“The goal of Fast Lightweight Autonomy (FLA) is to develop advanced algorithms to allow unmanned air or ground vehicles to operate without the guidance of a human tele-operator, GPS, or any datalinks going to or coming from the vehicle,” said JC Ledé, the DARPA FLA program manager. Autonomous flight capabilities are being developed and demonstrated using custom payloads on a commercial quadrotor platform (DJI Flamewheel 450 airframe, E600 motors with 12″ propellers, and 3DR Pixhawk autopilot).
A traditional approach to operating small UAVs uses a human operator as the pilot. The air vehicles are typically remotely controlled with the operator watching the vehicle or teleoperated with the operator watching data from on-board sensors. These techniques work only when a highly skilled operator is coupled with a communications channel having high availability and manageable latency. However, the approach breaks down when obstacles are added to the environment, as communications degrade, and as vehicle speed increases.
Birds and flying insects maneuver easily at high speeds near obstacles. The FLA program asks the question “How can autonomous flying robotic systems achieve similar high-speed performance?”
Another traditional approach to controlling small, unmanned air vehicles uses Global Positioning System (GPS) coordinates to specify a flight path as a series of predetermined waypoints. This method for navigation has proven effective only in situations where GPS is available. It fails when GPS is lost due to interference such as jamming or poor reception indoors; as well as in settings in which GPS bounds on accuracy are not adequate for the size and speed of the platform.
Birds and flying insects are able to perform well without using predetermined waypoints or an external position reference system.
“Most people don’t realize how dependent current UAVs are on either a remote pilot, GPS, or both. Small, low-cost unmanned aircraft rely heavily on tele-operators and GPS not only for knowing the vehicle’s position precisely, but also for correcting errors in the estimated altitude and velocity of the air vehicle, without which the vehicle wouldn’t know for very long if it’s flying straight and level or in a steep turn. In FLA, the aircraft has to figure all of that out on its own with sufficient accuracy to avoid obstacles and complete its mission.”
The technology is intended to support unmanned aerial vehicle flights in GPS-denied or GPS-unavailable environments and aid military operations or search and rescue missions, among others, DARPA said. Potential applications for the technology include safely and quickly scanning for threats inside a building before military teams enter, searching for a downed pilot in a heavily forested area or jungle in hostile territory where overhead imagery can’t see through the tree canopy, or locating survivors following earthquakes or other disasters when entering a damaged structure could be unsafe.
The Defense Advanced Research Projects Agency put unmanned quadcopters through a series of tests to demonstrate autonomous flight without the aid of human operators or global positioning systems. DARPA said three research teams under the Fast Lightweight Autonomy program flew small unmanned quadcopters through various environments using onboard cameras and sensors as well as smart algorithms for autonomous navigation.
IDST Monthly Access Membership Required
You must be a IDST Monthly Access member to access this content.