Aaron A Wallack

6681151, Jan 20, 2004

Dec 15, 2000

09/738542

Russ Weinzimmer - Milford NH
Aaron Wallack - Natick MA

Cognex Technology and Investment Corporation - Mountain View CA

G05B 1500

700259, 700245, 700254, 700 83, 700 85, 382146, 717104, 21912434, 21912185, 348 94, 348 95, 3562431, 3562371

A system and method for servoing robot marks using fiducial marks and machine vision provides a machine vision system having a machine vision search tool that is adapted to register a pattern, namely a trained fiducial mark, that is transformed by at least two translational degrees and at least one mon-translational degree of freedom. The fiducial is provided to workpiece carried by an end effector of a robot operating within a work area. When the workpiece enters an area of interest within a field of view of a camera of the machine vision system, the fiducial is recognized by the tool based upon a previously trained and calibrated stored image within the tool. The location of the work-piece is derived by the machine vision system based upon the viewed location of the fiducial. The location of the found fiducial is compared with that of a desired location for the fiducial. The desired location can be based upon a standard or desired position of the workpiece.

8442304, May 14, 2013

Dec 29, 2008

12/345130

Cyril C. Marrion - Acton MA, US
Nigel J. Foster - Natick MA, US
Lifeng Liu - Arlington MA, US
David Y. Li - West Roxbury MA, US
Guruprasad Shivaram - Chestnut Hill MA, US
Aaron S. Wallack - Natick MA, US
Xiangyun Ye - Framingham MA, US

Cognex Corporation - Natick MA

G06K 9/00

382154, 382190, 382294

This invention provides a system and method for determining the three-dimensional alignment of a modeled object or scene. A 3D (stereo) sensor system views the object to derive a runtime 3D representation of the scene containing the object. Rectified images from each stereo head are preprocessed to enhance their edge features. 3D points are computed for each pair of cameras to derive a 3D point cloud. The amount of 3D data from the point cloud is reduced by extracting higher-level geometric shapes (HLGS), such as line segments. Found HLGS from runtime are corresponded to HLGS on the model to produce candidate 3D poses. A coarse scoring process prunes the number of poses. The remaining candidate poses are then subjected to a further more-refined scoring process. These surviving candidate poses are then verified whereby the closest match is the best refined three-dimensional pose.