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.
Intelligent Speed Adaptation Using a Self-Organizing Neuro-Fuzzy Controller
2007 IEEE Intelligent Vehicles Symposium ; 846-851
2007-06-01
337731 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Intelligent Speed Adaptation Using a Self-Organizing Neuro-Fuzzy Controller
British Library Conference Proceedings | 2007
|An online self-organizing neuro-fuzzy control for autonomous underwater vehicles
Tema Archiv | 1999
|A self-organizing video neuro-tracker
British Library Online Contents | 1997
|A Model Reference Self-Organizing Fuzzy Logic Controller
British Library Online Contents | 1995
|Fuzzy and neuro-fuzzy controller for active suspension
Kraftfahrwesen | 2002
|