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
Budel0's R.O.O.S.T.E.R.
R.O.O.S.T.E.R: 6-wheeled Wild Thumper with 5-DOF arm, netbook, EZ-B control, six motors, ESCs, ping sensor and planned...
Dunning-Kruger's Ez Dog (Inmoov Frankendog Failure)
Failed experiment prototype; planning a new version with design improvements and fresh ideas.
Kenny's Radio Shack Robie Meets Roomba
Convert a vintage 1984 Radio Shack Robie into a Roomba-mounted retro cleaning robot with ez-b, camera, and custom arms.
