Author, Subjects, Keywords

Cited Author

 
 
   » By Author or Editor
 » Browse Author by Alphabet
 » By Journal
 » By Subjects
 » Malaysian Journals
 » By Type
 » By Year
 » By Latest Additions
 
 
   » By Author
 » Top 20 Authors
 » Top 20 Article
 » Top Journal Cited
 » Top Article Cited
 » Journal Citation Statistics
 » Usage Since Sept 2007


 
 
 

Login | Create Account

Evolutionary Multi-Objective Optimization for Automatic Synthesis of Artificial Neural Network Robot Controllers

Teo, Jason (2005) Evolutionary Multi-Objective Optimization for Automatic Synthesis of Artificial Neural Network Robot Controllers. Malaysian Journal of Computer Science, 18 (2). pp. 54-62. ISSN 0127-9084

Full text not available from this repository.

Official URL: http://mjcs.fsktm.um.edu.my/detail.asp?AID=341

Affiliations

Universiti Malaysia Sabah

Abstract

This paper investigates the use of a multi-objective approach for evolving artificial neural networks that act as controllers for the legged locomotion of a quadrupedal robot simulated in a 3-dimensional, physics-based environment. The Pareto-frontier Differential Evolution (PDE) algorithm is used to generate a Pareto optimal set of artificial neural networks that optimize the conflicting objectives of maximizing locomotion behavior and minimizing neural network complexity. In this study, insights are provided on how the controller generates the emergent walking behavior in the creature by analyzing the evolved artificial neural networks in operation. A comparison between Pareto optimal controllers showed that ANNs with varying numbers of hidden units resulted in noticeably different locomotion behaviors. It was also found that a much higher level of sensory-motor coordination was present in the best evolved controller

Item Type:Journal
Keywords:Evolutionary robotics, evolutionary multi-objective optimization, embodied cognition, evolutionary artificial neural networks, artificial life
Subjects:Q Science
ID Code:377

H.A. Abbass. “A memetic Pareto evolutionary approach to artificial neural networks” in 14th International Joint Conference on Artificial Intelligence (LNAI-2256), 2001, 1–12, Berlin, Springer-Verlag.

H.A. Abbass. “An evolutionary artificial neural network approach for breast cancer diagnosis”. Artificial Intelligence in Medicine, Vol. 25, No. 3, 2002, 265–281.

H.A. Abbass, R. Sarker & C. Newton. “PDE: A Pareto-frontier differential evolution approach for multiobjective optimization problems” in Congress on Evolutionary Computation, 2001, 971–978, Piscataway, IEEE Press.

J.C. Bongard & R. Pfeifer. “A method for isolating morphological effects on evolved behavior” in 7th International Conference on the Simulation of Adaptive Behavior, 305–311, 2002, Cambridge, MIT Press.

CM Labs. “Vortex” [online]. http://www.cm-labs.com [cited - 5 September 2004].

P. Eggenberger. “Evolving morphologies of simulated 3D organisms based on differential gene expression” in 4th European Conference on Artificial Life, 205–213, 1997, Cambridge, MIT Press.

D. Floreano & J. Urzelai, J. “Evolutionary robotics: The next generation” in Proceedings of Evolutionary Robotics III, 231–266, 2000, Ontario, AAI Books.

G.S. Hornby & J.B. Pollack. “Body-brain coevolution using L-systems as a generative encoding” in Genetic and Evolutionary Computation Conference, 868–875, 2001, San Francisco, Morgan Kauffman.

A.J. Ijspeert. “A 3-D biomechanical model of the salamander” in 2nd International Conference on Virtual Worlds, 225–234, 2000, Berlin, Springer.

M. Komosinski & A. Rotaru-Varga. “Comparison of different genotype encodings for simulated threedimensional agents”. Artificial Life, Vol. 7, No. 4, 2001, 395–418.

W.P. Lee, J. Hallam & H.H. Lund. “A hybrid GP/GA approach for co-evolving controllers and robot bodies to achieve fitness-specific tasks” in 3rd IEEE International Conference on Evolutionary Computation, 384– 389, 1997, Piscataway, IEEE Press.

L. Lichtensteiger & P. Eggenberger. “Evolving the morphology of a compound eye on a robot” in 3rd European Workshop on Advanced Mobile Robots, 127–134, 1999, Piscataway, IEEE Press.

H. Lipson & J.B. Pollack. “Automatic design and manufacture of robotic lifeforms”. Nature, Vol. 406, 2000, 974–978.

S. Nolfi & D. Floreano. “Synthesis of autonomous robots through evolution”. Trends in Cognitive Science, Vol. 6, No. 1, 2002, 31–36.

C. Paul & J.C. Bongard. “The road less travelled: Morphology in the optimization of biped robot locomotion” in IEEE/RSJ International Conference on Intelligent Robots and Systems, 226–232, 2001, Piscataway, IEEE Press.

R. Storn & K. Price. “Differential evolution: A simple and efficient adaptive scheme for global optimization over continuous spaces”. Technical Report TR-95-012, 1995, International Computer Science Institute, Berkeley.

T. Taylor & C. Massey. “Recent developments in the evolution of morphologies and controllers for physically simulated creatures”. Artificial Life, Vol. 7, No. 1, 2001, 77–87.

X. Yao. “Evolving artificial neural networks”. Proceedings of the IEEE, Vol. 87, No. 9, 1999, 1426–1447.

Repository Staff Only: item control page
 
 
 
 
 
 
© Copyright 2007 MyAIS Faculty of Computer Science and Information Technology, University of Malaya – All Rights Reserved. Malaysian Abstracting and Indexing System is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.