Estimation of vehicle pose and road curvature based on perception-net

Proposed is an algorithm to estimate the vehicle pose and the road curvature by geometrically fusing sensor data from camera image, velocity meter, and steering wheel encoder. To achieve computational efficiency in processing in real time sequence, we propose a method to model the lane on the road as a series of connected rectangular plates. We propose an algorithm, so called "Perception-Net", where not only variables denoting the vehicle pose and the road curvature, but also the corresponding uncertainties are propagated in forward and backward direction in such a way to satisfy the given constraint condition, maintain consistency, reduce the uncertainties, and guarantee robustness. An experimental result is also presented.