On-Road Vehicle Localization with GPS under Long Term Failure of a Vision Sensor

In this paper, we consider on-road vehicle localization with the global positioning system (GPS) under long term failure of a vision sensor. When the output of vision sensor is not available due to its malfunction and/or environmental conditions, it is necessary for the lateral control system to maintain its stability before the driver takes over control authority. We propose how to estimate lane coefficients with GPS data and the latest normal lane coefficients in the presence of failure. This lane estimation method enables the lane keeping system to keep its stability. The developed algorithm was validated via computational simulation results with CarSim and MATLAB/Simulink. We also included experimental results with a test vehicle equipped with an AutoBox from dSPACE.