18:46 13 February 2018
For drones that are used to navigate a busy environment, such as a forest or a warehouse at high speed, their ability to know their exact location and where they are going is of utmost importance. However, this is often not possible because unlike smart cars, they do not have the ability to process enormous amount of data in real-time.
Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAI) said that this can be addressed through the use of a NanoMap. This is an alternate method of navigation and obstacle avoidance that works by collecting 3D data about the environment. The collected data is then stored in a series of snapshots instead of a single map, allowing drones to react faster because they are processing less information each second.
CSAIL’s Peter Florence said: “Because we’re not taking hundreds of measurements and fusing them together, it’s really fast,” Florence tells The Verge. “And when we want to plan our way around the world, we just search back through the views we already have.”
“We have drones that can fly around now, but there’s nothing that’s as good as a hawk, for example, that can just blaze through a forest at top speeds,” says Florence. “When you’re going that fast, you just can’t expect to have perfect geometric measurements of the world. You need something else.”
“I think just working on robots that can move really fast and gracefully is fun, so that’s the main thing.”
Disclaimer: Supanet is not responsible for, and disclaims any and all liability for the content of comments written by contributors to this website