Learning to fly live — Project funded by the FWF
An exciting new funding opportunity in Austria for cutting edge, high-risk and unconventional research by the Austrian Science Fund (FWF) is now available to researchers from all disciplines. Read about a drone research project that got funded and my trip to Vienna.
Last Monday, I was honored to be invited to Vienna by the Austrian Science Fund (FWF) for a meeting and picture with FWF President Dr. Klement Tockner and the Federal Minister for Education, Science and Research of Austria, Dr. Heinz Faßmann, to promote the new research funding programme of the FWF, called “1000 Ideas” (“1000 Ideen” in German). This programme provides a unique opportunity to fund high-risk, unconventional research. In the first round, over 400 proposals were submitted but only 24 were funded. You can read more about the programme and the other funded projects on the website of the FWF.
In the funded project “Learning to Fly Live”, a drone will teach itself how to fly similar to how a human develops motor skills — by trial and error and by building on past experience. Starting from the simplest tasks such as hovering, the drone should gradually explore its motor skills, learn to understand the cause and effect of its motor control, and gain more experience and skills through constant practice until finally even challenging movements are possible. To that end, we will combine elements of continual learning with novel, AI-based algorithms. The innovative and high-risk element is that everything happens live on the drone. This approach carries significant risks. Drones require continuous control inputs to stabilize in the air. Crashes are almost always catastrophic to the system’s hardware. At the same time, the computing resources available onboard are limited because weight and power consumption directly reduce flight time. This makes the use of the latest AI algorithms a challenge and makes learning advanced AI algorithms on the device seemingly impossible. Nevertheless, we believe that with our approach, it will be possible to teach a drone how to fly complex and fast maneuvers with better precision and greater agility than previously possible. In addition, we hypothesize that rather than simply learning to repeat desired behavior for each new maneuver from scratch, the system will be able to build on its experience and reason about the optimal control sequence even for new maneuvers not previously encountered.
If successful, the project has the potential to initiate a paradigm shift in autonomous system navigation and control — away from the current trend of big data-driven, offline-trained algorithms with black box character, towards a more hardware-related and task-oriented design of AI algorithms. The ability to use self-learned knowledge about oneself to master new tasks can pave the way for the next generation of intelligent mechatronic systems — beyond the scope of drones.
