With the widespread application of unmanned aerial vehicles, harsh environments require higher control performance. Numerous existing works offer solutions for handling external disturbances during flight; however, timeliness disturbance compensation is rarely discussed. This study focuses on trajectory tracking under wind disturbances, specifically two types interference: average and shear. After compensating disturbance, a novel antidisturbance sliding mode designed based reference model,...

In recent years, multi-rotor unmanned aerial vehicles (UAV) have been widely applied for various applications; however, they are yet to be as commonly utilized in certain industrial transportation applications. Thus, this work designed and implemented a reference model-based integral sliding mode control (SMC) method the velocity controller of UAV. The was compared with an SMC scheme, then modeling robustness were verified. Finally, proposed six-rotor Three experiments involving...

In the field of object detection algorithms, task infrared vehicle holds significant importance. By utilizing sensors, this approach detects thermal radiation emitted by vehicles, enabling robust even during nighttime or adverse weather conditions, thus enhancing traffic safety and efficiency intelligent driving systems. Current techniques for encounter difficulties in handling low contrast, detecting small objects, ensuring real-time performance. domain lightweight certain existing...

This paper introduces a position controller for drone transmission line inspection (TLI) utilizing the integral sliding mode control (SMC) method. The controller, leveraging GNSS and visual deviation data, exhibits high accuracy robust anti-interference capabilities. A correction strategy is proposed to capture high-voltage information more robustly accurately. Lateral calculated using microwave radar attitude angle pixels derived from recognition via MobileNetV3. approach enables accurate...

In this paper, we study autonomous landing scene recognition with knowledge transfer for drones. Considering the difficulties in aerial remote sensing, especially that some scenes are extremely similar, or same has different representations altitudes, employ a deep convolutional neural network (CNN) based on and fine-tuning to solve problem. Then, LandingScenes-7 dataset is established divided into seven classes. Moreover, there still novelty detection problem classifier, address by...

The Deep Reinforcement Learning (DRL) algorithm is an optimal control method with generalization capacity for complex nonlinear coupled systems. However, the DRL agent maintains command saturation and response overshoot to achieve fastest response. In this study, a reference model-based strategy termed Model-Reference Twin Delayed Deterministic (MR-TD3) was proposed controlling pitch attitude depth of autonomous underwater vehicle (AUV) system. First, model based on actual AUV system...

Unmanned aerial vehicles (UAVs) face significant challenges when landing on moving targets due to disturbances, such as wind, that affect precision. This study develops a system leverages global navigation satellite (GNSS) signals and UAV visual data enable real-time precision landings, incorporates sliding mode controller (SMC) mitigate external disturbances throughout the process. To this end, reference-model-based SMC is proposed, which defines reference values for each state enhance...

With the rapid development of microelectronics, unmanned aerial vehicles (UAVs) for electric inspection tasks have become popular. Among these tasks, transmission line inspections are more complicated than component and tower owing to small size, poor functionality, severe magnetic field interference lines. Existing solutions invariably use high-precision devices maintain safety distances during inspections. However, capturing detailed information over long is challenging. Moreover,...

Due to the differences between simulations and real world, application of reinforcement learning (RL) in drone control encounters problems such as oscillations instability. This study proposes a strategy for quadrotor drones using reference model (RM) based on deep RL. Unlike conventional studies associated with optimal adaptive control, this method uses neural network design flight controller drones, which can map drone’s states target values commands directly. The was developed...