We are investigating the problem of removing 3D objects from a heap without having recourse to object models. Aswe are relying on geometric information alone, the use of range data is a natural choice. To ensure that we see opposite patches of the object surfaces, we use up to three range views from different directions. These views are triangulated using the data points as vertices. After merging the views, the resulting surface description is segmented into patches which correspond to object parts. We present a novel approach to search for grasping opportunities on a selected part. We allow all combinations of two vertices to be possible contact points for the two finger gripper. Based on evidence accumulation of local features, a quality measure is defined for each of these vertex pairs. A discrete optimization algorithm which is based on Tabu-Search then tries to find several good grasping configurations. Global constraints which are not part of the objective function (e.g. collisions) have to be respected.

Range data offer a direct way to produce shape descriptions of surfaces. Typically single range images have the form of a graph surface z=g(z,y) and thus suffer from occlusion. One can reduce this problem by taking several images from different locations and merging them together. The result is a real 3-D description of the object's surface. In this paper we address several problems that result from the 2 1/2 -D to 3-D transition. We present an algorithm which is able to merge depth images of an arbitrary shaped object using a highly local approach. An explicit sensor error model is used to support the merging. A key feature of our algorithm is the ability to update its result by an additional new view. Thus, it is possible to gradually improve the surface description in regions of high noise.>

Let A be a matrix algebra over C, closed under Hermitian adjoints, and given by a basis.