Home › Hard problems › Physical AI, robots and autonomy

Physical AI, robots and autonomy

Robot hands that cope with new objects

Follow, don't buildNeeds labs, hardware or big teams. Learn it and watch it.

In the labhard, known block: heldOutside the labsoft towel: slipsegg: crushednew shape: missed?the fingers feelalmost nothing
A robot hand that works on lab blocks fails on soft, fragile or unfamiliar things, because touch sensing and fine control are weak.

Why it is still open

Folding laundry or handling soft and unfamiliar things fails outside the lab. Touch sensing and fine control are weak.

An experiment one person can run in 8 weeks

Not a solo build. Watch the open robot models (such as Physical Intelligence's π0 family).

Verdict: Follow, don't build

It needs hardware and large data.

The solo test behind the verdict

  1. Can it be measured? There is a number that shows you did better, such as an error rate, a catch rate or a cost per answer.
  2. Is it cheap to try? It runs on a laptop, free open models and open data, or under about ₹50,000 of rented GPU time.
  3. Is there a public yardstick? A benchmark or dataset others use, so your result can be compared and believed.
  4. Would a small win get noticed? A lab, a funder or a customer would care about a 10% improvement, not only a full solution.

Four yeses means Solo: strong. Two or three means Solo: possible. Fewer means Follow, don't build.

NextToo little robot training data

All 79 hard problems · Working on this, or know of a result we missed? basant@cleandataengineering.ai