Abstract: Computer-implemented methods and systems for detecting loop closure in SLAM applications can include accessing one or more range measurement data scans that each provide a collection of consecutively observed spatial data obtained at a given location. A relative scan pose for each range measurement data scan can be determined. Frames from each of the one or more range measurement data scans then can be aligned to frames within one or more submaps based at least in part by the determined relative scan pose. An enhanced scan pose for each range measurement data scan and an enhanced submap pose for each submap can be periodically determined and used to identify one or more closed loops within the one or more submaps. An output indicative of the identified one or more closed loops can be provided, along with optionally generated floorplan maps and/or given location determinations.

Abstract: Systems and methods for extracting regions from occupancy grids are provided. One example method includes performing a plurality of assignment iterations. Each assignment iteration includes assigning each of a first plurality of cells to one of a plurality of centroids based on a cost formula such that a plurality of regions respectively associated with the plurality of centroids are formed. The region for each centroid comprises all of the cells assigned to such centroid. Each assignment iteration includes reassigning one or more of the first plurality of cells to one or more respective alternate regions. The one or more reassigned cells were included in one or more problem areas of one or more of the plurality of regions. Each assignment iteration includes relocating the plurality of centroids to be the respective means of the plurality of regions. One example system includes computing devices implementing instructions stored on non-transitory computer-readable media.

Abstract: Systems and methods for extracting regions from occupancy grids are provided. One example method includes performing a plurality of assignment iterations. Each assignment iteration includes assigning each of a first plurality of cells to one of a plurality of centroids based on a cost formula such that a plurality of regions respectively associated with the plurality of centroids are formed. The region for each centroid comprises all of the cells assigned to such centroid. Each assignment iteration includes reassigning one or more of the first plurality of cells to one or more respective alternate regions. The one or more reassigned cells were included in one or more problem areas of one or more of the plurality of regions. Each assignment iteration includes relocating the plurality of centroids to be the respective means of the plurality of regions. One example system includes computing devices implementing instructions stored on non-transitory computer-readable media.