There have been plenty of companies and startups touting autonomous drones that require no human control and that can avoid obstacles and fly on their own without any outside input, but many of these are just empty promises that have yet to be fulfilled. Thanks to Silicon Valley tech company Skydio though, the promise of a fully autonomous drone has finally been realized. Founded by members from Google X’s Project Wing and researchers from MIT, Skydio has developed a camera drone that will follow people and avoid any obstacles in its path, such as tree branches, all on its own.
Showing off their creation in a video, Skydio’s drone is seen following people as they jog or bike through a forest, gracefully avoiding obstacles in its path with some serious agility. Skydio’s drone is so dynamic, in fact, that the team’s attempts to spring surprise objects as obstacles on the drone to trip it up proved futile – the drone is lightning fast and extremely quick to react, avoiding anything thrown in its path while remaining on course. “All of the footage is just taken from our normal testing. Nothing was staged and it’s all fully autonomous,” said Adam Bry, co-founder of Skydio. “All of the navigation is done entirely based on a multi-camera array with all computation done onboard on a state of the art mobile CPU.”
Cultivating his impressive engineering research and background from MIT at Google X’s Project Wing, Bry and fellow researcher and Skydio co-founder Abe Bachrach were able to demonstrate an autonomous fixed-wing drone that successfully navigated an underground parking garage. It’s not hard to see how this experience has translated into the autonomous drone that Skydio has created, incorporating this research into more accessible consumer drone products through their own company. The key to the autonomy in Skydio’s camera drone is a smaller and less expensive LIDAR sensor that makes this advanced, autonomous technology that can control drones without human interaction available in consumer products.
It’s not just that Skydio’s drone is autonomous; it’s also adapting and learning from its environment. The drone uses “all of the available information from the environment to make intelligent decisions to get smooth, intelligent behavior – similar to what an expert pilot would do,” Bry notes. The built-in software and the advanced camera hardware that sit atop the Skydio drone are integral to the drone’s ability to carve out and fly its own path – the two work in tandem so that the drone doesn’t just detect and avoid potential obstacles, but can map out and navigate a path that will prove fastest, clearest and most efficient. Start calling the Skydio drone the little drone that could.