UAV Guidance & Alerting Algorithms · Detect-and-Avoid Systems
My Master’s thesis focuses on the design, implementation, and evaluation of guidance and alerting algorithms for Uncrewed Aerial Vehicles (UAVs), with application to Detect-and-Avoid (DAA) systems enabling safe Beyond Visual Line of Sight (BVLOS) operations.
The project is being undertaken in collaboration with Revolution Aerospace as part of an industry-based placement, and forms part of a broader effort to mature autonomous collision-avoidance capabilities for operational UAV platforms.
The thesis investigates algorithmic approaches to airborne collision avoidance, with emphasis on adapting and evaluating ACAS-Xu–based guidance and alerting logic for unmanned aircraft operating in shared airspace.
Work is primarily simulation-driven and examines system-level behaviour, including alert timing, guidance effectiveness, and trade-offs between safety, operational efficiency, and nuisance alerting.
Emphasises autonomy, aviation safety, and system-level evaluation rather than platform-specific hardware implementation.
Due to intellectual property and confidentiality constraints associated with industry collaboration, implementation details, source code, and proprietary data are not publicly available.
Public material is therefore limited to high-level system descriptions, methodology, and non-sensitive performance discussion.
Status: Ongoing
Degree: Master of Mechanical Engineering (Aerospace)
Institution: The University of Queensland
Industry Partner: Revolution Aerospace