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.
Other robots from Synthiam community

Ezang's My New Update Arm Robot 11/14/2019
My new update to the Robot arm, added a 5th servo to the gripper - using auto-position - Ez builder software and Ezb4...

Mitzeljk's Meet Modi
This is Modi (Mobile, online, digital , interface) , my first attempt at ever building a robot. I am new to pretty much...

Ptp's Star Wars Bb-8 Robot Suitcase
To get in the spirit of the Star Wars holiday ... I decided to share this project ... still in progress ... and...