Abstract
Spiking neural networks are usually limited in their applications due to their complex mathematical models and the lack of intuitive learning algorithms. In this paper, a simpler, novel neural network derived from a leaky integrate and fire neuron model, the ‘cavalcade’ neuron, is presented. A simulation for the neural network has been developed and two basic learning algorithms implemented within the environment. These algorithms successfully learn some basic temporal and instantaneous problems. Inspiration for neural network structures from these experiments are then taken and applied to process sensor information so as to successfully control a mobile robot.
Similar content being viewed by others
References
P. Tomei, Adaptive PD controller for robot manipulators, IEEE Transactions on Robotics and Automation, vol. 7, no. 4, (1991), 565–570
Bing Hao and Xuefeng Dai, The collision-free motion of robot with Fuzzy neural network, in International Conference on Industrial and Information Systems., (2010), 219–222
Dong-Sun Park, Sok Yoon, and YoungBu Kim, Robot end-e ector recognition using modular neural network for autonomous control, in International Joint Conference on Neural Networks, (1999), 2032–2036
E. T. Rolls, S. M. Stringer, Learning transform invariant object recognition in the visual system with multiple stimuli present during training, Neural Networks, vol. 21, no. 7, (2008), 888–903
J. M. Tromans, S. M Stringer, E. T. Rolls, Spatial scene representations formed by self-organizing learning in a hippocampal extension of the ventral visual system, Eur. J. Neurosci., vol. 28, no. 10, (2008), 2116–27
Y. S. Xia, Gang Feng, and Jun Wang, A primal-dual neural network for online resolving constrained kinematic redundancy in robot motion control, Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, vol. 35, no. 1, (2005), 54–64
Xiang Yu, S.X. Yang, and M. Ishikawa, Neural network robot controller based on structural learning with forgetting, in IEEE International Symposium on Intelligent Control., (2003), 264–268
C. D. Bamford and R. J. Mitchell, Cavacade Neural Network For Mobile Robot, Cybernetic Intelligent Systems (CIS), 2010 IEEE 9th International Conference on, (2010), 1–6
D. H., Macready, W. G. Wolpert, No Free Lunch Theorems for Optimization, IEEE Transactions on Evolutionary Computation, vol. 1, no. 1, (1997)
Xianyi Yang and M. Meng, A neural network approach to real-time motion planning and control of robot manipulators, in Systems, Man, and Cybernetics, (1999), 674–679
S. X. Yang, A biological inspired neural network approach to real-time collision-free motion planning of a nonholonomic car-like robot, in International Conference on Intelligent Robots and Systems IROS, (2000), 239–244
F. Alnajjar, I. Bin Mohd Zin, and K. Murase, A Spiking Neural Network with dynamic memory for a real autonomous mobile robot in dynamic environment, in IEEE International Joint Conference on Neural Networks, (2008), 2207–2213
R. -J. Wai, Y. -C. Huang, Z. -W. Yang, and C. -Y. Shih, Adaptive fuzzy-neural-network velocity sensorless control for robot manipulator position tracking, Control Theory & Applications, IET, vol. 4, no. 6, (2010), 1079–1093
Y. H. Kim and F. L. Lewis, Neural network output feedback control of robot manipulators, in IEEE Transactions on Robotics and Automation, (1999), 301–309
M. D. Capuozzo and D. L. Livingston, A compact evolutionary algorithm for integer spiking neural network robot controllers, in Southeastcon, 2011 Proceedings of IEEE, Baltimore, (2011), 237–242
F. Alnajjar and K. Murase, Sensor-fusion in spiking neural network that generates autonomous behavior in real mobile robot, in IEEE International Joint Conference on Neural Networks., (2008), 2200–2206
A. Schreibman, M. Häusser, M. E. Larkum, I. Segev, and M. London, The information e cacy of a Synapse, Nature Neuroscience, vol. 5, (2002), 332–340
W. L. Kath, N. Spruston, Dendritic Arithmetic, Nature Neuroscience, vol. 7, no. 1, (2004), 2004 567–569
Author information
Authors and Affiliations
Corresponding author
Additional information
This paper has been partially published in the IEEE 9th International Conference on Cybernetic Intelligent Systems, 2010, Reading, UK
About this article
Cite this article
Bamford, C.D., Mitchell, R.J. Modular non-computational-connectionist-hybrid neural network approach to robotic systems. Paladyn 2, 126–133 (2011). https://doi.org/10.2478/s13230-012-0003-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.2478/s13230-012-0003-6