Robust positioning using relaxed constraint-propagation

A robust 2-D vehicle-positioning system based on constraint propagation on a data horizon is proposed. Using asynchronous unreliable absolute positions and reliable proprioceptive measurements, the proposed method outputs the bounds of the pose at any desired rate. A bounded error approach is used to propagate the imprecision of the input data to the final pose estimation. Measurements are represented by intervals taking errors into account. Integrity is assumed on proprioceptive measurements error bounds. In opposition, the bounds set on exteroceptive positions are not required to be guaranteed. Indeed, a relaxed intersection of constraints is applied to achieve robustness, given a maximum ratio of erroneous positions. This approach is implemented for an automotive vehicle equipped with a GPS receiver and a CAN gateway. An real experimental validation is carried out with a dataset including wrong GPS measurements and the crossing of a tunnel.