A new drone crash avoidance system has been created by a researcher from MIT’s Computer Science and Artificial Intelligence Lab (CSAIL).
Andrew Barry has developed the obstacle-detection system to enable flying drones to autonomously manoeuvre through forests and other urban areas at upwards of 30 mph.
Check out the video below to see the autonomous drone software in action calculating the correct path the drone should take through the trees. CSAIL PhD student Andrew Barry the developer of the system explains more:
Everyone is building drones these days, but nobody knows how to get them to stop running into things. Sensors like lidar are too heavy to put on small aircraft, and creating maps of the environment in advance isn’t practical. If we want drones that can fly quickly and navigate in the real world, we need better, faster algorithms.
The software is capable of running 20 times faster than anything currently available on the market and includes a stereo-vision algorithm enabling the drone to detect objects and recalculate its path in real-time.
For more information on the new autonomous drone anti-collision software jump over to the MIT website for details via the link below