Drone
-
Adaptive Slicing-Assisted Hyper Inference for Enhanced Small Object Detection in High-Resolution Imagery
2026-04-21 08:36:51Francesco Moretti, Yi Jin, Guiqin MarioAbstract
Deep learning-based object detectors have achieved remarkable success across numerous computer vision applications, yet they continue to struggle with small object detection in high-resolution aerial and satellite imagery, where dense object distributions, variable shooting angles, diminutive target sizes, and substantial inter-class variability pose formidable challenges. Existing slicing strategies that partition high-resolution images into manageable patches have demonstrated promising results for enlarging the effective receptive field of small targets; however, their reliance on fixed slice dimensions introduces significant redundant computation, inflating inference cost and undermining detection speed. In this paper, we propose \textbf{Adaptive Slicing-Assisted Hyper Inference (ASAHI)}, a novel slicing framework that shifts the paradigm from prescribing a fixed slice size to adaptively determining the optimal number of slices according to image resolution, thereby substantially mitigating redundant computation while preserving beneficial overlap between adjacent patches. ASAHI integrates three synergistic components: (1)an adaptive resolution-aware slicing algorithm that dynamically generates 6 or 12 overlapping patches based on a learned threshold, (2)a slicing-assisted fine-tuning (SAF) strategy that constructs augmented training data comprising both full-resolution and sliced image patches, and (3)a Cluster-DIoU-NMS (CDN) post-processing module that combines the geometric merging efficiency of Cluster-NMS with the center-distance-aware suppression of DIoU-NMS to achieve robust duplicate elimination in crowded scenes. Extensive experiments on VisDrone2019 and xView, demonstrate that ASAHI achieves state-of-the-art performance with 56.8% on VisDrone2019-DET-val and 22.7% on xView-test, while reducing inference time by 20-25% compared to the baseline SAHI method.
Abstract (translated)
URL
https://arxiv.org/abs/2604.19233
PDF
-
Autonomous Unmanned Aircraft Systems for Enhanced Search and Rescue of Drowning Swimmers: Image-Based Localization and Mission Simulation
2026-04-20 11:05:21Sascha Emanuel Zell, Toni Schneidereit, Armin F\"ugenschuh, Michael Breu{\ss}Abstract
Drowning is an omnipresent risk associated with any activity on or in the water, and rescuing a drowning person is particularly challenging because of the time pressure, making a short response time important. Further complicating water rescue are unsupervised and extensive swimming areas, precise localization of the target, and the transport of rescue personnel. Technical innovations can provide a remedy: We propose an Unmanned Aircraft System (UAS), also known as a drone-in-a-box system, consisting of a fleet of Unmanned Aerial Vehicles (UAVs) allocated to purpose-built hangars near swimming areas. In an emergency, the UAS can be deployed in addition to Standard Rescue Operation (SRO) equipment to locate the distressed person early by performing a fully automated Search and Rescue (S&R) operation and dropping a flotation device. In this paper, we address automatically locating distressed swimmers using the image-based object detection architecture You Only Look Once (YOLO). We present a dataset created for this application and outline the training process. We evaluate the performance of YOLO versions 3, 5, and 8 and architecture sizes (nano, extra-large) using Mean Average Precision (mAP) metrics mAP@.5 and mAP@.5:.95. Furthermore, we present two Discrete-Event Simulation (DES) approaches to simulate response times of SRO and UAS-based water rescue. This enables estimation of time savings relative to SRO when selecting the UAS configuration (type, number, and location of UAVs and hangars). Computational experiments for a test area in the Lusatian Lake District, Germany, show that UAS assistance shortens response time. Even a small UAS with two hangars, each containing one UAV, reduces response time by a factor of five compared to SRO.
Abstract (translated)
URL
https://arxiv.org/abs/2604.18088
PDF
-
Shepherding UAV Swarm with Action Prediction Based on Movement Constraints
2026-04-19 01:32:37Yusuke Tsunoda, Yusuke Goto, Takao SatoAbstract
In this study, we propose a new sheepdog-inspired control method for a swarm of small unmanned aerial vehicles (UAVs), which predicts the swarm behavior while explicitly accounting for the motion constraints of real robots. Sheepdog-inspired guidance control refers to a framework in which a small number of navigator agents (sheepdog agents) indirectly drive a large number of autonomous agents (a flock of sheep agents) so as to steer the group toward a target position. In conventional studies on sheepdog-inspired guidance, both types of agents have typically been modeled as point masses, and the guidance law for the navigator agents has been designed using simple interaction vectors based on the instantaneous relative positions between the agents. However, when implementing such methods on real robots such as drones, it is necessary to consider each agent's motion constraints, including upper bounds on velocity and acceleration. Moreover, we argue that guidance can be made more efficient by predicting the future behavior of the autonomous swarm that is observable to the navigator agents. To this end, we propose a three-dimensional guidance control law based on behavior prediction of autonomous agents under motion constraints, inspired by the Dynamic Window Approach (DWA). At each control cycle, the navigator agent generates a set of feasible motion candidates that satisfy its motion constraints, and predicts the short-horizon swarm evolution using an internal model of the autonomous agents maintained within the navigator agent. The motion candidates are then evaluated according to criteria such as the progress velocity toward the target, the positioning strategy with respect to the swarm, and safety margins, and the optimal motion is selected to achieve safe and efficient guidance. Numerical simulation results demonstrate the effectiveness of the proposed guidance control law.
Abstract (translated)
URL
https://arxiv.org/abs/2604.17189
PDF
-
LAGS: Low-Altitude Gaussian Splatting with Groupwise Heterogeneous Graph Learning
2026-04-18 08:41:50Yikun Wang, Yujie Wan, Wei Zuo, Shuai Wang, Yik-Chung Wu, Chengzhong Xu, Huseyin ArslanAbstract
Low-altitude Gaussian splatting (LAGS) facilitates 3D scene reconstruction by aggregating aerial images from distributed drones. However, as LAGS prioritizes maximizing reconstruction quality over communication throughput, existing low-altitude resource allocation schemes become inefficient. This inefficiency stems from their failure to account for image diversity introduced by varying viewpoints. To fill this gap, we propose a groupwise heterogeneous graph neural network (GW-HGNN) for LAGS resource allocation. GW-HGNN explicitly models the non-uniform contribution of different image groups to the reconstruction process, thus automatically balancing data fidelity and transmission cost. The key insight of GW-HGNN is to transform LAGS losses and communication constraints into graph learning costs for dual-level message passing. Experiments on real-world LAGS datasets demonstrate that GW-HGNN significantly outperforms state-of-the-art benchmarks across key rendering metrics, including PSNR, SSIM, and LPIPS. Furthermore, GW-HGNN reduces computational latency by approximately 100x compared to the widely-used MOSEK solver, achieving millisecond-level inference suitable for real-time deployment.
Abstract (translated)
URL
https://arxiv.org/abs/2604.16910
PDF
-
Robust Fleet Sizing for Multi-UAV Inspection Missions under Synchronized Replacement Demand
Abstract
Multi-UAV inspection missions require spare drones to replace active drones during recharging cycles. Existing fleet-sizing approaches often assume steady-state operating conditions that do not apply to finite-horizon missions, or they treat replacement requests as statistically independent events. The latter provides per-request blocking guarantees that fail to translate to mission-level reliability when demands cluster. This paper identifies a structural failure mode where efficient routing assigns similar workloads to each UAV, leading to synchronized battery depletion and replacement bursts that exhaust the spare pool even when average capacity is sufficient. We derive a closed-form sufficient fleet-sizing rule, k = m(ceil(R) + 1), where m is the number of active UAVs and R is the recovery-to-active time ratio. This additive buffer of m spares absorbs worst-case synchronized demand at recovery-cycle boundaries and ensures mission-level reliability even when all UAVs deplete simultaneously. Monte Carlo validation across five scenarios (m in [2, 10], R in [0.87, 3.39], 1000 trials each) shows that Erlang-B sizing with a per-request blocking target epsilon = 0.01 drops to 69.9% mission success at R = 3.39, with 95% of spare exhaustion events concentrated in the top-decile 5-minute demand windows. In contrast, the proposed rule maintains 99.8% success (Wilson 95% lower bound 99.3%) across all tested conditions, including wind variability up to CV = 0.30, while requiring only four additional drones in the most demanding scenario.
Abstract (translated)
URL
https://arxiv.org/abs/2604.15890
PDF
-
Fuzzy Logic Theory-based Adaptive Reward Shaping for Robust Reinforcement Learning
2026-04-17 07:25:55H\"urkan \c{S}ahin, Van Huyen Dang, Erdi Sayar, Alper Yegenoglu, Erdal KayacanAbstract
Reinforcement learning (RL) often struggles in real-world tasks with high-dimensional state spaces and long horizons, where sparse or fixed rewards severely slow down exploration and cause agents to get trapped in local optima. This paper presents a fuzzy logic based reward shaping method that integrates human intuition into RL reward design. By encoding expert knowledge into adaptive and interpreable terms, fuzzy rules promote stable learning and reduce sensitivity to hyperparameters. The proposed method leverages these properties to adapt reward contributions based on the agent state, enabling smoother transitions between fast motion and precise control in challenging navigation tasks. Extensive simulation results on autonomous drone racing benchmarks show stable learning behavior and consistent task performance across scenarios of increasing difficulty. The proposed method achieves faster convergence and reduced performance variability across training seeds in more challenging environments, with success rates improving by up to approximately 5 percent compared to non fuzzy reward formulations.
Abstract (translated)
URL
https://arxiv.org/abs/2604.15772
PDF
-
FSDETR: Frequency-Spatial Feature Enhancement for Small Object Detection
2026-04-16 11:22:13Jianchao Huang, Fengming Zhang, Haibo Zhu, Tao YanAbstract
Small object detection remains a significant challenge due to feature degradation from downsampling, mutual occlusion in dense clusters, and complex background interference. To address these issues, this paper proposes FSDETR, a frequency-spatial feature enhancement framework built upon the RT-DETR baseline. By establishing a collaborative modeling mechanism, the method effectively leverages complementary structural information. Specifically, a Spatial Hierarchical Attention Block (SHAB) captures both local details and global dependencies to strengthen semantic representation. Furthermore, to mitigate occlusion in dense scenes, the Deformable Attention-based Intra-scale Feature Interaction (DA-AIFI) focuses on informative regions via dynamic sampling. Finally, the Frequency-Spatial Feature Pyramid Network (FSFPN) integrates frequency filtering with spatial edge extraction via the Cross-domain Frequency-Spatial Block (CFSB) to preserve fine-grained details. Experimental results show that with only 14.7M parameters, FSDETR achieves 13.9% APS on VisDrone 2019 and 48.95% AP50 tiny on TinyPerson, showing strong performance on small-object benchmarks. The code and models are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14884
PDF
-
Robust Energy-Aware Routing for Air-Ground Cooperative Multi-UAV Delivery in Wind-Uncertain Environments
2026-04-15 03:43:18Tianshun Li, Hongliang Lu, Yanggang Sheng, Zhongzhen Wang, Haoang Li, Xinhu ZhengAbstract
Ensuring energy feasibility under wind uncertainty is critical for the safety and reliability of UAV delivery missions. In realistic truck-drone logistics systems, UAVs must deliver parcels and safely return under time-varying wind conditions that are only partially observable during flight. However, most existing routing approaches assume static or deterministic energy models, making them unreliable in dynamic wind environments. We propose Battery-Efficient Routing (BER), an online risk-sensitive planning framework for wind-sensitive truck-assisted UAV delivery. The problem is formulated as routing on a time dependent energy graph whose edge costs evolve according to wind-induced aerodynamic effects. BER continuously evaluates return feasibility while balancing instantaneous energy expenditure and uncertainty-aware risk. The approach is embedded in a hierarchical aerial-ground delivery architecture that combines task allocation, routing, and decentralized trajectory execution. Extensive simulations on synthetic ER graphs generated in Unreal Engine environments and quasi-real wind logs demonstrate that BER significantly improves mission success rates and reduces wind-induced failures compared with static and greedy baselines. These results highlight the importance of integrating real-time energy budgeting and environmental awareness for UAV delivery planning under dynamic wind conditions.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13441
PDF
-
See&Say: Vision Language Guided Safe Zone Detection for Autonomous Package Delivery Drones
2026-04-14 20:54:31Mahyar Ghazanfari, Peng WeiAbstract
Autonomous drone delivery systems are rapidly advancing, but ensuring safe and reliable package drop-offs remains highly challenging in cluttered urban and suburban environments where accurately identifying suitable package drop zones is critical. Existing approaches typically rely on either geometry-based analysis or semantic segmentation alone, but these methods lack the integrated semantic reasoning required for robust decision-making. To address this gap, we propose See&Say, a novel framework that combines geometric safety cues with semantic perception, guided by a Vision-Language Model (VLM) for iterative refinement. The system fuses monocular depth gradients with open-vocabulary detection masks to produce safety maps, while the VLM dynamically adjusts object category prompts and refines hazard detection across time, enabling reliable reasoning under dynamic conditions during the final delivery phase. When the primary drop-pad is occupied or unsafe, the proposed See&Say also identifies alternative candidate zones for package delivery. We curated a dataset of urban delivery scenarios with moving objects and human activities to evaluate the approach. Experimental results show that See&Say outperforms all baselines, achieving the highest accuracy and IoU for safety map prediction as well as superior performance in alternative drop zone evaluation across multiple thresholds. These findings highlight the promise of VLM-guided segmentation-depth fusion for advancing safe and practical drone-based package delivery.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13292
PDF
-
DroneScan-YOLO: Redundancy-Aware Lightweight Detection for Tiny Objects in UAV Imagery
2026-04-14 20:14:57Yann V. BellecAbstract
Aerial object detection in UAV imagery presents unique challenges due to the high prevalence of tiny objects, adverse environmental conditions, and strict computational constraints. Standard YOLO-based detectors fail to address these jointly: their minimum detection stride of 8 pixels renders sub-32px objects nearly undetectable, their CIoU loss produces zero gradients for non-overlapping tiny boxes, and their architectures contain significant filter redundancy. We propose DroneScan-YOLO, a holistic system contribution that addresses these limitations through four coordinated design choices: (1) increased input resolution of 1280x1280 to maximize spatial detail for tiny objects, (2) RPA-Block, a dynamic filter pruning mechanism based on lazy cosine-similarity updates with a 10-epoch warm-up period, (3) MSFD, a lightweight P2 detection branch at stride 4 adding only 114,592 parameters (+1.1%), and (4) SAL-NWD, a hybrid loss combining Normalized Wasserstein Distance with size-adaptive CIoU weighting, integrated into YOLOv8's TaskAligned assignment pipeline. Evaluated on VisDrone2019-DET, DroneScan-YOLO achieves 55.3% mAP@50 and 35.6% mAP@50-95, outperforming the YOLOv8s baseline by +16.6 and +12.3 points respectively, improving recall from 0.374 to 0.518, and maintaining 96.7 FPS inference speed with only +4.1% parameters. Gains are most pronounced on tiny object classes: bicycle AP@50 improves from 0.114 to 0.328 (+187%), and awning-tricycle from 0.156 to 0.237 (+52%).
Abstract (translated)
URL
https://arxiv.org/abs/2604.13278
PDF
-
A High-Resolution Landscape Dataset for Concept-Based XAI With Application to Species Distribution Models
2026-04-14 19:16:38Augustin de la Brosse, Damien Garreau, Thomas Houet, Thomas CorpettiAbstract
Mapping the spatial distribution of species is essential for conservation policy and invasive species management. Species distribution models (SDMs) are the primary tools for this task, serving two purposes: achieving robust predictive performance while providing ecological insights into the driving factors of distribution. However, the increasing complexity of deep learning SDMs has made extracting these insights more challenging. To reconcile these objectives, we propose the first implementation of concept-based Explainable AI (XAI) for SDMs. We leverage the Robust TCAV (Testing with Concept Activation Vectors) methodology to quantify the influence of landscape concepts on model predictions. To enable this, we provide a new open-access landscape concept dataset derived from high-resolution multispectral and LiDAR drone imagery. It includes 653 patches across 15 distinct landscape concepts and 1,450 random reference patches, designed to suit a wide range of species. We demonstrate this approach through a case study of two aquatic insects, Plecoptera and Trichoptera, using two Convolutional Neural Networks and one Vision Transformer. Results show that concept-based XAI helps validate SDMs against expert knowledge while uncovering novel associations that generate new ecological hypotheses. Robust TCAV also provides landscape-level information, useful for policy-making and land management. Code and datasets are publicly available.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13240
PDF
-
GeoLink: A 3D-Aware Framework Towards Better Generalization in Cross-View Geo-Localization
2026-04-14 18:06:41Hongyang Zhang, Yinhao Liu, Haitao Zhang, Zhongyi Wen, Shuxian Liang, Xiansheng HuaAbstract
Generalizable cross-view geo-localization aims to match the same location across views in unseen regions and conditions without GPS supervision. Its core difficulty lies in severe semantic inconsistency caused by viewpoint variation and poor generalization under domain shift. Existing methods mainly rely on 2D correspondence, but they are easily distracted by redundant shared information across views, leading to less transferable representations. To address this, we propose GeoLink, a 3D-aware semantic-consistent framework for Generalizable cross-view geo-localization. Specifically, we offline reconstruct scene point clouds from multi-view drone images using VGGT, providing stable structural priors. Based on these 3D anchors, we improve 2D representation learning in two complementary ways. A Geometric-aware Semantic Refinement module mitigates potentially redundant and view-biased dependencies in 2D features under 3D guidance. In addition, a Unified View Relation Distillation module transfers 3D structural relations to 2D features, improving cross-view alignment while preserving a 2D-only inference pipeline. Extensive experiments on multiple benchmarks show that GeoLink consistently outperforms state-of-the-art methods and achieves superior generalization across unseen domains and diverse weather environments.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13183
PDF
-
Dynamic Multi-Robot Task Allocation under Uncertainty and Communication Constraints: A Game-Theoretic Approach
2026-04-13 18:48:51Maria G. Mendoza, Pan-Yang Su, Bryce L. Ferguson, S. Shankar SastryAbstract
We study dynamic multi-robot task allocation under uncertain task completion, time-window constraints, and incomplete information. Tasks arrive online over a finite horizon and must be completed within specified deadlines, while agents operate from distributed hubs with limited sensing and communication. We model incomplete information through hub-based sensing regions that determine task visibility and a communication graph that governs inter-hub information exchange. Using this framework, we propose Iterative Best Response (IBR), a decentralized policy in which each agent selects the task that maximizes its marginal contribution to the locally observed welfare. We compare IBR against three baselines: Earliest Due Date first (EDD), Hungarian algorithm, and Stochastic Conflict-Based Allocation (SCoBA), on a city-scale package-delivery domain with up to 100 drones and varying task arrival scenarios. Under full and sparse communication, IBR achieves competitive task-completion performance with lower computation time.
Abstract (translated)
URL
https://arxiv.org/abs/2604.11954
PDF
-
Positioning radiata pine branches requiring pruning by drone stereo vision
2026-04-12 10:10:19Yida Lin, Bing Xue, Mengjie Zhang, Sam Schofield, Richard GreenAbstract
This paper presents a stereo-vision-based system mounted on a drone for detecting and localising radiata pine branches to support autonomous pruning. The proposed pipeline comprises two stages: branch segmentation and depth estimation. For segmentation, YOLOv8, YOLOv9, and Mask R-CNN variants are compared on a custom dataset of 71 stereo image pairs captured with a ZED Mini camera. For depth estimation, both a traditional method (SGBM with WLS filtering) and deep-learning-based methods (PSMNet, ACVNet, GWCNet, MobileStereoNet, RAFT-Stereo, and NeRF-Supervised Deep Stereo) are evaluated. A centroid-based triangulation algorithm with MAD outlier rejection is proposed to compute branch distance from the segmentation mask and disparity map. Qualitative evaluation at distances of 1-2 m indicates that the deep learning-based disparity maps produce more coherent depth estimates than SGBM, demonstrating the feasibility of low-cost stereo vision for automated branch positioning in forestry.
Abstract (translated)
URL
https://arxiv.org/abs/2604.16480
PDF
-
A3-FPN: Asymptotic Content-Aware Pyramid Attention Network for Dense Visual Prediction
2026-04-11 13:38:40Meng'en Qin, Yu Song, Quanling Zhao, Xiaodong Yang, Yingtao Che, Xiaohui YangAbstract
Learning multi-scale representations is the common strategy to tackle object scale variation in dense prediction tasks. Although existing feature pyramid networks have greatly advanced visual recognition, inherent design defects inhibit them from capturing discriminative features and recognizing small objects. In this work, we propose Asymptotic Content-Aware Pyramid Attention Network (A3-FPN), to augment multi-scale feature representation via the asymptotically disentangled framework and content-aware attention modules. Specifically, A3-FPN employs a horizontally-spread column network that enables asymptotically global feature interaction and disentangles each level from all hierarchical representations. In feature fusion, it collects supplementary content from the adjacent level to generate position-wise offsets and weights for context-aware resampling, and learns deep context reweights to improve intra-category similarity. In feature reassembly, it further strengthens intra-scale discriminative feature learning and reassembles redundant features based on information content and spatial variation of feature maps. Extensive experiments on MS COCO, VisDrone2019-DET and Cityscapes demonstrate that A3-FPN can be easily integrated into state-of-the-art CNN and Transformer-based architectures, yielding remarkable performance gains. Notably, when paired with OneFormer and Swin-L backbone, A3-FPN achieves 49.6 mask AP on MS COCO and 85.6 mIoU on Cityscapes. Codes are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2604.10210
PDF
-
Online Intention Prediction via Control-Informed Learning
2026-04-10 13:11:32Tianyu Zhou, Zihao Liang, Zehui Lu, Shaoshuai MouAbstract
This paper presents an online intention prediction framework for estimating the goal state of autonomous systems in real time, even when intention is time-varying, and system dynamics or objectives include unknown parameters. The problem is formulated as an inverse optimal control / inverse reinforcement learning task, with the intention treated as a parameter in the objective. A shifting horizon strategy discounts outdated information, while online control-informed learning enables efficient gradient computation and online parameter updates. Simulations under varying noise levels and hardware experiments on a quadrotor drone demonstrate that the proposed approach achieves accurate, adaptive intention prediction in complex environments.
Abstract (translated)
URL
https://arxiv.org/abs/2604.09303
PDF
-
'Take Me Home, Wi-Fi Drone': A Drone-based Wireless System for Wilderness Search and Rescue
2026-04-10 08:52:16Weiying Hou, Luca Jiang-Tao Yu, Chenshu WuAbstract
Wilderness Search and Rescue (WiSAR) represents a longstanding and critical societal challenge, demanding innovative and automatic technological solutions. In this paper, we introduce Wi2SAR, a novel autonomous drone-based wireless system for long-range, through-occlusion WiSAR operations, without relying on existing infrastructure. Our basic insight is to leverage the automatic reconnection behavior of modern Wi-Fi devices to known networks. By mimicking these networks via on-drone Wi-Fi, Wi2SAR uniquely facilitates the discovery and localization of victims through their accompanying mobile devices. Translating this simple idea into a practical system poses substantial technical challenges. Wi2SAR overcomes these challenges via three distinct innovations: (1) a rapid and energy-efficient device discovery mechanism to discover and identify the target victim, (2) a novel RSS-only, long-range direction finding approach using a 3D-printed Luneburg Lens, amplifying the directional signal strength differences and significantly extending the operational range, and (3) an adaptive drone navigation scheme that guides the drone toward the target efficiently. We implement an end-to-end prototype and evaluate Wi2SAR across various mobile devices and real-world wilderness scenarios. Experimental results demonstrate Wi2SAR's high performance, efficiency, and practicality, highlighting its potential to advance autonomous WiSAR solutions. Wi2SAR is open-sourced at this https URL to facilitate further research and real-world deployment.
Abstract (translated)
URL
https://arxiv.org/abs/2604.09115
PDF
-
Lightweight Multimodal Adaptation of Vision Language Models for Species Recognition and Habitat Context Interpretation in Drone Thermal Imagery
2026-04-07 17:36:01Hao Chen, Fang Qiu, Fangchao Dong, Defei Yang, Eve Bohnett, Li AnAbstract
This study proposes a lightweight multimodal adaptation framework to bridge the representation gap between RGB-pretrained VLMs and thermal infrared imagery, and demonstrates its practical utility using a real drone-collected dataset. A thermal dataset was developed from drone-collected imagery and was used to fine-tune VLMs through multimodal projector alignment, enabling the transfer of information from RGB-based visual representations to thermal radiometric inputs. Three representative models, including InternVL3-8B-Instruct, Qwen2.5-VL-7B-Instruct, and Qwen3-VL-8B-Instruct, were benchmarked under both closed-set and open-set prompting conditions for species recognition and instance enumeration. Among the tested models, Qwen3-VL-8B-Instruct with open-set prompting achieved the best overall performance, with F1 scores of 0.935 for deer, 0.915 for rhino, and 0.968 for elephant, and within-1 enumeration accuracies of 0.779, 0.982, and 1.000, respectively. In addition, combining thermal imagery with simultaneously collected RGB imagery enabled the model to generate habitat-context information, including land-cover characteristics, key landscape features, and visible human disturbance. Overall, the findings demonstrate that lightweight projector-based adaptation provides an effective and practical route for transferring RGB-pretrained VLMs to thermal drone imagery, expanding their utility from object-level recognition to habitat-context interpretation in ecological monitoring.
Abstract (translated)
本研究提出了一种轻量级多模态适应框架，用于弥合基于RGB预训练视觉语言模型与热红外影像之间的表征差距，并利用真实无人机采集数据集验证了其实用价值。研究从无人机影像中构建了热红外数据集，并通过多模态投影器对齐对视觉语言模型进行微调，实现了从基于RGB的视觉表征到热辐射测量输入的迁移。在封闭集与开放集提示条件下，对InternVL3-8B-Instruct、Qwen2.5-VL-7B-Instruct和Qwen3-VL-8B-Instruct三个代表性模型进行了物种识别与个体计数的基准测试。其中，采用开放集提示的Qwen3-VL-8B-Instruct模型综合表现最佳，在鹿、犀牛和大象的识别中F1分数分别达到0.935、0.915和0.968，误差在1以内的计数准确率分别为0.779、0.982和1.000。此外，结合同步采集的热红外与RGB影像，模型能够生成包含土地覆盖特征、关键景观要素及可见人为干扰的生境背景信息。总体而言，研究结果表明，基于投影器的轻量级适应方法为将RGB预训练视觉语言模型迁移至热红外无人机影像提供了有效且实用的路径，使其应用范围从目标级识别拓展至生态监测中的生境背景解读。
URL
https://arxiv.org/abs/2604.06124
PDF
-
Precise Aggressive Aerial Maneuvers with Sensorimotor Policies
2026-04-07 13:00:59Tianyue Wu, Guangtong Xu, Zihan Wang, Junxiao Lin, Tianyang Chen, Yuze Wu, Zhichao Han, Zhiyang Liu, Fei GaoAbstract
Precise aggressive maneuvers with lightweight onboard sensors remains a key bottleneck in fully exploiting the maneuverability of drones. Such maneuvers are critical for expanding the systems' accessible area by navigating through narrow openings in the environment. Among the most relevant problems, a representative one is aggressive traversal through narrow gaps with quadrotors under SE(3) constraints, which require the quadrotors to leverage a momentary tilted attitude and the asymmetry of the airframe to navigate through gaps. In this paper, we achieve such maneuvers by developing sensorimotor policies directly mapping onboard vision and proprioception into low-level control commands. The policies are trained using reinforcement learning (RL) with end-to-end policy distillation in simulation. We mitigate the fundamental hardness of model-free RL's exploration on the restricted solution space with an initialization strategy leveraging trajectories generated by a model-based planner. Careful sim-to-real design allows the policy to control a quadrotor through narrow gaps with low clearances and high repeatability. For instance, the proposed method enables a quadrotor to navigate a rectangular gap at a 5 cm clearance, tilted at up to 90-degree orientation, without knowledge of the gap's position or orientation. Without training on dynamic gaps, the policy can reactively servo the quadrotor to traverse through a moving gap. The proposed method is also validated by training and deploying policies on challenging tracks of narrow gaps placed closely. The flexibility of the policy learning method is demonstrated by developing policies for geometrically diverse gaps, without relying on manually defined traversal poses and visual features.
Abstract (translated)
URL
https://arxiv.org/abs/2604.05828
PDF
-
MARS-Dragonfly: Agile and Robust Flight Control of Modular Aerial Robot Systems
2026-04-07 06:43:08Rui Huang, Zhiqian Cai, Siyu Tang, Pengxuan Wei, Lidong Li, Xin Chen, Wenhan Cao, Zhenyu Zhang, Lin ZhaoAbstract
Modular Aerial Robot Systems (MARS) comprise multiple drone units with reconfigurable connected formations, providing high adaptability to diverse mission scenarios, fault conditions, and payload capacities. However, existing control algorithms for MARS rely on simplified quasi-static models and rule-based allocation, which generate discontinuous and unbounded motor commands. This leads to attitude error accumulation as the number of drone units scales, ultimately causing severe oscillations during docking, separation, and waypoint tracking. To address these limitations, we first design a compact mechanical system that enables passive docking, detection-free passive locking, and magnetic-assisted separation using a single micro servo. Second, we introduce a force-torque-equivalent and polytope-constraint virtual quadrotor that explicitly models feasible wrench sets. Together, these abstractions capture the full MARS dynamics and enable existing quadrotor controllers to be applied across different configurations. We further optimize the yaw angle that maximizes control authority to enhance agility. Third, building on this abstraction, we design a two-stage predictive-allocation pipeline: a constrained predictive tracker computes virtual inputs while respecting force/torque bounds, and a dynamic allocator maps these inputs to individual modules with balanced objectives to produce smooth, trackable motor commands. Simulations across over 10 configurations and real-world experiments demonstrate stable docking, locking, and separation, as well as effective control performance. To our knowledge, this is the first real-world demonstration of MARS achieving agile flight and transport with 40 deg peak pitch while maintaining an average position error of 0.0896 m. The video is available at: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2604.05499
PDF
