Ultra-low altitude UAVs (below 120 meters) are gaining importance in the booming low-altitude economy, where GNSS signals are often unreliable or unavailable. Vision-based localization emerges as a promising alternative; however, existing benchmarks are not designed for ultra-low flight and typically adopt pinhole cameras with limited field of view, making them less effective in handling occlusions and repetitive textures near the ground. To address these limitations, we introduce the first panoramic UAV localization dataset tailored for ultra-low altitude scenarios. Built on a four-fisheye-camera system in the high-fidelity RflySim platform, our dataset captures diverse conditions — including day/night cycles, extreme weather, and dynamic obstacles — and contains over hundreds of thousands of frames. It is further enhanced with real-world UAV panoramic data to narrow the sim-to-real gap and will be continuously updated for broader applicability. Comprehensive experiments confirm the effectiveness and transferability of our dataset, establishing it as a robust benchmark for future research in vision-based UAV localization.

As unmanned aerial vehicles (UAVs) lead the way in the development of future digital smart cities, they continue to face scrutiny due to safety concerns. While robotics simulators offer UAVs efficient and cost-effective testing environments, they often lack comprehensive safety design considerations and user testing requirements. In this study, we introduce RflySimSaT, a dedicated safety testing platform for UAVs that addresses safety factors throughout the entire lifecycle. This platform incorporates diverse fault testing scenarios, high-fidelity dynamic models, an integrated safety assessment framework, standardized testing procedures, and customizable interfaces. The modular architecture and deployment of RflySimSaT facilitate plug-and-play cross-platform closed-loop safety testing. Users simply need to supply their aircrafts and autopilots, enabling them to efficiently navigate the phases of development, deployment, testing, and assessment using the customizable modules and standardized processes offered by the platform. To validate RflySimSaT’s credibility and versatility, we designed various test cases that demonstrate its practicality and scalability. Additionally, we provide a comprehensive user manual, detailed case studies, and a rich fault dataset. The platform is open-source and available at: https://github.com/RflySim/RFlySimSafe/tree/RflySimSaT.

We introduceSRDrone, a novel system designed for self-refinement task planning in industrial-grade embodied drones.SRDroneincorporates two key technical contributions: First, it employs a continuous state evaluation methodology to robustly and accurately determine task outcomes and provide explanatory feedback. This approach supersedes conventional reliance on single-frame final-state assessment for continuous, dynamic drone operations. Second,SRDroneimplements a hierarchical Behavior Tree (BT) modification model. This model integrates multi-level BT plan analysis with a constrained strategy space to enable structured reflective learning from experience. Experimental results demonstrate thatSRDroneachieves a 44.87% improvement in Success Rate (SR) over baseline methods. Furthermore, real-world deployment utilizing an experience base optimized through iterative self-refinement attains a 96.25% SR. By embedding adaptive task refinement capabilities within an industrial-grade BT planning framework,SRDroneeffectively integrates the general reasoning intelligence of Large Language Models (LLMs) with the stringent physical execution constraints inherent to embodied drones. Code is available athttps://github.com/ZXiiiC/SRDrone.

The performance of a vision simultaneous localization and mapping (SLAM) system based on hand-crafted features degrades significantly in harsh environments due to unstable feature tracking. With the breakthrough of convolutional neural networks in deep feature extraction tasks, many researchers have tried to incorporate them into SLAM systems. However, it’s challenging to guarantee the real-time performance of the entire SLAM system, and the erroneous usage scenarios limit the superior performance of deep feature extraction methods. To overcome these problems, we propose a visual-inertial SLAM system with multi-level detector and descriptor, called VINS-MLD2. In our framework, we first design an efficient deep feature extraction network that has the same performance as R2D2 by concatenating multi-level features, but runs 3 times faster under the image resolution commonly used in SLAM. Then, based on the camera baseline, we introduce the Matching Fusion, a matching method that fuses deep descriptor matching and optical flow matching results to improve matching accuracy for both short and wide baselines. In addition, an adaptive matching strategy is proposed to balance the running time and accuracy by adaptively adjusting the matching method. Experimental results in unmanned aerial vehicle (UAV) deployments and real-world environments demonstrate that the proposed method tracks features more stably and accurately. The code is public at https://github.com/dongdong-cai/VINS-MLD2.

In this article, we propose a downlink communication scheme for large-scale high-interference unmanned aerial vehicle (UAV) swarm network based on nonorthogonal multiple access (NOMA), clustering, and reinforcement learning (RL). Since a large number of UAVs increases the complexity of downlink communication, we first introduce a load-balancing fuzzy C-Means (LB-FCMs) algorithm for UAV clustering. Downlink communication consists of three stages: 1) UAV clustering; 2) data aggregation; and 3) data offloading. We have two goals: 1) maximize the data aggregation rate of the network while ensuring fairness of UAVs’ spectrum access for UAV-to-UAV (U2U) communications during data aggregation and 2) maximize network data offloading rate while ensuring ground station priority for UAV-to-ground (U2G) communications during data offloading. To address these two problems, first, we introduce uplink NOMA and downlink NOMA to eliminate part of the intrasystem interference, respectively. Then, we propose a multiagent RL framework for optimizing channel, transmit power, and trajectory scheduling (MARL-CPT). MARL-CPT consists of two parts of the algorithm, which solve the optimization problems in two stages, respectively. Simulation results show that our proposed method outperforms random decision-making and polling-based single-agent RL methods in terms of final score, fairness, and priority. For trajectory scheduling during data offloading, our method finds the optimal hover position while taking less than half the time compared to single-agent RL methods.

With the explosive growth of mobile devices and communication facilities, electromagnetic interference (EMI) has become a common phenomenon affecting the communication band. Based on the shielding capability of electromagnetic bands in EMI, frequency selective surfaces (FSSs) are used to shield or suppress specific electromagnetic bands. Additionally, EMI can be negative control and may change the EMI band. Thus, a single FSS cannot effectively shield EMI due to its limited shielding capacity. To address this issue, we first construct a novel interference shielding model to guard the target area. The related shielding problem is modeled as the UAV-driven FSS (UFSS) configuration problem. Second, we propose an intelligent configuration method based on a stochastic game to solve the configuration optimization problem effectively. In the proposed method, we model the interaction between UFSSs and interferers as a stochastic game, where we provide each UFSS with two different options for updating its shielding configuration strategy. According to the shielding configuration strategy generated by the proposed stochastic game, we propose a square loop resource allocation model based on resource constraints to promote each UFSS to update its square loop. Finally, the numerical results and analysis show that our proposed method is more effective and feasible than other band shielding configuration schemes.

The traditional multicopter design method usually requires a long iterative process to find the optimal design based on given performance requirements. The method is uneconomical and inefficient. In this article, a practical method is proposed to automatically calculate the optimal multicopter design according to the given design requirements including flight time, altitude, payload capacity, and maneuverability. The proposed method contains two algorithms, including an off-line algorithm and an online algorithm. The off-line algorithm finds the optimal components (propeller and electronic speed controller) for each motor to establish its component combination, and subsequently, these component combinations and their key performance parameters are stored in a combination database. The online algorithm obtains the multicopter design results that satisfy the given requirements by searching through the component combinations in the database and calculating the optimal parameters for the battery and airframe. Subsequently, these requirement-satisfied multicopter design results are obtained and sorted according to an objective function that contains evaluation indexes, including size, weight, performance, and practicability. The proposed method has the advantages of high precision and quick calculating speed because parameter calibrations and time-consuming calculations are completed offline. Experiments are performed to validate the effectiveness and practicality of the proposed method. Comparisons with the brutal search method and other design methods demonstrate the efficiency of the proposed method.Note to Practitioners—The proposed method is fast and practical to obtain an optimal solution by only using a low-performance web server, and the algorithm has been published online athttp://www.flyeval.com/recalc.htmlto provide an online optimization design service for users. To make it convenient to apply the proposed method to multicopter designs, the propulsion system combination database obtained by our off-line algorithm is released along with the article. This database includes more than 1500 experimentally calibrated propulsion combinations, which are adequate for readers to use the proposed optimization algorithms to design multicopters with weights (sizes) ranging from 0.2 to 50 kg.