Autonomous drone racing presents a unique challenge that requires both high-speed motion planning and strategic decision-making in a multi-agent setting. Prior work has primarily relied on model predictive control (MPC) methods that treat opponents as dynamic obstacles, limiting their ability to model strategic interactions. In this work, we formulate drone racing as a dynamic game and introduce game-theoretic planning methods that compute open-loop Nash equilibria, incorporate blocking strategies, and accelerate decision-making using learning-based techniques. These methods explicitly model opponent behavior, allowing drones to anticipate and react strategically in high-speed racing scenarios. To assess the effectiveness of our approach, we conduct a large-scale head-to-head tournament against MPC-based planners, demonstrating that interaction-aware planning enables more effective overtaking and defensive strategies, leading to a higher wining rate. However, computational delays in high-speed decision-making can limit performance, highlighting the need for efficient techniques that balance real-time feasibility with strategic adaptability. Our results show that learning-based acceleration significantly improves decision-making speed while preserving competitive advantages. Finally, high-fidelity simulations and real-world drone racing experiments validate the feasibility of these methods, confirming their ability to generate reliable and competitive strategies under practical racing conditions.

The goal of this report is to outline the sub-system design of the local sensing system chosen as the final concept in [1], to satisfy the mission need statement: measure the atmospheric conditions with full three-dimensional coverage of a wind farm to optimize its operational performance and control. This statement is derived from the need to improve the control and performance of wind farms through more informed processes and decisions, a task that meteorological masts would usually take on. However, the providable coverage is very low in comparison to the one a UAV based system could provide. UAVs have the potential to significantly increase the measurement coverage around an entire wind farm and in turn return to the user more valuable data. To approach the finding of a solution to this problem, the project was divided into four: planning, concept definition, concept exploration and detailed design. From the first two phases came unique concepts exploring remote and local sensing options, combined with a range of UAV types including hybrid, fixed-wing and rotor. Through a detailed trade-off process and sensitivity analysis, the agreed upon final solution came to be a local sensing concept that makes use of many hybrid drones. In the fourth and final phase, where we now find ourselves, the detailed concept is unpacked and designed into a marketable system that is capable of satisfying the underlying MNS. In this stage the design was split into three design groups: UAV design, ground station design, swarm design.