← Blog

SOLO — Teaching a Neural Network to Fly, From Scratch

I wanted to watch an AI become independent — literally — so I taught a neural network to fly, then cut the cord.

SOLO neural-flight build: a ship flying a gated obstacle course with blue sensor rays firing, the live neural-network visualization lit up below, learning curve at 100%, generation 30.

What it is

SOLO is a real neural network, hand-written in one file (forward pass, backprop, and a full neuroevolution loop — no libraries), that learns to fly a gated obstacle course. It can learn by cloning your piloting (with DAgger coaching to correct its drift), or by teaching itself from scratch with no teacher at all. Then it flies a course it has never seen, and you can watch the network fire live as it does.

How it’s built

  • A from-scratch MLP with forward + backprop + SGD with momentum; output[0] steers via tanh, output[1] throttles via sigmoid.
  • Two learning paths: behavioral cloning (+ DAgger) from demonstrations, and neuroevolution (population, fitness = flight progress, elitism + tournament + crossover + gaussian mutation) with no teacher.
  • Verified on the honest metric — completion of an unseen course (~91% cloning, ~95% evolution), not a misleading input-match proxy.
Close-up of SOLO’s from-scratch neural network: input nodes (sensors + goal), two hidden layers, and steer/thrust outputs, with red and blue weighted connections lighting up.
The network itself — blue edges positive weights, red negative, brightness tracking live activation.
SOLO “Watch the Fleet” mode: all 44 evolving pilot ships flying the same course at once, the current best in gold, the rest in blue.
“Watch the Fleet” — 44 pilots fly the same course at once, making natural selection visible.

On the theme

Independence is a measurable moment here: when the network stops needing you and completes a course it’s never seen, on its own.

Try it →Code →All the builds →

Shout-out

Part of the competition is cross-referencing other builders. So: shout-out to Eric Rhea — host of Summer Into AI; worth a follow if you’re tracking the competition.

Built for Summer Into AI 2026 (Competition #2), hosted by Eric Rhea. More in the build log.