On-the-fly particle filter registration for laser data

Abstract

This work is focused on streaming particle filter registration of surface models such as homogeneous triangle meshes and point clouds. Part of the approach is a streaming curvature feature calculation. The investigated approach utilizes a particle filter to incrementally update pose estimates during data acquisition. The method is evaluated in real data experiments with a high-precision laser striper system attached to an industrial robot. During the laser scan, the data is integrated on-the-fly in order to calculate features and based on these to estimate the object's pose. Experiments show the method's competitiveness in accuracy and reliability compared to state-of-the-art offline algorithms.