A heuristic method has been developed for registering two sets of 3-D curves obtained by using an edge-based stereo system, or two dense 3-D maps obtained by using a correlation-based stereo system. Geometric matching in general is a difficult unsolved problem in computer vision. Fortunately, in many practical applications, some a priori knowledge exists which considerably simplifies the problem. In visual navigation, for example, the motion between successive positions is usually approximately known. From this initial estimate, our algorithm computes observer motion with very good precision, which is required for environment modeling (e.g., building a Digital Elevation Map). Objects are represented by a set of 3-D points, which are considered as the samples of a surface. No constraint is imposed on the form of the objects. The proposed algorithm is based on iteratively matching points in one set to the closest points in the other. A statistical method based on the distance distribution is used to deal with outliers, occlusion, appearance and disappearance, which allows us to do subset-subset matching. A least-squares technique is used to estimate 3-D motion from the point correspondences, which reduces the average distance between points in the two sets. Both synthetic and real data have been used to test the algorithm, and the results show that it is efficient and robust, and yields an accurate motion estimate.

Parts manufactured to tolerances have variations in shape. Most previous work in robotic manipulation assumes that parts do not have shape variations. Orienting devices such as bowl feeders often fail due to variations in part shape. We study the effects of uncertainty in part shape on orienting to develop systems that can orient toleranced polygonal parts. We present a tolerance model in which the part center of mass and vertices lie in circular uncertainty zones around their nominal positions. The variations in part shape are characterized by the tolerance model and the part's nominal shape. We describe the nondeterminism that arises due to part shape uncertainty for a conveyor-based orienting system and show that sensor-based and sensorless orienting plans can exist for toleranced polygonal parts. We present implemented planners that generate orienting plans for the entire variational class of part shapes given a nominal part shape and tolerance bounds. These plans use both deterministic and nondeterministic actions to orient the parts, and we describe experiments to demonstrate them.