Conference Proceeding

Intelligent Speed Adaptation Using a Self-Organizing Neuro-Fuzzy Controller

Inst. Nat. Polytech. de Grenoble, Grenoble
07/2007; DOI:10.1109/IVS.2007.4290222 pp.846 - 851 In proceeding of: Intelligent Vehicles Symposium, 2007 IEEE
Source: IEEE Xplore

ABSTRACT The need to increase road safety is a major concern, with millions of road users and pedestrians being killed in traffic accidents each year. The Centre for Computational Intelligence (C2i) at NTU has developed an intelligent driving system based on hybrid fuzzy neural networks, which is able to park autonomously, drive on highways, and take some decisions such as lane changing, car following, and overtaking. This paper presents a new approach to autonomously adapt the speed of a vehicle by learning from a human driver and using anticipation. The architecture of the system is a specific fuzzy neural network realized at C2i: the Generic Self Organizing Fuzzy Neural Network using the Yager inference scheme (GenSoFNN(Yager)). Experiments have been conducted in simulation to test the longitudinal control and the ability of the system to anticipate curves. Results found are very promising.

0 0
 · 
0 Bookmarks
 · 
28 Views
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.

Keywords

able
 
curves
 
Generic Self Organizing Fuzzy Neural Network
 
GenSoFNN(Yager)
 
human driver
 
hybrid fuzzy neural networks
 
increase road safety
 
intelligent
 
major concern
 
paper presents
 
road users
 
specific fuzzy neural network
 
traffic accidents
 
Yager inference scheme