The plan is a recreation of Jer Thorp's “smart rockets” — a classic demonstration of a genetic algorithm. A population of rockets is spawned with a randomised “DNA” of thrust vectors; each generation they fire those thrusts in sequence, flying until they crash, time out, or reach the target. Rockets are then scored on how close they got (with penalties for hitting obstacles), the fittest genes are combined and mutated, and the cycle repeats. Over time the population “learns” a flight path to the goal.
Inspired by, and following along with, Daniel Shiffman's Coding Train tutorial.