ArticlesNo Access

SELF-ORGANIZATION OF SPIKING NEURAL NETWORK THAT GENERATES AUTONOMOUS BEHAVIOR IN A REAL MOBILE ROBOT

FADY ALNAJJAR

Department of Human and Artificial Intelligence Systems, University of Fukui, Fukui 910-8507, Japan

Search for more papers by this author

and

KAZUYUKI MURASE

Department of Human and Artificial Intelligence Systems, University of Fukui, Fukui 910-8507, Japan

Search for more papers by this author

https://doi.org/10.1142/S0129065706000640Cited by:13 (Source: Crossref)

Abstract

In this paper, we propose self-organization algorithm of spiking neural network (SNN) applicable to autonomous robot for generation of adoptive and goal-directed behavior. First, we formulated a SNN model whose inputs and outputs were analog and the hidden unites are interconnected each other. Next, we implemented it into a miniature mobile robot Khepera. In order to see whether or not a solution(s) for the given task(s) exists with the SNN, the robot was evolved with the genetic algorithm in the environment. The robot acquired the obstacle avoidance and navigation task successfully, exhibiting the presence of the solution. After that, a self-organization algorithm based on a use-dependent synaptic potentiation and depotentiation at synapses of input layer to hidden layer and of hidden layer to output layer was formulated and implemented into the robot. In the environment, the robot incrementally organized the network and the given tasks were successfully performed. The time needed to acquire the desired adoptive and goal-directed behavior using the proposed self-organization method was much less than that with the genetic evolution, approximately one fifth.

Keywords:

References

M. Maass, Networks of spiking neural network, the third generation of neural networks models, Proc. 7th Australian Conf. Neural Networks (1996) pp. 1–10. Google Scholar
B. Ruf and M. Schmitt, IEEE Trans. Neural Networks 9(3), 575 (1998), DOI: 10.1109/72.668899. Crossref, Medline, Web of Science, Google Scholar
B. Ruf and M. Schmitt, Neural Processing Letters 5(1), 9 (1997), DOI: 10.1023/A:1009697008681. Crossref, Web of Science, Google Scholar
D. Floreano and C. Mattiussi, Evolutionary Robotics IV (SpringerVerlag, Berlin, 2001) pp. 38–61. Google Scholar
K. Murase and Md. Monirul Islam, IEICE Trans. E85D(7), 1118 (2002). Web of Science, Google Scholar
D. M. Sala, K. J. Cios and J. T. Wall, Australian J. Intelligent Information Processing Systems 5(3), 161 (1998). Web of Science, Google Scholar
D. Floreano, J. C. Zufferey and C. Mattiussi, Dynamic Systems Approach for Embodiment and Sociality (Advanced Knowledge International, Adelaide, Australia, 2003) pp. 65–70. Google Scholar
D. Floreano, J. C. Zufferey and J. D. Nicoud, Artificial Life 11(12), 121 (2005), DOI: 10.1162/1064546053278900. Crossref, Medline, Web of Science, Google Scholar
G. Hinton and T. J. Sejnowski , Unsupervised learning and map formation: Foundations of neural computation ( MIT Press , USA , 1999 ) . Crossref, Google Scholar
J. Tani, M. Ito and Y. Sugita, Neural Networks 17(8–9), 1273 (2004), DOI: 10.1016/j.neunet.2004.05.007. Crossref, Medline, Web of Science, Google Scholar
R. W. Paine and J. Tani, Neural Networks 17(8–9), 1291 (2004), DOI: 10.1016/j.neunet.2004.08.005. Crossref, Medline, Web of Science, Google Scholar
E. Zalama, P. Gaudiano and J. L. Coronado, Neural Networks 8(1), 103 (1995), DOI: 10.1016/0893-6080(94)00063-R. Crossref, Web of Science, Google Scholar
P. Gaudiano, E. Zalama and J. L. Coronado, IEEE Trans. Neural Networks 26(3), 485 (1996). Google Scholar
E. Zalama, G. M. Paul and J. R. Perán, IEEE Trans. System Man and Cybernetics, Part A: Systems and Humans 32(1), 160 (2001), DOI: 10.1109/3468.995537. Crossref, Web of Science, Google Scholar
A. Arleo, F. Smeraldi and W. Gerstner, IEEE Trans. Neural Network 15(3), 639 (2004), DOI: 10.1109/TNN.2004.826221. Crossref, Medline, Web of Science, Google Scholar
P. F. M. Verschure, B. J. A. Kröse and R. Pfeifer, Robotics and Autonomous Systems 9(3), 181 (1992), DOI: 10.1016/0921-8890(92)90054-3. Crossref, Google Scholar
C. Chang, IEEE Trans. Neural Networks 16(6), 1582 (2005), DOI: 10.1109/TNN.2005.853714. Crossref, Medline, Web of Science, Google Scholar
D. Lambrinos, C. Scheier and R. Pfeifer, Unsupervised classification of sensory-motor states in a real world artifact using a temporal kohonen map, Proc. Int. Conf. Artificial Neural Networks (1995) pp. 467–472. Google Scholar
B. Ruf and M. Schmitt, IEEE Trans. Neural Networks 9(3), 575 (1998), DOI: 10.1109/72.668899. Crossref, Medline, Web of Science, Google Scholar
T. Natschläger, B. Ruf and M. Schmitt, Self-Organizing Neural Networks, Springer Series on Studies in Fuzziness and Soft Computing (Springer-Verlag, Heidelberg, 2001) pp. 45–73. Google Scholar
R. Amir and A. A Saffari, Unknown environment representation for mobile robot using spiking neural networks, Proc. 4th World Informatics Conf. (2005) pp. 49–52. Google Scholar
H. Burgsteiner, Training networks of biological realistic spiking neurons for real-time robot control, Proc. 9th Int. Conf. Engineering Application of Neural Network (2005) pp. 129–136. Google Scholar
H. Burgsteineret al., Movement prediction from real-world images using a liquid state machine, Proc. 18th Int. Conf. Industrial & Engineering Applications of Artificial Intelligence & Expert Systems (2005) pp. 121–131, DOI: 10.1007/11504894_19. Google Scholar
Y. Choe and R. Miikkulainen, Self-organization and segmentation with laterally connected spiking neurons, Proc. 5th Int. Joint Conf. Artificial Intelligence (1997) pp. 1120–1125. Google Scholar
P. Joshi and W. Maass, Neural Computation 17(8), 1715 (2005), DOI: 10.1162/0899766054026684. Crossref, Medline, Web of Science, Google Scholar
D. Roggenet al., Hardware spiking neural network with run-time reconfigurable connectivity in an autonomous robot, The 2003 NASA/DoD Conf. Evolvable Hardware (2003) pp. 189–198, DOI: 10.1109/EH.2003.1217666. Google Scholar
J. Nielsen and H. H. Lund, Spiking neural building block robot with hebbian learning, Proc. Int. Conf. Intelligent Robots and Systems (2003) pp. 1363–1369. Google Scholar
W. Gerstner and W. M. Kistler , Spiking Neuron Models ( Cambridge University Press , London , 2002 ) . Crossref, Google Scholar
W. Maass, Computation with spiking neurons, Proc. Int. Conf. Neural Information Processing (1997) pp. 187–188. Google Scholar