Measuring up to 10 x 10 x 10 meters, the Flying Machine Arena (FMA) consisted of a high-precision motion capture system, a wireless communication network, and custom software executing sophisticated algorithms for estimation and control.

The motion capture system of the Flying Machine Arena could locate multiple objects in the space at rates exceeding 200 frames per second. While this may seem extremely fast, the objects of interest could move at speeds in excess of 10 m/s, resulting in displacements of over 5 cm between successive snapshots. This information was fused with other data and models of the system dynamics to predict the state of the objects in the future.

This knowledge was used to determine which commands the vehicles should execute next in order to achieve their desired behavior such as performing high-speed flips, balancing objects, building structures, or engaging in a game of Paddle Ball. The system then wirelessly broadcasted the commands to the vehicles, which were executed with the aid of onboard computers and sensors such as rate gyros and accelerometers.

Although various objects could fly in the Flying Machine Arena, the predominant machine of choice was the quadcopter due to its agility, mechanical simplicity and robustness, and ability to hover. Furthermore, the quadcopter is a great platform for research in adaptation and learning: it has well-understood, low-order first-principle models near hover while being difficult to characterize when performing high-speed maneuvers due to complex aerodynamic effects. These effects were handled with algorithms that initially use first-principle models to approximate what a vehicle should do to perform a given task, then learn and adapt based on flight data.