The research, conducted by ESA's Advanced Concepts Team and the Micro Air Vehicle Laboratory (MAVLab) of TUDelft, is detailed in the latest issue of Science Robotics.

"Through a long-term collaboration, we've been looking into the use of trainable neural networks for the autonomous oversight of all kinds of demanding spacecraft manoeuvres, such as interplanetary transfers, surface landings and dockings," said Dario Izzo, scientific coordinator of ESA's ACT.

"In space, every onboard resource must be utilised as efficiently as possible - including propellant, available energy, computing resources, and often time. Such a neural network approach could enable optimal onboard operations, boosting mission autonomy and robustness. But we needed a way to test it in the real world, ahead of planning actual space missions.

"That's when we settled on drone racing as the ideal gym environment to test end-to-end neural architectures on real robotic platforms, to increase confidence in their future use in space."

Drones compete to achieve the best time through a set course within the Cyber Zoo at TU Delft, a 10x10 m test area maintained by the University's Faculty of Aerospace Engineering. Human-steered 'Micro Air Vehicle' quadcopters alternate with autonomous counterparts using neural networks trained in various ways.

"The traditional way that spacecraft manoeuvres work is that they are planned in detail on the ground then uploaded to the spacecraft to be carried out," explained ACT Young Graduate Trainee Sebastien Origer. "Essentially, when it comes to mission Guidance and Control, the Guidance part occurs on the ground, while the Control part is undertaken by the spacecraft."

The space environment is unpredictable, with potential for unforeseen factors such as gravitational variations and atmospheric turbulence. When a spacecraft deviates from its planned path, its control system works to return it to the set profile, which can be costly in resource terms.

Sebastien added, "Our alternative end-to-end Guidance and Control Networks, G&C Nets, approach involves all the work taking place on the spacecraft. Instead of sticking to a single set course, the spacecraft continuously replans its optimal trajectory, starting from the current position it finds itself at, which proves to be much more efficient."

In computer simulations, neural nets performed well when trained using 'behavioural cloning', based on exposure to expert examples. The researchers turned to drones to test this approach in the real world.

"There's quite a lot of synergies between drones and spacecraft, although the dynamics involved in flying drones are much faster and noisier," commented Dario.

"When it comes to racing, the main scarce resource is time, but we can use that as a substitute for other variables that a space mission might prioritize, such as propellant mass. Satellite CPUs are quite constrained, but our G&CNETs are surprisingly modest, perhaps storing up to 30 000 parameters in memory, which can be done using only a few hundred kilobytes, involving less than 360 neurons in all."

For the G&CNet to be optimal, it should send commands directly to the actuators. For a spacecraft, these are the thrusters; for drones, they are the propellers.

"The main challenge that we tackled for bringing G&CNets to drones is the reality gap between the actuators in simulation and in reality," said Christophe De Wagter, principal investigator at TU Delft. "We deal with this by identifying the reality gap while flying and teaching the neural network to deal with it. For example, if the propellers give less thrust than expected, the drone can notice this via its accelerometers. The neural network will then regenerate the commands to follow the new optimal path."

"There's a whole academic community of drone racing, and it all comes down to winning races," said Sebastien. "For our G&CNets approach, the use of drones represents a way to build trust, develop a solid theoretical framework and establish safety bounds, ahead of planning an actual space mission demonstrator."

Related Links
MAVLab
Advanced Concepts Team
UAV News - Suppliers and Technology