Neuro-fuzzy techniques for traffic control

被引：47

作者：

Henry, JJ ^{[1
]}

Farges, JL ^{[1
]}

Gallego, JL ^{[1
]}

机构：

[1] Off Natl Etud & Rech Aeronaut, F-31055 Toulouse, France

来源：

CONTROL ENGINEERING PRACTICE | 1998年 / 6卷 / 06期

关键词：

transportation control; traffic control; fuzzy control; neural networks; optimal control; algorithms; dynamic programming;

D O I：

10.1016/S0967-0661(98)00081-1

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 [计算机科学与技术];

摘要：

Neuro-fuzzy techniques are proposed here to control each light of an intersection, at one-second intervals. Rules, fuzzification and inference are modeled by a neural network. For each signal, the neuro-fuzzy control selects between 'switch on' and 'switch off', and presents the required action to a Petri net. A neuro-fuzzy acceleration of Forward Dynamic Programming (FDP) is obtained by enumerating controls only when there are no rules to apply, or when the rules are conflicting Simulations on different intersections show decreases in delays with respect to fixed timing from 0% to 30% for neuro-fuzzy control, and from 15% to 35% for neuro-fuzzy acceleration of FDP. (C) 1998 Elsevier Science Ltd. All rights reserved.

引用

页码：755 / 761

页数：7

共 14 条

[1]

[Anonymous], 1988, POSSIBILITY THEORY

[2]

FARGES JL, 1991, ADVANCED TELEMATICS IN ROAD TRANSPORT, VOLS 1 AND 2, P527

[3]

FARGES JL, 1990, P 8 C BRAS AUT, P348

[4]

Design by Petri nets of an intersection signal controller [J].

Gallego, JL ;

Farges, JL ;

Henry, JJ .

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 1996, 4 (04) :231-248

[5]

Gartner N. H., 1990, Control, Computers, Communications in Transportation. Selected Papers from the IFAC/IFIP/IFORS Symposium, P241

[6]

HENRY JJ, 1983, P 4 IFAC IFIP IFORS

[7]

LANGARI R, 1992, HDB INTELLIGENT CONT, P93

[8]

Mauro V., 1990, Control, Computers, Communications in Transportation. Selected Papers from the IFAC/IFIP/IFORS Symposium, P245

[9]

McDonald M., 1991, CONCISE ENCY TRAFFIC, P400

[10]

POMMIER L, 1992, MANUEL UTILISATEUR S

← 1 2 →