The influence of unmanned air vehicles (UAV) in the lower airspace increases every day. With the next boom in aerial space operations less than 400 feet planned by experts, drones are becoming increasingly important. Currently, the busiest airports are limited to the management of only 300 aircraft operations per hour, but with the growing number of UAV, this is insufficient.
The Federal Aviation Administration (FAA) offers the concept of UAV traffic management (UTM) as a potential solution to the congestioned airspace. However, systems based on human intervention may not be effective in the context of the large number of operations projected by 2027. In this context, the replacement of operations assisted by humans by autonomous systems becomes the best option to ensure the safety and efficiency of the lower air space.
A team of researchers led by Lanier Watkins and Louis Whitcomb at the Institute for Autonomy provided has developed a new robust approach that can meet these challenges by introducing artificial intelligence in air operations management to ensure a safe future for unmanned aviation. The approach they have developed suggests replacing processes involving human intervention with autonomous systems, using artificial intelligence to model a more reliable drone control system. This article was published in Computer review.
The researchers decided to explore how autonomous algorithms could improve safety in the lower airspace. The first step was to assess the impact of autonomous algorithms in a simulation of three -dimensional airspace. To this end, collision avoidance algorithms have been used, which has already reduced the number of accidents. In addition, the application of strategic deconflicted algorithms that adjust journey times to prevent collisions has further improved security and reduces the number of incidents.
To create more realistic simulations, scientists have introduced two important aspects to their simulator. The “noisy sensors” were introduced to simulate unpredictable conditions, which makes the system more adaptive. The “blurred interference system” has calculated the level of risk for each drone, taking into account various factors, including the proximity of obstacles and membership of the planned routes. Thanks to these innovations, the system is able to make autonomous decisions to avoid collisions.
The project covers a variety of scenarios, including situations with “rogue drones” deviating from planned routes. The results of this work are encouraging and demonstrate the potential to improve the safety and efficiency of lower airspace.
In the future, researchers plan to further improve their simulations by incorporating dynamic obstacles, such as weather conditions, to further simulate real world situations. This project is based on more than two decades of research in the applied physics laboratory at Johns Hopkins University and is essential to the development of the American airspace system, guaranteeing a safe and efficient aviation in the future.
