(task) Drones that dodge obstacles without guidance can pursue you like paparazzi - MIT Technology Review

GRS USRS

4 cover

AI, machine intelligence, drones, privacy,

>
> https://www.technologyreview.com/s/610246/drones-that-dodge-obstacles-without-guidance-can-pursue-you-like-paparazzi/?google_editors_picks=true <https://www.technologyreview.com/s/610246/drones-that-dodge-obstacles-without-guidance-can-pursue-you-like-paparazzi/?google_editors_picks=true>
>
> Drones that dodge obstacles without guidance can pursue you like paparazzi
>
> A skilled autopilot function will make drones far more ubiquitous and useful.
>
> Will Knight </profile/will-knight/>
>
> Artificially intelligent drones are coming—and they’re going to shoot some really sick snowboarding videos along the way.
>
> A startup called Skydio <https://www.skydio.com/> is launching the first drone capable of visually imprinting on a person, a bit like a needy duckling, and then following him or her around, deftly navigating around trees, pylons, and other obstacles while shooting video. In other words, your very own robotic, airborne paparazzo.
>
> The new drone, called R1, will be marketed as an easy way to capture action like biking, skiing, or rafting in high-quality video. But Adam Bry <https://www.technologyreview.com/lists/innovators-under-35/2016/inventor/adam-bry/>, founder and CEO of Skydio, says his company is thinking about how it could be used to inspect roofs for damage and to patrol properties.
>
> Aerial vehicles are already being used to inspect buildings, perform security patrols, and tally inventory inside warehouses. But to navigate a complex and unfamiliar environment, a drone typically needs to be controlled by an expert pilot on the ground, or else its surroundings must be mapped in great detail.
>
>
>
>
> Hayk Martiros
> The R1 drone uses deep learning <https://www.technologyreview.com/s/513696/deep-learning/> to recognize a person. It employs conventional methods for mapping and navigation, along with a mathematical approach to path planning that Bry has been working on since his time as a student at MIT. One of his projects involved teaching a plane with a two-foot wingspan to fly through a busy garage without crashing (see “Daredevil drone flies through the trees like an ace <https://www.technologyreview.com/s/600925/daredevil-drone-flies-through-the-trees-like-an-ace/>”).
>
> Self-flying drones are harder to perfect than self-driving cars. Mapping the environment and planning a path must be done in three dimensions rather than two, and drones typically cannot carry much in the way of computing power.
>
> But navigating a busy physical world is a fundamental challenge for machines of many kinds, so advances in drone control could perhaps prove useful for AI more broadly.
>
> Researchers at MIT recently announced another technique that could further improve the agility of drones. A group led by Russ Tedrake <https://groups.csail.mit.edu/locomotion/russt.html>, a professor at MIT’s Computer Science and Artificial Intelligence Lab (CSAIL), published a paper <http://link.email.dynect.net/link.php?DynEngagement=true&H=WAA0HYy4enWklLGLVOCoftvRiKxkwcx7028A%2BNZlWSzSEaUD3cyAX4UDFn296210VqjFVgcUi%2BEV3J%2Bc%2FzmxW3ghCBx%2B7t0XednjlsvJVg0MfzqDqwbk5Oxp9m7zpfEVrxRtoqF5xS0%3D&G=0&R=http%3A%2F%2Fgroups.csail.mit.edu%2Frobotics-center%2Fpublic_papers%2FFlorence17.pdf&I=20180212161643.0000008fd904%40mail6-33-usnbn1&X=MHwxMDQ2NzU4OjVhN2RjMzA3NDEzYzBlMGEwYzcxYWJiYTs%3D&S=aCQOMCVAFSFymVi5pg_m8eyRY4FT2b_iatrAR7pD8zo> showing how some understanding of uncertainty can help a drone navigate through a complex environment even at high speed. Embracing uncertainty is an idea that could have broad implications in AI (see “Google and others are building AI systems that doubt themselves <https://www.technologyreview.com/s/609762/google-and-others-are-building-ai-systems-that-doubt-themselves/>”).
>
> The R1, which costs $2,499, features 13 cameras for capturing its surroundings, and a compact chipset for AI applications called the Jetson <https://www.nvidia.com/en-us/autonomous-machines/embedded-systems-dev-kits-modules/> TX1, designed by Nvidia. The drone uses a software and hardware stack that the company calls the Skydio Autonomy Engine.