自主无人机必须可靠地检测如电线、杆子和树枝等薄障碍物以在真实环境中安全导航。这些结构难以感知，因为它们占据像素少，视觉对比弱，并受类别不平衡影响。现有分割方法主要针对较粗的障碍物，未能充分利用所需多模态互补信息。我们提出EDFNet，一种模块化早期融合分割框架，整合RGB、深度和边缘信息用于杂乱空中场景中的薄结构感知。我们在Drone Depth and Obstacle Segmentation (DDOS)数据集上评估EDFNet，使用U-Net和DeepLabV3在预训练和非预训练设置下进行十六种模态-主干配置测试。结果表明，早期RGB-深度-边缘融合提供了一个竞争性和平衡的基线，在边界敏感和召回率指标上获得最一致的提升。预训练的RGBDE U-Net在整体性能上最佳，Thin-Structure Evaluation Score最高为0.244，均值IoU为0.219，边界IoU为0.234，同时在评估硬件上保持竞争性的运行性能（19.62 FPS）。然而，所有模型在最罕见的超薄类别上的表现仍较低，表明可靠的超薄分割仍是一个开放性挑战。总体而言，这些发现将早期RGB-深度-边缘融合定位为无人机导航中薄障碍物分割的实用且模块化的基线。
英文摘要：
Autonomous Unmanned Aerial Vehicles (UAVs) must reliably detect thin obstacles such as wires, poles, and branches to navigate safely in real-world environments. These structures remain difficult to perceive because they occupy few pixels, often exhibit weak visual contrast, and are strongly affected by class imbalance. Existing segmentation methods primarily target coarser obstacles and do not fully exploit the complementary multimodal cues needed for thin-structure perception. We present EDFNet, a modular early-fusion segmentation framework that integrates RGB, depth, and edge information for thin-obstacle perception in cluttered aerial scenes. We evaluate EDFNet on the Drone Depth and Obstacle Segmentation (DDOS) dataset across sixteen modality-backbone configurations using U-Net and DeepLabV3 in pretrained and non-pretrained settings. The results show that early RGB-Depth-Edge fusion provides a competitive and well-balanced baseline, with the most consistent gains appearing in boundary-sensitive and recall-oriented metrics. The pretrained RGBDE U-Net achieves the best overall performance, with the highest Thin-Structure Evaluation Score (0.244), mean IoU (0.219), and boundary IoU (0.234), while maintaining competitive runtime performance (19.62 FPS) on our evaluation hardware. However, performance on the rarest ultra-thin categories remains low across all models, indicating that reliable ultra-thin segmentation is still an open challenge. Overall, these findings position early RGB-Depth-Edge fusion as a practical and modular baseline for thin-obstacle segmentation in UAV navigation.
We propose a framework for Google Map aided UAV navigation in GPS-denied environment. Geo-referenced navigation provides drift-free localization and does not require loop closures. The UAV position is initialized via correlation, which is simple and efficient. We then use optical flow to predict its position in subsequent frames. During pose tracking, we obtain inter-frame translation either by motion field or homography decomposition, and we use HOG features for registration on Google Map. We employ particle filter to conduct a coarse to fine search to localize the UAV. Offline test using aer…
With the rapidly growing expansion in the use of UAVs, the ability to autonomously navigate in varying environments and weather conditions remains a highly desirable but as-of-yet unsolved challenge. In this work, we use Deep Reinforcement Learning to continuously improve the learning and understanding of a UAV agent while exploring a partially observable environment, which simulates the challenges faced in a real-life scenario. Our innovative approach uses a double state-input strategy that combines the acquired knowledge from the raw image and a map containing positional information. This po…
In this work, we propose a new learning approach for autonomous navigation and landing of an Unmanned-Aerial-Vehicle (UAV). We develop a multimodal fusion of deep neural architectures for visual-inertial odometry. We train the model in an end-to-end fashion to estimate the current vehicle pose from streams of visual and inertial measurements. We first evaluate the accuracy of our estimation by comparing the prediction of the model to traditional algorithms on the publicly available EuRoC MAV dataset. The results illustrate a $25 \%$ improvement in estimation accuracy over the baseline. Finally…
From Semantic Grounding to Decision Optimization: A Unified Framework for Long-Horizon UAV Vision-Language Navigation
State Key Laboratory of Virtual Reality Technology and Systems, Beihang University（北京航空航天大学虚拟现实技术与系统国家重点实验室）；School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）
Survey Copter / Airbus Defense and Space（空客防务与航天公司Survey Copter部门）；Hubert Curien Laboratory（于贝尔·居里安实验室）；Center for Research in Computer Vision, UCF（中佛罗里达大学计算机视觉研究中心）
In recent years, consumer Unmanned Aerial Vehicles have become very popular, everyone can buy and fly a drone without previous experience, which raises concern in regards to regulations and public safety. In this paper, we present a novel approach towards enabling safe operation of such vehicles in urban areas. Our method uses geodetically accurate dataset images with Geographical Information System (GIS) data of road networks and buildings provided by Google Maps, to compute a weighted A* shortest path from start to end locations of a mission. Weights represent the potential risk of injuries …
Is your VLM Sky-Ready? A Comprehensive Spatial Intelligence Benchmark for UAV Navigation
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Peng Cheng Laboratory（鹏城实验室）；Xiaomi EV（小米电动汽车）；Georgia Institute of Technology（佐治亚理工学院）；Institute of Automation, CAS（中国科学院自动化研究所）；National University of Singapore（新加坡国立大学）
Beyond Matching to Tiles: Bridging Unaligned Aerial and Satellite Views for Vision-Only UAV Navigation
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；State Key Laboratory of Blockchain and Data Security, Zhejiang University（浙江大学区块链与数据安全全国重点实验室）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新区（滨江）区块链与数据安全研究院）
DynFly: Dynamic-Aware Continuous Trajectory Generation for UAV Vision-Language Navigation in Urban Environments
Beijing Institute of Technology（北京理工大学）；Tsinghua University（清华大学）；Dalian University of Technology（大连理工大学）；Xidian University（西安电子科技大学）；Huazhong University of Science and Technology（华中科技大学）
Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology
Institute of Artificial Intelligence, Beihang University（北京航空航天大学人工智能学院）；MMLab, CUHK（香港中文大学MMLab）；Centre for Perceptual and Interactive Intelligence（感知与交互智能中心）
The use of autonomous UAVs for surveillance purposes and other reconnaissance tasks is increasingly becoming popular and convenient.These tasks requires the ability to successfully ingress through the rectangular openings or windows of the target structure.In this paper, a method to robustly detect the window in the surrounding using basic image processing techniques and efficient distance measure, is proposed.Furthermore, a navigation scheme which incorporates this detection method for performing navigation task has also been proposed.The whole navigation task is performed and tested in the s…
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）
Automating the navigation of unmanned aerial vehicles (UAVs) in diverse scenarios has gained much attention in recent years. However, teaching UAVs to fly in challenging environments remains an unsolved problem, mainly due to the lack of training data. In this paper, we train a deep neural network to predict UAV controls from raw image data for the task of autonomous UAV racing in a photo-realistic simulation. Training is done through imitation learning with data augmentation to allow for the correction of navigation mistakes. Extensive experiments demonstrate that our trained network (when su…
LongFly: Long-Horizon UAV Vision-and-Language Navigation with Spatiotemporal Context Integration
School of Mechanical Engineering, Beijing Institute of Technology（北京理工大学机械工程学院）；Chongqing Innovation Center, Beijing Institute of Technology（北京理工大学重庆创新中心）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；Department of Automation, Tsinghua University（清华大学自动化系）；School of Software, Dalian University of Technology（大连理工大学软件学院）；School of Artificial Intelligence, Xidian University（西安电子科技大学人工智能学院）
See-and-Reach: Precise Vision-Language Navigation for UAVs within the Field of View
School of Information Science and Engineering, Shandong University（山东大学信息科学与工程学院）；Faculty of Engineering and Information Technology, University of Technology Sydney（悉尼科技大学工程与信息技术学院）；School of Computer Science and Technology, Shandong University（山东大学计算机科学与技术学院）；School of Artificial Intelligence, Shandong University（山东大学人工智能学院）；School of Computer Science and Artificial Intelligence, Shandong Normal University（山东师范大学计算机科学与人工智能学院）；Interdisciplinary Research Center of General Artificial Intelligence, Shandong Normal University（山东师范大学通用人工智能跨学科研究中心）
RASR: Range-Aware Scale Recovery for Metric UAV Navigation
College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics（南京航空航天大学电子信息工程学院）；Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Noah Ark Lab, Huawei（华为诺亚方舟实验室）；College of Automation Engineering, Nanjing University of Aeronautics and Astronautics（南京航空航天大学自动化工程学院）；College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics（南京航空航天大学人工智能学院）；College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics（南京航空航天大学计算机科学与技术学院）
NavAgent: Multi-scale Urban Street View Fusion For UAV Embodied Vision-and-Language Navigation
Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；University of Chinese Academy of Sciences（中国科学院大学）；School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences（中国科学院大学电子电气与通信工程学院）
SpatialFly: Implicit 3D Prior-Guided Visual Reparameterization for Continuous UAV Vision-and-Language Navigation
School of Mechanical Engineering, Beijing Institute of Technology（北京理工大学机械工程学院）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；Tsinghua University（清华大学）；Department of Automation, Tsinghua University（清华大学自动化系）；School of Artificial Intelligence, Xidian University（西安电子科技大学人工智能学院）；Jianghan University（江汉大学）
FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Models
School of Intelligent Systems Engineering, Sun Yat-Sen University（中山大学智能系统工程学院）；DP Technology（DP技术公司）；Beijing University Of Posts and Telecommunications（北京邮电大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Tongji University（同济大学）；School of Integrated Innovation, Chulalongkorn University（朱拉隆功大学创新学院）
