My robot would be sitting at a table, and it would look down at the objects on that table. It would be able identify the objects on the table: salt, pepper, a can of beer, a knife, a plate a spoon, and carrots on the plate. It would also know the coordinates of each object in 3D space of each object. Knowing that it would reach out and pick up the beer. I think Tensorflow can do some of this already. Microsoft Cognitive vision gives you the objects it sees, but not the locations.
Discover more robots
DJ's Elastic Band Shooter
Elastic band shooter for hexapod in Synthiam ARC: servo uses a hexapod leg to raise/lower the body for vertical aiming....
DJ's Jd Humanoid Controlled By Microsoft Kinect
Control Kinect with Synthiam ARC using Kinect plugins for EZ-Builder-simple setup plugin and a highly configurable PTP...
Ezang's MEASURING DISTANCE TO OBSTACLE USING THE HC-SR04
Measure distance in inches with HC-SR04 on Arduino using Synthiam ARC serial monitor; converts pulse microseconds to...
