As the commercial unmanned aircraft system (UAS) industry advances, the use of artificial intelligence and machine learning is becoming more common, and some industry experts claim that it would not have been successful without it.
According to a report by the Brookings Institution, AI generally refers to machines that react to simulations in a manner similar to traditional human responses. Artificial intelligence uses algorithms created from data to create these responses. Machine learning looks for trends in AI data. Together, these two technologies can be used to enable intelligent decision-making.
The Tel Aviv-based software provider leveraged AI's UAS to create an unmanned traffic management (UTM) system. It is currently being tested in a pilot project, with five drone companies all flying their fleets in the same corridor, which has never been tried before. UTM communicates with the newly developed UAS Service System (USS) to manage the airspace.
UTM can get more information than USS, such as weather and non-flight zones. Once the UTM receives a request from the USS, it starts sorting through the information in order to approve or reject the flight plan, and does this by using artificial intelligence.
I'm the creator of the technology UTM replaces the ATM's software, the air traffic management, the software in the control tower, and the people in the control tower, so the decisions are also done by the UTM. USS is requesting a specific flight path from UTM, and UTM is checking to compare it to the offline area, weather conditions, and the capabilities of the drone itself, as it could be multiple drones, and if there are any conflicts with other drones.
This is all done before the flight. While humans can participate in loops at the USS level, they can't at the UTM level because there isn't enough time for humans to think and make decisions.
This thing won't work without artificial intelligence, drones will never be able to deliver food to you in the city, conduct inspections, set off fireworks, and so on.
If it's done manually, which means you have to predefine the drone route for the operator, you might get 10% or 5% of the features, but you'll never really get the full potential of the drone.
The network uses AI in route planning, flight control, flight safety decision-making, sensor fusion, recovery systems, and automated air traffic control.