|
NEAR-OPTIMAL-TIME PATH PLANNING IN CAD-GUIDED PART DIMENSIONAL INSPECTION
Weihua Sheng* Ning Xi* Mumin Song** Yifan Chen**
* Electrical and Computer Engineering Dept.,
Michigan State University, East Lansing, 48824, USA
** Scientific Research Laboratory,
Ford Motor Company, Dearborn, MI 48121, USA
A CAD-guided vision sensor planning system is developed in our lab. To improve the efficiency of the inspection system, the path planning problem is rendered as a Traveling Salesman Problem(TSP). A new approach is developed to solve the TSP into its sub-optimality quickly. First, viewpoints are clustered into several groups. Second, clustered Traveling Salesman Problem is solved by favoring the inter-group paths. Experimental results on real parts show that the proposed approach is effective.
Keywords: CAD, Path Planning, Traveling Salesman Problem
Session slot T-Tu-A21: Posters of Manufacturing and Instrumentation/Area code 1a : Advanced Manufacturing Technology
 | 