Nearly all robotics research has gone into getting robots to walk. What was the point of that? It has almost no commercial value compared to wheeled transport (ok shut up about esoteric use cases). Where we need to have been focusing on is getting the robots to pick and place things better or even almost equal to a human. We need better grippers and better manipulation technology.
I'm saying why not spend all that capital and resources on getting close to passing the Robot Dexterity Turing test (I said close, because it's likely to be absolutely impossible to achieve, but then so many people say that about fusion)? I know it's fucking hard, but it's also what will make robots useful:
1. From a table on which there are about 20 screws of varying sizes strewn about confidently pick up only the eyeglass frame screw.
2. Place and screw the picked-up screw into an eyeglass frame
3. Pick up a single red m&m only from a table that has m&m strewn on it
4. Pick up a dry rice grain from a table.
5. From a small bag of various trinkets, feel around and pick out only the rubber band from it.
6. Sculpt a recognizable face on a small piece of clay
7. Assemble a standard lego set
8. Assemble a motor, including wrapping of stator wires
9. Sculpt a face into granite.
10. Draw the Mona Lisa.
No robotic hand or gripper is even close to being able to doing those.