Drones are stupid. This isn't a subjective judgement; without the hands of a canny pilot, most flying quadcopters or remotely controlled planes will crash into obstacles in their path, like the world's largest, clumsiest insects. That's fine for casual flight in open fields, but if drones are ever to navigate dense obstacles like forests or the insides of buildings, they need to be a lot smarter. Thanks to a project by MIT's Computer Science And Artificial Intelligence Laboratory (CSAIL), drones can now navigate dense obstacle courses without crashing. It works for quadcopters:
And fixed-wing airplanes too:
Here's how it works. An algorithm (made by CSAIL and available on Github] plots the open spaces the drone needs to fly through. This is based on work CSAIL did for ATLAS, their walking robot entrant into DARPA's Great Robotics Challenge. Here's how MIT describes it:
“Rather than plan paths based on the number of obstacles in the environment, it's much more manageable to look at the inverse: the segments of space that are 'free' for the drone to travel through,” says recent master's graduate Benoit Landry, who was first author on a related paper just accepted to the IEEE International Conference on Robotics and Automation (ICRA). “Using free-space segments is a more 'glass-half-full' approach that works far better for drones in small, cluttered spaces.”
That's great for quadcopters, which move calmly through space, but doesn't quite work for the fast-flying planes. Instead, they created a separate tool to guide fixed-wing drones. Again, from CSAIL:
PhD student Anirudha Majumdar showed off a fixed-wing plane that is guaranteed to avoid obstacles without any advanced knowledge of the space, and even in the face of wind gusts and other dynamics. His approach was to pre-program a library of dozens of distinct “funnels” that represent the worst-case behavior of the system, calculated via a rigorous verification algorithm.
“As the drone flies, it continuously searches through the library to stitch together a series of paths that are computationally guaranteed to avoid obstacles,” says Majumdar, who was lead author on a related technical report. “Many of the individual funnels will not be collision-free, but with a large-enough library you can be certain that your route will be clear.
As drones move away from simple remote-controlled toys and become more autonomous flying tools, programs like these will keep them flying safely through unfamiliar terrain.
Watch quadcopters navigate obstacles below:
