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

Sulla's R2d2 Bb-8 Mashup Robot Project
Thought you guys might find the project I am working on interesting. Its an R2D2 BB-8 mashup robot. So far coming along...

Tmesserschmidt's Meet Robot Betty9
Meet Robot Betty9! My sassy 6 tall fembot. She has two servos in each arm, two in her neck, blue LEDs in her eyes, two...

Adfe74's Meet Suki 6Dof Leg Dynamixel Ax-18A
Meet SUKI, my 6 DOF leg biped robot using inverse kinematics. This Video shows body IK rotation and translation, the IMU...