DARPA’s Fast Lightweight Autonomy program recently tested one of its drones on an indoor test flight. It has been quite a while since DARPA’s bird-of-prey inspired drone system. But this recently tested drone could zoom around a cluttered warehouse in a Cape Cod Air Force base at 45 MPH – the target speed and environment the outfit was aiming for back in 2014.
The company’s FLA program aims to develop and test algorithms that could reduce the amount of processing power, communications, and human intervention needed for unmanned aerial vehicles (UAVs) to accomplish low-level tasks, such as navigation around obstacles in a cluttered environment. If it becomes successful, FLA would reduce operator workload and stress. It will allow humans to focus on higher-level supervision of multiple formations of manned and unmanned platforms as part of a single system.
Spectacularly so, this unit is able to hit speed even carrying sonar, inertia sensors, and an HD camera on such a small frame. Thus, the demo flight was entirely autonomous. Zero pilots were involved in getting the drone around the stacks of boxes. DARPA mentions that as advancements are made, the Massachusetts training course will grow more complex.
DARPA researchers recently completed the first flight data collection from the common quadcopter UAV platform that three research teams are using for the program. The flight test data validated that the platform is capable of achieving the required flight speed of 20 meters per second while carrying high-definition on board cameras and other sensors, such as LIDAR, sonar, and inertial measurement units. During the testing, researchers also demonstrated initial autonomous capabilities, such as seeing obstacles and flying around them at slow speed unaided by a human controller.
Thus, the company’s FLA project is unique because it hits the balance between size, speed, and capabilities, whereas others are limited to only one of the three simultaneously. It is what makes the program so challenging for a drone with limited computing power to perform a complex mission with complete autonomy.