Home › Hard problems › Physical AI, robots and autonomy

Physical AI, robots and autonomy

Flying and moving without GPS

Solo: possibleOne person can test a narrow slice of it.

GPS jammed or blockedindoors, undergroundminute 1minute 2minute 3solid: where it really isdashed: where it thinks it isdrift
Without GPS, a drone or robot guesses its position from its own motion, and the small errors add up to real drift within minutes.

Why it is still open

Drones and robots lose position indoors, underground or when GPS is jammed, and drift builds up within minutes.

An experiment one person can run in 8 weeks

On a public drone flight dataset, compare 3 open visual positioning methods on drift per minute.

Verdict: Solo: possible

Public datasets exist; real flights need hardware.

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.

PreviousProving an autonomous system is safeNextBatteries limit every robot

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