The impact of unmanned aerial vehicles (UAV) in the lower airspace increases every day. Along with the upcoming air space boom below 400 feet expected by experts, UAV is becoming more and more important. Currently, the most busy airports are limited to servicing only 300 aircraft operations per hour, but with the increase in the number of UAV it is insufficient.
The Federal Aviation Administration (FAA) proposes the concept of UAV (UTM) traffic management as a potential solution of crowded aircraft. However, systems based on human intervention may not be effective in the context of a huge number of operations projected by 2027. In this context, replacing human assisted operations with autonomous systems becomes the best option to ensure safety and performance in lower aircraft.
A team of scientists led by the Watkins and Louis Whitcomba lanier at the Institute for Asused Autonomy has developed a new, solid approach that can meet these challenges by introducing artificial intelligence to managing aviation operations to ensure a safe future for unmanned aviation. The approach they developed suggests replacing processes covering human intervention into autonomous systems, using artificial intelligence to model a more reliable drone control system. This article was published in Computer warehouse.
Scientists decided to examine how autonomous algorithms can improve safety in the lower airspace. The first step was to assess the impact of autonomous algorithms on three -dimensional airspace simulation. For this purpose, collision avoidance algorithms were used, which have already reduced the number of accidents. In addition, the use of strategic deconflication algorithms that adapt travel time to prevent collisions, increased safety and reduced the number of incidents.
To create more realistic simulations, scientists introduced two important aspects to their simulator. “Noisy sensors” were introduced to simulate unpredictable conditions, thanks to which the system is more adaptive. The “fuzzy disturbance system” calculated the risk level of each drone, taking into account various factors, including the proximity of obstacles and compliance with planned routes. Thanks to these innovations, the system is able to make autonomous decisions to avoid collisions.
The project includes various scenarios, including situations from “Rogue Drone” deviating from planned routes. The results of this work are encouraging and show the potential for improving safety and efficiency in the lower airspace.
In the future, scientists plan to improve their simulations even more by including dynamic obstacles, such as weather conditions, in order to simulate the situation in the real world even more accurately. The project is based on over two decades of research at Johns Hopkins University applied Physics Laboratory and is necessary for the development of the national US aircraft system, ensuring safe and efficient aviation in the future.
