Researchers have developed an approach that allows a rotary wing unmanned air vehicle (UAV) to land on a moving unmanned ground vehicle (UGV) without the aid of GPS and recharge before moving on. Teams of autonomous air and ground agents will enable operations in search and rescue environments that are too remote or dangerous for humans but often require extensive positioning and communication infrastructure.
A critical function of UAVs is landing autonomously on static and moving ground vehicles, recharging, then taking off to perform new missions. UAVs will not be able to rely on GPS, as it is easily disrupted, so these behaviors will need to be performed using other sources such as onboard vision.
Researchers performed computations onboard the vehicle using low-cost sensors and computers. Also, no communications occurred between the UAV and UGV. The team conducted both software-in-the-loop simulations and outdoor experiments and demonstrated the algorithm to be effective at performing landing maneuvers. Using a small, custom-built quadrotor and a UGV at jogging speeds, the researchers experimented with landings.
The work combines GPS-denied behaviors and an experimentally proven behavior. It uses vision-based localization with visual-inertial odometry, a unique marker on top of the ground vehicle designed for this application, and onboard behaviors and control. Additionally, these behaviors were performed onboard a small UAS with significant computational constraints.
The custom marker on top of the ground vehicle is specifically designed for the landing task. It contains smaller markers within the bigger marker that can still be viewed even as the camera approaches the marker. The approach could reduce dependence on the fiducial marker on top of the ground vehicle and replace it with artificial intelligence that recognizes the vehicle it wants to land on.
For more information, contact DEVCOM, Army Research Laboratory Public Affairs at 703-693-6477.