[dheera]

Not a PI employee, but diffusion policies are like diffusion models for image generation, they generate actions from noise in multiple steps. With current compute you can't run 100+Hz control loops with that kind of architecture.

Some combination of distillation, new architectures, faster compute, can eventually attack these problems. Historically as long as something in tech has been shown to be possible, speed has almost always been a non-issue in the years afterwards.

For now even getting a robot to understand what to do in the physical world is a major leap from before.

[davidguetta]

That's not the reason, Pi0 was basically predicting at 10hz and predicting a temporal chunk up to 50 points so it could go up to 500Hz.

It's slow because the original telop is slow, and the learned controllers through imitation learning is always a bit slower.

Source : i work on this (not at PI)

[cloudbonsai]

Another practical reason is that it's dangerous.

Pi0 uses ARX robot arm which weights 3-4kg per arm. It can easily break things or harm people if you allow it to move fast.

[davidguetta]

Not really if you clamp the torque aggressively.

But yeah in general the physical world is more dangerous than we tend to think

[amelius]

You're probably right, but for some tasks I suppose you need processing speed, for example bipedal walking.