Watch a drone autonomously avoid obstacles at 50 km/h [VIDEO]
MIT-developed algorithm that runs 20 times faster than existing software to help the drone detect objects in its field of view.
CAMBRIDGE, Mass. — A PhD researcher the the Massachusetts Institute of Technology’s Computer Science and Artificial Intelligence Lab (CSAIL) has developed an obstacle-detection system that allows a drone to narrowly avoid obstacles at more than 50 kilometres per hour….autonomously.
Andrew Barry developed the autonomously flying machine’s system as part of his these with MIT professor Russ Tedrake. He has developed a stereo-vision algorithm that runs 20 times faster than existing software to help the drone detect objects and build a full map of its surroundings in real-time.
The software operates at 120 frames per second and extracts depth information at a speed of 8.3 milliseconds per frame.
The drone weighs just over a pound and has a 34-inch wingspan. It was made from off-the-shelf components and cost about $1,700, including cameras on each wing and two CPU processors similar to those you’d find in your cell phone.