drone operations teams

Abstract: Referring expression grounding in overhead imagery requires oriented bounding boxes rather than horizontal ones, since aerial objects appear at arbitrary orientations. Most grounding models emit box coordinates sequentially; Parallel Box Decoding (PBD) instead predicts all geometry slots in one forward pass, but only for four-coordinate horizontal boxes. We extend this block-aligned interface to a six-slot oriented representation using a double-angle parameterization. Rather than assuming correctness from a decreasing loss curve, we verify the extension with image/prompt-shuffle controls and visibility/leakage probes, which show that the corrected model depends on both the image and the prompt rather than on prompt statistics alone. On the aerial vehicle visual grounding (AVVG) benchmark, whose targets are genuinely oriented, the extended model improves rotated intersection over union (rotIoU) from 0.1253 for the zero-shot baseline to 0.303 +/- 0.012 (mean +/- standard deviation over three training seeds) across the complete 6139-record test split spanning all 120 images. Learning oriented boxes rather than their axis-aligned envelopes adds 0.055 +/- 0.008 rotIoU beyond a matched control (per-seed 95% confidence intervals all excluding zero), whereas block expansion alone yields no rotIoU gain distinguishable from zero.

Abstract: When a team of drones explores a building together, each drone tells the others which frontier it is going to and shares the map it has built. This avoids duplicated effort, but it also means that the team trusts every identity from which it receives messages. In a Sybil attack, one compromised drone creates fake identities, and these fake teammates claim frontiers and send fabricated scans, so the real drones leave parts of the building unexplored and end up with walls in their maps that do not exist. We study five such attackers, including one that seals off the openings between floors, and five levels of defence that need no security infrastructure, only the drones' own sensors and maps: an audit of received map data against what a drone sees itself, a check that a body is present where an identity claims to be, trust only for identities whose body has been seen, a quarantine for identities that no drone has observed, and a rule that binds each observed body to one identity. Tests in simulation cover 70 maps of seven kinds, from offices and tunnels to three-storey buildings and caves. Without a defence, one compromised drone leaves on average up to 25% of a map unexplored (45% in offices), and the floor-sealing attacker cuts the explored part of a three-storey building to 82.3%, or 34.6% on the worst map. The quarantine brings exploration back to the level of an unattacked team in every setting, and in most settings it also brings the false data back to that level. The exceptions are two colluding attackers, fakes placed next to real drones, three of the ten caves and a team of 16 drones, and binding bodies to identities fixes the last three. Over 2,350 missions, an honest drone was revoked by a teammate only twice.

Abstract: Continuous aerial tracking often requires multiple drones to maintain target coverage over long periods. During handoff, the receiving UAV may lack prior target observations and must actively acquire a usable view without disrupting the sender's ongoing coverage. This work introduces HARP, a handoff-aware recovery planner that registers bounded sender predictions in the receiver's local map, distinguishes field-of-view failure from physical occlusion, and generates failure-specific yaw, translation, and parallax viewpoints. Candidate motions are checked for receiver clearance, sender-fiducial observability, protected sender--target visibility, temporal validity, and deadline compliance. When a complete trajectory cannot be admitted, HARP may execute a sampled admissible nonzero prefix and replan from updated evidence. In simulation, HARP acquired the target in all 49 standard trials and in 15 of 16 stress trials. Field trials validated HARP's recovery geometry under field-of-view limitation and environmental occlusions.

Abstract: Protection levels (PLs) bound position errors under specified fault hypotheses and risk budgets, but advanced re-ceiver autonomous integrity monitoring (ARAIM) is formulated for snapshot GNSS estimation rather than the correlated poste-rior of tightly coupled GNSS/IMU factor graph optimization (FGO). This paper formulates ARAIM solution separation and PL computation on the FGO posterior. Because current-epoch pseudorange factors enter only the current-state block of the fixed-lag information matrix, the fault-excluded position covari-ance, solution separation, and nominal-bias propagation follow exactly from the linearized current-state marginal, which re-tains correlations with velocity, IMU-bias, and clock states and with historical information. Woodbury updates with selected-output evaluation compute these quantities for fault-free, single-satellite, constellation-wide, and second-order hypotheses with-out repeated full-state inversion or graph re-optimization. Sur-rounding monitoring layers screen measurements, handle post-fit outliers, and determine PL validity and availability. In two road experiments, both nominal sequences achieve 100% hori-zontal and vertical empirical bounding over PL-valid epochs, with a maximum error-to-PL ratio of 0.96. Normalized errors show that the posterior covariance alone does not capture slowly varying ranging biases: a covariance-only bound computed from the same posteriors retains no resolvable margin, and strong temporal correlation limits the empirical evidence to consisten-cy checks rather than validation of the integrity budget. On identical Experiment A posteriors, the proposed method reduces fault-hypothesis evaluation and PL solving time by 65.2% rela-tive to direct full-state inversion with matching integrity deci-sions, and controlled fault injections demonstrate fail-safe PL invalidation while navigation continues.

Abstract: The CLARKE building and road damage assessment AI classifier was incorporated into the Catastrophic Unmanned Remote Sensing Exercise (CURSE) 2026, which trained 23 small uncrewed aerial systems (sUAS) teams from state and local agencies and non-governmental organizations in Florida and Missouri on how to collect imagery for an incident command Remote Sensing Cell. Although CLARKE has been operationally deployed to two hurricanes (Debby and Helene), CURSE'26 presented an opportunity to evaluate the machine learning model with a larger set of never-before-seen orthomosaics. The results show that building and road damage assessment together ran in 3.5 minutes on average, and that building damage assessment achieved a Micro F1 of 0.834 with no manual adjustments to correct spatial misalignment and delivered that performance in both Florida and Missouri, demonstrating good geographic transfer. It also showed that road damage assessment performed poorly due to sensitivity to misalignment between road maps and the images, and to lighting and environmental conditions in an urban setting. The analysis of CURSE'26 presents five other findings of value to the sUAS community: that the use of sUAS and machine learning is now operationally normalized and accepted, sUAS teams in the field can improve classification accuracy by timing their flights, exercises are good operational tests but their value for evaluating learning models is less clear, edge computing is needed to overcome the wireless upload barrier, and the application of sUAS and AI to disaster response has ethical and legal ramifications for pilots and data managers.

Abstract: The solar-powered High-Altitude Platforms (HAP) can provide persistent communication and computing services beyond terrestrial coverage. However, changing mission priorities, coupled resource demands, and uncertain solar supply complicate sustainable scheduling, while large language model proposals require independent feasibility checks. This paper proposes SAGE, a Sustainability-certified Agentic Ground-service Engine for a HAP. We formulate an energy-causal stochastic optimization problem incorporating semantic modes, multi-user interference, channel aging, essential platform loads, and battery stress. An agent translates operator intent into typed admission, mode, and grouping candidates, while deterministic convex refinement and an action shield verify resource and reserve feasibility using calibrated solar lower bounds before execution. Agent proposals and deterministic fallbacks share the same certification path. Residual-based forecasting and memory-assisted replanning close the control loop. We establish fixed-candidate convexity, reserve safety under calibrated solar coverage and bounded actuation error, and an online utility bound accounting for candidate-generation error. At nominal load, simulations show 2.38 percentage points higher completion and 5.27% greater useful-workload energy efficiency than energy-harvesting Lyapunov control. Under stressed load and solar uncertainty, reserve violations occur in 1/50 runs, versus 47/50 without energy certification. A 600-record calibrated inference replay further shows 23.5--36.5% utility gains over deterministic-only candidates under compound stress.

Abstract: Aerial and remote sensing video is increasingly evaluated like web video, by posing multiple-choice questions to multimodal large language models (MLLMs) over sampled frames and reporting accuracy. This paper argues that this recipe measures the wrong aspect, and supports the claim with a convergent meta-analysis of a broad set of published results, organized in four evidence tiers, in which a claim becomes a position only when collected evidence agrees. Parameter scale exhibits a median of +3.4 accuracy points per tenfold increase on aerial benchmarks, far below a human gap of at least 19 points, whereas acquisition conditions control perception, as 315 of 318 evaluations in 19 within-paper contrasts lose accuracy when conditions such as altitude, view, object size or time horizon become harder. No aerial benchmark in the corpus combines video input with per-task human and random baselines, competence collapses from answering to acting in closed-loop navigation, and the same MLLMs score higher on the aerial benchmark than on ground spatial ones, but lower on studies that test cross-view geometry. From these findings the current study derives five falsifiable principles and proposes the AVU-Card, a reporting card for aerial video benchmarks

Abstract: Synthetic UAV imagery can expand pre-deployment test evidence when task-specific Real data are scarce, but visual plausibility or semantic label alignment alone does not establish validity for model selection. We study when Synthetic evaluation preserves the model-selection conclusions obtained from Real UAV data through two complementary cases under fixed evaluation protocols. In a requirement-specific road-debris benchmark, four language-conditioned perception systems obtain lower absolute F1 on Synthetic data, yet the point-estimate ordering and top-ranked model are preserved; bootstrap analysis yields no supported pairwise reversal, and size-matched resampling preserves the top-model decision. In contrast, a closed-set stress test on a separately materialized business corpus, using four VisDrone-compatible detectors over eight empirically supported classes, changes the point-estimate top-ranked detector and reverses three of six pairwise point-estimate preference directions. A complementary audit of five UAV business scenarios further reveals substantial Real-Synthetic mismatch in class composition, object density, and target scale, including systematic under-representation of small targets. These results show that Synthetic UAV benchmark trust is conditional: semantic coverage is insufficient, and validity must be established empirically for the task, operating regime, and model panel of interest.

Abstract: Globally consistent, real-time state estimation in large-scale, perceptually degraded environments is essential for autonomous vehicles and aerial robots, and requires fusing LiDAR, inertial, and GNSS measurements. Existing fusion methods, however, share a scan-to-map front-end with two failure modes. First, each scan is aligned to an incrementally built map that drifts under degeneracy, and once the estimate diverges the error is irrecoverable. Second, even without divergence, a registration biased by dynamic objects or wrong correspondences is propagated as a single pose constraint with an over-confident covariance, leaving its correspondences unavailable for GNSS to re-weight or relinearize. We propose GLIO2, a tightly-coupled LiDAR-Inertial-GNSS system whose GPU-parallel front-end jointly optimizes scan-to-multiscan LiDAR, IMU pre-integration, and raw GNSS measurements in a single sliding-window factor graph, sustaining real-time operation on edge hardware. A complementary offline back-end reuses the same cached factors to refine the entire trajectory in batch, completing the 30-min, 4.51-km UrbanNav Whampoa sequence in about 24 s. Across three public benchmarks (UrbanNav, MARS-LVIG, M3DGR) and self-collected UAV and vehicle data, GLIO2 attains the best overall accuracy among evaluated systems. On a 5.66-km bridge traversed at up to 96 km/h, where every competing baseline diverges under LiDAR degeneracy, it maintains 1.6 m horizontal accuracy. On an NVIDIA Jetson Orin NX, the full pipeline runs at about 25 Hz (39.60 ms per scan). The source code and datasets will be released.

Abstract: We study absolute metric UAV localization within a provided geo-referenced satellite region, recovering continuous map position and viewing heading from a single oblique image or a short multi-view clip. Existing cross-view geo-localization methods retrieve the most similar satellite tile from a gallery and report Recall@K, but retrieval depends on gallery sampling, provides no heading estimate, and returns a tile index rather than a continuous coordinate. We propose SatFix, a feed-forward UAV--satellite localization framework built on VGGT-$Ω$. Satellite-grid features act as queries that aggregate UAV visual evidence, and two lightweight heads regress a 3-DoF pose in the satellite-map frame: continuous 2D position and heading. SatFix requires no explicit 3D map, rendered bird's-eye image, auxiliary sensor, or test-time pose alignment. A single model supports both single- and multi-view inputs, with trajectory constraints used during multi-view training. For metric evaluation, we introduce University-Metric, where satellite imagery is re-collected over a region up to 10.7$\times$ longer on a side (about 114$\times$ the ground area) than the original University-1652 tiles, with continuous position and heading labels for the original UAV tours. With one UAV view, SatFix localizes 52.08% of test frames within 50 m and 17.34% within 10 m, with median position and heading errors of 45.66 m and $20.81^\circ$, respectively. Inference takes under 0.1 s per single-view query on an NVIDIA RTX 4090. With nine UAV views, the median position error falls to 21.96 m and the median heading error to $8.73^\circ$. Compared with a fine-tuned VGGT-$Ω$ baseline, SatFix reduces median position error by 34.0% and nine-view median heading error from $25.43^\circ$ to $8.73^\circ$.

Abstract: Space-air-ground integrated networks (SAGINs) are expected to support ubiquitous three-dimensional (3D) communication and sensing services in future sixth-generation (6G) wireless networks. However, heterogeneous mobility and service requirements across the space, air, and ground segments challenge fixed-boresight or fixed-sector antennas in supporting wide-area coverage, maintaining directional alignment over time-varying communication links, and flexibly adjusting observation directions for sensing tasks. To address these limitations, rotatable antenna (RA) technology has emerged as a promising solution by enabling mechanical or electronic boresight adjustment while keeping the antenna positions fixed. This article investigates the roles of RA technology in enabling communication and sensing in SAGINs. Specifically, we first explain how RA boresight control complements platform mobility and supports wide-area coverage, dynamic directional transmission, cross-segment cooperative operation, and cooperative sensing. We then discuss the main design challenges, potential approaches, and future research directions, including channel acquisition and predictive tracking, joint orientation control and access/handover coordination, cross-segment coordination and resource management, as well as deployment tradeoffs and practical implementation. Finally, an RA array prototype and two representative simulation studies are presented to illustrate the feasibility and potential performance gains of RA-enabled SAGINs.

Abstract: Teams of unmanned aerial vehicles (UAVs) deployed for search and monitoring missions frequently operate as partially connected networks, forcing each robot to trade off exploring the environment against relaying information to teammates. This tradeoff is especially acute when robots are semantically heterogeneous: an observation that appears uninformative to the robot that made it may be critical to a teammate with complementary detection capabilities. In this work, we formalize this setting as the heterogeneous mission-aware coverage (HMAC) problem, which couples complete multi-robot coverage of an area with capability-constrained mission-relevant target (MRT) discovery under intermittent communication. We then present DORA, a divergence-oriented data-relay algorithm that drives communication by the value of information to the team rather than by discovery alone. DORA quantifies the mission-relevant divergence between a robot's current information state and its estimate of each teammate's knowledge, capturing mission relevance, discovery novelty, sensor uncertainty, and the age of information. We evaluate DORA in simulation across four environments with differing object densities and spatial structure, and validate it on a physical UAV platform. Our results show that DORA improves MRT resolution delay by up to 74.8% over traditional time-based communication scheduling methods.

Abstract: Collective intelligence is a collaborative autonomy paradigm in which multiple agents pursue shared objectives through local perception, information exchange, and coordinated action. UAV swarms embody this paradigm by coordinating multiple vehicles in tasks such as search, inspection, and tracking. Recent advances in large language model (LLM) agents have strengthened natural-language task understanding and high-level planning, providing a flexible semantic interface between mission descriptions and collective behavior. While these advances expand semantic reasoning, applying LLM agents to UAV swarms raises challenges in grounding model decisions in executable capabilities, reconciling global task reasoning with distributed execution, and using mission-specific experience for continual adaptation. To address these challenges, we introduce AeroWeaver, an embodied-agent harness that weaves individual UAV skills into coordinated mission-level behavior. AeroWeaver connects semantic decisions to governed skills, organizes role-conditioned local agents for distributed coordination, and uses role-indexed state-action-reward experience to refine skill selection online. Experiments and runtime validation show that AeroWeaver maintains valid skill execution under tested conditions and supports body-local multi-UAV operation without a central agent generating joint actions from global context, while reward-guided online updates provide a training-free path for adaptive learning swarm agents from accumulated execution experience. Code: https://github.com/Admire-ljb/AeroWeaver.

Abstract: Training multi-agent drone-swarm policies directly in high-fidelity (HF) rigid-body physics is accurate but computationally expensive. This cost scales poorly with team size, as each additional agent multiplies contact-resolution complexity and sharply raises the in-simulation crash rate. To address this, we propose a mixed-fidelity training scheme that eliminates HF reinforcement learning entirely. A single shared, decentralized policy is optimized inside a fully-differentiable, JAX-native low-fidelity (LF) point-mass simulator. The simulator is corrected by a small, per-agent bagged residual ensemble fit once, offline, using short calibration flights in the HF simulator. Because calibration requires only one isolated drone, the data collection budget does not compound with team size. Reference trajectories are generated by rolling out an existing LF-only policy and tracked in the HF simulator by a zero-training PD controller. Evaluated across four cooperative drone tasks and team sizes from 3 to 18, the residual-corrected policy outperforms an uncorrected LF baseline in all combinations, and a from-scratch HF policy in 22 of 24 combinations tested. It trails an HF-finetuned policy by a margin that narrows steadily with team size. Ultimately, the proposed method achieves near-equivalent performance at the largest team sizes at a fraction of the computational cost, completely avoiding the high crash rates typical of HF training.