Affiliation:
1. Hebei Normal University
2. Chinese Academy of Sciences
Abstract
This paper focuses on the third generation of neural networks- Spiking neural networks (SNNs), the novel Spiking neuron model- probabilistic Spiking neuron model (pSNM), and their applications. pSNM is used in mobile robots' behavior control, and a novel mobile robots' wall-following controller based on pSNM is proposed. In the pSNM controller, Spiking time-delayed coding is used for the sensory neurons of the input layer and pSNM is used for the motor neurons in the output layer. Thorpe and Hebbian learning rules are used in the controller. The experimental results show that the controller can control the mobile robots to follow the wall clockwise and counterclockwise successfully. The structure of the controller is simple, and the controller can study online.
Publisher
Trans Tech Publications, Ltd.
Reference14 articles.
1. J. Vreeken, Spiking neural networks, an introduction. TechnicalReport UU-CS-2003-008, Institute for Information and ComputingSciences, Utrecht University (2002).
2. D. Floreano, Y. Epars, J. C. Zufferey, C. Mattiussi, Evolution of spiking neural circuits in autonomous mobile robots. International Journal of Intelligent Systems. 21 (2006) 1005-1024.
3. D. Floreano, J. C. Zufferey, J. D. Nicoud, From wheels to wings with evolutionary spiking neurons. Artificial Life. 11 (2005) 121-138.
4. Joshi P. On the role of feedback in enhancing the computational power of generic neural microcircuits. [Ph. D. Thesis]. Graz: Graz University of Technology, (2007).
5. H. Hagras, A. Pounds-Cornish, M. Colley, Evolving spiking neural network controllers for autonomous robots, in: The Proceeding of IEEE International Conference on Robotics & Automation 2004 (New Orleans, LA, USA, 2004) 4620-4626.