A Hybrid Neuro-Fuzzy System for Adaptive Vehicle Separation Control

Authors:
I-Chang Jou;Chung-Jyi Chang;Huey-Kuo Chen
Affiliations:
National Kaoshiung First Science and Technology University, Kaoshiung, Taiwan 800, R.O.C.;National Central University, Taoyuan, Taiwan 320, R.O.C.;National Central University, Taoyuan, Taiwan 320, R.O.C.
Venue:
Journal of VLSI Signal Processing Systems
Year:
1999

Citing 7
Cited 0

An efficient gradient-based algorithm for on-line training of recurrent network trajectories

Neural Computation
Fuzzy sets and fuzzy logic: theory and applications

Fuzzy sets and fuzzy logic: theory and applications
Hybridization of neural and fuzzy systems by a multi agent architecture for motor gearbox control

Fuzzy Sets and Systems - Special issue: application of neuro-fuzzy systems
Fuzzy Control Systems

Fuzzy Control Systems
Intelligent Hybrid Systems

Intelligent Hybrid Systems
A constructive approach for nonlinear system identification using multilayer perceptrons

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Stable adaptive control using fuzzy systems and neural networks

IEEE Transactions on Fuzzy Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

The primary purpose of this paper is to develop a robust adaptivevehicle separation control in the increasingly important roles of intelligenttransportation system (ITS). A hybrid neuro-fuzzy system (HNFS) is proposed for developingthe adaptive vehicle separation control to minimize the distance (headway) between successive cars. This hybrid system consists oftwo modules: a headway identification (prediction) module and a controldecision module. Each of these modules is realized with a distinctneuro-fuzzy network that upgrades hierarchical granularity and reduces thecomplexity in the control system. Given the current headway and relativevelocity between the two consecutive cars, the headway identification modulepredicts the headway of the next time instant. This identified headway, together with the desired velocity are input to the control decision modulewhose output is the actual acceleration/deceleration control output. The HNFSencapsulates the adaptive learning capabilities of a neural network into afuzzy logic control framework to fine-tune the fuzzy control rules. On theother hand, rules derived initially from well-defined fuzzy phase planeaccelerate the training of the neural network. Simulation results are veryencouraging. It is observed that the headway decreases significantly withoutsacrificing speed. Furthermore, both stability and robustness of HNFS aredemonstrated.