Teleoperation Data Is the New Oil
The race in robotics is not for better motors. It is for hours of demonstrated motion.
The argument
Sim-to-real is a tax you pay twice. The simulator that trains the policy never quite matches the friction, the lighting, the wear. Closing that gap is most of the engineering effort.
Embodiment raises the stakes. A language model that is wrong produces a bad sentence; a robot that is wrong produces a bad outcome in a room with people standing in it.
The hard part of a robot is not the motor; it is the policy. Learned control has closed gaps that hand-tuned controllers never could, but the data to train it stays expensive and stubbornly physical.