Software Verification of Redundancy in Neuro-Evolutionary Robotics
Evolutionary methods are now commonly used to automatically generate autonomous controllers for physical robots as well as for virtually embodied organisms. Although it is generally accepted that some amount of redundancy may result from using an evolutionary approach, few studies have focused on empirically testing the actual amount of redundancy that is present in controllers generated using artificial evolutionary systems. Network redundancy in certain application domains such as defence, space, and safeguarding, is unacceptable as it puts the reliability of the system at great risk. Thus, our aim in this paper is to test and compare the redundancies of artificial neural network (ANN) controllers that are evolved for a quadrupedal robot using four different evolutionary methodologies. Our results showed that the least amount of redundancy was generated using a self-adaptive Pareto evolutionary multi-objective optimization (EMO) algorithm compared to the more commonly used single-objective evolutionary algorithm (EA) and weighted sum EMO algorithm. Finally, self-adaptation was found to be highly beneficial in reducing redundancy when compared against a hand-tuned Pareto EMO algorithm.
Unable to display preview. Download preview PDF.
- 1.Abbass, H.A.: Speeding up back-propagation using multiobjective evolutionary algorithms. Neural Computation (2003) (to appear)Google Scholar
- 2.Bongard, J.C., Pfeifer, R.: A method for isolating morphological effects on evolved behavior. In: 7th International Conference on the Simulation of Adaptive Behavior, pp. 305–311. MIT Press, Cambridge (2002)Google Scholar
- 3.CM Labs. Vortex (2002), [online] http://www.cm-labs.com
- 4.Floreano, D., Urzelai, J.: Evolution and learning in autonomous mobile robots. In: Bio-Inspired Computing Machines, PPEUR, Lausanne, Switzerland, pp. 317–364 (1998)Google Scholar
- 5.Floreano, D., Urzelai, J.: Evolutionary robotics: The next generation. In: 7th International Symposium on Evolutionary Robotics, AAI Books, Ontario, pp. 231–266. (2000)Google Scholar
- 8.Husbands, P., Harvey, I., Jakobi, N., Thompson, A., Cliff, D.: Evolutionary robotics. In: Handbook of Evolutionary Computation, pp. 1–11. IOP Publishing, Bristol (1997)Google Scholar
- 12.Nolfi, S., Floreano, D.: Evolutionary Robotics. MIT Press, Cambridge (2000)Google Scholar
- 15.Teo, J., Abbass, H.A.: Coordination and synchronization of locomotion in a virtual robot. In: 9th International Conference on Neural Information Processing, Singapore, vol. 4, pp. 1931–1935 (2002)Google Scholar
- 16.Teo, J., Nguyen, M.H., Abbass, H.A.: Multi-objectivity as a tool for constructing hierarchical complexity. In: Cantú-Paz, E., Foster, J.A., Deb, K., Davis, L., Roy, R., O’Reilly, U.-M., Beyer, H.-G., Kendall, G., Wilson, S.W., Harman, M., Wegener, J., Dasgupta, D., Potter, M.A., Schultz, A., Dowsland, K.A., Jonoska, N., Miller, J., Standish, R.K. (eds.) GECCO 2003. LNCS, vol. 2723, pp. 483–494. Springer, Heidelberg (2003)CrossRefGoogle Scholar