An automatic robot unstacking system based on binocular stereo vision

Unstacking is a process widely used in many industrial applications. This paper proposes an automatic unstacking system using an industrial robot and stereo vision. To detect a package to be picked, a shape-based matching (SBM) method is applied on 2D images. The 3D position of a selected package among pick-up candidates is calculated by acquiring a pair of correspondence points in the left and right images of a binocular camera. In order to improve the 3D pose estimation performance, the SBM method is also used instead of the conventional stereo matching method. Since SBM is a robust image processing algorithm, the proposed vision system can be employed for various general-purpose applications. Furthermore an unstacking strategy, in which the robot automatically picks packages in each layer of the stack, is established. Experimental results on a stack of commercial packages validated the 3D positioning accuracy of the vision system and the robot successfully manipulates the stacked packages.