FPGA implementation of a neural network control system for a helicopter

Authors:
M. Zheng;M. Tarbouchi;D. Bouchard;J. Dunfield
Affiliations:
Department of Electrical and Computer Engineering, Royal Military College of Canada, Kingston, Ontario, Canada;Department of Electrical and Computer Engineering, Royal Military College of Canada, Kingston, Ontario, Canada;Department of Electrical and Computer Engineering, Royal Military College of Canada, Kingston, Ontario, Canada;Department of Electrical and Computer Engineering, Royal Military College of Canada, Kingston, Ontario, Canada
Venue:
NN'06 Proceedings of the 7th WSEAS International Conference on Neural Networks
Year:
2006

Citing 1
Cited 1

Artificial neural network implementation on a single FPGA of a pipelined on-line backpropagation

ISSS '00 Proceedings of the 13th international symposium on System synthesis

A model of analogue K-winners-take-all neural circuit

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper the design and development of an intelligent controller based on artificial neural networks (ANN) on a Field Programmable Gate Array (FPGA), for a fourrotor helicopter to be capable of achieving vertical take off and to be able to sustain a specified attitude, is presented. To overcome challenges due to the complexities of creating a Neural Networks Controller to work in real-time, a hardware-friendly training algorithm is chosen. The ANN is implemented on a Virtex-II Pro XC2VP30 FPGA from Xilinx. Simulation results are analyzed to highlight the performance of the hardware.