Drone
-
Multi-Task Reinforcement Learning of Drone Aerobatics by Exploiting Geometric Symmetries
2026-02-11 16:21:48Zhanyu Guo, Zikang Yin, Guobin Zhu, Shiliang Guo, Shiyu ZhaoAbstract
Flight control for autonomous micro aerial vehicles (MAVs) is evolving from steady flight near equilibrium points toward more aggressive aerobatic maneuvers, such as flips, rolls, and Power Loop. Although reinforcement learning (RL) has shown great potential in these tasks, conventional RL methods often suffer from low data efficiency and limited generalization. This challenge becomes more pronounced in multi-task scenarios where a single policy is required to master multiple maneuvers. In this paper, we propose a novel end-to-end multi-task reinforcement learning framework, called GEAR (Geometric Equivariant Aerobatics Reinforcement), which fully exploits the inherent SO(2) rotational symmetry in MAV dynamics and explicitly incorporates this property into the policy network architecture. By integrating an equivariant actor network, FiLM-based task modulation, and a multi-head critic, GEAR achieves both efficiency and flexibility in learning diverse aerobatic maneuvers, enabling a data-efficient, robust, and unified framework for aerobatic control. GEAR attains a 98.85\% success rate across various aerobatic tasks, significantly outperforming baseline methods. In real-world experiments, GEAR demonstrates stable execution of multiple maneuvers and the capability to combine basic motion primitives to complete complex aerobatics.
Abstract (translated)
自主微型飞行器（MAV）的飞行控制正从平衡点附近的稳定飞行转向更激进的特技动作，如翻滚、筋斗和动力环路。尽管强化学习（RL）在这些任务中表现出巨大潜力，但传统RL方法通常面临数据效率低且泛化能力有限的问题。这种挑战在需要掌握多种机动动作的多任务场景中尤为突出。本文提出了一种新的端到端多任务强化学习框架GEAR（Geometric Equivariant Aerobatics Reinforcement），该框架充分利用了MAV动力学中的SO(2)旋转对称性，并将这一属性明确地融入到了策略网络架构中。通过整合等变演员网络、FiLM基元的任务调节以及多头评论家，GEAR在学习多样化的特技机动时实现了高效性和灵活性，从而提供了一个数据效率高、鲁棒性强且统一的特技控制框架。GEAR在各种特技任务中的成功率为98.85%，显著优于基准方法。在真实世界实验中，GEAR展示出执行多种动作的稳定性，并能将基本运动原语组合以完成复杂的特技飞行。
URL
https://arxiv.org/abs/2602.10997
PDF
-
Omnidirectional Dual-Arm Aerial Manipulator with Proprioceptive Contact Localization for Landing on Slanted Roofs
2026-02-11 10:03:17Martijn B. J. Brummelhuis, Nathan F. Lepora, Salua HamazaAbstract
Operating drones in urban environments often means they need to land on rooftops, which can have different geometries and surface irregularities. Accurately detecting roof inclination using conventional sensing methods, such as vision-based or acoustic techniques, can be unreliable, as measurement quality is strongly influenced by external factors including weather conditions and surface materials. To overcome these challenges, we propose a novel unmanned aerial manipulator morphology featuring a dual-arm aerial manipulator with an omnidirectional 3D workspace and extended reach. Building on this design, we develop a proprioceptive contact detection and contact localization strategy based on a momentum-based torque observer. This enables the UAM to infer the inclination of slanted surfaces blindly - through physical interaction - prior to touchdown. We validate the approach in flight experiments, demonstrating robust landings on surfaces with inclinations of up to 30.5 degrees and achieving an average surface inclination estimation error of 2.87 degrees over 9 experiments at different incline angles.
Abstract (translated)
在城市环境中操作无人机通常意味着它们需要降落在具有不同几何形状和表面不规则性的屋顶上。使用传统的传感方法，如基于视觉或声学的方法来准确检测屋顶的倾斜角度可能不可靠，因为测量质量会受到外部因素（包括天气条件和表面材料）的影响。 为了解决这些问题，我们提出了一种新颖的无人航空机械手形态设计，该设计采用双臂空中机械手，并具有全方位3D工作空间和扩展的工作范围。在此基础上，我们开发了一种基于动量扭矩观察器的本体感受接触检测与定位策略。这种方法使UAM（Unmanned Aerial Manipulator）能够在不依赖视觉信息的情况下通过物理互动推断出倾斜表面的角度，在触地之前进行准确判断。 我们在飞行实验中验证了这一方法的有效性，展示了在不同倾斜角度下（最多30.5度），平均表面倾斜角估计误差仅为2.87度的良好性能。
URL
https://arxiv.org/abs/2602.10703
PDF
-
Acoustic Drone Package Delivery Detection
2026-02-10 17:16:20Fran\c{c}ois Marcoux, Fran\c{c}ois GrondinAbstract
In recent years, the illicit use of unmanned aerial vehicles (UAVs) for deliveries in restricted area such as prisons became a significant security challenge. While numerous studies have focused on UAV detection or localization, little attention has been given to delivery events identification. This study presents the first acoustic package delivery detection algorithm using a ground-based microphone array. The proposed method estimates both the drone's propeller speed and the delivery event using solely acoustic features. A deep neural network detects the presence of a drone and estimates the propeller's rotation speed or blade passing frequency (BPF) from a mel spectrogram. The algorithm analyzes the BPFs to identify probable delivery moments based on sudden changes before and after a specific time. Results demonstrate a mean absolute error of the blade passing frequency estimator of 16 Hz when the drone is less than 150 meters away from the microphone array. The drone presence detection estimator has a accuracy of 97%. The delivery detection algorithm correctly identifies 96% of events with a false positive rate of 8%. This study shows that deliveries can be identified using acoustic signals up to a range of 100 meters.
Abstract (translated)
近年来，无人飞行器（UAV）在监狱等限制区域非法进行包裹递送已成为一个重要的安全挑战。尽管许多研究集中在无人机检测或定位上，但对递送事件识别的关注较少。本研究提出了首个基于地面麦克风阵列的声学包裹递送检测算法。该方法仅通过声学特征就能估算出无人机螺旋桨的速度和递送事件。 所提出的方法使用深度神经网络从梅尔频谱图中检测无人机的存在，并估计螺旋桨旋转速度或叶片通过频率（BPF）。算法会分析这些BPF，基于特定时间点前后突然变化来识别可能的递送时刻。当无人机距离麦克风阵列不到150米时，螺旋桨叶片通过频率估算器的平均绝对误差为16 Hz。无人机存在检测估计器具有97%的准确性。包裹递送算法正确地识別了96％的事件，并且误报率为8％。 研究表明，使用声学信号可以在距离麦克风阵列最多100米范围内识别出递送行为。
URL
https://arxiv.org/abs/2602.09991
PDF
-
KidMesh: Computational Mesh Reconstruction for Pediatric Congenital Hydronephrosis Using Deep Neural Networks
2026-02-09 11:09:29Haoran Sun, Zhanpeng Zhu, Anguo Zhang, Bo Liu, Zhaohua Lin, Liqin Huang, Mingjing Yang, Lei Liu, Shan Lin, Wangbin DingAbstract
Pediatric congenital hydronephrosis (CH) is a common urinary tract disorder, primarily caused by obstruction at the renal pelvis-ureter junction. Magnetic resonance urography (MRU) can visualize hydronephrosis, including renal pelvis and calyces, by utilizing the natural contrast provided by water. Existing voxel-based segmentation approaches can extract CH regions from MRU, facilitating disease diagnosis and prognosis. However, these segmentation methods predominantly focus on morphological features, such as size, shape, and structure. To enable functional assessments, such as urodynamic simulations, external complex post-processing steps are required to convert these results into mesh-level representations. To address this limitation, we propose an end-to-end method based on deep neural networks, namely KidMesh, which could automatically reconstruct CH meshes directly from MRU. Generally, KidMesh extracts feature maps from MRU images and converts them into feature vertices through grid sampling. It then deforms a template mesh according to these feature vertices to generate the specific CH meshes of MRU images. Meanwhile, we develop a novel schema to train KidMesh without relying on accurate mesh-level annotations, which are difficult to obtain due to the sparsely sampled MRU slices. Experimental results show that KidMesh could reconstruct CH meshes in an average of 0.4 seconds, and achieve comparable performance to conventional methods without requiring post-processing. The reconstructed meshes exhibited no self-intersections, with only 3.7% and 0.2% of the vertices having error distances exceeding 3.2mm and 6.4mm, respectively. After rasterization, these meshes achieved a Dice score of 0.86 against manually delineated CH masks. Furthermore, these meshes could be used in renal urine flow simulations, providing valuable urodynamic information for clinical practice.
Abstract (translated)
URL
https://arxiv.org/abs/2602.13299
PDF
-
Intelligent support for Human Oversight: Integrating Reinforcement Learning with Gaze Simulation to Personalize Highlighting
2026-02-09 09:04:48Thorsten Kl\"o{\ss}ner, Jo\~ao Belo, Zekun Wu, J\"org Hoffmann, Anna Maria FeitAbstract
Interfaces for human oversight must effectively support users' situation awareness under time-critical conditions. We explore reinforcement learning (RL)-based UI adaptation to personalize alerting strategies that balance the benefits of highlighting critical events against the cognitive costs of interruptions. To enable learning without real-world deployment, we integrate models of users' gaze behavior to simulate attentional dynamics during monitoring. Using a delivery-drone oversight scenario, we present initial results suggesting that RL-based highlighting can outperform static, rule-based approaches and discuss challenges of intelligent oversight support.
Abstract (translated)
人类监督的界面必须在时间紧迫的情况下有效地支持用户的态势感知。我们探索了基于强化学习（RL）的用户界面适应，以个性化警报策略，在突出关键事件的好处和中断的认知成本之间取得平衡。为了实现不进行实际部署即可学习的目标，我们将用户注视行为模型整合进来，以此来模拟监控过程中的注意力动态变化。通过一个送货无人机监督场景，我们展示了初步结果表明基于RL的高亮显示方法可以优于静态、规则驱动的方法，并讨论了智能监督支持所面临的挑战。
URL
https://arxiv.org/abs/2602.08403
PDF
-
CA-YOLO: Cross Attention Empowered YOLO for Biomimetic Localization
2026-02-07 12:38:45Zhen Zhang, Qing Zhao, Xiuhe Li, Cheng Wang, Guoqiang Zhu, Yu Zhang, Yining Huo, Hongyi Yu, Yi ZhangAbstract
In modern complex environments, achieving accurate and efficient target localization is essential in numerous fields. However, existing systems often face limitations in both accuracy and the ability to recognize small targets. In this study, we propose a bionic stabilized localization system based on CA-YOLO, designed to enhance both target localization accuracy and small target recognition capabilities. Acting as the "brain" of the system, the target detection algorithm emulates the visual focusing mechanism of animals by integrating bionic modules into the YOLO backbone network. These modules include the introduction of a small target detection head and the development of a Characteristic Fusion Attention Mechanism (CFAM). Furthermore, drawing inspiration from the human Vestibulo-Ocular Reflex (VOR), a bionic pan-tilt tracking control strategy is developed, which incorporates central positioning, stability optimization, adaptive control coefficient adjustment, and an intelligent recapture function. The experimental results show that CA-YOLO outperforms the original model on standard datasets (COCO and VisDrone), with average accuracy metrics improved by 3.94%and 4.90%, this http URL time-sensitive target localization experiments validate the effectiveness and practicality of this bionic stabilized localization system.
Abstract (translated)
在现代复杂环境中，实现准确高效的定位目标对于众多领域而言至关重要。然而，现有的系统通常面临精度和识别小目标能力上的局限性。本研究提出了一种基于CA-YOLO的仿生稳定定位系统，旨在提升目标定位精度以及对小目标的识别能力。作为系统的“大脑”，目标检测算法通过将仿生模块整合进YOLO骨干网络中来模拟动物视觉聚焦机制。这些模块包括引入小目标检测头部和开发特征融合注意机制（CFAM）。此外，该研究从人类前庭眼动反射（VOR）中获得灵感，发展了一种仿生云台跟踪控制策略，集成了中心定位、稳定性优化、自适应控制系数调整以及智能重捕功能。实验结果表明，在标准数据集(COCO和VisDrone)上，CA-YOLO的表现优于原始模型，平均精度指标分别提高了3.94%和4.90%，这证明了该仿生稳定定位系统在时间敏感的目标定位试验中的有效性和实用性。
URL
https://arxiv.org/abs/2602.07523
PDF
-
Adaptive Image Zoom-in with Bounding Box Transformation for UAV Object Detection
2026-02-07 12:16:45Tao Wang, Chenyu Lin, Chenwei Tang, Jizhe Zhou, Deng Xiong, Jianan Li, Jian Zhao, Jiancheng LvAbstract
Detecting objects from UAV-captured images is challenging due to the small object size. In this work, a simple and efficient adaptive zoom-in framework is explored for object detection on UAV images. The main motivation is that the foreground objects are generally smaller and sparser than those in common scene images, which hinders the optimization of effective object detectors. We thus aim to zoom in adaptively on the objects to better capture object features for the detection task. To achieve the goal, two core designs are required: \textcolor{black}{i) How to conduct non-uniform zooming on each image efficiently? ii) How to enable object detection training and inference with the zoomed image space?} Correspondingly, a lightweight offset prediction scheme coupled with a novel box-based zooming objective is introduced to learn non-uniform zooming on the input image. Based on the learned zooming transformation, a corner-aligned bounding box transformation method is proposed. The method warps the ground-truth bounding boxes to the zoomed space to learn object detection, and warps the predicted bounding boxes back to the original space during inference. We conduct extensive experiments on three representative UAV object detection datasets, including VisDrone, UAVDT, and SeaDronesSee. The proposed ZoomDet is architecture-independent and can be applied to an arbitrary object detection architecture. Remarkably, on the SeaDronesSee dataset, ZoomDet offers more than 8.4 absolute gain of mAP with a Faster R-CNN model, with only about 3 ms additional latency. The code is available at this https URL.
Abstract (translated)
从无人机捕获的图像中检测对象由于目标尺寸较小而具有挑战性。在这项工作中，我们探索了一种简单且高效的自适应缩放框架，用于无人机图像中的目标检测。主要动机是前景物体通常比常见场景图片中的物体更小、更稀疏，这阻碍了有效目标检测器的优化。因此，我们的目标是对每个对象进行自适应地放大，以便更好地捕捉用于检测任务的对象特征。 为了实现这一目标，需要两个核心设计： 1) 如何高效地对每张图像执行非均匀缩放？ 2) 如何使基于已缩放图像空间的目标检测训练和推理成为可能？ 为此，我们引入了一种轻量级偏移预测方案，并结合一种新颖的基于框的缩放目标，以学习在输入图象上的非均匀缩放。根据所学的缩放变换，提出了一种对角线对齐的边界框转换方法。该方法将地面实况边界框变形到已缩放的空间中进行目标检测训练，并在推断时将预测的边界框变形回原始空间。 我们在三个具有代表性的无人机目标检测数据集上进行了广泛的实验，包括VisDrone、UAVDT和SeaDronesSee。提出的ZoomDet是架构独立的，可以应用于任意对象检测架构。值得注意的是，在SeaDronesSee数据集上，使用Faster R-CNN模型时，ZoomDet比原方案提供了超过8.4的mAP绝对增益，并且仅增加了约3毫秒的额外延迟。 相关代码可在提供的URL处访问。
URL
https://arxiv.org/abs/2602.07512
PDF
-
aerial-autonomy-stack -- a Faster-than-real-time, Autopilot-agnostic, ROS2 Framework to Simulate and Deploy Perception-based Drones
2026-02-06 23:29:33Jacopo Panerati, Sina Sajjadi, Sina Soleymanpour, Varunkumar Mehta, Iraj ManteghAbstract
Unmanned aerial vehicles are rapidly transforming multiple applications, from agricultural and infrastructure monitoring to logistics and defense. Introducing greater autonomy to these systems can simultaneously make them more effective as well as reliable. Thus, the ability to rapidly engineer and deploy autonomous aerial systems has become of strategic importance. In the 2010s, a combination of high-performance compute, data, and open-source software led to the current deep learning and AI boom, unlocking decades of prior theoretical work. Robotics is on the cusp of a similar transformation. However, physical AI faces unique hurdles, often combined under the umbrella term "simulation-to-reality gap". These span from modeling shortcomings to the complexity of vertically integrating the highly heterogeneous hardware and software systems typically found in field robots. To address the latter, we introduce aerial-autonomy-stack, an open-source, end-to-end framework designed to streamline the pipeline from (GPU-accelerated) perception to (flight controller-based) action. Our stack allows the development of aerial autonomy using ROS2 and provides a common interface for two of the most popular autopilots: PX4 and ArduPilot. We show that it supports over 20x faster-than-real-time, end-to-end simulation of a complete development and deployment stack -- including edge compute and networking -- significantly compressing the build-test-release cycle of perception-based autonomy.
Abstract (translated)
无人驾驶航空器（无人机）正在快速变革多个应用领域，从农业和基础设施监测到物流和国防。向这些系统引入更多的自主性可以同时提高其有效性和可靠性。因此，迅速研发并部署自主飞行系统的能力建立起了战略重要性。 在2010年代，高性能计算、数据以及开源软件的结合引发了当前深度学习与人工智能的繁荣时期，这使得以前数十年的理论工作得以实现。机器人技术正处在类似的变革边缘。然而，物理领域的人工智能（AI）面临着独特的挑战，这些挑战通常被统称为“仿真到现实差距”。这些问题涵盖了从建模不足到垂直整合现场机器人中常见的高度异构硬件和软件系统的复杂性等各个方面。 为解决后者的问题，我们引入了aerial-autonomy-stack，这是一个开源的、端到端的框架，旨在简化从（GPU加速）感知到（基于飞行控制器的动作）这一全流程。我们的栈允许使用ROS2进行空中自主性的开发，并提供了两个最受欢迎的自动驾驶仪：PX4和ArduPilot之间的通用接口。我们展示它支持超过20倍于实时的速度、端到端的仿真，包括边缘计算与网络——这极大地压缩了基于感知的自主系统构建-测试-发布的周期。
URL
https://arxiv.org/abs/2602.07264
PDF
-
Strategizing at Speed: A Learned Model Predictive Game for Multi-Agent Drone Racing
2026-02-06 18:20:13Andrei-Carlo Papuc, Lasse Peters, Sihao Sun, Laura Ferranti, Javier Alonso-MoraAbstract
Autonomous drone racing pushes the boundaries of high-speed motion planning and multi-agent strategic decision-making. Success in this domain requires drones not only to navigate at their limits but also to anticipate and counteract competitors' actions. In this paper, we study a fundamental question that arises in this domain: how deeply should an agent strategize before taking an action? To this end, we compare two planning paradigms: the Model Predictive Game (MPG), which finds interaction-aware strategies at the expense of longer computation times, and contouring Model Predictive Control (MPC), which computes strategies rapidly but does not reason about interactions. We perform extensive experiments to study this trade-off, revealing that MPG outperforms MPC at moderate velocities but loses its advantage at higher speeds due to latency. To address this shortcoming, we propose a Learned Model Predictive Game (LMPG) approach that amortizes model predictive gameplay to reduce latency. In both simulation and hardware experiments, we benchmark our approach against MPG and MPC in head-to-head races, finding that LMPG outperforms both baselines.
Abstract (translated)
自主无人机竞速推动了高速运动规划和多智能体策略决策的边界。在这个领域取得成功需要无人机不仅要在极限条件下导航，还要能够预测并应对竞争对手的动作。本文研究了一个在该领域中出现的基本问题：一个智能体在采取行动之前应深入思考到什么程度？为此，我们比较了两种规划范式：模型预测博弈（Model Predictive Game, MPG），它以更长的计算时间为代价找到考虑到互动策略的方法；以及轮廓模型预测控制（contouring Model Predictive Control, MPC），这种方法可以快速制定策略但不考虑交互。通过广泛的实验来研究这一权衡，我们发现MPG在中等速度下优于MPC，但在高速时由于延迟问题而失去优势。为解决这个问题，我们提出了一种学习模型预测博弈（Learned Model Predictive Game, LMPG）方法，该方法将模型预测游戏进行分摊处理以减少延迟。通过模拟和硬件实验，在一对一竞速中将我们的方法与MPG和MPC进行了基准测试，发现LMPG优于两个基线方法。 这段翻译阐明了自主无人机竞速中的策略制定问题，并比较了几种不同的规划方法的效果，突出了所提出的LMPG方法在减少延迟的同时维持性能方面的优势。
URL
https://arxiv.org/abs/2602.06925
PDF
-
A 26-Gram Butterfly-Inspired Robot Achieving Autonomous Tailless Flight
2026-02-06 15:58:50Weibin Gu, Chenrui Feng, Lian Liu, Chen Yang, Xingchi Jiao, Yuhe Ding, Xiaofei Shi, Chao Gao, Alessandro Rizzo, Guyue ZhouAbstract
Flapping-wing micro air vehicles (FWMAVs) have demonstrated remarkable bio-inspired agility, yet tailless two-winged configurations remain largely unexplored due to their complex fluid-structure and wing-body coupling. Here we present \textit{AirPulse}, a 26-gram butterfly-inspired FWMAV that achieves fully onboard, closed-loop, untethered flight without auxiliary control surfaces. The AirPulse robot replicates key biomechanical traits of butterfly flight, including low wing aspect ratio, compliant carbon-fiber-reinforced wings, and low-frequency, high-amplitude flapping that induces cyclic variations in the center of gravity and moment of inertia, producing characteristic body undulation. We establish a quantitative mapping between flapping modulation parameters and force-torque generation, and introduce the Stroke Timing Asymmetry Rhythm (STAR) generator, enabling smooth, stable, and linearly parameterized wingstroke asymmetry for flapping control. Integrating these with an attitude controller, the AirPulse robot maintains pitch and yaw stability despite strong oscillatory dynamics. Free-flight experiments demonstrate stable climbing and turning maneuvers via either angle offset or stroke timing modulation, marking the first onboard controlled flight of the lightest two-winged, tailless butterfly-inspired FWMAV reported in peer-reviewed literature. This work corroborates a foundational platform for lightweight, collision-proof FWMAVs, bridging biological inspiration with practical aerial robotics. Their non-invasive maneuverability is ideally suited for real-world applications, such as confined-space inspection and ecological monitoring, inaccessible to traditional drones, while their biomechanical fidelity provides a physical model to decode the principles underlying the erratic yet efficient flight of real butterflies.
Abstract (translated)
振翅微型飞行器（FWMAV）已经展示了生物启发的高度敏捷性，但无尾双翼配置由于其复杂的流体-结构耦合和翼身耦合问题，至今仍较少被探索。本文介绍了名为“AirPulse”的26克蝴蝶启发式FWMAV，它实现了完全自主、闭环的无绳飞行，无需辅助控制表面。AirPulse机器人复制了蝴蝶飞行的关键生物力学特性，包括低翼展比、柔性的碳纤维增强翅膀以及低频高振幅拍打，这种拍打方式导致重心和转动惯量的周期性变化，从而产生特征性的身体摆动。 我们建立了一个关于拍打调节参数与力矩产生的定量映射，并引入了击翅时间不对称节奏（STAR）生成器，使翼扇不对称能够平滑、稳定且线性地调整飞行控制。结合这些技术和姿态控制器后，AirPulse机器人能够在强烈的振荡动力学下保持俯仰和偏航稳定性。自由飞行实验表明，通过角度偏移或拍打时间调节，它可以实现稳定的爬升和转弯操作，这是迄今为止在同行评审文献中报告的最轻量级无尾双翼蝴蝶启发式FWMAV自主控制飞行。 这项工作验证了一个为轻型、防撞FWMAV提供的基础平台，它将生物灵感与实用的空中机器人技术相结合。它们非侵入性的机动性非常适合传统无人机无法进入的实际应用领域，例如狭窄空间检查和生态监测，并且它们的高度机械逼真度提供了一种物理模型，用于解码真实蝴蝶飞行中混乱却又高效的基本原理。
URL
https://arxiv.org/abs/2602.06811
PDF
-
DroneKey++: A Size Prior-free Method and New Benchmark for Drone 3D Pose Estimation from Sequential Images
2026-02-05 21:41:20Seo-Bin Hwang, Yeong-Jun ChoAbstract
Accurate 3D pose estimation of drones is essential for security and surveillance systems. However, existing methods often rely on prior drone information such as physical sizes or 3D meshes. At the same time, current datasets are small-scale, limited to single models, and collected under constrained environments, which makes reliable validation of generalization difficult. We present DroneKey++, a prior-free framework that jointly performs keypoint detection, drone classification, and 3D pose estimation. The framework employs a keypoint encoder for simultaneous keypoint detection and classification, and a pose decoder that estimates 3D pose using ray-based geometric reasoning and class embeddings. To address dataset limitations, we construct 6DroneSyn, a large-scale synthetic benchmark with over 50K images covering 7 drone models and 88 outdoor backgrounds, generated using 360-degree panoramic synthesis. Experiments show that DroneKey++ achieves MAE 17.34 deg and MedAE 17.1 deg for rotation, MAE 0.135 m and MedAE 0.242 m for translation, with inference speeds of 19.25 FPS (CPU) and 414.07 FPS (GPU), demonstrating both strong generalization across drone models and suitability for real-time applications. The dataset is publicly available.
Abstract (translated)
准确的3D姿态估计对于无人机的安全和监控系统至关重要。然而，现有的方法通常依赖于预先存在的无人机信息，如物理尺寸或三维网格模型。同时，当前的数据集规模较小，仅限于单个型号，并且是在受控环境中收集的，这使得验证泛化能力变得困难。我们提出了一种名为DroneKey++的无先验框架，该框架能够同时进行关键点检测、无人机分类和3D姿态估计。此框架采用了一个关键点编码器来实现同步的关键点检测与分类，并使用基于射线的几何推理和类嵌入的姿势解码器来估算3D姿态。 为了解决数据集限制问题，我们构建了6DroneSyn，这是一个大规模的人工合成基准测试集，包含超过5万张图片，涵盖了7种无人机型号以及88种户外背景环境，并使用全景合成技术生成。实验表明，DroneKey++在旋转估计中达到了17.34度的平均绝对误差（MAE）和17.1度的中位数绝对误差（MedAE），在平移估计中的误差分别为0.135米（MAE）和0.242米（MedAE）。此外，该框架还表现出卓越的速度性能，在CPU上的推断速度为每秒19.25帧，在GPU上的推断速度为每秒414.07帧。这些结果表明DroneKey++在不同无人机型号之间的泛化能力以及适用于实时应用的潜力。数据集现已公开可用。
URL
https://arxiv.org/abs/2602.06211
PDF
-
From Bench to Flight: Translating Drone Impact Tests into Operational Safety Limits
2026-02-05 17:34:49Aziz Mohamed Mili, Louis Catar, Paul G\'erard, Ilyass Tabiai, David St-OngeAbstract
Indoor micro-aerial vehicles (MAVs) are increasingly used for tasks that require close proximity to people, yet practitioners lack practical methods to tune motion limits based on measured impact risk. We present an end-to-end, open toolchain that converts benchtop impact tests into deployable safety governors for drones. First, we describe a compact and replicable impact rig and protocol for capturing force-time profiles across drone classes and contact surfaces. Second, we provide data-driven models that map pre-impact speed to impulse and contact duration, enabling direct computation of speed bounds for a target force limit. Third, we release scripts and a ROS2 node that enforce these bounds online and log compliance, with support for facility-specific policies. We validate the workflow on multiple commercial off-the-shelf quadrotors and representative indoor assets, demonstrating that the derived governors preserve task throughput while meeting force constraints specified by safety stakeholders. Our contribution is a practical bridge from measured impacts to runtime limits, with shareable datasets, code, and a repeatable process that teams can adopt to certify indoor MAV operations near humans.
Abstract (translated)
室内微型航空车辆（MAVs）在需要与人近距离接触的任务中使用得越来越频繁，然而操作者缺乏基于实际冲击风险测量来调整运动限制的实用方法。我们提出了一种端到端、开放式的工具链，能够将实验台上的碰撞测试数据转化为无人机可部署的安全控制器。 首先，我们描述了一个紧凑且易于复制的碰撞测试装置和协议，用于捕捉不同类型的无人机及接触面在碰撞过程中的力-时间曲线。 其次，我们提供了一些基于数据驱动模型的方法，这些方法可以将预碰撞速度映射到冲量和接触持续时间上，从而直接计算出达到特定力限制所需的最高速度阈值。 最后，我们发布了一系列脚本以及一个ROS2节点，用于在线执行这些速度边界并记录合规情况，并支持不同设施的具体政策。 我们在多个商用现成的四旋翼无人机及代表性的室内设备上验证了这一工作流程的有效性。结果表明，由此衍生出的安全控制器能够保证任务吞吐量的同时满足安全利益相关方所指定的力量限制条件。我们的贡献在于提供了一座从实际碰撞测量到运行时限制之间实用桥梁，通过共享的数据集、代码和可重复的过程，团队可以采用这些方法来认证室内MAVs在人类周围的操作安全性。
URL
https://arxiv.org/abs/2602.05922
PDF
-
A 96pJ/Frame/Pixel and 61pJ/Event Anti-UAV System with Hybrid Object Tracking Modes
2026-02-05 15:04:39Yuncheng Lu, Yucen Shi, Aobo Li, Zehao Li, Junying Li, Bo Wang, Tony Tae-Hyoung KimAbstract
We present an energy-efficient anti-UAV system that integrates frame-based and event-driven object tracking to enable reliable detection of small and fast-moving drones. The system reconstructs binary event frames using run-length encoding, generates region proposals, and adaptively switches between frame mode and event mode based on object size and velocity. A Fast Object Tracking Unit improves robustness for high-speed targets through adaptive thresholding and trajectory-based classification. The neural processing unit supports both grayscale-patch and trajectory inference with a custom instruction set and a zero-skipping MAC architecture, reducing redundant neural computations by more than 97 percent. Implemented in 40 nm CMOS technology, the 2 mm^2 chip achieves 96 pJ per frame per pixel and 61 pJ per event at 0.8 V, and reaches 98.2 percent recognition accuracy on public UAV datasets across 50 to 400 m ranges and 5 to 80 pixels per second speeds. The results demonstrate state-of-the-art end-to-end energy efficiency for anti-UAV systems.
Abstract (translated)
我们提出了一种节能的反无人机系统，该系统结合了基于帧和事件驱动的对象跟踪技术，以实现对小型快速移动无人机的可靠检测。该系统使用行程长度编码重构二进制事件帧，并生成区域提案。根据目标大小和速度，它可以自适应地在帧模式和事件模式之间切换。快速物体跟踪单元通过自适应阈值调整和基于轨迹分类提高了高速目标的鲁棒性。神经处理单元支持灰度补丁和轨迹推理，采用了一套定制指令集以及零跳过MAC（矩阵乘法累加）架构，在减少冗余神经计算方面超过了97%的效率。 在40纳米CMOS技术中实现的芯片面积为2平方毫米，该系统在0.8伏电压下每帧每像素的能量消耗为96皮焦耳，每个事件的能量消耗为61皮焦耳。它在公开的无人机数据集上实现了高达98.2%的识别准确率，在50到400米的距离范围内和每秒5至80个像素的速度时性能均表现良好。 实验结果表明该系统达到了反无人机系统的端到端能耗效率的新水平。
URL
https://arxiv.org/abs/2512.17939
PDF
-
Depth as Prior Knowledge for Object Detection
2026-02-05 14:52:39Moussa Kassem Sbeyti, Nadja KleinAbstract
Detecting small and distant objects remains challenging for object detectors due to scale variation, low resolution, and background clutter. Safety-critical applications require reliable detection of these objects for safe planning. Depth information can improve detection, but existing approaches require complex, model-specific architectural modifications. We provide a theoretical analysis followed by an empirical investigation of the depth-detection relationship. Together, they explain how depth causes systematic performance degradation and why depth-informed supervision mitigates it. We introduce DepthPrior, a framework that uses depth as prior knowledge rather than as a fused feature, providing comparable benefits without modifying detector architectures. DepthPrior consists of Depth-Based Loss Weighting (DLW) and Depth-Based Loss Stratification (DLS) during training, and Depth-Aware Confidence Thresholding (DCT) during inference. The only overhead is the initial cost of depth estimation. Experiments across four benchmarks (KITTI, MS COCO, VisDrone, SUN RGB-D) and two detectors (YOLOv11, EfficientDet) demonstrate the effectiveness of DepthPrior, achieving up to +9% mAP$_S$ and +7% mAR$_S$ for small objects, with inference recovery rates as high as 95:1 (true vs. false detections). DepthPrior offers these benefits without additional sensors, architectural changes, or performance costs. Code is available at this https URL.
Abstract (translated)
检测小而远的物体对于目标检测器来说仍然是一个挑战，原因在于尺度变化、低分辨率和背景杂乱。安全关键应用需要可靠地检测这些对象以进行安全规划。深度信息可以提高检测效果，但现有的方法通常需要复杂的、模型特定的架构修改。我们提供了关于深度与检测关系的理论分析和实证研究。两者共同解释了深度如何导致系统性性能下降以及为什么基于深度的信息监督可以缓解这一问题。 为此，我们提出了DepthPrior框架，它将深度信息作为先验知识使用，而不是将其融合为特征表示，从而在无需修改检测器架构的情况下提供可比的益处。DepthPrior由三个部分组成：训练时的基于深度损失加权（DLW）和基于深度损失分层（DLS），以及推理时的深度感知置信度阈值（DCT）。唯一的额外开销是在初始阶段进行深度估计的成本。 在四个基准数据集（KITTI、MS COCO、VisDrone、SUN RGB-D）上，以及两种检测器模型（YOLOv11和EfficientDet）上的实验展示了DepthPrior的有效性，在小物体的平均精度(mAP$_S$)和平均召回率(mAR$_S$)分别提高了高达9%和7%，并且推理恢复率达到惊人的95:1（真实与假阳性检测的比例）。重要的是，DepthPrior无需额外传感器、架构变化或性能成本即可提供这些益处。 代码可以在提供的URL中获取。
URL
https://arxiv.org/abs/2602.05730
PDF
-
Reactive Knowledge Representation and Asynchronous Reasoning
2026-02-05 13:02:01Simon Kohaut, Benedict Flade, Julian Eggert, Kristian Kersting, Devendra Singh DhamiAbstract
Exact inference in complex probabilistic models often incurs prohibitive computational costs. This challenge is particularly acute for autonomous agents in dynamic environments that require frequent, real-time belief updates. Existing methods are often inefficient for ongoing reasoning, as they re-evaluate the entire model upon any change, failing to exploit that real-world information streams have heterogeneous update rates. To address this, we approach the problem from a reactive, asynchronous, probabilistic reasoning perspective. We first introduce Resin (Reactive Signal Inference), a probabilistic programming language that merges probabilistic logic with reactive programming. Furthermore, to provide efficient and exact semantics for Resin, we propose Reactive Circuits (RCs). Formulated as a meta-structure over Algebraic Circuits and asynchronous data streams, RCs are time-dynamic Directed Acyclic Graphs that autonomously adapt themselves based on the volatility of input signals. In high-fidelity drone swarm simulations, our approach achieves several orders of magnitude of speedup over frequency-agnostic inference. We demonstrate that RCs' structural adaptations successfully capture environmental dynamics, significantly reducing latency and facilitating reactive real-time reasoning. By partitioning computations based on the estimated Frequency of Change in the asynchronous inputs, large inference tasks can be decomposed into individually memoized sub-problems. This ensures that only the specific components of a model affected by new information are re-evaluated, drastically reducing redundant computation in streaming contexts.
Abstract (translated)
在复杂的概率模型中进行精确推理往往会导致高昂的计算成本，这对需要频繁实时更新信念的动态环境中的自主代理来说尤其是一个挑战。现有的方法通常无法高效地处理持续性的推理问题，因为它们会在每次变化时重新评估整个模型，而未能利用现实世界信息流具有不同的更新频率这一特性。为了解决这个问题，我们从一种反应式、异步和概率性推理的角度来解决问题。首先，我们介绍了一种名为Resin（Reactive Signal Inference）的概率编程语言，它将概率逻辑与反应式编程相结合。 为了给Resin提供高效且精确的语义学基础，我们提出了“反应电路”(Reactive Circuits, RCs)这一概念。RCs作为一种代数电路和异步数据流上的元结构，它们是时间动态有向无环图(DAG)，能够根据输入信号的变化率自动调整自己。 在高保真无人机群模拟实验中，我们的方法相比频率不敏感的推理方法实现了几个数量级的速度提升。我们证明了RCs的结构适应性成功地捕捉到了环境动力学变化，显著减少了延迟，并促进了反应式的实时推理。通过基于异步输入的变化频率来划分计算任务，大型推断任务可以被分解成单独存储化（memoized）的小问题。 这样确保了只有模型中受到新信息影响的具体部分会被重新评估，极大地减少了流式处理环境中的冗余计算。
URL
https://arxiv.org/abs/2602.05625
PDF
-
VLN-Pilot: Large Vision-Language Model as an Autonomous Indoor Drone Operator
2026-02-05 11:23:11Bessie Dominguez-Dager, Sergio Suescun-Ferrandiz, Felix Escalona, Francisco Gomez-Donoso, Miguel CazorlaAbstract
This paper introduces VLN-Pilot, a novel framework in which a large Vision-and-Language Model (VLLM) assumes the role of a human pilot for indoor drone navigation. By leveraging the multimodal reasoning abilities of VLLMs, VLN-Pilot interprets free-form natural language instructions and grounds them in visual observations to plan and execute drone trajectories in GPS-denied indoor environments. Unlike traditional rule-based or geometric path-planning approaches, our framework integrates language-driven semantic understanding with visual perception, enabling context-aware, high-level flight behaviors with minimal task-specific engineering. VLN-Pilot supports fully autonomous instruction-following for drones by reasoning about spatial relationships, obstacle avoidance, and dynamic reactivity to unforeseen events. We validate our framework on a custom photorealistic indoor simulation benchmark and demonstrate the ability of the VLLM-driven agent to achieve high success rates on complex instruction-following tasks, including long-horizon navigation with multiple semantic targets. Experimental results highlight the promise of replacing remote drone pilots with a language-guided autonomous agent, opening avenues for scalable, human-friendly control of indoor UAVs in tasks such as inspection, search-and-rescue, and facility monitoring. Our results suggest that VLLM-based pilots may dramatically reduce operator workload while improving safety and mission flexibility in constrained indoor environments.
Abstract (translated)
本文介绍了VLN-Pilot，这是一个新颖的框架，在该框架中，一个大型视觉与语言模型（VLLM）扮演室内无人机导航的人类飞行员角色。通过利用VLLMs的多模态推理能力，VLN-Pilot可以解释自由形式的自然语言指令，并将其与视觉观察相结合以在没有GPS的室内环境中规划和执行无人机轨迹。不同于传统的基于规则或几何路径规划的方法，我们的框架将语言驱动的语义理解与视觉感知相结合，能够实现上下文感知、高层级飞行行为，同时减少了特定任务所需的工程量。 VLN-Pilot支持无人机完全自主地遵循指令，通过推理空间关系、障碍物规避以及对未预见事件的动态反应来完成任务。我们在一个定制的真实感室内模拟基准上验证了我们的框架，并展示了VLLM驱动代理在复杂指令执行任务中实现高成功率的能力，包括具有多个语义目标的长时导航。 实验结果强调了用语言引导的自主代理替代远程无人机飞行员的可能性，为在检查、搜索救援和设施监控等任务中控制室内UAV提供了一种可扩展且人性化的途径。我们的研究结果表明，基于VLLM的飞行员可能大幅减少操作员的工作量，并提高受限室内环境中的安全性和任务灵活性。
URL
https://arxiv.org/abs/2602.05552
PDF
-
Cross-talk based multi-task learning for fault classification of physically coupled machine system
2026-02-05 00:10:16Wonjun Yi, Rismaya Kumar Mishra, Yong-Hwa ParkAbstract
Machine systems inherently generate signals in which fault conditions and various physical variables are physically coupled. Although many existing fault classification studies rely solely on direct fault labels, the aforementioned signals naturally embed additional information shaped by other physically coupled information. Herein, we leverage this coupling through a multi-task learning (MTL) framework that jointly learns fault conditions and the related physical variables. Among MTL architectures, crosstalk structures have distinct advantages because they allow for controlled information exchange between tasks through the cross-talk layer while preventing negative transfer, in contrast to shared trunk architectures that often mix incompatible features. We build on our previously introduced residual neural dimension reductor model, and extend its application to two benchmarks where physical coupling is prominent. The first benchmark is a drone fault dataset, in which machine type and maneuvering direction significantly alter the frequency components of measured signals even under the same nominal condition. By learning fault classification together with these physical attributes, the cross-talk architecture can better classify faults. The second benchmark dataset is the motor compound fault dataset. In this system, each fault component, inner race fault, outer race fault, misalignment, and unbalance is coupled to the other. For motor compound fault, we also test classification performance when we use single-channel data or multi-channel data as input to the classifier. Across both benchmarks, our residual neural dimension reductor, consistently outperformed single-task models, multi-class models that merge all label combinations, and shared trunk multi-task models.
Abstract (translated)
机器系统内在地会产生信号，在这些信号中，故障条件和各种物理变量是通过物理方式耦合在一起的。尽管许多现有的故障分类研究仅依赖于直接的故障标签，但上述信号自然嵌入了其他物理相关信息塑造的额外信息。在此基础上，我们利用这种耦合关系并通过一个多任务学习（MTL）框架同时学习故障条件及其相关的物理变量。在多任务架构中，交叉结构具有明显的优点，因为它们允许通过交叉层进行受控的信息交换，从而防止负向迁移，而与之相对的共享主干架构往往混合了不兼容的特征。 我们在此基础上扩展了之前介绍的残差神经维度缩减模型，并将其应用到两个突出物理耦合的重要基准数据集上。第一个基准是无人机故障数据集，在同一名义条件下，机器类型和操控方向会显著改变测量信号中的频率成分。通过同时学习故障分类及这些物理属性，交叉架构能够更好地进行故障分类。 第二个基准数据集是电机复合故障数据集。在这个系统中，每个故障组件（内圈故障、外圈故障、不对中和不平衡）都与其他组件耦合在一起。对于电机复合故障，我们还测试了单通道输入或多个通道输入到分类器时的分类性能表现。 在这两个基准上，我们的残差神经维度缩减模型始终优于单一任务模型、合并所有标签组合的多类别模型以及共享主干架构的多任务模型。
URL
https://arxiv.org/abs/2602.05146
PDF
-
AGMA: Adaptive Gaussian Mixture Anchors for Prior-Guided Multimodal Human Trajectory Forecasting
2026-02-04 04:42:57Chao Li, Rui Zhang, Siyuan Huang, Xian Zhong, Hongbo JiangAbstract
Human trajectory forecasting requires capturing the multimodal nature of pedestrian behavior. However, existing approaches suffer from prior misalignment. Their learned or fixed priors often fail to capture the full distribution of plausible futures, limiting both prediction accuracy and diversity. We theoretically establish that prediction error is lower-bounded by prior quality, making prior modeling a key performance bottleneck. Guided by this insight, we propose AGMA (Adaptive Gaussian Mixture Anchors), which constructs expressive priors through two stages: extracting diverse behavioral patterns from training data and distilling them into a scene-adaptive global prior for inference. Extensive experiments on ETH-UCY, Stanford Drone, and JRDB datasets demonstrate that AGMA achieves state-of-the-art performance, confirming the critical role of high-quality priors in trajectory forecasting.
Abstract (translated)
人类轨迹预测需要捕捉行人行为的多模态特性。然而，现有的方法存在先验偏差的问题。它们学习到或固定的先验通常无法完全捕捉到所有可能未来的分布，从而限制了预测的准确性和多样性。理论上讲，我们建立了预测误差由先验质量下限决定的观点，表明先验建模是性能瓶颈的关键所在。基于这一见解，我们提出了AGMA（自适应高斯混合锚点）方法，通过两个阶段构建表达性的先验：从训练数据中提取多样化的行为模式，并将其提炼成用于推理的场景适应性全局先验。在ETH-UCY、斯坦福无人机和JRDB数据集上的大量实验表明，AGMA实现了最先进的性能，证实了高质量先验在轨迹预测中的关键作用。
URL
https://arxiv.org/abs/2602.04204
PDF
-
FDA Flocking: Future Direction-Aware Flocking via Velocity Prediction
2026-02-03 21:00:33Hossein B. Jond, Martin SaskaAbstract
Understanding self-organization in natural collectives such as bird flocks inspires swarm robotics, yet most flocking models remain reactive, overlooking anticipatory cues that enhance coordination. Motivated by avian postural and wingbeat signals, as well as multirotor attitude tilts that precede directional changes, this work introduces a principled, bio-inspired anticipatory augmentation of reactive flocking termed Future Direction-Aware (FDA) flocking. In the proposed framework, agents blend reactive alignment with a predictive term based on short-term estimates of neighbors' future velocities, regulated by a tunable blending parameter that interpolates between reactive and anticipatory behaviors. This predictive structure enhances velocity consensus and cohesion-separation balance while mitigating the adverse effects of sensing and communication delays and measurement noise that destabilize reactive baselines. Simulation results demonstrate that FDA achieves faster and higher alignment, enhanced translational displacement of the flock, and improved robustness to delays and noise compared to a purely reactive model. Future work will investigate adaptive blending strategies, weighted prediction schemes, and experimental validation on multirotor drone swarms.
Abstract (translated)
理解自然集体（如鸟群）中的自我组织可以启发群体机器人学，然而大多数的群体模型仍然保持反应式的特征，忽略了增强协调性的预见性线索。受鸟类姿态和翼拍信号以及多旋翼倾斜角度在方向变化前的表现启发，这项工作引入了一种原理性和生物启发式的前瞻性增益技术，称为“未来方向感知型”（Future Direction-Aware, FDA）群体模型。在这个框架中，代理者将反应式对齐与基于邻居短期速度估计的预测性术语相结合，并通过一个可调插值参数在反应和预见行为之间进行调节。这种预测结构可以增强速度共识、凝聚力分离平衡，并减轻传感及通信延迟以及测量噪声导致的不稳定效应。 仿真结果表明，FDA模型相较于纯粹的反应式模型，在对齐速度与幅度、鸟群整体位移能力以及对抗时延和噪音扰动的鲁棒性方面表现出更优的效果。未来的研究将探索自适应调节策略、加权预测方案及多旋翼无人机群体实验验证等方向。
URL
https://arxiv.org/abs/2602.04012
PDF
-
Conformal Reachability for Safe Control in Unknown Environments
2026-02-03 18:01:38Xinhang Ma, Junlin Wu, Yiannis Kantaros, Yevgeniy VorobeychikAbstract
Designing provably safe control is a core problem in trustworthy autonomy. However, most prior work in this regard assumes either that the system dynamics are known or deterministic, or that the state and action space are finite, significantly limiting application scope. We address this limitation by developing a probabilistic verification framework for unknown dynamical systems which combines conformal prediction with reachability analysis. In particular, we use conformal prediction to obtain valid uncertainty intervals for the unknown dynamics at each time step, with reachability then verifying whether safety is maintained within the conformal uncertainty bounds. Next, we develop an algorithmic approach for training control policies that optimize nominal reward while also maximizing the planning horizon with sound probabilistic safety guarantees. We evaluate the proposed approach in seven safe control settings spanning four domains -- cartpole, lane following, drone control, and safe navigation -- for both affine and nonlinear safety specifications. Our experiments show that the policies we learn achieve the strongest provable safety guarantees while still maintaining high average reward.
Abstract (translated)
设计可证明安全的控制是可信自主系统中的核心问题。然而，先前大多数相关工作要么假设系统的动力学特性已知或为确定性的，要么假设状态和动作空间是有限的，这大大限制了应用范围。为了克服这一局限性，我们开发了一个针对未知动态系统的概率验证框架，该框架结合了符合预测（conformal prediction）与可达性分析（reachability analysis）。具体来说，通过使用符合预测来获得每个时间步中未知动力学的有效不确定性区间，并利用可达性分析验证在符合预测的不确定性范围内是否能维持安全性。接下来，我们开发了一种算法方法，用于训练控制策略，在优化名义奖励的同时最大化规划时间范围，并确保具有坚实的概率安全保证。 我们在七种不同的安全控制设置下评估了所提出的方法，这些设置涵盖了四个领域——倒立摆（cartpole）、车道跟随、无人机控制以及安全导航——并且针对仿射和非线性安全规范进行了测试。我们的实验结果表明，我们学习到的策略能够实现最强有力的可证明的安全保证，同时保持较高的平均奖励。 这段描述强调了开发一个适用于未知且具有不确定性的动态系统的概率验证框架的重要性，并展示了如何通过结合预测模型和安全性分析来优化控制策略，在确保安全的同时提高性能。这种方法为构建更加可靠、实用的自主系统提供了一种新途径。
URL
https://arxiv.org/abs/2602.03799
PDF
