Automation of a Drone Swarm Surveillance System

Abstract

This thesis addresses the need for a scalable and flexible drone-based surveillance platform for the autonomous vehicle testing industry. The platform should support cooperation between drones from different manufacturers through a unified communication interface and automatically generate missions in response to detected objects. The project was conducted as a collaboration between Chalmers University of Technology, Sweden, and The Pennsylvania State University, USA, for AstaZero, a research and testing facility for automated and connected vehicles. The developed platform integrates a backend system responsible for drone coordination, mission planning, and communication between system components with a web-based operator interface. The interface allows operators to define surveillance areas on an interactive map, monitor live video streams and telemetry data, and manage the generated missions when objects are detected. The system also evaluates available drones based on hardware capabilities and operational status to autonomously select the most suitable one for a selected mission, and determine appropriate flight parameters for effective surveillance coverage. Experimental validation, including on-site testing at AstaZero, demonstrated the platform’s ability to communicate with multiple drones, dispatch missions, stream real-time video, and integrate object detection into the surveillance workflow. Limitations regarding object detection reliability and hardware dependencies were identified during the project. Nevertheless, the project shows the feasibility of a scalable multi-drone surveillance platform for autonomous vehicle testing environments.