Using an elastic net spread between the three drones, they can toss a ball to themselves or shoot it through a hoop being held by two other drones. The most amazing part is that this isn’t a programmed routine. It’s all improvised, and they learn as they go.
The algorithms that are used include an optimality-based real-time trajectory generation for the catching manoeuvre, a time-varying trajectory following control strategy to control the individual vehicles under consideration of the forces induced by the net, and learning algorithms that accommodate model inaccuracies in the aiming of the ball.
It’s more than amazing — it’s downright unnerving. [IDSC, ETH Zürich]