{"id":350811,"date":"2021-10-08T18:53:09","date_gmt":"2021-10-08T15:53:09","guid":{"rendered":"https:\/\/en.buradabiliyorum.com\/drones-can-now-fly-through-forests-at-40kmph-run-and-hide-humans\/"},"modified":"2021-10-08T18:53:09","modified_gmt":"2021-10-08T15:53:09","slug":"drones-can-now-fly-through-forests-at-40kmph-run-and-hide-humans","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/drones-can-now-fly-through-forests-at-40kmph-run-and-hide-humans\/","title":{"rendered":"#Drones can now fly through forests at 40kmph \u2014 run and hide, humans"},"content":{"rendered":"

“#Drones can now fly through forests at 40kmph \u2014 run and hide, humans<\/strong>”
\n<\/p>\n

If you\u2019re ever lost in the woods (or on the lam), watch out for high-speed quadcopters following you through the trees.<\/p>\n

The drones can now fly through complex and unknown environments at up to 40kmph, thanks to a new AI app<\/a>roach developed at the University of Zurich.<\/span><\/p>\n

<\/a>The team says their approach reduces failure rates at high speeds by up to 10 times when compared with other state-of-the-art methods. Credit: UZH.<\/figcaption><\/figure>\n

The quadcopter\u2019s flight lessons took place in a simulation.<\/p>\n

An algorithm first piloted a computer-generated drone through a simulated environment that contained complex obstacles.<\/p>\n

This data was used to train the drone\u2019s neural network to predict a flight path based on information from onboard sensors.<\/p>\n

The system was then tested in various real-world environments, such as forests, collapsed buildings, and derailed trains.<\/p>\n

\u201cOur approach was able to successfully navigate in all environments that it was tested in, the team said in their study paper<\/a>. \u201cNote that our policy was trained in simulation and was never exposed to any of these environments or conditions at training time.\u201d<\/p>\n