NASA is using a specially developed camera pod packed with sensors to support the development of computer vision technology for autonomous flight. The agency’s Airborne Instrumentation for Real-world Video of Urban Environments (AIRVUE) pod has been mounted on a helicopter and is in service for flight testing by researchers at the Kennedy Space Center in Florida.
The equipment, which was developed and built at NASA’s Armstrong Flight Research Center in Edwards, California, is collecting a wide array of visual data sets showing weather and other obstacles to autonomous flight. NASA’s objective is to build a data cloud that can be used by developers of eVTOL aircraft and drones to assess what their autonomous flight control systems can “see.”
NASA is hosting the data cloud on its Tech Port site, where some initial data sets can already be accessed. The agency said it is open to partnering with companies to improve the quality, relevance, and diversity of the data.
“Data is the fuel for machine learning,” said Nelson Brown, lead researcher for NASA’s AIRVUE project. “We hope to inspire innovation by providing the computer vision community with realistic flight scenarios. Accessible data sets have been essential to advances in driver aids and self-driving cars, but so far, we haven’t seen open data sets like this in aviation.”
NASA engineers are refining the pod's design and plan to make more of them available for deployment on various types of aircraft.