Purpose and goal
The project combines expertise in machine learning, advanced camera technology, sound systems, and drone technology to use AI to detect, classify, and position a set of drones. The project conducts advanced data collection and develops new algorithms based on a combination of data-driven and model-based methods. The goal is a system that can perceive (multiple) UAVs early and without a human operator gather information from multiple sources to identify the UAVs.
Expected effects and result
The audiovisual technology, with the development of models for positioning, identification and target tracking, will generate important knowledge for autonomous systems. The technology can contribute to a cost-effective solution for analyzing the airspace for defence. The knowledge and technology can also be used, for example, for monitoring vulnerable facilities and work environments or listening to signals at sea. The research has great potential to strengthen Sweden´s competitiveness.
Planned approach and implementation
The project is carried out by three groups in three stages with joint field tests. One group is responsible for situational awareness using cameras, one group is responsible for situational awareness using acoustics, and one group manages flights for coordinated data collection and testing. Firstly, a test flight is made and preliminary data is collected. Secondly, detection models and a tracking system are created. Thirdly, the system is refined and usability is evaluated and tested.
The project description has been provided by the project members themselves and the text has not been looked at by our editors.
