skip to main content

Research flights lay the groundwork for teaching unmanned aircraft to detect and avoid obstacles

August 25, 2016

Mid-Atlantic Aviation Partnership pilots check video cameras attached to a fixed-wing UAS

Mid-Atlantic Aviation Partnership pilots check video cameras attached to a fixed-wing UAS
Aerospace and ocean engineering graduate student Hunter McClelland, left, and Mid-Atlantic Aviation Partnership aviation safety officer Andrew Kriz check optical cameras on each wing of an unmanned aircraft. The cameras, along with a radar system on the aircraft's body, collected data on how potential obstacles might appear to an unmanned aircraft in flight.

For unmanned aircraft systems to safely fly in increasingly crowded airspace, they must be able to accurately detect and avoid obstacles like trees, power lines, and critically, other aircraft.

In efforts to safely introduce more unmanned aircraft into the nation’s skies, Virginia Tech researchers and scientists from Brigham Young University have equipped an unmanned aircraft with a newly designed radar system and optical video cameras to collect data that will help aerospace engineers develop avoidance technology.

“This is one of the core challenges with unmanned aircraft systems: the ability to detect and avoid other aircraft,” said Mark Blanks, the director of the Virginia Tech Mid-Atlantic Aviation Partnership, which is headquartered at the Institute for Critical Technology and Applied Science.

In the future, unmanned aircraft will likely rely on advanced sensors and control software to detect and avoid obstacles, and these systems must be rigorously tested.

“Until someone demonstrates that their hardware and algorithms can meet or exceed human capabilities, unmanned aircraft won’t be able to fly beyond an operator’s visual line of sight, and that limits their application,” said Craig Woolsey, a professor of aerospace and ocean engineering in the College of Engineering and an expert in control systems. “The first phase is collecting realistic data that the community can use to test their algorithms.”

Acquiring that data was the goal of research flights last week involving the Mid-Atlantic Aviation Partnership, Woolsey, and Karl Warnick, a professor of electrical and computer engineering at Brigham Young University.

They aim to create a database similar to ones used in computer vision research, where huge repositories of labeled images are used as test sets for visual-recognition software. In this case, the database will provide researchers with information on what potential obstacles, like a telephone pole or a small quadcopter, would look like to an aircraft’s sensors.

“We want to gather this data in advance so that we can enable people to test their algorithms before they get implemented,” Woolsey said.

The flight team, which included graduate and undergraduate students from Virginia Tech and Brigham Young, along with Woolsey, Warnick, and Mid-Atlantic Aviation Partnership personnel, outfitted a 35-pound fixed-wing unmanned aircraft with a video camera on each wing and a unique radar system designed in Warnick’s lab.

Flying over a rural test range near the Blacksburg campus, the aircraft collected video imagery and radar signals of fixed objects and two other unmanned aircraft — a quadcopter and a small fixed-wing vehicle — from a variety of distances and angles.

Using two types of sensors could allow aircraft control software to assess potential hazards more accurately.

For example, the high resolution of optical cameras offers enough detail to identify objects the camera detects. However, optical cameras are less effective under certain lighting and weather conditions. Adding radar to the system can provide both the distance and direction to an obstacle, in any weather.

Warnick’s system, which weighs less than half a pound, is the first phased-array radar light enough to be carried by a small unmanned aircraft.

The researchers are analyzing and processing the sensor data from the flights, and will store the data in a publicly available database, along with the GPS coordinates corresponding to each data point — showing an obstacle’s true location as well as its sensed location.

This data will aid the community’s understanding of the capabilities and challenges of detecting and avoiding small unmanned aircraft, and allow researchers — including Woolsey’s and Warnick’s groups — to develop and refine aircraft control systems.

“We want to start testing our own ideas against images in the database,” Woolsey said.

The project is funded through the Center for Unmanned Aircraft Systems, a National Science Foundation Industry/University Cooperative Research Center led by Brigham Young. Woolsey is the director of Virginia Tech’s arm of the center, which uses university research to tackle fundamental challenges preventing the integration of unmanned aircraft systems in the national airspace.

“This is an exciting project, because having a readily accessible database like this will be a key enabler for development of new technology to facilitate unmanned aircraft systems integration,” Blanks said. “It will be phenomenally impactful for the future of unmanned aircraft in the national airspace.”

The Virginia Tech Mid-Atlantic Aviation Partnership runs one of only six national test sites for unmanned aircraft systems designated by the Federal Aviation Administration.

The test site’s work in areas including agriculture, journalism and emergency management has positioned Virginia Tech as a leader in unmanned aircraft systems research.

Current research topics include flight beyond visual line of sight, flight operations over people, unmanned aircraft system airworthiness certification, air traffic management, remote sensing and payload development support, and airspace integration. 

Contact: