Comparison Between Different Learning Rates in a Car Safety Controller

In spite of all the efforts made by researchers to decrease car accidents in many countries, it is still challenging to design a system adaptive to the driver rather than the automotive characteristics. The implemented adaptive car safety system (ADCSS) observes the skills of the driver as well as the parameters of the vehicle and the locations of the car on the road using GPS information to estimate and control a safe speed. Particularly, the implemented neural network as part of ADCSS learns how expert the driver is while facing different situations and updates the speed limits in different locations on the road. A comparison between applying different learning rates has also been discussed.