LAUSR

This paper presents a visual odometry method that estimates the location and orientation of a robot. The visual odometry approach is based on the Fourier transform, which extracts the translation between consecutive image’s regions captured using a ground-facing camera. The proposed method is especially suited if no distinct visual features are present on the ground. This approach is resistant to wheel slippage because it is independent of the kinematics of the vehicle. The method has been tested on different experimental platforms and evaluated against the ground truth, including a successful loop-closing test, to demonstrate its general use and performance.