Cellular Automata. Unpublished PhD thesis, University of Wisconsin at Madison, Wisconsin, 2001.
Claude E. Shannon. A mathematical theory of communication. The Bell System Technical Journal, 27(3):379–423, 1948.
Karl Sims. Evolving 3D morphology and behavior by competition. In R. Brooks and P. Maes (Eds), Artificial Life IV: Proceedings of the Fourth International Workshop on the Synthesis and Simulation of Living Systems, pages 28–39. MIT Press, Cambridge, MA, 1994.
Russell K. Standish. On complexity and emergence [online]. Complexity International, 9, 2001.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Teo, J., Nguyen, M.H., Abbass, H.A. (2003). Multi-objectivity as a Tool for Constructing Hierarchical Complexity. In: Cantú-Paz, E., et al. Genetic and Evolutionary Computation — GECCO 2003. GECCO 2003. Lecture Notes in Computer Science, vol 2723. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45105-6_60
Download citation
DOI: https://doi.org/10.1007/3-540-45105-6_60
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40602-0
Online ISBN: 978-3-540-45105-1
eBook Packages: Springer Book Archive