Vehicle Localization Technique for Traffic Light Advisor Application

The recent developments in Intelligent Transportation Systems (ITS) have unveiled a great potential for the improvement of traffic management through Advanced Driver Assist Systems (ADAS), both from a safety and environmental point of view. This paper proposes a vehicle localization technique based on Kalman filtering, being the ego-vehicle position a prerequisite for the Traffic Light Advisor (TLA) system to work. The localization algorithm implemented is thought to provide accurate results that can be used for the implementation of ADAS designed to achieve a safer and smoother driving style, which will translate into fewer safety hazards and less energy consumption. In particular, the challenge is to cope with the issues that Global Positioning Systems (GPS) face in urban scenarios, thus proposing a multi-rate sensor fusion approach based on Kalman Filter with Map Matching and a simple kinematic one-dimensional model. The experimental results show an estimation accuracy below 0.5 m on an urban road with long GPS missing areas. Moreover, the paper presents an experimental validation of a Traffic Light Advisor adopting the proposed localization algorithm, showing a 40% reduction in energy consumption with respect to normal driving.