Roboceptions new CADMatch module, coupled with its rc_visard stereo sensor, enables robotic systems to reliably detect, localize and pick objects from unmixed load carriers, fully independent of the object‘s position and orientation. After feeding a CAD-based template into the CADMatch Module and defining one (or several) grasp point(s) on the relevant object with just a few mouse clicks, the solution will easily deliver task-relevant information for robotic applications such as machine tending.

The rc_reason CADMatch module uses a CAD model as input and relies on AppliedAI-based machine learning processes: A machine learning approach enables the usability, while a classical refinement ensures accuracy – this combination of ‘the best of both worlds’ is AppliedAI at its best!

Not a Vision Expert? Not a Problem!  Intuitive user interfaces make the implementation as easy as can be: Non-experts are hence able to configure the grasp points and implement the pick-and-place process with just a few mouseclicks. The software allows the specification of one or more grasp points per object, hence enabling picking by a two-finger gripper or a suction device.