Home › Hard problems › Physical AI, robots and autonomy

Physical AI, robots and autonomy

Batteries limit every robot

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

a humanoid or dronea work shift, say 8 hoursruns 1–2 hoursflat, on the charger0h1h2h3h4h5h6h7h8henergy per kilogramyearsonly a few percent better a year
Humanoids and drones run for only 1–2 hours, and battery energy per kilogram improves only a few percent a year.

Why it is still open

Humanoids and drones run 1–2 hours. Energy density improves only a few percent a year.

An experiment one person can run in 8 weeks

No solo build. Track how battery energy per kilogram improves each year.

Verdict: Follow, don't build

It is a chemistry and manufacturing problem.

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.

PreviousFlying and moving without GPS

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