Smart Drones Fly Without GPS
Watch this video to see how Carnegie Mellon University’s Kenji Shimada made a smart drone that flies in environments without GPS signals — such as tunnels and construction sites — and avoids moving objects.
“To our knowledge, this is the first time 3D scanning with an autonomous drone has been done in dynamic, under-construction tunnel environments,” said Zhefan Xu , the lead Ph.D. student of the drone project.
Transcript
00:00:08 We make a smart drone that flies in the environment without GPS signals and avoiding moving objects. So this type of drone has a lot of practical applications especially in the construction industry. We hear about drones every day. There are 900,000 drones in the United States registered today, but number of commercial drones has been increasing quickly. And those commercial drones are great in outdoor open environment with GPS signals. They don't work well in an indoor or underground environment. Another limitation is inability to avoid moving objects in a confined space. Our research overcomes these limitations by giving the drone an eye and the brain.
00:01:04 Our drone has a camera and powerful onboard computers with smart algorithms. Our drone uses a camera to make a three dimensional map of the environment and then find its location on the map. The camera information is used to detect moving objects. And then our pass planning algorithm will predict the movement of those objects and then adjust the flight paths to avoid collisions. Our project has been supported by industry sponsors. They built tunnels for cars and trains. and they wanted to fly a drone in the tunnel to measure the 3D shape of a new tunnel being excavated so that they can compare that data with their design data.
00:02:01 We are so excited that our drone can fly through the tunnel, avoiding moving objects, and measuring the 3D shape accurately. Our sponsors are interested in using our technology in actual construction operation, and we have been discussing how to make a practical version of our drone system. Our research continues, and my students and I are excited about the next phase of this research and technology development.