Xiaozhou Zhu

Online incremental orthophoto generation with multiple unmanned aerial vehicles (UAVs) remains challenging, as it requires accurate, efficient, and scalable mapping from distributed aerial observations. In this paper, we present a centralized GNSS-assisted multi-UAV 3D Gaussian Splatting SLAM framework for online incremental orthophoto mapping. Each UAV independently performs visual odometry to build local submaps, which are first aligned into a unified global coordinate system using GNSS constraints and further refined via inter-agent visual loop closures for improved cross-agent consistency. To enable scalable and high-quality mapping, we introduce two complementary Gaussian map maintenance modules: plane-guided grid-based collaborative densification, which improves mapping quality and accelerates convergence under multi-UAV conditions, and visibility-aware adaptive pruning, which effectively controls redundancy and memory usage. These components allow efficient joint optimization within a unified Gaussian representation. Experiments on multiple aerial datasets using video-derived image frames captured by consumer-grade UAV cameras demonstrate that the proposed system provides a favorable trade-off between geo-consistency, visual fidelity, and efficiency compared with existing methods. Quantitatively, the proposed method achieves a GCP RMSE of 2.32 m, completes multi-UAV orthophoto generation within 3.3–5.5 min, and reduces the total mapping time by approximately 35–55% compared with the corresponding single-UAV setting, while supporting online tracking and incremental orthophoto updates with bounded latency and memory consumption.

While traditional oblique photogrammetry offers high-fidelity accuracy, it suffers from significant processing latency, making it less suitable for time-sensitive applications such as emergency response. Real-time incremental aerial mapping, which prioritizes immediate visualization, faces key challenges including the efficiency–accuracy trade-off, long-range drift, and appearance inconsistency under resource constraints and illumination variation. To address these issues, we propose a novel real-time large-scale orthomosaicking system that integrate learning-based VO(visual odometry) with GNSS(global navigation satellite system) via hierarchical alignment for efficient aerial orthomosaic generation. By combining robust hybrid VO with tightly-coupled optimization of GNSS-derived relative transforms, our method effectively mitigates long-range drift in large-scale environments. Furthermore, we introduce a semantic-aware coarse-to-fine mosaic plane fitting and a dual orthorectification strategy to adaptively balances local accuracy and global geomatric consistency. Finally, the multi-band Laplacian blending is employed to ensure seamless appearance transitions. Experimental results demonstrate that our system outperforms commercial solutions in both speed and consistency, particularly in complex urban structures, texture-sparse regions, and flight boundary areas. These results confirm that our method is able to deliver superior mapping quality while maintaining real-time performance.

Dynamic task allocation in multi-AAV systems, where pickup-and-delivery tasks arrive randomly with time windows, is challenging due to two main factors: (1) strict temporal and spatial constraints, and (2) reduced allocation optimality caused by unforeseen tasks. This letter proposes a distributed auction algorithm based on potential rewards to maximize total system profit. The algorithm operates in two phases. In the first phase, each AAV independently generates feasible task groups according to temporal and spatial constraints and evaluates candidate tasks by considering selection flexibility, cost-effectiveness, and discounted future value. In the second phase, AAVs engage in a distributed auction, exchanging bids with neighbors to reach consensus and achieve conflict-free assignments. To further enhance flexibility, a task transfer protocol is introduced, allowing idle AAVs to take over assigned but unpicked-up tasks if the tasks can be completed ahead of schedule, thereby freeing the originally assigned AAVs to pursue more profitable opportunities. Simulation results on 30 benchmark instances adapted from the Solomon dataset show that the proposed method outperforms three state-of-the-art online baselines—Consensus-Based Bundle Algorithm (CBBA), CBBA with Partial Replanning (CBBA-PR), and Distributed Group-Based Auction Algorithm (DGAA). Moreover, it achieves near-optimal performance in balanced scenarios and competitive results in high-density cases when compared with the offline solver OR-Tools.

The employment of linear features to enhance the positioning precision and robustness of point-based VIO (visual-inertial odometry) has attracted mounting attention, especially for UAV (unmanned aerial vehicle) applications where reliable 6-DoF pose estimation is critical for autonomous navigation, mission execution, and safety. This paper presents GPLVINS—GNSS (global navigation satellite system)-point-line-visual-inertial navigation system—a UAV-tailored enhancement of the nonlinear optimization-based GVINS (GNSS-visual-inertial navigation system). Unlike GVINS, which struggles with feature extraction in weak-texture environments and depends entirely on point features, GPLVINS innovatively integrates line features into its state optimization framework to enhance robustness and accuracy. While existing studies adopt the LSD (line segment detector) algorithm for line feature extraction, this approach often generates numerous short line segments in real-world scenes. Such an outcome not only increases computational costs but also degrades pose estimation performance. In order to address this issue, the present study proposes an NMS (non-maximum suppression) strategy for the refinement of LSD. The line reprojection residual is then formulated as the distance between point and line, which is incorporated into the nonlinear optimization process. Experimental validations on open-source datasets and self-collected UAV datasets across indoor, outdoor, and indoor–outdoor transition scenarios demonstrate that GPLVINS exhibits superior positioning performance and enhanced robustness for UAVs in environments with feature degradation or drastic lighting intensity variations.

This paper presents a fuzzy adaptive dynamic surface control strategy for Unmanned Aerial Vehicles (UAVs) subjected to external disturbances, parameter uncertainties and actuator failures. The control framework integrates three key components: (1) a fuzzy logic system that approximates and compensates for parameter uncertainties using universal approximation principles, (2) a real-time disturbance observer that estimates and actively suppresses external disturbances, and (3) a dynamic surface control structure that mitigates the differential explosion issue inherent in traditional backstepping approaches while reducing computational complexity. Lyapunov stability analysis proves that the proposed controller ensures semi-globally uniformly ultimately bounded tracking errors and robust output trajectory tracking. Comparative numerical simulations demonstrate superior performance over existing methods, particularly in disturbance rejection and uncertainty handling. Physical experiments on a quadrotor UAV platform validate the practical feasibility and effectiveness of the proposed approach.

Cameras and LiDAR sensors have been extensively utilized in autonomous systems to enhance perception accuracy and robustness, owing to the highly complementary nature of their characteristics. The spatial and temporal relationships between these sensors are crucial for multi-sensor fusion technology, making calibration between heterogeneous sensors extremely important. This calibration process typically involves estimating the extrinsic parameters between sensors. Over the past two decades, with the advancement of camera and LiDAR technologies, numerous spatial calibration solutions have been proposed for various sensor configurations. The question of whether LiDAR-camera calibration has been fully resolved has arisen and been extensively discussed. This review addresses this question by thoroughly analyzing the anatomy of mainstream LiDAR-camera calibration systems. Consequently, we thoroughly dissect the key technologies in each component of the calibration framework and discuss the future efforts in each direction. Furthermore, we summarize and list available open-source codes and datasets for LiDAR-camera calibration to facilitate other researchers’ use and comparison of these tools. To further contribute to the community, the latest open-source code and datasets in this research field will be continuously maintained and updated on our homepage https://github.com/haoxinnihao/LiDAR-camera-calibration-summary.

In this paper, we investigate the paradigm of deep learning techniques to enhance the performance of visual-based SLAM systems, particularly in challenging environments. By leveraging deep feature extraction and matching methods, we propose a robust, versatile hybrid visual SLAM framework, Rover-SLAM, aimed at improving adaptability in adverse conditions, such as dynamic lighting conditions, areas with weak textures, and camera jitter. Building on excellent learning-based algorithms of recent years, we designed from scratch a novel system that uses the same feature extraction and matching approaches for all SLAM tasks. Our system supports multiple modes, including monocular, stereo, monocular-inertial, and stereo-inertial configurations, offering flexibility to address diverse real-world scenarios. Through comprehensive experiments conducted on publicly available datasets and self-collected data, we demonstrate the superior performance of our Rover-SLAM system compared to the SOTA approaches. We also conducted an in-depth analysis of the integration of visual SLAM with deep learning methods quantitatively to provide insights for future research endeavors in this domain. The experimental results showcase the system’s capability of achieving higher localization accuracy and robust tracking performance.