Sensor fault detection and isolation (SFDI) is a fundamental topic in unmanned aerial vehicle (UAV) development, where attitude estimation plays a key role in flight control systems and its accuracy is crucial for UAV reliability. In commercial drones with low maximum take-off weights, typical redundant architectures, based on triplex, can represent a strong limitation in UAV payload capabilities. This paper proposes an FDI algorithm for low-cost multi-rotor drones equipped with duplex sensor architecture. Here, attitude estimation involves two 9-DoF inertial measurement units (IMUs) including 3-axis accelerometers, gyroscopes and magnetometers. The SFDI algorithm is based on a particle filter approach to promptly detect and isolate IMU faulted sensors. The algorithm has been implemented on a low-cost embedded platform based on a Raspberry Pi board. Its effectiveness and robustness were proved through experimental tests involving realistic faults on a real tri-rotor aircraft. A sensitivity analysis was carried out on the main algorithm parameters in order to find a trade-off between performance, computational burden and reliability.

Sensor fault detection and isolation (SFDI) is a fundamental topic in unmanned underwater vehicles (UUV) development, since control system reliability strongly depends on the accuracy of attitude estimation. In small UUVs, typical redundant architectures, based on triplex redundancy, can represent a strong limitation in terms of payload and power consumption. This work proposes an FDI algorithm for small UUVs equipped with duplex sensor architecture. Here, attitude estimation relies upon the usage of two 9-DoF inertial measurement units (IMUs) including 3-axis accelerometers, gyroscopes and magnetometers. The proposed SFDI algorithm is based on an unscented Kalman filter (UKF) approach to efficiently detect and isolate faulted IMU sensors. Its effectiveness and robustness were proved through experimental tests involving realistic faults on a real underwater vehicle. A sensitivity analysis was carried out on the relevant algorithm parameters in order to find a trade-off between performance, computational burden and reliability.