In a breakthrough, a team of Indian-origin scientists are developing a drone that can navigate autonomously, choose a landing site, and land on a moving object. For the astonishing feat, researchers are using a branch of artificial intelligence called as fuzzy logic.
“Its the only realistic way that drones will have commercially viable uses such as delivering that roll of toilet paper to customers,” said Manish Kumar, associate professor at the University of Cincinnati in the US.
Study authors explained that humans use fuzzy logic every day to complete daily tasks with ease. Fuzzy logic is different from other computing approaches as it is based on “degrees of truth” unlike traditional ‘true or false’ approach also known as Boolean logic.
Fuzzy logic enables a drone to take most appropriate decision in crunch situations. This is why drones powered by fuzzy logic make good navigational decisions. Degrees of truth change over time depending on different scenarios and drone continuously discards the lesser solutions; thus, the system is also called “genetic-fuzzy”.
At present, the real drone running on fuzzy logic is under development phase. However, researchers have successfully tested the fuzzy logic on simulation, and it worked fine. During simulations, scientists tested navigational, landing, and decision-making capabilities of a quadcopter drone, and found it to be a success. The quadcopters autonomously chose the landing site on a moving object and landed safely in the simulation phase.
Researchers further explained that landing drone on moving object, in reality, will be difficult due to ever-changing airspace. Scientists are still working on the problem and are designing quadcopter to combat the problem of changing airspace.
Many believe that autonomous drones are the future and can influence our lifestyle to a great extent. While giving an example, Kumar said that the drone could be used to deliver products to home or weapons during the war, etc.