Modifying Neuro Evolution For Mobile Robotic Behavior Development

Sekou Remy, Ashraf Saad

2005

Abstract

This work examines the effect of two modifications of typical approaches to evolving neuro controllers for robotic behaviors. First evolutionary methods were constrained to modify only one element of the population, the only element to be evaluated in the robot. Secondly the algorithm was allowed to incorporate genotypes provided by external sources. These modifications were evaluated through the use of a mobile robot simulator. Each was allowed to evolve in an arena that allowed it to interact with other robots. Experiments were conducted to investigate the effect of sharing genotypes and their corresponding fitness among homogeneous robots - the robots differed only in the initial random phenotype. The experiments showed that the ability to incorporate successful genotypes from others increased the rate at which evolution progressed. Communication of good genotypes allowed behaviors to get fitter faster, and made small initial population sizes feasible.

References

  1. Arkin, R. (1998). Behavior-Based Robotics. MIT Press, Cambridge.
  2. Balakrishnan, K. and Honavar, V. (1996). Analysis of neurocontrollers designed by simulated evolution. In Proc. of the IEEE International Conf. on Neural Networks.
  3. Billard, A. and Dautenhahn, K. (2000). Experiments in social robotics: grounding and use of communication in autonomous agents. In Adaptive Behaviour, volume 7.
  4. Cliff, D., Husbands, P., and Harvey, I. (1993). Analysis of evolved sensory-motor controllers. In Proc. of the Second European Conf. on Artificial Life.
  5. Connell, J. and Viola, P. (1990). Cooperative control of a semi-autonomous mobile robot. In Proc. of the 1990 IEEE International Conf. on Robotics and Automation.
  6. Duvivier, D., Preux, P., C.Fonlupt, Robilliard, D., and Talbi, E.-G. (1998). The fitness function and its impact on local search methods. In Proc. of the IEEE International Conf. on Systems, Man, and Cybernetics, volume 3.
  7. Floreano, D. and Mondada, F. (1994). Automatic creation of an autonomous agent: Genetic evolution of a neural-network driven robot. In From Animals to Animats 3: Proc. of the Third International Conf. on Simulation of Adaptive Behavior.
  8. Hoque, T., Chetty, M., and Dooley, L. (2004). An efficient algorithm for computing the fitness function of a hydrophobic-hydrophilic model. In Proc. of the IEEE International Conf. on Evolutionary Computation, volume 1.
  9. Houck, C., Joines, J., and Kay, M. (1995). A Genetic Algorithm for Function Optimization: A Matlab Implementation. NCSU-IE TR 95-09.
  10. Lippmann, R. P. (1989). Pattern classification using neural networks. In IEEE Communications Magazine.
  11. Maher, M. and Poon, J. (1995). Co-evolution of the fitness function and design solution for design exploration. In Proc. of the IEEE International Conf. on Evolutionary Computation, volume 1.
  12. Nehmzow, U. (2002). Physically embedded genetic algorithm learning in multi-robot scenarios: The pega algorithm. In Proc. of the Second International Workshop on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems, volume 94, Lund, Sweden. Lund University Cognitive Studies.
  13. Ripley, B. D. (1994). Flexible non-linear approaches to classification. In Cherkassky, V., Friedman, J. H., and Wechsler, H., editors, From Statistics to Neural Networks. Theory and Pattern Recognition Applications, Berlin. Springer Verlag.
  14. Saxena, A. and Saad, A. (2004). Genetic algorithms for ann-based condition monitoring system design for rotating mechanical systems. In 9th Online World Conf. on Soft Computing in Industrial Applications.
  15. Sorokin, S. N., Savelyev, V. V., Ivanchenko, E. V., and Oleynik, M. P. (2002). Fitness function calculation technique in yagi-uda antennas evolutionary design. In Proc. of the IEEE International Conf. on Mathematical Methods in Electromagnetic Theory, volume 2.
  16. Spears, W. M., DeJong, K. A., Baeck, T., Fogel, D. B., and deGaris, H. (1993). An overview of evolutionary computation. In Proc. of the 1993 European Conf. on Machine Learning.
  17. Stanley, K. O. and Miikkulainen, R. (2002). Evolving neural networks through augmenting topologies. In Evolutionary Computation, volume 10, Cambridge. MIT Press.
  18. Storm, T. (2004). KIKS is Khepera Simulator 2.2.0. (http://www.tstorm.se/projects/kiks/).
  19. Wagner, A. and Arkin, R. C. (2003). Internalized plans for communication-sensitive robot team behaviors. In Proc. of the IEEE/RSJ Conf. on Intelligent Robots and Systems.
  20. Whitley, L. D. (1994). A genetic algorithm tutorial. In Statistics and Computing, volume 4.
  21. Yao, X. (1999). Evolving artificial neural networks. In Proc. of the IEEE, volume 87.
Download


Paper Citation


in Harvard Style

Remy S. and Saad A. (2005). Modifying Neuro Evolution For Mobile Robotic Behavior Development . In Proceedings of the 1st International Workshop on Multi-Agent Robotic Systems - Volume 1: MARS, (ICINCO 2005) ISBN 972-8865-34-1, pages 155-164. DOI: 10.5220/0001192901550164


in Bibtex Style

@conference{mars05,
author={Sekou Remy and Ashraf Saad},
title={Modifying Neuro Evolution For Mobile Robotic Behavior Development},
booktitle={Proceedings of the 1st International Workshop on Multi-Agent Robotic Systems - Volume 1: MARS, (ICINCO 2005)},
year={2005},
pages={155-164},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001192901550164},
isbn={972-8865-34-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 1st International Workshop on Multi-Agent Robotic Systems - Volume 1: MARS, (ICINCO 2005)
TI - Modifying Neuro Evolution For Mobile Robotic Behavior Development
SN - 972-8865-34-1
AU - Remy S.
AU - Saad A.
PY - 2005
SP - 155
EP - 164
DO - 10.5220/0001192901550164