Computer vision system for identification, measurement, and duplication of machined parts

A strategy for identifying, measuring, and duplicating machined parts using an EOL (endpoint open loop), position based, visual servo robot is presented. The procedure is demonstrated using the representative, and commercially important, problem of duplicating keys for automobiles. The tasks to be completed for this application are: (1) identify the blank type of the original, (2) measure the unique cut pattern or "code" that activates the tumblers, (3) correct deviations, possibly due to wear, from manufacturer specified acceptable cut profiles, and (4) grind the duplicate. There are over three hundred blank types in use in the U.S. alone, each varying in length, width, groove pattern on each side, and outline of the handle. These variations are often subtle, making identification difficult, even for a human. Part identification is done with a head-eye camera configuration that captures two sets of parameters: outline information and surface depth profiles obtained by directing a laser plane onto the object surface. After the blank type is identified, the cut pattern is read from the original. Then reconstruction laws based on manufacturers specifications are used to determine the original cuts made on the factory original. This process corrects for wear or previous sloppy duplication yielding a perfectly functioning duplicate even from a worn and "sticky" original. The corrected cut profile is then passed to a grinding system for cutting the duplicate. Actual implementation of the procedure shows a consistent success rate over 97%, with the robot system maintaining consistent grinding tolerances within 0.003 ".