6 Ways Robotics Can Help Protect Our Oceans
February 13, 2020
Wacom One review: A great, no-frills drawing tablet for budding artists
February 13, 2020
Show all

How We Trained a Deep Neural Pilot to Autonomously Fly the Skydio Drone

A version of this article was originally published on Medium. The views expressed here are solely those of the authors and do not represent positions of IEEE Spectrum or the IEEE.

We here at Skydio have been developing and deploying machine learning systems for years due to their ability to scale and improve with data. However, to date our learning systems have only been used for interpreting information about the world; in this post, we present our first machine learning system for actually acting in the world.

Using a novel learning algorithm, the Skydio autonomy engine, and only 3 hours of “off-policy” logged data, we trained a deep neural network pilot that is capable of filming and tracking a subject while avoiding obstacles.