Man-powered sailplane launch. Photo courtesy of Nevada Institute for Autonomous Systems
Microsoft is testing artificial intelligence on a 16.5-foot, 12.5-pound sailplane in Nevada, the Nevada Institute for Autonomous Systems (NIAS) said. Microsoft’s unmanned aerial system (UAS) research team has collaborated with NIAS and the Nevada Governor’s Office of Economic Development to conduct a test at the Hawthorne Advanced Drone Multiplex test range. It is an FAA-approved unmanned aircraft system test site.
"Microsoft researchers have created a system that uses artificial intelligence to keep the sailplane in the air without using a motor, by autonomously finding and catching rides on naturally occurring thermals, like how wild birds stay aloft,” said Ashish Kapoor, a principal Microsoft researcher. “Birds do this seamlessly, and all they're doing is harnessing nature and they do it with a peanut-sized brain."
The sailplane being tested uses battery to run onboard computation equipment and controls, NIAS said. This includes the rudder and radios. It also has a motor, allowing a pilot to take over manual operation, if necessary. When in the air, the drone demonstrated ability to operate autonomously. NIAS said it could find and use thermals to travel without a motor or human.
Both simple and complex UAS testing was conducted at the multiplex, a 230-sqare-mile facility. Microsoft was based at the Hawthorne Industrial Airport. After preliminary tests were conducted there, the teams moved to another location six miles away. NIAS said Microsoft flew three different sailplanes. They reached an altitude of 1,700 feet and flew almost 24 Nevada UAS Test Site Certification of Authorization flights earlier this month.
"Innovative AI technology like what Microsoft tested with NIAS is clearly where the most dramatic global UAS Industry disruptions will occur. When you think of artificial intelligence or AI, there are many perspectives on the value-add to the UAS Industry,” said Chris Walach, director of the FAA-designated Nevada UAS Test Site. “Very evident to me, developing and testing AI, or machine-learning technology, is going to have multiple applications that will significantly benefit the UAS Industry and the American way of life. This is one of the most exciting developments I have seen over the past several years in Nevada and globally."