A Statistical GPS Error Model for Autonomous Driving

Autonomous driving (AD) is envisioned to have a significant impact on people's life regarding safety and comfort. Positioning is one of the key challenges in realizing AD, where global navigation systems (GNSS) is traditionally used as an important source of information. The area of GNSS are well explored and the different sources of error are deeply investigated. However the existing modeling methods often have very comprehensive requirements for the training data where all affecting conditions, such as ephemeris data and satellite clock should be well known. The main goal of this paper is to develop a solution to model GPS error that only requires information which is available in the vehicle without having access to detailed information about the conditions. For this purpose, we propose a state-based semi-stochastic model and an efficient learning algorithm, where stochastic parts are modelled using autoregression and Gaussian mixture models. The resulting model successfully mimics the distributions of the absolute error and the first difference, for data with ideal GNSS conditions.