Swarm in Blocks, originally developed for CopterHack 2022, is a high-level interface that simplifies drone swarm programming using a block-based language. Building on the Clover platform, this tool enables users to create functionalities like loops and conditional structures by assembling code blocks. In 2023, we introduced Swarm in Blocks 2.0, further refining the platform to address the complexities of swarm management in a user-friendly way. As drone swarm applications grow in areas like delivery, agriculture, and surveillance, the challenge of managing them, especially for beginners, has also increased. The Atena team developed this interface to make swarm handling accessible without requiring extensive knowledge of ROS or programming. The block-based approach not only simplifies swarm control but also expands educational opportunities in programming.
Swarm in Blocks 是一个最初为 CopterHack 2022 开发的高级接口,它使用积木式的编程语言简化了无人机群组编程。基于 Clover 平台,该工具让用户通过拼接代码块来创建循环和条件结构等功能。在 2023 年,我们推出了 Swarm in Blocks 2.0 版本,进一步完善平台以更加用户友好的方式解决群组管理的复杂性问题。随着无人机群应用在交付、农业和监控等领域的增长,管理和控制这些群体的挑战也越来越大,尤其是在初学者中更为明显。Atena 团队开发此界面旨在使无人机群操作易于掌握,无需深入了解 ROS 或编程知识。积木式的编程方式不仅简化了无人机群组的控制,还为编程教育提供了更多的机会。
https://arxiv.org/abs/2508.11498
Convolutional neural networks (CNNs) have demonstrated strong performance in visual recognition tasks, but their inherent reliance on regular grid structures limits their capacity to model complex topological relationships and non-local semantics within images. To address this limita tion, we propose the hierarchical graph feature enhancement (HGFE), a novel framework that integrates graph-based rea soning into CNNs to enhance both structural awareness and feature representation. HGFE builds two complementary levels of graph structures: intra-window graph convolution to cap ture local spatial dependencies and inter-window supernode interactions to model global semantic relationships. Moreover, we introduce an adaptive frequency modulation module that dynamically balances low-frequency and high-frequency signal propagation, preserving critical edge and texture information while mitigating over-smoothing. The proposed HGFE module is lightweight, end-to-end trainable, and can be seamlessly integrated into standard CNN backbone networks. Extensive experiments on CIFAR-100 (classification), PASCAL VOC, and VisDrone (detection), as well as CrackSeg and CarParts (segmentation), validated the effectiveness of the HGFE in improving structural representation and enhancing overall recognition performance.
卷积神经网络(CNN)在视觉识别任务中表现出强大的性能,但它们对规则网格结构的依赖限制了其建模复杂拓扑关系和图像中的非局部语义的能力。为了解决这一局限性,我们提出了一种新颖的框架——分层图特征增强(HGFE),该框架将基于图的推理整合到CNN中,以提升模型在结构感知和特征表示方面的表现能力。HGFE构建了两个互补层次的图结构:窗口内的图卷积用于捕捉局部空间依赖关系,以及窗口间的超节点交互用于建模全局语义关系。 此外,我们还引入了一种自适应频率调制模块,该模块能够动态平衡低频和高频信号的传播,在保留关键边缘和纹理信息的同时缓解过度平滑的问题。所提出的HGFE模块轻量、端到端可训练,并且可以无缝集成到标准CNN骨干网络中。 在CIFAR-100(分类)、PASCAL VOC和VisDrone(检测),以及CrackSeg和CarParts(分割)等数据集上的广泛实验验证了HGFE在改进结构表示并提升整体识别性能方面的有效性。
https://arxiv.org/abs/2508.11497
Generalized planning using deep reinforcement learning (RL) combined with graph neural networks (GNNs) has shown promising results in various symbolic planning domains described by PDDL. However, existing approaches typically represent planning states as fully connected graphs, leading to a combinatorial explosion in edge information and substantial sparsity as problem scales grow, especially evident in large grid-based environments. This dense representation results in diluted node-level information, exponentially increases memory requirements, and ultimately makes learning infeasible for larger-scale problems. To address these challenges, we propose a sparse, goal-aware GNN representation that selectively encodes relevant local relationships and explicitly integrates spatial features related to the goal. We validate our approach by designing novel drone mission scenarios based on PDDL within a grid world, effectively simulating realistic mission execution environments. Our experimental results demonstrate that our method scales effectively to larger grid sizes previously infeasible with dense graph representations and substantially improves policy generalization and success rates. Our findings provide a practical foundation for addressing realistic, large-scale generalized planning tasks.
使用深度强化学习(RL)与图神经网络(GNNs)相结合进行通用规划,在由PDDL描述的各种符号规划领域中取得了显著成果。然而,现有方法通常将规划状态表示为完全连接的图形,这导致随着问题规模的增长边缘信息组合爆炸和大量稀疏性,特别是在大型网格环境中尤为明显。这种密集表示法会稀释节点级别的信息,内存需求呈指数级增长,并最终使得大规模问题的学习变得不可行。为了应对这些挑战,我们提出了一种稀疏且目标感知的GNN表示方法,该方法选择性地编码相关的局部关系,并明确整合与目标相关的位置特征。通过在网格世界中基于PDDL设计新的无人机任务场景,以有效地模拟现实中的任务执行环境来验证我们的方法。实验结果表明,相对于密集图表示,我们的方法能够有效扩展到先前不可行的更大规模网格,并显著提高策略泛化能力和成功率。我们的研究为解决大规模通用规划的实际问题提供了实用基础。
https://arxiv.org/abs/2508.10747
Infrared-visible object detection has shown great potential in real-world applications, enabling robust all-day perception by leveraging the complementary information of infrared and visible images. However, existing methods typically require dual-modality annotations to output detection results for both modalities during prediction, which incurs high annotation costs. To address this challenge, we propose a novel infrared-visible Decoupled Object Detection framework with Single-modality Annotations, called DOD-SA. The architecture of DOD-SA is built upon a Single- and Dual-Modality Collaborative Teacher-Student Network (CoSD-TSNet), which consists of a single-modality branch (SM-Branch) and a dual-modality decoupled branch (DMD-Branch). The teacher model generates pseudo-labels for the unlabeled modality, simultaneously supporting the training of the student model. The collaborative design enables cross-modality knowledge transfer from the labeled modality to the unlabeled modality, and facilitates effective SM-to-DMD branch supervision. To further improve the decoupling ability of the model and the pseudo-label quality, we introduce a Progressive and Self-Tuning Training Strategy (PaST) that trains the model in three stages: (1) pretraining SM-Branch, (2) guiding the learning of DMD-Branch by SM-Branch, and (3) refining DMD-Branch. In addition, we design a Pseudo Label Assigner (PLA) to align and pair labels across modalities, explicitly addressing modality misalignment during training. Extensive experiments on the DroneVehicle dataset demonstrate that our method outperforms state-of-the-art (SOTA).
红外-可见光物体检测技术在实际应用中展现出巨大潜力,通过利用红外图像和可见光图像的互补信息,实现了全天候感知。然而,现有方法通常需要双模态注释来输出两种模式的检测结果,这导致了高昂的标注成本。为解决这一挑战,我们提出了一种新颖的单模态标签红外-可见光解耦物体检测框架(DOD-SA)。该框架基于单一和双重模态协作教师-学生网络(CoSD-TSNet),包含一个单模态分支(SM-Branch)和一个双模态解耦分支(DMD-Branch)。教师模型生成未标注模式的伪标签,同时支持学生模型的训练。这种协同设计使得知识可以从已标注的模态传递到未标注的模态,并促进有效的SM到DMD分支监督。 为了进一步提高模型的解耦能力和伪标签质量,我们引入了一种渐进式和自适应训练策略(PaST),该策略将模型训练分为三个阶段:(1) 预训练单模态分支;(2) 使用单模态分支指导双模态解耦分支的学习;以及 (3) 优化和完善双模态解耦分支。此外,我们设计了一种伪标签分配器(PLA),用于跨模式对齐和配对标签,明确解决了训练过程中模态不匹配的问题。 在DroneVehicle数据集上的广泛实验表明,我们的方法优于当前最先进的技术(SOTA)。
https://arxiv.org/abs/2508.10445
Visual geo-localization for drones faces critical degradation under weather perturbations, \eg, rain and fog, where existing methods struggle with two inherent limitations: 1) Heavy reliance on limited weather categories that constrain generalization, and 2) Suboptimal disentanglement of entangled scene-weather features through pseudo weather categories. We present WeatherPrompt, a multi-modality learning paradigm that establishes weather-invariant representations through fusing the image embedding with the text context. Our framework introduces two key contributions: First, a Training-free Weather Reasoning mechanism that employs off-the-shelf large multi-modality models to synthesize multi-weather textual descriptions through human-like reasoning. It improves the scalability to unseen or complex weather, and could reflect different weather strength. Second, to better disentangle the scene and weather feature, we propose a multi-modality framework with the dynamic gating mechanism driven by the text embedding to adaptively reweight and fuse visual features across modalities. The framework is further optimized by the cross-modal objectives, including image-text contrastive learning and image-text matching, which maps the same scene with different weather conditions closer in the respresentation space. Extensive experiments validate that, under diverse weather conditions, our method achieves competitive recall rates compared to state-of-the-art drone geo-localization methods. Notably, it improves Recall@1 by +13.37\% under night conditions and by 18.69\% under fog and snow conditions.
无人机视觉地理定位在天气变化(如雨和雾)条件下会面临严重的性能退化,现有方法存在两个根本性的局限:1) 过度依赖有限的天气类别,限制了其泛化能力;2) 对纠缠在一起的场景与天气特征解耦不够理想,通过伪天气类别来处理。我们提出了WeatherPrompt,这是一种多模态学习范式,通过融合图像嵌入和文本上下文来建立不受天气影响的表现形式。 我们的框架有两个关键贡献: 1. **无训练天气推理机制**:利用现成的大型多模态模型,通过类似人类的推理合成多种天气条件下的文字描述。这改善了对未见过或复杂天气情况的适应能力,并能反映不同强度的天气变化。 2. 为了更好地分离场景和天气特征,我们提出了一种基于文本嵌入驱动的动态门控机制多模态框架,该机制能够自适应地重新加权并融合跨模式的视觉特性。通过图像-文本对比学习和图像-文本匹配等跨模态目标进一步优化框架,使得在不同天气条件下相同的场景能够在表示空间中更接近。 广泛的实验验证了我们的方法在各种天气条件下均能达到与当前最先进的无人机地理定位方法相当或更高的召回率:特别是在夜间情况下提高了13.37%,而在雾和雪的情况下提升了18.69%。
https://arxiv.org/abs/2508.09560
Detecting tiny objects in multimodal Red-Green-Blue-Thermal (RGBT) imagery is a critical challenge in computer vision, particularly in surveillance, search and rescue, and autonomous navigation. Drone-based scenarios exacerbate these challenges due to spatial misalignment, low-light conditions, occlusion, and cluttered backgrounds. Current methods struggle to leverage the complementary information between visible and thermal modalities effectively. We propose COXNet, a novel framework for RGBT tiny object detection, addressing these issues through three core innovations: i) the Cross-Layer Fusion Module, fusing high-level visible and low-level thermal features for enhanced semantic and spatial accuracy; ii) the Dynamic Alignment and Scale Refinement module, correcting cross-modal spatial misalignments and preserving multi-scale features; and iii) an optimized label assignment strategy using the GeoShape Similarity Measure for better localization. COXNet achieves a 3.32\% mAP$_{50}$ improvement on the RGBTDronePerson dataset over state-of-the-art methods, demonstrating its effectiveness for robust detection in complex environments.
在多模态红绿蓝热(RGBT)图像中检测微小物体是计算机视觉中的一个关键挑战,尤其是在监控、搜索和救援以及自主导航等领域。基于无人机的场景由于空间错位、低光照条件、遮挡和杂乱背景等因素而加剧了这些问题。当前的方法难以有效利用可见光与热成像模态之间的互补信息。我们提出了一种名为COXNet的新框架,用于RGBT微小物体检测,通过三大核心创新解决了上述问题:i) 跨层融合模块,将高级别的可见光特征和低级别的热成像特征进行融合,以提高语义和空间精度;ii) 动态对齐与尺度细化模块,纠正跨模态的空间错位,并保持多尺度特征;iii) 使用GeoShape相似度测量的优化标签分配策略,用于更好的定位。COXNet在RGBTDronePerson数据集上比最先进的方法提高了3.32%的mAP$_{50}$,证明了其在复杂环境中进行稳健检测的有效性。
https://arxiv.org/abs/2508.09533
Drones operating in complex environments face a significant threat from thin obstacles, such as steel wires and kite strings at the submillimeter level, which are notoriously difficult for conventional sensors like RGB cameras, LiDAR, and depth cameras to detect. This paper introduces SkyShield, an event-driven, end-to-end framework designed for the perception of submillimeter scale obstacles. Drawing upon the unique features that thin obstacles present in the event stream, our method employs a lightweight U-Net architecture and an innovative Dice-Contour Regularization Loss to ensure precise detection. Experimental results demonstrate that our event-based approach achieves mean F1 Score of 0.7088 with a low latency of 21.2 ms, making it ideal for deployment on edge and mobile platforms.
在复杂环境中运行的无人机面临着来自细小障碍物(如钢丝和风筝线)的重大威胁,这些障碍物通常小于毫米级,对于传统的传感器来说非常难以检测,比如RGB相机、激光雷达和深度摄像头。本文介绍了SkyShield,这是一种基于事件驱动、端到端设计的框架,专门用于感知毫米以下级别的障碍物。通过利用细小障碍物在事件流中呈现的独特特征,我们的方法采用了轻量级U-Net架构,并创新性地引入了Dice轮廓正则化损失,以确保精确检测。 实验结果显示,基于事件的方法实现了0.7088的平均F1分数和21.2毫秒的低延迟,使其非常适合部署在边缘计算和移动平台上。
https://arxiv.org/abs/2508.09397
This paper introduces an advanced AI-driven perception system for autonomous quadcopter navigation in GPS-denied indoor environments. The proposed framework leverages cloud computing to offload computationally intensive tasks and incorporates a custom-designed printed circuit board (PCB) for efficient sensor data acquisition, enabling robust navigation in confined spaces. The system integrates YOLOv11 for object detection, Depth Anything V2 for monocular depth estimation, a PCB equipped with Time-of-Flight (ToF) sensors and an Inertial Measurement Unit (IMU), and a cloud-based Large Language Model (LLM) for context-aware decision-making. A virtual safety envelope, enforced by calibrated sensor offsets, ensures collision avoidance, while a multithreaded architecture achieves low-latency processing. Enhanced spatial awareness is facilitated by 3D bounding box estimation with Kalman filtering. Experimental results in an indoor testbed demonstrate strong performance, with object detection achieving a mean Average Precision (mAP50) of 0.6, depth estimation Mean Absolute Error (MAE) of 7.2 cm, only 16 safety envelope breaches across 42 trials over approximately 11 minutes, and end-to-end system latency below 1 second. This cloud-supported, high-intelligence framework serves as an auxiliary perception and navigation system, complementing state-of-the-art drone autonomy for GPS-denied confined spaces.
这篇论文介绍了一种先进的AI驱动感知系统,用于在无GPS的室内环境中自主四旋翼飞行器导航。所提出的框架利用云计算来卸载计算密集型任务,并且集成了一个定制设计的印制电路板(PCB),以实现高效的传感器数据采集,从而实现在狭窄空间中的稳健导航。 该系统结合了YOLOv11进行物体检测、Depth Anything V2进行单目深度估计、配备飞行时间(ToF)传感器和惯性测量单元(IMU)的PCB以及基于云端的大规模语言模型(LLM),用于上下文感知决策。通过校准后的传感器偏移量实施虚拟安全保护区,以确保碰撞避免,并且多线程架构实现了低延迟处理。增强了空间意识,借助卡尔曼滤波器进行三维边界框估计。 在室内测试环境中进行了实验结果验证,展示了强大的性能:物体检测的平均精度(mAP50)达到0.6,深度估计均方绝对误差(MAE)为7.2厘米,在大约11分钟内的42次试验中仅有16次安全保护区域违反事件,并且端到端系统延迟低于1秒。 这种基于云支持、高智能的框架作为一个辅助感知和导航系统,可以补充最先进的无人机自主技术在无GPS限制的小型空间中的应用。
https://arxiv.org/abs/2508.07885
Field trials are vital in herbicide research and development to assess effects on crops and weeds under varied conditions. Traditionally, evaluations rely on manual visual assessments, which are time-consuming, labor-intensive, and subjective. Automating species and damage identification is challenging due to subtle visual differences, but it can greatly enhance efficiency and consistency. We present an improved segmentation model combining a general-purpose self-supervised visual model with hierarchical inference based on botanical taxonomy. Trained on a multi-year dataset (2018-2020) from Germany and Spain using digital and mobile cameras, the model was tested on digital camera data (year 2023) and drone imagery from the United States, Germany, and Spain (year 2024) to evaluate robustness under domain shift. This cross-device evaluation marks a key step in assessing generalization across platforms of the model. Our model significantly improved species identification (F1-score: 0.52 to 0.85, R-squared: 0.75 to 0.98) and damage classification (F1-score: 0.28 to 0.44, R-squared: 0.71 to 0.87) over prior methods. Under domain shift (drone images), it maintained strong performance with moderate degradation (species: F1-score 0.60, R-squared 0.80; damage: F1-score 0.41, R-squared 0.62), where earlier models failed. These results confirm the model's robustness and real-world applicability. It is now deployed in BASF's phenotyping pipeline, enabling large-scale, automated crop and weed monitoring across diverse geographies.
田间试验在除草剂的研究和开发中至关重要,用于评估作物和杂草在不同条件下的影响。传统上,评估依赖于手动视觉评估,这既耗时又费力,并且具有主观性。由于细微的视觉差异,自动物种识别和损伤识别颇具挑战性,但可以大大提高效率和一致性。我们提出了一种改进的分割模型,结合了通用自监督视觉模型与基于植物分类学的层次推理方法。该模型在来自德国和西班牙(2018-2020年)多年度数据集上使用数字和移动相机训练,并通过美国、德国和西班牙(2023年和2024年)采集的数字相机数据和无人机图像进行测试,以评估域转移情况下的鲁棒性。这种跨设备评估标志着模型在不同平台上的泛化能力的关键步骤。 我们的模型在物种识别(F1分数:从0.52提高到0.85,R平方值:从0.75提升至0.98)和损伤分类(F1分数:从0.28增至0.44,R平方值:从0.71升至0.87)方面相对于先前的方法有了显著改进。在域转移条件下(无人机图像),尽管性能略有下降(物种:F1分数 0.60,R平方值 0.80;损伤:F1分数 0.41,R平方值 0.62),该模型仍保持了强大的表现能力,而早期的模型在此情况下则完全失效。这些结果证实了我们模型的强大鲁棒性和现实应用价值。 目前,该模型已被部署在巴斯夫公司的表型分析管道中,在广泛的地理区域内实现了大规模、自动化的作物和杂草监测。
https://arxiv.org/abs/2508.07514
The diffusion of drones presents significant security and safety challenges. Traditional surveillance systems, particularly conventional frame-based cameras, struggle to reliably detect these targets due to their small size, high agility, and the resulting motion blur and poor performance in challenging lighting conditions. This paper surveys the emerging field of event-based vision as a robust solution to these problems. Event cameras virtually eliminate motion blur and enable consistent detection in extreme lighting. Their sparse, asynchronous output suppresses static backgrounds, enabling low-latency focus on motion cues. We review the state-of-the-art in event-based drone detection, from data representation methods to advanced processing pipelines using spiking neural networks. The discussion extends beyond simple detection to cover more sophisticated tasks such as real-time tracking, trajectory forecasting, and unique identification through propeller signature analysis. By examining current methodologies, available datasets, and the distinct advantages of the technology, this work demonstrates that event-based vision provides a powerful foundation for the next generation of reliable, low-latency, and efficient counter-UAV systems.
无人机的扩散带来了显著的安全和挑战。传统的监控系统,尤其是基于帧的传统摄像头,在可靠地检测这些小型、机动性强且在复杂光照条件下导致运动模糊的目标时遇到了困难。本文对新兴的事件驱动视觉技术进行了概述,将其作为解决这些问题的强大方案。事件相机几乎消除了运动模糊,并能在极端照明环境下实现持续检测。它们输出稀疏而不同步的信息,能够抑制静态背景,使系统能够在低延迟的情况下快速聚焦于运动线索。我们回顾了基于事件的无人机检测领域的最新进展,从数据表示方法到使用尖端脉冲神经网络处理管道的技术。 本文不仅限于简单的检测任务,还涵盖了实时追踪、轨迹预测以及通过螺旋桨特征分析进行独特识别等更复杂的任务。通过对当前的方法论、可用的数据集以及该技术的独特优势进行评估,本工作展示了事件驱动视觉为下一代可靠、低延迟和高效的反无人机系统奠定了强大的基础。
https://arxiv.org/abs/2508.04564
We use unmanned aerial drones to estimate wildlife density in southeastern Austria and compare these estimates to camera trap data. Traditional methods like capture-recapture, distance sampling, or camera traps are well-established but labour-intensive or spatially constrained. Using thermal (IR) and RGB imagery, drones enable efficient, non-intrusive animal counting. Our surveys were conducted during the leafless period on single days in October and November 2024 in three areas of a sub-Illyrian hill and terrace landscape. Flight transects were based on predefined launch points using a 350 m grid and an algorithm that defined the direction of systematically randomized transects. This setup allowed surveying large areas in one day using multiple drones, minimizing double counts. Flight altitude was set at 60 m to avoid disturbing roe deer (Capreolus capreolus) while ensuring detection. Animals were manually annotated in the recorded imagery and extrapolated to densities per square kilometer. We applied three extrapolation methods with increasing complexity: naive area-based extrapolation, bootstrapping, and zero-inflated negative binomial modelling. For comparison, a Random Encounter Model (REM) estimate was calculated using camera trap data from the flight period. The drone-based methods yielded similar results, generally showing higher densities than REM, except in one area in October. We hypothesize that drone-based density reflects daytime activity in open and forested areas, while REM estimates average activity over longer periods within forested zones. Although both approaches estimate density, they offer different perspectives on wildlife presence. Our results show that drones offer a promising, scalable method for wildlife density estimation.
我们使用无人驾驶无人机在奥地利东南部估算野生动物密度,并将这些估算结果与相机陷阱数据进行比较。传统方法,如捕捉-标记-重捕、距离抽样或相机陷阱等技术已经成熟,但劳动强度大且地理覆盖有限。利用热成像(红外)和RGB图像,无人机能够实现高效、非侵入式的动物计数。我们的调查于2024年10月和11月的落叶期在伊里利亚丘陵和台地景观中的三个区域进行,在单日内完成。 飞行路线基于使用350米网格及定义系统随机化航线方向算法的预设发射点设置。这种布局允许我们通过多架无人机一天内调查大面积,并减少重复计数的情况。飞行高度设定为60米,以避免干扰狍(Capreolus capreolus)同时确保检测到动物。在记录的影像中手动标注动物并推算每平方公里内的密度。 我们应用了三种递增复杂度的外推方法:基于面积的简单外推、自助法和零膨胀负二项模型。为了比较,使用相机陷阱数据计算随机相遇模型(REM)估计值。无人机基础方法产生了类似的结果,通常显示出比REM更高的密度,但在10月的一个区域中除外。 我们假设无人机估算出的密度反映了白天开放及森林地区中的动物活动量,而REM估计则平均了较长时期内森林区域内的活动情况。尽管这两种方法都用于估算密度,但它们提供了不同的视角来理解野生动物的存在状态。我们的结果表明,无人机提供了一种有前景、可扩展的方法来进行野生动物密度评估。
https://arxiv.org/abs/2508.03545
The exponential growth in Unmanned Aerial Vehicles (UAVs) usage underscores the critical need of detecting them at extended distances to ensure safe operations, especially in densely populated areas. Despite the tremendous advances made in computer vision through deep learning, the detection of these small airborne objects remains a formidable challenge. While several datasets have been developed specifically for drone detection, the need for a more extensive and diverse collection of drone image data persists, particularly for long-range detection under varying environmental conditions. We introduce here the Long Range Drone Detection (LRDD) Version 2 dataset, comprising 39,516 meticulously annotated images, as a second release of the LRDD dataset released previously. The LRDDv2 dataset enhances the LRDDv1 by incorporating a greater variety of images, providing a more diverse and comprehensive resource for drone detection research. What sets LRDDv2 apart is its inclusion of target range information for over 8,000 images, making it possible to develop algorithms for drone range estimation. Tailored for long-range aerial object detection, the majority of LRDDv2's dataset consists of images capturing drones with 50 or fewer pixels in 1080p resolution. For access to the complete Long-Range Drone Detection Dataset (LRDD)v2, please visit this https URL .
无人飞行器(UAV)使用的指数增长凸显了在远距离检测这些设备以确保安全操作的迫切需求,尤其是在人口密集地区。尽管通过深度学习在计算机视觉领域取得了巨大进步,但对这些小型空中物体进行检测仍然是一个严峻挑战。虽然已经开发出了一些专门用于无人机检测的数据集,但对于长期检测在不同环境条件下更为广泛和多样化的无人机图像数据的需求依然存在。在此,我们推出了Long Range Drone Detection (LRDD) Version 2 数据集,包含39,516张精心标注的图片,作为先前发布的LRDD数据集的第二次发布版本。与LRDDv1相比,LRDDv2数据集通过纳入更多样化的图像内容而得到了增强,为无人机检测研究提供了更为多样和全面的资源。LRDDv2的独特之处在于它包含了超过8,000张图片的目标范围信息,从而使得开发用于估计无人机距离的算法成为可能。此数据集特别针对长程空中物体检测设计,其大多数图像以1080p分辨率捕捉到50个像素或更少的无人机影像。要访问完整的Long-Range Drone Detection Dataset (LRDD)v2,请访问这个[链接](https://this https URL)(请将URL中的“this https”替换为实际链接)。
https://arxiv.org/abs/2508.03331
Fire scene datasets are crucial for training robust computer vision models, particularly in tasks such as fire early warning and emergency rescue operations. However, among the currently available fire-related data, there is a significant shortage of annotated data specifically targeting building this http URL tackle this issue, we introduce an annotated dataset of building units captured by drones, which incorporates multiple enhancement techniques. We construct backgrounds using real multi-story scenes, combine motion blur and brightness adjustment to enhance the authenticity of the captured images, simulate drone shooting conditions under various circumstances, and employ large models to generate fire effects at different this http URL synthetic dataset generated by this method encompasses a wide range of building scenarios, with a total of 1,978 images. This dataset can effectively improve the generalization ability of fire unit detection, providing multi-scenario and scalable data while reducing the risks and costs associated with collecting real fire data. The dataset is available at this https URL.
火灾现场数据集对于训练稳健的计算机视觉模型至关重要,特别是在早期火灾预警和应急救援操作等任务中。然而,在现有的与火灾相关的数据中,专门用于构建此类模型的标注数据存在显著短缺。为了解决这一问题,我们引入了一个由无人机捕捉并经过标注的建筑单元数据集,并采用多种增强技术来丰富数据集的内容。我们使用真实的多层场景构建背景环境,结合运动模糊和亮度调整以提升所拍摄图像的真实性;模拟不同条件下无人机拍摄的情况;利用大型模型生成不同程度的火灾效果。通过这种方法生成的合成数据集涵盖了广泛的建筑情景,总共有1,978张图片。该数据集能够有效提高对火灾单元检测的一般化能力,并提供多场景和可扩展的数据,同时降低收集真实火灾数据的风险与成本。此数据集可通过以下链接访问:[请在此处插入实际的网址]。
https://arxiv.org/abs/2508.03139
Advances in artificial intelligence (AI) including large language models (LLMs) and hybrid reasoning models present an opportunity to reimagine how autonomous robots such as drones are designed, developed, and validated. Here, we demonstrate a fully AI-generated drone control system: with minimal human input, an artificial intelligence (AI) model authored all the code for a real-time, self-hosted drone command and control platform, which was deployed and demonstrated on a real drone in flight as well as a simulated virtual drone in the cloud. The system enables real-time mapping, flight telemetry, autonomous mission planning and execution, and safety protocolsall orchestrated through a web interface hosted directly on the drone itself. Not a single line of code was written by a human. We quantitatively benchmark system performance, code complexity, and development speed against prior, human-coded architectures, finding that AI-generated code can deliver functionally complete command-and-control stacks at orders-of-magnitude faster development cycles, though with identifiable current limitations related to specific model context window and reasoning depth. Our analysis uncovers the practical boundaries of AI-driven robot control code generation at current model scales, as well as emergent strengths and failure modes in AI-generated robotics code. This work sets a precedent for the autonomous creation of robot control systems and, more broadly, suggests a new paradigm for robotics engineeringone in which future robots may be largely co-designed, developed, and verified by artificial intelligence. In this initial work, a robot built a robot's brain.
人工智能(AI)的发展,包括大型语言模型(LLMs)和混合推理模型的进步,为重新构思自主机器人如无人机的设计、开发和验证提供了机会。在这里,我们展示了一个完全由人工智能生成的无人机控制系统:在最少的人类干预下,一个AI模型编写了所有代码以创建实时、自托管的无人机指令与控制平台,并且该系统已经在实际飞行中的真实无人机以及云端模拟虚拟无人机上进行了部署和演示。此系统能够实现实时地图绘制、飞行遥测、自主任务规划与执行以及安全协议,并通过直接在无人机自身上托管的网络界面进行统一管理。没有一行代码是由人类编写的。 我们对系统的性能、代码复杂度和开发速度进行了定量基准测试,将其与先前由人工编码的架构进行了比较,发现AI生成的代码可以在成数量级更快的开发周期内交付功能完整的指令和控制堆栈,尽管目前存在一些与具体模型上下文窗口以及推理深度有关的可识别限制。我们的分析揭示了当前模型规模下人工智能驱动机器人控制系统生成的实际边界、出现的优势以及潜在故障模式。这项工作为自主创建机器人控制系统开创了一个先例,并更广泛地提出了一个新的机器人工程范式——在未来,许多机器人的设计、开发和验证可能主要由人工智能力主导。在这个初步工作中,一个机器人创造出了另一个机器人的“大脑”。
https://arxiv.org/abs/2508.02962
In order to expand the operational range and payload capacity of robots, wire-driven robots that leverage the external environment have been proposed. It can exert forces and operate in spaces far beyond those dictated by its own structural limits. However, for practical use, robots must autonomously attach multiple wires to the environment based on environmental recognition-an operation so difficult that many wire-driven robots remain restricted to specialized, pre-designed environments. Here, in this study, we propose a robot that autonomously connects multiple wires to the environment by employing a multi-small flying anchor system, as well as an RGB-D camera-based control and environmental recognition method. Each flying anchor is a drone with an anchoring mechanism at the wire tip, allowing the robot to attach wires by flying into position. Using the robot's RGB-D camera to identify suitable attachment points and a flying anchor position, the system can connect wires in environments that are not specially prepared, and can also attach multiple wires simultaneously. Through this approach, a wire-driven robot can autonomously attach its wires to the environment, thereby realizing the benefits of wire-driven operation at any location.
为了扩大机器人的操作范围和载荷能力,有人提出了利用外部环境的线驱动机器人。这种机器人能够施加力量并在远远超出其自身结构限制的空间内进行操作。然而,在实际应用中,机器人必须基于对环境的认识自主地将多根线连接到环境中——这是一个非常困难的操作,导致许多线驱动机器人仍然局限于特定设计的环境之中。在本研究中,我们提出了一种利用多小型飞行锚系统的机器人,该系统可以自主地将多根线连接到环境中,并且还使用RGB-D相机进行控制和环境识别方法。 每个飞行锚都是一个配备了绳索末端固定机制的无人机,使得机器人可以通过飞行到达指定位置来固定绳索。通过机器人配备的RGB-D摄像头来识别合适的附着点以及飞行锚的位置,该系统能够在未特别准备的环境中连接线缆,并且可以同时连接多根线缆。通过这种方法,线驱动机器人能够自主地将自身的线缆连接到环境之中,在任何地方实现线驱动操作的好处。
https://arxiv.org/abs/2508.02544
This paper proposes an adaptive lattice-based motion planning solution to address the problem of generating feasible trajectories for systems, represented by a linearly parameterizable non-linear model operating within a cluttered environment. The system model is considered to have uncertain model parameters. The key idea here is to utilize input/output data online to update the model set containing the uncertain system parameter, as well as a dynamic estimated parameter of the model, so that the associated model estimation error reduces over time. This in turn improves the quality of the motion primitives generated by the lattice-based motion planner using a nominal estimated model selected on the basis of suitable criteria. The motion primitives are also equipped with tubes to account for the model mismatch between the nominal estimated model and the true system model, to guarantee collision-free overall motion. The tubes are of uniform size, which is directly proportional to the size of the model set containing the uncertain system parameter. The adaptive learning module guarantees a reduction in the diameter of the model set as well as in the parameter estimation error between the dynamic estimated parameter and the true system parameter. This directly implies a reduction in the size of the implemented tubes and guarantees that the utilized motion primitives go arbitrarily close to the resolution-optimal motion primitives associated with the true model of the system, thus significantly improving the overall motion planning performance over time. The efficiency of the motion planner is demonstrated by a suitable simulation example that considers a drone model represented by Euler-Lagrange dynamics containing uncertain parameters and operating within a cluttered environment.
这篇论文提出了一种自适应格子基础的运动规划解决方案,旨在解决在复杂环境中为非线性模型(该模型可通过线性参数化表示)生成可行轨迹的问题。系统模型被认为具有不确定的模型参数。其核心思想是利用输入/输出数据在线更新包含不确定系统参数的模型集以及动态估计的模型参数,从而随着时间推移减少相关模型估算误差。这反过来改进了基于选定名义估计模型(依据适当标准选取)生成的运动原语的质量。这些运动原语还配备了管状结构以考虑名义估计模型和真实系统模型之间的模型偏差,确保整个运动无碰撞。管状结构的大小是统一且直接与包含不确定系统参数的模型集大小成正比。自适应学习模块保证了模型集合直径以及动态估算参数与真实系统参数之间估计误差的减小,这直接意味着实施的管状结构尺寸减少,并确保所使用的运动原语可以无限接近于真实系统的分辨率最优运动原语,从而随着时间推移显著提高整体运动规划性能。通过考虑包含不确定参数并在复杂环境中操作的无人机模型(以欧拉-拉格朗日动力学表示)的适当仿真示例来展示了该运动计划器的有效性。
https://arxiv.org/abs/2508.02350
This paper addresses the critical need for efficient and accurate weed segmentation from drone video in precision agriculture. A quality-aware modular deep-learning framework is proposed that addresses common image degradation by analyzing quality conditions-such as blur and noise-and routing inputs through specialized pre-processing and transformer models optimized for each degradation type. The system first analyzes drone images for noise and blur using Mean Absolute Deviation and the Laplacian. Data is then dynamically routed to one of three vision transformer models: a baseline for clean images, a modified transformer with Fisher Vector encoding for noise reduction, or another with an unrolled Lucy-Robinson decoder to correct blur. This novel routing strategy allows the system to outperform existing CNN-based methods in both segmentation quality and computational efficiency, demonstrating a significant advancement in deep-learning applications for agriculture.
本文解决了精准农业中从无人机视频高效且准确地进行杂草分割的关键需求。提出了一个质量感知的模块化深度学习框架,该框架通过分析诸如模糊和噪声等质量问题,并将输入路由到专门针对每种退化类型优化的预处理和变压器模型来应对常见图像降质问题。 系统首先使用平均绝对偏差(Mean Absolute Deviation)和拉普拉斯算子对无人机拍摄的图像进行噪声和模糊度的分析。然后,数据会被动态地导向三个视觉变换器模型之一:一种用于清晰图像的基本模型、一种通过费舍尔向量编码来减少噪声的改进型变压器模型,或者另一种具有展开的Lucy-Robinson解码器以纠正模糊的模型。 这种新颖的路由策略使得系统在分割质量和计算效率方面均优于现有的基于CNN的方法,在农业深度学习应用中取得了显著进步。
https://arxiv.org/abs/2508.03751
The convergence of autonomous indoor drones with physics-aware sensing technologies promises to transform property assessment from subjective visual inspection to objective, quantitative measurement. This comprehensive review examines the technical foundations enabling this paradigm shift across four critical domains: (1) platform architectures optimized for indoor navigation, where weight constraints drive innovations in heterogeneous computing, collision-tolerant design, and hierarchical control systems; (2) advanced sensing modalities that extend perception beyond human vision, including hyperspectral imaging for material identification, polarimetric sensing for surface characterization, and computational imaging with metaphotonics enabling radical miniaturization; (3) intelligent autonomy through active reconstruction algorithms, where drones equipped with 3D Gaussian Splatting make strategic decisions about viewpoint selection to maximize information gain within battery constraints; and (4) integration pathways with existing property workflows, including Building Information Modeling (BIM) systems and industry standards like Uniform Appraisal Dataset (UAD) 3.6.
自主室内无人机与物理感知技术的融合,预示着房产评估将从主观视觉检查转变为客观、量化的测量。本文综述了推动这一范式转变的技术基础,并深入探讨四个关键领域:(1)针对室内导航优化的平台架构,在重量限制驱动下,异构计算、碰撞容错设计以及分层控制系统方面的创新层出不穷;(2)先进的感知模式,将感知能力拓展到超越人类视觉范畴的范围,包括用于材料识别的高光谱成像技术,用于表面特征描述的偏振感应技术,以及通过元光子学实现极端小型化的计算成像技术;(3)智能自主性,通过主动重建算法实现,配备了三维高斯点集法(3D Gaussian Splatting)的无人机在电池电量限制内做出战略性视角选择决策以最大化信息获取量;(4)与现有房产工作流程的集成路径,包括建筑信息模型(BIM)系统和行业标准如统一评估数据集(UAD) 3.6。
https://arxiv.org/abs/2508.01965
Multi-object tracking (MOT) aims to track multiple objects while maintaining consistent identities across frames of a given video. In unmanned aerial vehicle (UAV) recorded videos, frequent viewpoint changes and complex UAV-ground relative motion dynamics pose significant challenges, which often lead to unstable affinity measurement and ambiguous association. Existing methods typically model motion and appearance cues separately, overlooking their spatio-temporal interplay and resulting in suboptimal tracking performance. In this work, we propose AMOT, which jointly exploits appearance and motion cues through two key components: an Appearance-Motion Consistency (AMC) matrix and a Motion-aware Track Continuation (MTC) module. Specifically, the AMC matrix computes bi-directional spatial consistency under the guidance of appearance features, enabling more reliable and context-aware identity association. The MTC module complements AMC by reactivating unmatched tracks through appearance-guided predictions that align with Kalman-based predictions, thereby reducing broken trajectories caused by missed detections. Extensive experiments on three UAV benchmarks, including VisDrone2019, UAVDT, and VT-MOT-UAV, demonstrate that our AMOT outperforms current state-of-the-art methods and generalizes well in a plug-and-play and training-free manner.
多目标跟踪(MOT)旨在追踪给定视频中多个对象,并在帧之间保持一致的身份识别。对于无人飞行器(UAV)记录的视频,频繁变化的视角和复杂的UAV与地面之间的相对运动动态带来了显著挑战,这通常会导致不稳定的亲和力测量及模糊关联问题。现有的方法通常分别建模运动和外观线索,忽略了它们在时空中的相互作用,并导致次优的跟踪性能。 在此项工作中,我们提出了AMOT(Appearance-Motion Oriented Tracking),该方法通过两个关键组件共同利用了外观和运动线索:外观-运动一致性(AMC)矩阵及基于运动感知的轨迹延续(MTC)模块。具体来说,AMC矩阵在外观特征指导下计算双向空间一致性,从而实现更可靠且具有上下文意识的身份关联。MTC模块则通过与卡尔曼预测对齐的外观引导预测来重新激活未匹配的跟踪,以此减少由于检测遗漏导致的断裂轨迹。 我们在这项工作中的方法已在三个UAV基准测试集上进行了广泛的实验:VisDrone2019、UAVDT以及VT-MOT-UAV。结果表明,我们的AMOT方法不仅超过了现有的最先进水平,并且能够以即插即用和无需训练的方式良好地推广到其他场景中。
https://arxiv.org/abs/2508.01730
We propose a novel Energy-Predictive Drone Service (EPDS) framework for efficient package delivery within a skyway network. The EPDS framework incorporates a formal modeling of an EPDS and an adaptive bidirectional Long Short-Term Memory (Bi-LSTM) machine learning model. This model predicts the energy status and stochastic arrival times of other drones operating in the same skyway network. Leveraging these predictions, we develop a heuristic optimization approach for composite drone services. This approach identifies the most time-efficient and energy-efficient skyway path and recharging schedule for each drone in the network. We conduct extensive experiments using a real-world drone flight dataset to evaluate the performance of the proposed framework.
我们提出了一种新颖的能量预测无人机服务(EPDS)框架,用于在天空网络中的高效包裹递送。该EPDS框架包括一个正式建模的EPDS和一种自适应双向长短期记忆(Bi-LSTM)机器学习模型。此模型能够预测在同一天空网络中运行的其他无人机的能量状态和随机到达时间。利用这些预测结果,我们开发了一种复合无人机服务的启发式优化方法。该方法可以识别每架无人机在网络中的最省时、节能的飞行路径和充电计划。通过使用真实世界的无人机飞行数据集进行广泛的实验来评估所提出的框架性能。
https://arxiv.org/abs/2508.01671