DocumentCode :
3318393
Title :
Fuzzy Logic Obstacle Identity Declaration and Fusion in the Autotaxi System
Author :
Escamilla-Ambrosio, P.J. ; Lieven, N.
Author_Institution :
Bristol Univ., Bristol
fYear :
2007
fDate :
23-26 July 2007
Firstpage :
1
Lastpage :
6
Abstract :
The Autotaxi system is a safety critical sensor system developed to perform the sensing required for an autonomous vehicle to drive safely along a dedicated paved guideway network. The host vehicle is equipped with a set of sensors used to detect and track any object of interest in the field of view. In this work a multiple-sensor obstacle identification and fusion approach for the Autotaxi system is proposed. Based on the knowledge about the vehicles, the obstacles to be detected, and the guideway network system, two obstacle classifier systems are designed using the principles of fuzzy logic. In Classifier 1 the classification process is carried out based on the obstacle´s width and kind of road in which the host vehicle is navigating. In Classifier 2 the classification process is carried out based on the obstacle´s width and height together with the kind of road in which the host vehicle is navigating. Furthermore, as different declarations of identity can be performed by using information from different sensors, a method to fuse these identity declarations is proposed. The viability of the proposed approach is demonstrated through a simulated example. Promising results are reported.
Keywords :
automobiles; driver information systems; fuzzy logic; sensor arrays; autonomous vehicle; autotaxi system fusion; fuzzy logic obstacle identity declaration; guideway network; guideway network system; multiple-sensor obstacle identification; obstacle classifier systems; Fuzzy logic; Mobile robots; Navigation; Object detection; Remotely operated vehicles; Road vehicles; Sensor systems; Vehicle detection; Vehicle driving; Vehicle safety;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Fuzzy Systems Conference, 2007. FUZZ-IEEE 2007. IEEE International
Conference_Location :
London
ISSN :
1098-7584
Print_ISBN :
1-4244-1209-9
Electronic_ISBN :
1098-7584
Type :
conf
DOI :
10.1109/FUZZY.2007.4295545
Filename :
4295545
Link To Document :
بازگشت