Maritime activities have become increasingly frequent with the deepening of economic globalization, highlighting the burgeoning significance of maritime rescue. However, in practical applications, UAVs for maritime rescue face numerous challenges, such as limited endurance and inadequate autonomous planning capabilities. To optimize flight routes and circumvent adverse sea conditions, an improved Pied Kingfisher Optimizer (IPKO) that incorporates refraction reverse learning, variable spiral search, and Cauchy mutation strategies was proposed. Comparative experiments conducted on CEC2005 and CEC2022 datasets with seven traditional algorithms demonstrate that the proposed algorithm exhibits superior precision and convergence speed. Subsequently, a path planning objective function was constructed based on trajectory cost and threat cost to simulate a 3D space for UAV maritime rescue missions, and the IPKO algorithm was applied to address the UAV path planning problem. The results showed that the total cost incurred by the IPKO algorithm decreased by 5.77% compared to the PKO algorithm and by 51.19% compared to the SCA algorithm. Finally, through UAV flight tests validating its practical applicability, it is ascertained that IPKO can enhance rescue efficiency in complex maritime rescue environments.

In order to deal with strong nonlinearity and external interference in the braking process, this paper proposes a robust self-learning PID algorithm based on particle swarm optimization, which does not depend on a precise mathematical model of the controlled object. The self-learning function is used to adapt to the diversity of the runway road surface friction, the particle swarm algorithm is used to optimize the rate of self-learning, and robust control is used to deal with the modeling uncertainty and external disturbance of the system. The convergence of the control strategy is proved by theoretical analysis and simulation experiments. The superiority and accuracy of the method are verified by NASA ground test results. The simulation results shows that the adverse effect of the external disturbance is suppressed, and the ideal trajectory is tracked.

A high-quality and secure touchdown run for an aircraft is essential for economic, operational, and strategic reasons. The shortest viable touchdown run without any skidding requires variable braking pressure to manage the friction between the road surface and braking tire at all times. Therefore, the manipulation and regulation of the anti-skid braking system (ABS) should be able to handle steady nonlinearity and undetectable disturbances and to regulate the wheel slip ratio to make sure that the braking system operates securely. This work proposes an active disturbance rejection control technique for the anti-skid braking system. The control law ensures action that is bounded and manageable, and the manipulating algorithm can ensure that the closed-loop machine works around the height factor of the secure area of the friction curve, thereby improving overall braking performance and safety. The stability of the proposed algorithm is proven primarily by means of Lyapunov-based strategies, and its effectiveness is assessed by means of simulations on a semi-physical aircraft brake simulation platform.

Variable environments and constrained edge devices pose the significantly challenging task of directly recognizing the relative attitude of unmanned aerial vehicles (UAVs). Furthermore, datasets of UAV landing markers that are accessible to the general public are scarce. To tackle these challenges, we first constructed a dataset on UAV landing markers called the UAV landing marker dataset (ULMD). Then, we enhanced the You Only Look Once (YOLO) model to devise a model specifically tailored for directly recognizing the relative attitude of UAVs, termed UAV relative attitude YOLO (URA-YOLO). Within URA-YOLO, we propose an enhanced multiscale feature fusion (EMF) module that increases the network’s perceptual range and extracts feature information corresponding to various image sizes. Additionally, we propose a lightweight and efficient feature extraction (LE) module to acquire high-dimensional semantic information. Finally, to mitigate background noise interference, we propose an efficient layer aggregation network with convolutional block attention (ELAN-CA) module. The experimental results demonstrate that our model outperforms the baseline by 10.8% in terms of accuracy while occupying a mere 5.8 M in size, representing a reduction of 6.5%, achieving a satisfactory balance between performance and resource consumption.