Recognition and Localization of Overlapping Parts from Sparse Data,
MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB
Pagination or Media Count:
In order to interact intelligently with its environment, a robot must know what objects are where that is, it must be able to identify and locate objects in its workspace. In this paper, we treat these two tasks under the title of the recognition problem. We will stress localization over identification since in most industrial robotics tasks the identity of the objects is known. This paper discusses how sparse local measurements of positions and surface normals may be used to identify and locate overlapping objects. The objects are modeled as polyhedra or polygons having up to six degrees of positional freedom relative to the sensors. The approach operates by examining all hypotheses about pairings between sensed data and object surfaces and efficiently discarding inconsistent ones by using local constraints on distances between faces, angles between face normals, and angles relative to the surface normals of vectors between sensed points. The method described here is an extension of a method for recognition and localization of non-overlapping parts previously described.
- Theoretical Mathematics