{"id":3593,"date":"2018-09-11T20:05:30","date_gmt":"2018-09-11T20:05:30","guid":{"rendered":"https:\/\/athis-consulting.com\/news\/?p=3593"},"modified":"2018-10-12T10:31:00","modified_gmt":"2018-10-12T17:31:00","slug":"insect-inspired-vision-system-helps-drones-pass-through-small-gaps","status":"publish","type":"post","link":"https:\/\/athis-technologies.com\/news\/video\/2018\/insect-inspired-vision-system-helps-drones-pass-through-small-gaps\/","title":{"rendered":"Insect-Inspired Vision System Helps Drones Pass Through Small Gaps"},"content":{"rendered":"

Bees\u00a0<\/a> make this work through a sort of minimalist brute-force approach to the problem: They fly up to a small hole or gap, hover, wander back and forth a little bit to collect visual information about where the edges of the gap, and then steer themselves through. It\u2019s not fast, and it\u2019s not particularly elegant, but it\u2019s reliable and doesn\u2019t take much to execute.<\/p>\n

Reliable and not-taking-much to execute is one way to summarize the focus of the next generation of practical robotics\u2014in other words, robotic platforms that offer affordable real-world autonomy. The University of Maryland\u2019s Perception and Robotics Group has been working on\u00a0a system that allows a drone to fly through very small and completely unknown gaps\u00a0using just a single camera and onboard processing. And it\u2019s based on a bee-inspired strategy that yields a success rate of 85 percent.<\/p>\n

We\u2019ve posted before about\u00a0autonomous drones\u00a0flying through small gaps, but the big difference here is that in this case, the drone has no information about the location or size of the gap in advance. It doesn\u2019t need to build up any kind of 3D map of its environment or model of the gap, which is good because that would be annoying to do with a monocular camera. Instead, UMD\u2019s strategy is to \u201crecover a minimal amount of information that is sufficient to complete the task under consideration.\u201d<\/p>\n

To detect where the gap is, the drone uses an optical-flow technique. It takes a picture, moves a little bit, and then takes another picture. It identifies similar features in each picture, and thanks to parallax, the farther away features behind the gap will appear to have moved less than the closer features around the gap. The edges of the gap are the places where you\u2019ve got the biggest difference between the amount that features appear to have moved. And now that you know where all those things are, you can just zip right through!<\/p>\n