Modular non-computational-connectionist-hybrid neural network approach to robotic systems

被引：0

作者：

Bamford C.D. ^{[1
]}

Mitchell R.J. ^{[1
]}

机构：

[1] Cybernetics, School of Systems Engineering, University of Reading, Reading

来源：

Paladyn | 2011年 / 2卷 / 03期

关键词：

hybrid systems; neural networks; robotics; spiking neurons;

D O I：

10.2478/s13230-012-0003-6

中图分类号：

学科分类号：

摘要：

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. © C.D. Bamford et al. 2011.

引用

页码：126 / 133

页数：7

共 18 条

[1]

Tomei P., Adaptive PD controller for robot manipulators, IEEE Transactions on Robotics and Automation, 7, 4, pp. 565-570, (1991)

[2]

Hao B., Dai X., The collision-free motion of robot with Fuzzy neural network, International Conference on Industrial and Information Systems, pp. 219-222, (2010)

[3]

Park D., Yoon S., Kim Y., Robot end-eector recognition using modular neural network for autonomous control, International Joint Conference on Neural Networks, pp. 2032-2036, (1999)

[4]

Rolls E.T., Stringer S.M., Learning transform invariant object recognition in the visual system with multiple stimuli present during training, Neural Networks, 21, 7, pp. 888-903, (2008)

[5]

Tromans J.M., Stringer S.M., Rolls E.T., Spatial scene representations formed by self-organizing learning in a hippocampal extension of the ventral visual system, Eur. J. Neurosci, 28, 10, pp. 2116-2127, (2008)

[6]

Xia Y.S., Feng G., Wang J., A Primal-dual Neural Network for Online Resolving Constrained Kinematic Redundancy in Robot Motion Control, Systems, Man, and Cybernetics, Part B: Cybernetics, 35, 1, pp. 54-64, (2005)

[7]

Yu X., Yang S.X., Ishikawa M., Neural network robot controller based on structural learning with forgetting, in, IEEE International Symposium on Intelligent Control, pp. 264-268, (2003)

[8]

Bamford C.D., Mitchell J.R., Cavacade Neural Network for Mobile Robot, Cybernetic Intelligent Systems (CIS, pp. 1-6, (2010)

[9]

Macready D.H., Wolpert G.W., No Free Lunch Theorems for Optimization, IEEE Transactions on Evolutionary Computation, 1, 1, (1997)

[10]

Yang X., Meng M., A Neural Network Approach to Real-Time Motion Planning and Control of Robot Manipulators, in Systems, Man, and Cybernetics, pp. 674-679, (1999)

← 1 2 →