Coarse-to-fine vision-based localization for mobile robots using an object and spatial layout-based hybrid map

This paper presents a novel vision-based global localization approach that uses an object and spatial layout based hybrid map. We model any indoor environments using the following visual cues with a stereo camera; local invariant features for object recognition and their 3D positions for object pose estimation. Also, we use the depth information at the horizontal centerline in images where the optical axis passes through, which is similar to the data of a 2D laser range finder. Therefore, we can build a hybrid local node for a topological map that is composed of a metric map and an object location map. Based on such modeling, we suggest a coarse-to-fine strategy for the global localization. The coarse pose is obtained by means of object recognition and a least-squares fitting, and then its fine pose is estimated with a particle filtering algorithm. With real experiments, we show that our proposed method can be an effective vision-based global localization algorithm.