Development of a structured-light sensor based bin-picking system using ICP algorithm

This paper proposes a general-purpose structured-light sensor based bin-picking system. At first, to determine the workpiece to be picked, a geometric pattern matching (GPM) method with respect to the 2D image is applied. A structured-light sensor with gray-coded patterns is employed to get the reliable 3D range image for the pick-up candidate. The pose of the object is acquired by just comparing the 3D point cloud between models in database and a range image acquired from the structured-light sensor through iterative closest point (ICP) algorithm in contrast with the conventional bin-picking systems which require complete knowledge of the object. Through experiments on an industrial workpiece, we validate that the proposed vision system accurately measures the 3D pose of complex objects.