35th Congress of the International Council of the Aeronautical Sciences

06.2 - Flight Dynamics and Control (UAV related)

FLIGHT TRIALS OF DRONES CONTROLLED BY AI LARGE LANGUAGE MODELS

S. Crase¹, S. Pywell¹, K. Rosser¹; ¹Defence Science and Technology Group, Australia

For aerial autonomy, the ability of LLMs to interpret natural language and generate executable code introduces opportunities for dynamic, adaptive drone operations. While other researchers show the feasibility of LLMs for drones control through simulation, we have carried our research through to real-world flight trials. These successful flights and lessons learned form the basis for this paper.


View Paper

DOI: 10.71945/icas2026_0156