Detection and reconstruction of actuator faults in a flight control system are crucial to avoid negative impacts on the aircraft itself, as well as human and environmental systems. In this study, an actuator fault detection and reconstruction scheme based on fault classification for Hex-rotor unmanned aerial vehicle is designed. First, the fault type of actuator is analyzed and classified, then an actuator fault model is established based on multiple fault classification. Secondly, a fault detection and reconstruction (FDR) scheme for the Hex-rotor unmanned aerial vehicle is proposed. In the proposed scheme, a fault observer group based on an extended Kalman Filter (EKF) is designed for fault detection and isolation, and the flight state feedback required by the fault observer group is provided by the multi-sensor navigation unit (MSNU). Then a fault reconstruction algorithm of actuator is proposed by using the output of the fault observer group. The designed FDR system is applied to Hex-rotor unmanned aerial vehicle prototype for its evaluation. The simulation results show that the proposed design is capable of fault detection and the reconstruction of actuator faults, and the actual flight verifies the effectiveness of the proposed methods.

Energy management plays a crucial role in achieving extended endurance for solar-powered Unmanned Aerial Vehicles (UAVs). Current studies in energy management primarily focus on natural energy harvesting and task-oriented path planning. This paper aims to optimize energy consumption during the climb and glide stages by exploring variable climb speeds and glide powers. To achieve this, fitness functions are established for both the climb and glide stages, taking into account the maximum climb speed and glide power limits of the aircraft. The particle swarm optimization (PSO) algorithm is employed to solve the problem, resulting in significant energy savings of over 68% in the climb stage and 4.8% in the glide stage. Based on an analysis of the optimization trends, this study proposes an energy-management strategy to fulfill the demand for long-endurance flights. The findings of this study can serve as a valuable reference for high-altitude missions that require extended flight times.

Tail-sitter unmanned aerial vehicles (UAVs) are promising vertical takeoff and landing (VTOL) UAV suitable for multi-missions but the road to the commercialization of tail-sitter UAVs is tortuous. This paper aims to provide a systematic design methodology and present the development process for a novel biplane quadrotor tail-sitter UAV platform named TW10 to accelerate commercialization of this type of UAV. All the design choices and trade-offs in aerodynamics, structure, avionics, and the control scheme are detailed. A simulation and real flight test results are demonstrated to prove the feasibility of our design methodology. TW10 can carry a 1 kg mission load to achieve more than 2.5 h of flight time. This work serves as a meaningful reference for the promotion of tail-sitter UAVs in practical industrial applications.

With the rapid development of remote sensing technology, remote sensing target detection faces many problems; for example, there is still no good solution for small targets with complex backgrounds and simple features. In response to the above, we have added dynamic snake convolution (DSC) to YOLOv7. In addition, SPPFCSPC is used instead of the original spatial pyramid pooling structure; the original loss function was replaced with the EIoU loss function. This study was evaluated on UAV image data (VisDrone2019), which were compared with mainstream algorithms, and the experiments showed that this algorithm has a good average accuracy. Compared to the original algorithm, the mAP0.5 of the present algorithm is improved by 4.3%. Experiments proved that this algorithm outperforms other algorithms.

Recently, visual simultaneous localization and mapping (SLAM) has been widely used in robotics and autonomous vehicles. It performs well in static environments. However, real-world environments are often dynamic scenarios. Because it is difficult for SLAM to deal with moving objects such as pedestrians and moving cars, SLAM does not meet the actual needs of robots and autonomous vehicles in real-world scenarios. Visual odometry (VO) is a key component of SLAM systems. In this paper, to extend SLAM to dynamic scenarios, we propose a monocular VO based on direct sparse odometry (DSO) to solve the problems arising in a dynamic environment. The proposed method, called DSO-Dynamic (DSOD), combines a semantic segmentation network with a depth prediction network to provide prior depth and semantic information. Experiments were conducted on the KITTI and Cityscapes datasets, and the results show our method achieves good performance compared with the baseline algorithm, DSO.