16
Feb

Loma Mar PropetyHikers often get lost when out trekking in the woods and with new emerging technology they might be guided back safely using SAR drone quadcopter navigation that uses a deep neural network.

The deep neural network enables an unsupervised drone to determine the direction of a path using an on-board camera.

In an article published by the Tech Times, A team of researchers and robotics and perception experts have developed an algorithm to train drones to follow hiking trails for search and rescue operations. They have been training drones to recognise and follow forest trails and now want to teach them to recognise humans!

A team of researchers led by Professor Davide Scaramuzza, Department of Informatics, University of Zurich have developed a way to train drones to follow forest trails in an effort to assist search and rescue missions for lost hikers.

According to the research his team figured out a method of machine learning through Deep Neural Networks (DNNs) which enables an unsupervised drone to determine the direction of a path using an on-board camera.

The results were surprising when it was tested because the autonomous quadcopter was able to navigate a completely new trail and stay on course as well as, and sometimes even better, than humans. The same path and test was done with two humans against the drone to determine how effective the DNNs based machine learning was and, on one test, the quadcopter was successful 85.2 percent of the time as opposed to the two people who were accurate 86.5 and 82 percent of the time. A second test with different conditions resulted in the quadcopter being accurate 95 percent of the time when the two people were 91 and 88 percent accurate.

What does new technology mean for Search and Rescue? Technology and SAR will be discussed at the 2016 Australian and New Zealand Search and Rescue Conference (ANZSAR) will be held at the Jupiters, Gold Coast on the 1 June 2016.

To register for the Conference CLICK HERE.



Tags: ,
%d bloggers like this: