Fault tolerant adaptive neuro-fuzzy based automated cruise controller on FPGA

Abstract

The objective of the paper is to implement a system which effectively reduces vehicle collisions by using a combination of image processing and neuro-fuzzy based techniques. It uses an image processing module in order to determine the distance of the front vehicle. The distance measurements are given to a sugeno type adaptive neuro-fuzzy system. Since the operation of the system is mission critical in nature, a fault tolerant field programmable gate array (FPGA) implementation of the system is proposed to balance the reliability, availability and performance criteria. Finally, a comparison is made with respect to difference in errors and speed, between neural network and adaptive neuro-fuzzy based methods.

Hardware implemented adaptive neuro fuzzy system

“…Many related works [1], [2], [5] proves, that the hardware implemented neuro-fuzzy systems will be an important part of the automation's future. The ANFIS structure consists of the two conditions and two inference components, which are connected by a set of rules.…”

Application of Artificial Neural Networks to Streamline the Process of Adaptive Cruise Control

“…The aim is to create a driver model imitating the driver's activity based on real data and The problem of adaptive cruise control (ACC) can be transformed into the problem of optimal tracking control for complex nonlinear systems. This task is currently solved by different methods using different methods-for example with experience playback technology [14], neural networks [15][16][17][18][19][20][21][22][23][24][25][26][27][28], fuzzy-neural approaches [29][30][31], adaptive algorithms [32,33], or combinations thereof [34][35][36] or modern function approximation techniques together with gradient learning algorithms [37].…”