3D vision system assists in robotic bin picking

Bin picking, the task of picking random objects from a container or bin in vision-guided robotics, presents a number of different challenges. In order for a robot to be able to accurately detect the shape, size, position, and alignment of an object, a suitable vision system must be selected. One particularly effective method for this is 3D machine vision cameras.

bsAutomatisierung GmbH, a company that specializes in the development and construction of systems for fast and precise loading and unloading of production machinery and parts handling, recently installed a system that utilizes Ensenso N10 stereo 3D cameras from IDS Imaging Development Systems in order to identify and pick parts. Ensenso N10 cameras feature two 752 x 480 pixel global shutter CMOS image sensors, and a USB interface. bsAutomatisierung utilized the cameras for its bin picking robot cells, which automatically pick individual, randomly aligned parts out of a container and pass them on to downstream production processes.

One of the features of the N10 cameras is an infrared pattern projector, which projects a random pattern of dots onto the object to be captured, allowing structures that are not visible or only faintly visible on the surface to be enhanced or highlighted. This is necessary becausestereo matching requires the identification of "interest points" in a given image.

Once the interest points are identified, the object is then captured by the two CMOS sensors and3D coordinates are reconstructed for each pixel using geometric relations based on the triangulation principle. Even if parts with a relatively monotone surface are placed in the bin, a 3D image of the surface can be generated without additional technical effort, according to IDS.

Page 1 |Page 2