SLDS - Self-Learning Drone Surveillance

Purpose and goal:

The security risks posed by the widespread use of drones have led organizations and businesses to monitor their airspace as well. New drones arrive daily and the more radio protocols and frequency bands, the more challenging it becomes to monitor drones.

Self-Learning Drone Surveillance (SLDS) is the name of a machine learning-based system that can identify drones with previously unknown radio protocols and generate algorithms for future use. SLDS aims to achieve self-learning/autonomous detection and identification of new wireless drone protocols. Expected results and effects:

Upon the successful completion of the project, the strategy for commercialization will be tiered and adaptive, aligning with the Technology Readiness Level (TRL) scale. Initially, the project aims to reach TRL 7, indicating system prototype demonstration in an operational environment, particularly within Securitas Technology’s operations. This practical demonstration will serve as a

pivotal stepping stone towards full commercialization. Approach and implementation:

The project spans from July 2024 to December 2025, involving three main actors: Skysense, Securitas, and KTH, with a budget allocation reflecting their roles and contributions: Skysense , Securitas Technology, and KTH. The project is structured into four key work packages (WPs), each led by a different partner to leverage their specific expertise. Collaboration between the partners is facilitated through regular meetings, shared platforms for document and data exchange, and joint testing and validation sessions.