Method and system to generate a 3D model for a robot scene

A control system comprising:

• a controller configured to:
• determine a predefined collision free robot path;
• move a robot along the predefined collision free robot path;
• scan an industrial scene with a scanning sensor mounted on the robot while moving along the predefined collision free robot path to obtain first scanned images;
• store scanned images of the industrial scene in a memory;
• construct a 3D model of the industrial scene based on the scanned images;
• perform a 3D object detection and recognition analysis of the 3D model;
• based on the 3D object detection and recognition analysis of the 3D model failing to meet a detection and analysis threshold, update the 3D model by moving the robot along one or more first new collision free robot paths and scanning the industrial scene with the scanning sensor based on moving the robot along the one or more first new collision free robot paths, wherein the detection and analysis threshold indicates whether the 3D model is sufficient to detect and recognize an object;
• based on the 3D object detection and recognition analysis of the 3D model meeting the detection and analysis threshold, perform an object grasping and position analysis of the 3D model;
• based on the object grasping and position analysis failing to meet a grasping and position analysis threshold, update the 3D model by moving the robot along one or more second new collision free robot paths and scanning the industrial scene with the scanning sensor based on moving the robot along the one second new collision free robot paths, wherein the grasping and position analysis threshold indicates whether the 3D model is sufficient to direct the robot to grasp the object;
• and
• based on the object grasping and position analysis meeting the grasping and position analysis threshold, direct the robot to grasp and pick up the object.