1/14/2024 0 Comments Neural network radar![]() ![]() To be clear, Krolik and his team aren't flying drones across campus at all hours of the day and night. ![]() On Duke's campus, the system has been able to successfully classify drones versus cyclists, pedestrians, cars and other objects 98 percent of the time. Over time, the algorithm learns what radar signals are normal for a given space so that when a drone flies by, with propeller motion and trajectory that is very different to what is normally found in the area, it will trip an alarm. And while bicycles and pedestrians have more variable dynamics, their micro-Doppler signatures are very distinctive. "This one learns from its environment, because most of the time a drone isn't there."įor example, cars generally follow paths defined by roadways. "Most systems are designed in a laboratory to be taken out into the field," said Krolik. Radar and video setups peer down from a parking garage window (left) to in an attempt to spot a drone flying below (right). But the 1940s technology is getting a 2020s upgrade with the help of a type of machine learning called Deep Neural Networks (DNN). Instead, Krolik is turning to the same technology that turned the tide against aerial enemies in World War II-radar. A telescopic lens could be used, but then its field of view would be greatly constrained. While a computer can be trained to visually spot a drone, an optical system would have a very limited range. "We need detection systems that can spot these things wherever and whenever they're airborne, regardless of how they're being controlled." "Systems exist that can detect the signals used to control off-the-shelf drones, but they tend to be pretty expensive and there are already commercial drones that can be flown autonomously without any radio control at all," said Krolik. Once again funded by DARPA, Krolik is turning to radar, machine learning and specialized hardware to make a drone surveillance system with sufficient range to allow drones to be detected and stopped before they reach a protected area in a city. However, in settings where protection of a fixed asset such as an embassy, hospital or encampment is the goal, a system that can maintain a perimeter from a safe stand-off distance is required. Using a fleet of friendly drones to find enemy drones makes sense in a setting for a military unit that is trying to secure a wide urban area. The project has recently successfully concluded with an urban test in Rossyln, Virginia, but challenges remain in discriminating drones from urban "clutter." During his time as a Defense Advanced Research Projects Agency (DARPA) program manager, Jeffrey Krolik, professor of electrical and computer engineering at Duke University, launched one such project called "Aerial Dragnet." Using a network of drones hovering above a cityscape or other large, developed area in need of defense, multiple types of sensors would peer down into the city's canyons and pick out any drones. With only distance, speed and direction to go on, drones can easily be "hidden in plain sight" on radar displays among slowly moving cars, bicyclists, a person jogging or even the spinning blades of an air conditioning unit.Īs drones become more popular and more worrisome from a security standpoint, many projects have sought to engineer systems to spot them. But if radar signals move down from the clouds and into a city's streets, there are suddenly many objects that can be mistaken for one another. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |