Abstract: A computer-implemented method is provided. The method may include receiving or identifying a first point cloud associated with a train-time object or model. The method may further include selecting one or more probes associated with the first point cloud wherein selection of the one or more probes is based upon, at least in part, a score of a particular feature associated with the first point cloud. The method may also include analyzing a second point cloud associated with a run-time object, wherein the analysis is based upon the first point cloud. This analysis may produce an estimate of the difference in pose between the train time object and the run time object. Pose estimates may be obtained by matching points between the two point clouds based in part on features used during probe selection. Pose estimates may be scored, and refined, using the points selected as probes.

Abstract: A computer-implemented method is provided. The method may include receiving or identifying a first point cloud associated with a train-time object or model. The method may further include selecting one or more probes associated with the first point cloud wherein selection of the one or more probes is based upon, at least in part, a score of a particular feature associated with the first point cloud. The method may also include analyzing a second point cloud associated with a run-time object, wherein the analysis is based upon the first point cloud. This analysis may produce an estimate of the difference in pose between the train time object and the run time object. Pose estimates may be obtained by matching points between the two point clouds based in part on features used during probe selection. Pose estimates may be scored, and refined, using the points selected as probes.