Current tenders 🖊️
Masterthesis, Advanced Design Project (ADP)
Unmanned Aerial Vehicles (UAVs) operate (autonomously) in unpredictable environments, where unexpected faults can compromise safety and mission success. Traditional monitoring relies on labeled fault data, which is difficult to obtain due to the rarity and variety of real failures. As UAVs integrate high-dimensional sensors, manual inspection and rule-based methods can no longer capture subtle, evolving anomalies. With longer autonomous missions, early detection of abnormal behavior is essential to prevent catastrophic outcomes and ensure reliable UAV operation.
Supervisor: Florian von Beren Coors, M.Sc.
2026/05/20
Masterthesis, Bachelorthesis
Unmanned Aerial Vehicles (UAVs) operate (autonomously) in unpredictable environments, where unexpected faults can compromise safety and mission success. Traditional monitoring relies on labeled fault data, which is difficult to obtain due to the rarity and variety of real failures. As UAVs integrate high-dimensional sensors, manual inspection and rule-based methods can no longer capture subtle, evolving anomalies. With longer autonomous missions, early detection of abnormal behavior is essential to prevent catastrophic outcomes and ensure reliable UAV operation.
Supervisor: Florian von Beren Coors, M.Sc.
Masterthesis, Bachelorthesis
Unmanned Aerial Vehicles (UAVs) operate (autonomously) in unpredictable environments, where unexpected faults can compromise safety and mission success. Traditional monitoring relies on labeled fault data, which is difficult to obtain due to the rarity and variety of real failures. As UAVs integrate high-dimensional sensors, manual inspection and rule-based methods can no longer capture subtle, evolving anomalies. With longer autonomous missions, early detection of abnormal behavior is essential to prevent catastrophic outcomes and ensure reliable UAV operation.
Supervisor: Florian von Beren Coors, M.Sc.
Masterthesis, Bachelorthesis
Unmanned Aerial Vehicles (UAVs) operate (autonomously) in unpredictable environments, where unexpected faults can compromise safety and mission success. Traditional monitoring relies on labeled fault data, which is difficult to obtain due to the rarity and variety of real failures. As UAVs integrate high-dimensional sensors, manual inspection and rule-based methods can no longer capture subtle, evolving anomalies. With longer autonomous missions, early detection of abnormal behavior is essential to prevent catastrophic outcomes and ensure reliable UAV operation.
Supervisor: Florian von Beren Coors, M.Sc.