SLING-UAV
| Dossier | HT.KIEM.03.037 |
|---|---|
| Status | Initieel |
| Subsidie | € 40.000 |
| Startdatum | 1 september 2026 |
| Einddatum | 31 augustus 2027 |
| Regeling | KIEM HighTech 2024-2026 |
Drones offer a flexible, cost-effective solution for inspection and environmental monitoring. Their high manoeuvrability, rapid deployment, and ability to access large or hard-to-reach areas make them well-suited for applications such as dyke inspection, farmland monitoring, and air quality assessment in industrial zones. Equipped with advanced multimodal sensors, including ground-penetrating radar, thermal, infrared, hyperspectral, RGB cameras, and electronic noses, semi-autonomous drones have demonstrated strong potential to increase productivity, improve inspection frequency, and deliver actionable insights.
However, one of the main remaining challenges is the aerodynamic downwash generated by drone propellers disturbs the surrounding environment, compromising data quality during close-range inspection, air sampling, and sensitive detection tasks such as locating illegally buried cadavers. This issue has been consistently observed in prior collaborative projects (CSI-Drone, BEVERS, and FAST), despite clear interest in practical deployment.
This feasibility study is directly driven by strong and urgent demand from public and industrial partners, who have raised a central question: Can drones perform close inspection and sampling while ensuring reliable, undisturbed measurements? Addressing this is critical for real-world adoption.
The project therefore investigates: How can a drone system be designed to enable accurate, close-proximity inspection and sampling without compromising data integrity due to propeller-induced disturbances?
To answer this, this feasibility study explores mechatronic redesign strategies, including optimized sensor placement and advanced control strategies. In alignment with the National Technology Strategy (NTS), particularly its focus on mechatronic design, the project also applies AI-based control methods, with an emphasis on reinforcement learning for robust and adaptive flight control.
Conducted in close collaboration with partners, researchers, and students, this study will deliver actionable insights and lay the foundation for follow-up projects toward next-generation drone technologies.
Contactinformatie
Saxion