Visual servoing is a control method that utilizes image feedback to control robot motion, and it has been widely applied in unmanned aerial vehicle (UAV) motion control. However, due to field-of-view (FOV) constraints, visual servoing still faces challenges, such as easy target loss and low control efficiency. To address these issues, visual servoing control for UAVs based on the deep reinforcement learning (DRL) method is proposed, which dynamically adjusts the servo gain in real time to avoid target loss and improve control efficiency. Firstly, a Markov model of visual servoing control for a UAV under field-of-view constraints is established, which consists ofquintuplet and considers the improvement of the control efficiency. Secondly, an improved deep Q-network (DQN) algorithm with a target network and experience replay is designed to solve the Markov model. In addition, two independent agents are designed to adjust the linear and angular velocity servo gains in order to enhance the control performance, respectively. In the simulation environment, the effectiveness of the proposed method was verified using a monocular camera.

Accurate trajectory tracking of quadrotor UAVs remains challenging due to highly nonlinear dynamics, model uncertainties, and time-varying external disturbances, which make it difficult to achieve both precise position tracking and stable attitude regulation under control constraints. To tackle these coupled problems, this paper develops a hierarchical control framework in which the outer-loop particle swarm optimization (PSO)-compensated model predictive controller (PSMC) adaptively mitigates prediction errors and enhances robustness, while the inner-loop enhanced linear quadratic regulator (LQR), augmented with gain scheduling and control-rate relaxation, accelerates attitude convergence and ensures smooth control actions under varying flight conditions. A Lyapunov-based stability analysis is conducted to ensure closed-loop convergence. Simulation results on a helical reference trajectory show that, compared with the conventional MPC–LQR baseline, the proposed framework reduces the mean tracking errors by more than 13.2%, 17.1%, and 28% in the x-, y-, and z-directions under calm conditions, and by more than 34%, 26.2%, and 46.8% under wind disturbances. These results prove that the proposed hierarchical PSMC–LQR framework achieves superior trajectory tracking accuracy, strong robustness, and high practical implement ability for quadrotor control applications.

Unmanned Aerial Vehicles (UAVs) play vital roles in traffic surveillance, disaster management, and border security, highlighting the importance of reliable infrared–visible image detection under complex illumination conditions. However, UAV-based infrared–visible detection still faces challenges in multi-scale target recognition, robustness to lighting variations, and efficient cross-modal information utilization. To address these issues, this study proposes a lightweight Dual-modality Adaptive Pyramid Transformer (DAP) module integrated into the YOLOv8 framework. The DAP module employs a hierarchical self-attention mechanism and a residual fusion structure to achieve adaptive multi-scale representation and cross-modal semantic alignment while preserving modality-specific features. This design enables effective feature fusion with reduced computational cost, enhancing detection accuracy in complex environments. Experiments on the DroneVehicle and LLVIP datasets demonstrate that the proposed DAP-based YOLOv8 achieves mAP_50:95 scores of 61.2% and 62.1%, respectively, outperforming conventional methods. The results validate the capability of the DAP module to optimize cross-modal feature interaction and improve UAV real-time infrared–visible target detection, offering a practical and efficient solution for UAV applications such as traffic monitoring and disaster response.

Coordinated compression and ventilation feedback in manikin-based cardiopulmonary resuscitation (CPR) training requires clear links between sensor measurements, detected events and quality decisions. We characterise these links in an STM32 prototype combining a BF350 strain gauge, an AD620 interface and an HU108 airflow switch. Five static laser-reference pairs used for recalibration yielded a mean system-minus-reference bias of +1.14 mm, MAE of 1.34 mm and RMSE of 1.98 mm. Loading–unloading separation was 0.7–2.3 mm, and refitted conversion coefficients varied with installation. Laser-labelled qualified-compression trials yielded count-based sensitivities of 88.0–93.5% across regular rhythms; false-positive proportions were 46.5% for shallow actions and 20.5% for incomplete release. Controlled forward-flow tests detected 30/30 routine pulses and 3/30 weakest pulses, with 99.89% specificity in the defined one-second no-flow windows. Across 100 electrical input-to-LED-driver tests, mean delay was 26.4 ms and the observed range was 17.5 ms. These results define an operating envelope for the prototype and identify calibration, action qualification and airflow intensity as distinct determinants of feedback reliability. The reported endpoints are calibration-set agreement, count-based classification and electrical driver timing; accuracy on held-out data, physical compression-to-light/sound latency and educational effectiveness require separate evaluation.

Typhoon-eye sensing places unmanned aerial vehicle (UAV) swarms in a setting where the wind field that carries the target signal also displaces aircraft, drains energy, weakens links, and increases failure risk. A rule that improves only routing or only motion can therefore move the swarm into another failure mode. This paper proposes a risk-driven cross-layer coordination scheme for such missions. A bounded risk index, computed from isolation, connectivity loss, and wind intensity, acts as a supervisory variable for multi-hop reachability maintenance, isolated-node recovery, and layered altitude adaptation. For evaluation, graph reachability is separated from useful data return through a degraded multi-hop aggregation model that includes distance loss, wind-dependent reliability, rain-induced packet loss, relay forwarding loss, and mothership collection capacity. The simulator combines a bounded Holland-type storm field, stochastic turbulence, nonlinear propulsion energy consumption, and wind-dependent structural failure. Against three literature-inspired baselines, two AI-inspired comparators, and six ablation variants, the method keeps a balanced profile across connectivity, isolation, wind exposure, data collection, and survival. In 30-run steady-state robustness tests under heavy-rain attenuation, the full strategy showed clear gains over routing-only and multi-agent reinforcement learning (MARL)-routing comparators in connectivity and isolation, but did not uniformly dominate topology reconstruction or the multi-agent deep deterministic policy gradient–artificial potential field (MADDPG-APF) recovery comparator. The results indicate that, in storm-dominated swarm sensing, resilience comes mainly from coordinating exposure reduction with topology stabilization, rather than from optimizing a single layer.

The paramount value of image fusion is manifested in effectively enhancing downstream tasks. However, compatibility with subsequent tasks is compromised due to the semantic deficiency of fusion representations generated by current approaches. To mitigate this limitation, a semantic-guided multi-level collaborative fusion network is proposed, termed DSIFuse. By leveraging semantic priors and global context extracted from auxiliary segmentation branches, a multi-level interaction space is constructed to explicitly refine cross-modal features. Specifically, a cross-modal feature correction mechanism is designed to enhance semantic alignment by injecting complementary visible–infrared information at each layer, while a three-level interaction strategy gradually integrates unimodal features and semantic maps to generate semantically enriched representations. To mitigate semantic information loss during image reconstruction, a semantic compensation block is employed, incorporating interactive representations from prior layers and global semantic maps into the multi-scale decoder. Finally, the overall loss integrates semantic supervision, gradient, and intensity loss. Experiments conducted on public datasets indicate that clear fusion images are generated by DSIFuse, with improved structural consistency and reduced artifacts. Under a unified benchmark, the fused representations subsequently yield improved performance in downstream object detection tasks.