Robot Vision for Machine Tending – with No Manual Intervention
How adding a robot vision component enables precise pick-and-place for automated machine tending with 100+ different parts
The rc_reason SilhouetteMatch machine tending software module detects the position and orientation of relatively flat objects that are positioned on a plane, by matching the current scene to a previously taught template. Increased usability enables users to generate templates through the web interface by uploading a DXF-file of the object.
How adding a robot vision component enables precise pick-and-place for automated machine tending with 100+ different parts
The rc_reason SilhouetteMatch module is an optional software component that users can easily activated on board of any rc_visard or on the rc_cube and operated through the standard interface. It enables our 3D stereo sensors to detect relatively flat objects lying on a planar surface in unmixed scenes. Particularly, the 3D position and orientation of each object is determined.
The rc_reason SilhouetteMatch machine tending software module requires a template of the objects that are to be detected. Users can easily generate these templates in the web interface by uploading a DXF file.
The rc_reason SilhouetteMatch module automatically detects the base plane of the scene at hand, which is then stored on the rc_visard in order to be occluded during the sensing operation. Typical applications include machine tending or emptying load carriers of several (separated) layers of objects.
With the latest extension, SilhouetteMatch can now also be used for destacking e.g. sheets of metal. In this case, the object closest to the camera is detected as relevant plane and no base plane calibration is required.
Depending on scene/ object complexity, and especially when the base plane is detected using the point cloud, coupling the module with an rc_randomdot projector is advisable.
How adding a robot vision component enables precise pick-and-place for automated machine tending with 100+ different parts
| Hardware requirements | Any compatible 3D stereo sensor (plus rc_cube as needed) On-board installation, no additional hardware required If using plane estimation via point cloud: RandomDot Projector and IOControl Module Robotic system equipped with grasping device |
| Grasp computation time | 1 to 3 seconds (depending on object and scene) |
| Capturing mode | One-shot mode |
For more detailed information about our products and our software modules for your robot vision solution, please visit our Knowledge Base:
You would like to find out whether our portfolio is suitable for your robotic application? Simply request a feasibility study free of charge, and get a live demo of our products.
Would you like to try out one of our sensors and software solutions? Our Try-&-Buy-option gives you the chance to test our products before you decide, and to be sure you make the right choice for your application.
