Tordivel has released Scorpion 3D Stinger for Robot Vision, software designed for robot part picking from a conveyor belt, a pallet or a crate. Scorpion 3D Stinger captures images, identifies and locates the product and sends the ID and 3D location to a robot.
The automation software identifies and locates any part in 3D and accurately locates the 3D coordinates in space. To teach the system, the part's physical dimension is described in a simple text file. This is used by Scorpion 3D Stinger together with information from the camera images, to calculate the most accurate picking position in space. The system combines the 3D stereo vision images with the 3D data to provide a robust object detection system.
The basis for the product is Scorpion Vision software, developed by Tordivel. This is a generic software package for 2D and 3D machine vision. Image analysis with the software does not require programming.
Scorpion has built-in modules for communication with all industrial robots and is easily adapted to any motion control unit. The product contains a large toolbox for 2D and 3D imaging and can easily be extended with new tools. The system is an open framework built around the script language python and uses only well known industry standard interfaces. Cameras from all major camera vendors can be used with the software.
Scorpion 3D Stinger for Robot Vision was developed in the AutoCast R&D project sponsored by the Norwegian Research Council and coordinated by Jøtul. The software is currently being tested at Jøtul in manufacturing of cast iron stoves in Fredrikstad, Norway.
