Millions of road users and pedestrians are killed in traffic accidents each year. The need to increase road safety is one of the major concerns, and the better way to increase safety is to develop systems which are able to automatically drive, the principal cause of road accidents being human error. Centre for Computational Intelligence (C2i) has developed a simulated system based on fuzzy neural network, which is able to drive on highway, and to take some decisions like lane changing and car following or overtaking. The aim of our project is to go one step beyond this system, by implementing intelligent speed adaptation (ISA), so the car can anticipate curves by adapting its speed according to the degree of curvature of the road. In order to implement ISA, we will use the GenSoYagerFNN, a fuzzy neural network developed in the laboratory, which has shown good performances for autonomous driving. The information about the environment is given by a camera put in front of the car, and image processing is used for lane detection and to extract necessary data. These data are then fed into the network, which gives in output the vehicle controls (i.e. steering, brake and throttle). The GenSoYagerFNN must first learn from a training set, given by collecting data from a human driver, in order to be able to drive correctly the vehicle. Experimental results have shown that the GenSoYager was able to correctly adapt its speed according to the curvature of the road, in the same way that human do. The learning process from a human training set has been a success for a simple test, and results are encouraging for the continuation of the project.