Adaptive Path Planning for UAV-Based Pollution Sampling

Unmanned Aerial Vehicles (UAVs) continue to gain popularity in applications such as military reconnaissance, environmental monitoring in remote locations, and package delivery. High-Altitude Long-Endurance (HALE) UAVs can remain airborne for extended periods, enabling air pollution measurements to be conducted across a wide range of altitudes, from a few hundred meters above ground level to the lower stratosphere. However, the challenges posed by dynamic environmental conditions and strict energy limitations necessitate the use of adaptive path planning algorithms that account for UAV and environmental models. To address these challenges, we propose a two-tier Adaptive Path Planner (APP), which comprises a Global Path Planner (GPP) and a Local Path Planner (LPP). The GPP, operating offline, generates obstacle-free, energy-efficient paths that adhere to the UAV’s kinematic constraints, while the LPP dynamically recalculates alternative routes in real time when obstacles arise. The APP leverages a novel data-driven environmental model, integrating terrain, wind, airspace, and measurement maps. Extensive Model-in-the-Loop testing was conducted to evaluate various single-objective optimization algorithms for the GPP. Subsequently, the APP was successfully validated in simulation scenarios inspired by real-world pollution monitoring missions conducted in Poland and the Arctic. Additionally, the proposed approach was tested under real-world conditions, demonstrating significant application potential. A comparative analysis of the generated paths demonstrated that the APP effectively replaces human operators. Further testing confirmed the APP’s capability for adaptive re-planning during mission execution.