Keywords: Path Planning, Airspace Management, Manned/Unmanned Aviation
Abstract: This paper addresses the problem of planning feasible air corridors for UAVs. We propose a novel path planner based on a co-evolutionary approach that considers minimum curvature, no-fly zones, interactions with other air corridors, and adherence to specified altitude-safe zones, with each central path represented by a Non-Uniform Rational B-Spline (NURBS) curve. In addition, our approach accommodates UAVs, such as fixed-wing aircraft, which cannot hover or remain stationary in the air, by providing paths that guide the robots to tangent landing or take-off regions (vertiports). The results of different scenarios with different numbers of vertiports and no-fly zones demonstrate the planner's ability to generate a set of feasible air corridors.

Keywords: Multirotor Design and Control, Networked Swarms, Micro- and Mini- UAS
Abstract: This paper evaluates a dual quaternion-based control algorithm designed to manage dynamic changes in the number of vehicles in robot formations. By defining a virtual structure, the algorithm coordinates the formation’s position, orientation, and shape parameters, ensuring seamless transitions when the number of vehicles changes. The approach enables a low-level controller to calculate commands for individual robots while maintaining the overall formation integrity. The strategy’s performance is analyzed through simulations, demonstrating its effectiveness in handling variations in the number of vehicles of robotic formations.

Keywords: Fail-Safe Systems, Multirotor Design and Control, Control Architectures
Abstract: This manuscript introduces a transfer learning method for adapting propeller fault detection neural networks to different unmanned aerial vehicles (UAVs). After training a simple model for detecting if any propeller in a specific vehicle has a failure (in this case, a chipped tip), a domain adaptation based in the vehicles' physics is performed in order to use the same model to detect failures in vehicles with different structures, weights, or motor-propeller sets. A key feature is that the detection model uses only inertial sensors that are standard in commercial UAVs, making it broadly applicable without the need for additional hardware.

Keywords: UAS Applications, Control Architectures, Air Vehicle Operations
Abstract: Autonomous take-off and landing capabilities are crucial in UAV vision-based missions, ensuring adaptive navigation, especially in challenging environments where real-time identification and interaction with a variety of landing platforms are required. In this context, this paper presents a servo-visual controller that uses pattern detection and color segmentation techniques to identify take-off/landing platforms and estimate their current orientation. The proposed system was subjected to experimental validation with four platforms positioned in different orientations, heights, and positions, demonstrating its versatility in various conditions. Our study addresses the Flying Robots Trial League challenge, which emulates mapping and inspection tasks in offshore platforms.

Keywords: Control Architectures, Navigation, UAS Applications
Abstract: This paper proposes a null space-based behavioral controller embedding an adaptive sliding mode control law to guide the formation of two UAVs (unmanned aerial vehicles) carrying a cable-suspended load when tracking a trajectory. This controller is based on hierarchically organizing the two subtasks moving the formation accordingly and keeping the formation shape. The influence of the load on the UAVs, including the force dragging each UAV towards the other, is dealt with as a perturbation, which the sliding mode term allows to reject. The proposed controller guides the UAVs as a virtual structure corresponding to the straight line linking them, keeping both at the same altitude, preserving the distance between them, and rejecting the disturbance caused by the load. Keeping the formation's shape is the priority, and moving the formation is the secondary task. This approach modifies the control signal for the UAVs, ensuring a rigid shape for the formation, thus preserving the distance between the UAVs, keeping them at the same altitude, and providing additional energy to reject the load disturbance, hence improving the performance of the UAV-UAV-load system. Therefore, the whole system is dealt with as a virtual structure for which the null space-based controller, the formation controller, generates velocity references for the two UAVs, whereas a dynamic compensator embedding an adaptive sliding mode control law works as an individual controller for the drones, reducing the disturbance caused by the load.

Keywords: Aerial Robotic Manipulation, Control Architectures, Simulation
Abstract: This paper presents an adaptive control strategy for cooperative cargo transportation using quadcopters in a tandem configuration. By modeling the payload and the unmanned aerial vehicles (UAVs) as a unified rigid-body system, the proposed framework addresses the dynamic interactions among them, ensuring robust performance in tasks such as cargo transportation. The system uses an underactuated adaptive control approach, capable of dealing with variations in payload weight while maintaining stability and agility during flight. The proposed strategy is validated through numerical experiments, demonstrating its effectiveness in trajectory tracking tasks. The results show the system's ability to adapt the parameters of the system modeling to the observed and measured values, guaranteeing the tracking of the proposed trajectory and the robust payload handling. This work contributes to the development of cooperative aerial cargo transportation systems, with applications in transportation missions that exceed the individual capacity of each UAV.

Keywords: Integration, Payloads, Perception and Cognition
Abstract: Global navigation satellite system (GNSS) receivers have become ubiquitous geopositioning sensors in unmanned aerial, ground, and surface systems (UxS). GNSS require line of sight communication with orbiting satellites and the resulting measurement’s precision and accuracy can be greatly affected by satellite geometry, atmospheric conditions, and obstructions from buildings or foliage, among other effects. These uncertainties can be difficult to manipulate for test and evaluation of a small-scale UAS control system's robustness to GNSS uncertainty. This work presents the implementation of a GNSS emulator with the same interface design as a GNSS receiver. Using a Raspberry Pi connected wirelessly to a local positioning source, we provide a plug-and-play alternative to a standard commercial-off-the-shelf (COTS) GNSS unit that communicates using the DroneCAN protocol. This system allows the user to simulate GNSS measurements and GNSS performance changes by generating synthetic measurements in a controlled laboratory setting. Data collected from outdoor flights in four different environments is used to characterize baseline GNSS message parameter values, which quantify the fix quality in different geographic locations. This information is used to generate synthetic GNSS measurements fed to a Cube autopilot running ArduCopter flight control software in a hardware in the loop simulation. Results show the GNSS emulator can send DroneCAN GNSS messages providing position and fix quality information to the flight controller. These results illustrate how the plug-and-play GNSS emulator can enable test and evaluation of flight controller robustness to uncertainties, signal dropout, and other conditions affecting GNSS measurements in a controlled laboratory environment.

Keywords: Path Planning, Simulation
Abstract: A common task for unmanned aerial vehicles (UAVs) is wide area search using an onboard camera with an object detection model. However, constraints of flight time, camera optics, and onboard compute, particularly in time sensitive applications like search and rescue, requires trade-offs in strategies that balance precision and speed. To address these needs, we propose a novel method for evaluating coverage path plans by estimating the probabilities of detection and false alarm for ground targets for a set of poses that the UAV can reach in the search domain. To demonstrate our method, we evaluate trajectories for various coverage path plans flown by a UAV in a high-fidelity simulation.

Keywords: Certification, Control Architectures, Sensor Fusion
Abstract: The Office of Naval Research's Advanced Autonomous Air-to-Air Refueling System (A4RS) project explores the application of deep neural networks (DNNs) for automated UAV refueling. In this study, we present a monocular camera system integrated with a DNN to accurately estimate coordinates and range to a refueling drogue within the final 25 feet of approach. Our method employs a similar-triangle algorithm that computes range from DNN-generated bounding boxes, with ground truth provided by a calibrated motion capture system. Experiments using UR10, YASKAWA, and Linear Track manipulators demonstrate that the DNN achieves perfect precision and recall, with an mAP50 of 0.995 and mAP50-95 scores of 0.945 for the drogue, 0.851 for the coupler, and 0.898 overall. Combined with the monocular vision system, the estimated coupler range is within 4 inches of the motion capture measurements for distances between 7 and 25 feet, aside from minor deviations at 20 and 23 feet. This work advances the prospects of automated air-to-air refueling by providing a robust, vision-based solution for accurate target detection and range estimation.

Keywords: Manned/Unmanned Aviation, Regulations, Reliability of UAS
Abstract: We present a framework for including human-readable specifications in the design of black-box autonomous systems, or systems whose construct are prohibitively complex to analyze or intuit. By integrating parametric Signal Temporal Logic (pSTL), we can systematically evaluate and refine deep reinforcement learning policies to ensure compliance with predefined system specifications. Our approach is tested in a simulated autonomous driving environment, where we train a deep reinforcement learning agent in Mario Kart SNES using Proximal Policy Optimization. The agent is evaluated based on its ability to navigate a structured driving course while satisfying a set of a priori requirements; this evaluation is performed by writing and solving the parameters in a pSTL statement. This work contributes to the broader effort of bridging formal methods and data-driven learning, providing insights for researchers and operators alike in developing AI-based controllers for real-world autonomous systems.

Keywords: UAS Communications, Technology Challenges, Security
Abstract: Unencrypted communications between unmanned aerial vehicles (UAVs) are susceptible to various security attacks, such as interception and spoofing. Both symmetric and asymmetric cryptography currently allow for secure communication between parties. However, industry and academia are working on implementing quantum computers, which will invalidate several of the most widely used cryptographic algorithms. As researchers develop novel quantum encryption methods, they will need standardized testing approaches to determine which are most optimal, especially for the unique characteristics of UAV systems. This paper describes a methodology to test and measure the efficiency of key exchange algorithms for a UAV communicating with a ground control station (GCS). The method requires a framework that models a UAV performing tasks while communicating in encrypted messages with the GCS. In addition, the calculations used for comparing algorithms require a purpose-built bandwidth equation for the quantum algorithm. The first test of this methodology is an experiment designed to compare classical key exchange with the 256-bit Advanced Encryption Standard (AES-256) and quantum key distribution (QKD) used with a variety of parameters in the framework. A comparison of the runtime of each model facilitates the evaluation of each key exchange algorithm for UAV systems. This methodology can be used to test the efficiency of other post-quantum cryptographic algorithms in the future.

Keywords: Path Planning, Navigation, UAS Applications
Abstract: This paper proposes a method for integrating trajectory optimization with vector field-based motion planning methods. This approach aims to address motion planning challenges, particularly in scenarios like UAV navigation, where vector fields are efficient but struggle with dynamic obstacles and motion constraints. Such challenges also include scenarios where there is no defined goal configuration such as border following, loitering, and curve circulation. Several vector field methods have been proposed to solve these problems but they are prone to failure when encountering previously unmodeled or dynamic obstacles as well as no-fly zones. The method proposed in this paper uses a vector field for high-level planning. The vector field is used to create paths for the vehicle, which are optimized for smoothness, obstacle avoidance, and vector field adherence before they are followed. The result is a smooth path that is fast to plan and easy to follow for a motion-constrained vehicle. A series of simulations was used to validate this methodology, which is compared with a previous method that uses RRT*.

Keywords: Path Planning, Risk Analysis, Navigation
Abstract: This study develops a framework to advance Beyond Visual Line of Sight (BVLOS) Uncrewed Aerial Vehicle (UAV) flight operations, focusing on assessing and incorporating the risks associated with cellular connectivity degradation or loss in flight path planning. We utilize stochastic metrics for a detailed analysis of cellular communication reliability, forming the core of our navigation strategy. The process is carried out in four steps: 1) Surveying the operational area to create maps that probabilistically represent cellular network signal connectivity; 2) Utilizing these maps over the potential flight volume, for flight path planning aimed at minimizing the likelihood of losing communication while adhering to shortest route; 3) Carrying out the flight according to the optimized route; and 4) Updating and refining the probabilistic maps with data collected during the flight. This approach not only achieves a balance between operational efficiency and the minimization of connectivity risks but also systematically enhances the reliability and safety of BVLOS UAV operations. Integrating stochastic cellular network assessments into UAV flight planning, this work paves the way for safer and more robust BVLOS operations.

Keywords: Path Planning, See-and-avoid Systems, Airspace Management
Abstract: This paper presents a combination of an artificial potential field (APF) and the modified Constrained Wavefront Expansion (mCOWEX) algorithm for conflict avoidance in UAVs. As the goal of highly automated UAVs is to be used in shared airspace, i.e. airspace that is used by manned and unmanned aircraft, automatic conflict detection and avoidance is a key requirement. The mCOWEX algorithm presents a capable algorithm to avoid complex conflict scenarios but often generates paths that are hard to predict for human pilots. The APF-mCOWEX algorithm presented in this paper generates paths that are more predictable for human pilots while still being able to solve complex scenarios. The APF-mCOWEX algorithm is a modified form of the original mCOWEX algorithm. These modifications include changes to the placement logic of waves in the mCOWEX algorithm and a changed cost function based on APFs. The final algorithm is then validated on different scenarios of varying complexity.

Keywords: Path Planning, Simulation, Manned/Unmanned Aviation
Abstract: This paper proposes a FOV-aware, area-based coordination framework for UAV–UGV collaborative surveillance under real-world constraints such as limited battery capacity and road-constrained UGV mobility. Unlike traditional point-based reconnaissance approaches, our method discretizes the surveillance region into realistic grid cells based on UAV camera footprints and guides UAVs to maximize coverage using heading-constrained field-of-view (FOV) planning. A single UGV navigates a predefined fixed route extracted from GeoJSON road data and serves as a mobile charging station with two wireless pads. We formulate the task as a Team Orienteering Problem (TOP) and address it using a structured meta-heuristic algorithm. Key innovations include heading-aware path construction, dynamic reward reinitialization to prevent local stagnation, and tight synchronization with an ILP-based UAV scheduling algorithm that considers operational flight time and charging constraints. UAVs autonomously select their next positions within a ±5° heading cone to optimize new area coverage while minimizing redundant overlap. Simulation results conducted over the Texas A&M campus demonstrate that our method achieves up to 19% higher area coverage, reduces redundancy by 11.3%, and lowers UAV charging delays compared to point-based and naive area-based baselines. These findings validate the effectiveness of integrating FOV-driven spatial planning with temporal scheduling and adaptive reward modeling, offering a scalable and robust framework for autonomous persistent surveillance missions.

Keywords: Path Planning, UAS Applications, Navigation
Abstract: Path planning is a fundamental capability of autonomous Unmanned Aerial Vehicles (UAVs), enabling them to efficiently navigate toward a target region or explore complex environments while avoiding obstacles. Traditional path-planning methods, such as Rapidly-exploring Random Trees (RRT), have proven effective but often encounter significant challenges. These include high search space complexity, suboptimal path quality, and slow convergence, issues that are particularly problematic in high-stakes applications like disaster response, where rapid and efficient planning is critical. To address these limitations and enhance path-planning efficiency, we propose Vision Language Model RRT (VLM-RRT), a hybrid approach that integrates the pattern recognition capabilities of Vision Language Models (VLMs) with the path-planning strengths of RRT. By leveraging VLMs to provide initial directional guidance based on environmental snapshots, our method biases sampling toward regions more likely to contain feasible paths, significantly improving sampling efficiency and path quality. Extensive quantitative and qualitative experiments with various state-of-the-art VLMs demonstrate the effectiveness of this proposed approach.

Keywords: Path Planning, UAS Applications, Training
Abstract: The advancement of 3D modeling applications in various domains has been significantly propelled by innovations in 3D computer vision models. However, the efficacy of these models, particularly in large-scale 3D reconstruction, is dependent on the quality and coverage of viewpoints. This paper addresses optimizing the trajectory of an unmanned aerial vehicle (UAV) for collecting optimal Next-Best View (NBV) for 3D reconstruction models. Unlike traditional methods that rely on predefined criteria or continuous tracking of the 3D model's development, our approach leverages reinforcement learning to select the NBV based solely on single camera images and the relative positions of the UAV with the reference points to a target. The UAV is positioned with respect to four reference waypoints at the structure's corners, maintaining its orientation (field of view) towards the structure. Our method eliminates the need for continuous tracking of 3D reconstruction accuracy in policy learning for 3D reconstruction, thereby enhancing the efficiency and autonomy of the data collection process. The implications of this research extend to applications in inspection, surveillance, and mapping, where optimal viewpoint selection is crucial for information gain and operational efficiency.

Keywords: UAS Applications, Simulation, Swarms
Abstract: In this paper we present a new search planning method for a coordinated swarm of UAVs based on the Theory of Search which provides a precise and robust probabilistic model for Search and Rescue (SAR) operations where lost victims need to be found as soon as possible. Using any ``a priori'' information about the victims' positions, a probability density function for each one is built and used to compute the optimal search effort allocation for the resources available. The priority assigned to each region of the area of interest is derived for such allocation using probability theory. This defines a set of priority sub-areas that span all the possible locations where a victim could be located. The optimal UAV distribution and order at which each sub-area is visited is computed using a Traveling Salesman Problem solver. The coverage paths within each sub-area are computed using an energy-aware path planner. We also address how to solve potential collisions with the terrain and/or other UAVs of the team. We have performed extensive simulations to validate our approach obtaining promising results in terms of probability of finding the victims and path feasibility.

Keywords: Simulation, UAS Applications, Reliability of UAS
Abstract: This paper presents a novel simulation framework designed for high-fidelity multi-physics simulation of shock waves due to blast phenomena. The framework includes simulation of the physical pressure wave and the acoustic and visual phenomena associated with the blast event using the Gazebo environment. The framework integrates advanced technologies, including the Robot Operating System (ROS), QGroundControl, and PX4 Software-In-The-Loop (SITL), to synchronize visual, acoustic, and dynamic pressure data, ensuring realistic and efficient simulations. A key innovation in this framework is the use of a client-server architecture, which enables real-time adjustments and precise multimedia data synchronization, effectively minimizing latency and improving overall simulation quality and allowing multi-vehicle simulations in a single virtual scene. The specialized plugins employed for rendering and acoustic modeling capture the intricate dynamics of explosions, enhancing the realism of visual and auditory representations. Creation of this technology allows development of control algorithms that improve autonomous vehicle control algorithms in the presence of extreme perturbations with impacts in autonomous vehicle safety and defense sectors. The proposed framework offers a robust solution for interactive simulations, demonstrating significant advancements in both the fidelity and applicability of blast effect modeling.

Keywords: Simulation, Technology Challenges
Abstract: Recent advances in Unmanned Aerial Vehicle (UAV) designs have increasingly incorporated Distributed Electric Propulsion (DEP) systems, characterized by multiple propellers attached on the leading edge of the wing. The increased interest in DEP necessitates understanding the aerodynamic effect of such multi-propeller configurations on aircraft performance. The development of a propeller model using Computational Fluid Dynamics (CFD) ensures flexibility in simulating different situations and analyzing the flow around the wing. In the present study, a CFD model developed to simulate the propeller slipstream was validated in the presence of a wing in different configurations. Simulations were assessed by varying freestream velocity, propeller advance ratio, and wing geometry. The effects produced by a single propeller were examined first before extending the analysis to multi-propeller configurations. The aerodynamic coefficients, specifically lift and drag, were compared to existing experimental results, demonstrating good agreement.

Keywords: Simulation, UAS Applications, Path Planning
Abstract: The application of Unmanned Aerial Vehicles (UAVs) in electrical system inspection and maintenance has grown significantly - although most research focuses on transmission systems, with relatively few works addressing distribution networks. In this context, this paper introduces an innovative simulation environment designed to replicate real-world conditions for UAV-based fault detection missions in wind farms electrical distribution networks. By leveraging Unity for visualization and user interaction, and Python for simulating a DJI Matrice 350 aircraft’s dynamic behavior, this computational platform enables the testing of task operational concepts with minimal risk and cost. The proposed system features an intuitive user interface, supports weather integration, and allows for flexible mission configurations through a user-friendly interface. The results demonstrate the environment's capability to simulate realistic scenarios, highlighting its potential to support the development and validation of UAV technologies for electrical systems inspections.

Keywords: Simulation, UAS Applications, Reliability of UAS
Abstract: This article describes a new suite of simulation plugins for the Gazebo 3D simulator to facilitate realistic simulation of time-varying 3D wind fields and gusts. The plugins integrate with ROS and Pixhawk PX4 Software-In-The-Loop (SITL) firmware to aid in the development of robust UAS control systems. Our approach features two main components: (1) real-time plugins for simulating environmental and sensed versions of complex, spatially varying wind velocity fields, using a Fourier-based compression of large CFD datasets, and (2) real-time plugins for modeling environmental and sensed versions of short-duration windblasts. By building on open-source Gazebo and ROS software, the developed framework provides high-accuracy physics simulation with support for multiple vehicles, fostering improved flight controller design and testing in cluttered or challenging atmospheric conditions.

Keywords: Control Architectures, Simulation, Autonomy
Abstract: Unmanned Aerial Vehicles (UAVs) mission management requires methodologies that rely on sophisticated path planning and following capabilities. In this paper, we examine the performance of two different control approaches for achieving flyable paths that are represented by B-Splines. A Proximal Policy Optimization (PPO) approach, which belongs to the Reinforcement Learning (RL) methodologies, is presented and evaluated for the control of the roll angle of a fixed-wing UAV in the presence of varying wind conditions. The performance of the PPO is examined in parallel with a simple PD-like Fuzzy Logic Controller (FLC) of Mamdani type. It turns out that the trained roll controller (RL) is just slightly better than the heuristically (FLC) designed one in terms of statistical performance, while being less transparent and generic. Potential future research directions are identified for further refinement of the method and expansion of the application scope.

Keywords: Autonomy, Multirotor Design and Control, Control Architectures
Abstract: Aiming to promote the wide adoption of safety filters for autonomous aerial robots, this paper presents a safe control architecture designed for seamless integration into widely used open-source autopilots. Departing from methods that require consistent localization and mapping, we formalize the obstacle avoidance problem as a composite control barrier function constructed only from the online onboard range measurements. The proposed framework acts as a safety filter, modifying the acceleration references derived by the nominal position/velocity control loops, and is integrated into the PX4 autopilot stack. Experimental studies using a small multirotor aerial robot demonstrate the effectiveness and performance of the solution within dynamic maneuvering and unknown environments.

Keywords: Control Architectures, Multirotor Design and Control
Abstract: In this paper we propose a disturbance observer based control for the class of multirotor aerial vehicles having co-planar and collinear propellers, following a geometric approach. The control scheme is based on the well known inner-outer loop structure, where the tracking control problem on the group of rotations is extended with an observer. To prove the asymptotic stability of the tracking error, a Lyapunov stability analysis is provided, taking into account kinematics, dynamics, and disturbance observer errors. For this purpose, disturbance rejection is achieved leveraging the disturbance model, which is assumed to be generated by exogenous systems having arbitrary orders. Simulations are performed on a hexarotor under elaborate external disturbances, which take into account unmodeled dynamics and time-varying wind effects. Simulation results show that the proposed control scheme can compensate for the disturbances, even when the embedded exogenous system model is coarse, outperforming the baseline geometric controller without disturbance compensation.

Keywords: Control Architectures, Multirotor Design and Control, UAS Applications
Abstract: Modeling the kinematics and dynamics of UAVs with cable-suspended loads using dual quaternions remains an area requiring further exploration, especially when considering the offset between the attachment point and the UAV's center of mass. This work introduces a novel control strategy based on dual quaternions for sling load cargo UAV (cUAV) systems with offset attachments. Leveraging the mathematical efficiency and compactness of dual quaternions, we establish a unified representation of the kinematics and dynamics of both the UAV and its suspended load. Extensive simulations and real-world experiments were conducted to evaluate the accuracy and robustness of the proposed strategy. The results demonstrate the controller's reliability and stability across various conditions in practical cUAV applications. This study makes a contribution to the presentation of this novel control strategy that harnesses the benefits of dual quaternions for cUAVs. Our work also holds promise for inspiring future innovations in under-actuated systems control using dual quaternions.

Keywords: Multirotor Design and Control, Payloads, Aerial Robotic Manipulation
Abstract: This paper presents the development of a payload-centric controller for manipulating a slender object with two multirotor UAVs. The paper formulates a 2.5D planar problem that allows the payload to be oriented and positioned in the horizontal plane while independently controlling the height. The aim is to enable abstracted dynamics of the UAVs providing the lift, to allow for simple control of the payload whilst enabling disproportionate control effort between the two UAVs. The control system has been experimentally implemented with two Crazyfly UAVs connected by a lightweight slender payload. In comparison to a combined position setpoint controller, the payload-centric control system shows a reduction in steady-state error for hover tests and reference tracking, and a reduction in oscillations caused by the UAVs competing to hold position. Reference tracking testing validates the performance of the reference tracking controller. The payload-centric controller is tested in simulation with a heterogeneous multi-lift system to demonstrate the versatility of the controller.

Keywords: Multirotor Design and Control, Technology Challenges, Energy Efficient UAS
Abstract: Coaxial rotors offer design advantages for drones, in that they enable a smaller airframe while allowing for larger rotors. While larger rotors provide greater thrust and efficiency, they are not optimal for gust rejection, as their high inertia limits the rotor response frequency. Variable pitch propellers are a solution, decoupling the rotor response from the rotational inertia, but increase the complexity and mass of the system. This work looks at the agility advantages of a design compromise, using variable pitch only on the lower rotor of a coaxial pair. The results show that adapting variable-pitch lower rotor into coaxial configuration increased the overall stacked efficiency by 22%, and improved agility by 10.8% compared to the fixed-pitch, enhancing the overall coaxial performance.

Keywords: UAS Applications, Navigation
Abstract: Autonomous aerial refueling (AAR) enables extended mission endurance for both manned and unmanned aircraft without relying on ground-based support. Traditional AAR methods use active sensors such as radar and light detection and ranging (LiDAR), which are susceptible to jamming and interference. This paper investigates a passive, vision-based approach using You Only Look Once (YOLO) convolutional neural networks (CNNs) to detect and track refueling components using only monocular imagery. Two flight test campaigns were conducted to evaluate system performance: one using a scalemodel unmanned aircraft system (UAS) receiver and the other using full-scale aircraft. The results demonstrate that larger objects like tankers can be accurately tracked at greater distances, while smaller objects like drogues require closer proximity for reliable pose estimation. A method leveraging a separate network for tanker tracking provides azimuth and elevation cues, guiding the receiver toward the drogue until it is close enough for precise docking. Additionally, extensive flight imagery was collected for future validation using recorded Global Positioning System (GPS) data. These findings highlight the feasibility of vision-based AAR and inform future work toward a fully autonomous refueling capability.

Keywords: Autonomy, Certification, Navigation
Abstract: This paper introduces a deep neural network (DNN) framework designed to accurately determine the relative bearing between a naval surface vessel and an uncrewed aerial system (UAS) using video data collected from drone operations in a maritime environment. Utilizing a dataset of 2,773 augmented images categorized into twelve 30-degree angular classes, the DNN was trained with the YOLOv11s architecture to identify and localize the relative bearing of a Yard Patrol vessel effectively. The model demonstrated exceptional performance, achieving an overall precision of 89%, recall of 91.3%, and a mean average precision (mAP) of 93.6% at a 50% intersection over union (IoU) threshold. Furthermore, the mAP averaged 83.1% across IoU thresholds from 50% to 95%, highlighting the model’s robustness in diverse conditions. These metrics indicate that the DNN can reliably estimate the UAS’s bearing relative to the naval vessel, thereby facilitating autonomous recovery operations in communication-denied maritime environments. This advancement supports the United States Navy’s initiative to integrate rotary-wing UASs onto existing naval platforms, ensuring safe and efficient flight operations from stern landing areas

Keywords: Perception and Cognition, Navigation, UAS Testbeds
Abstract: This paper proposes a vision-in-the-loop simulation environment for deep monocular pose estimation of a UAV operating in an ocean environment. Recently, a deep neural network with a transformer architecture has been successfully trained to estimate the pose of a UAV relative to the flight deck of a research vessel, overcoming several limitations of GPS-based approaches. However, validating the deep pose estimation scheme in an actual ocean environment poses significant challenges due to the limited availability of research vessels and the associated operational costs. To address these issues, we present a photo-realistic 3D virtual environment leveraging recent advancements in Gaussian splatting, a novel technique that represents 3D scenes by modeling image pixels as Gaussian distributions in 3D space, creating a lightweight and high-quality visual model from multiple viewpoints. This approach enables the creation of a virtual environment integrating multiple real-world images collected in situ. The resulting simulation enables the indoor testing of flight maneuvers while verifying all aspects of flight software, hardware, and the deep monocular pose estimation scheme. This approach provides a cost-effective solution for testing and validating the autonomous flight of shipboard UAVs, specifically focusing on vision-based control and estimation algorithms.

Keywords: Perception and Cognition, Air Vehicle Operations, Certification
Abstract: The future of the United States Navy’s (USN) carrier airwing hinges on effective Uncrewed Aerial Vehicles (UAVs), whose autonomy critically depends on robust aerial refueling systems. This work seeks to refine the process and measurement noise parameters in a hybrid Deep Neural Network (DNN) and Kalman Filter (KF) framework to improve drogue tracking reliability under challenging operational conditions. The proposed study employs a structured experimentation protocol combining simulated lab environments—featuring robotic arms replicating drogue motions—along with video datasets from actual refueling operations. Preliminary results obtained via a trial-and-error tuning approach indicate promising performance, achieving an overall RMSE of 0.155~m. Building on these encouraging findings, we seek to implement systematic fine tuning methods, specifically grid search and Bayesian optimization, to further reduce RMSE and enhance system accuracy and robustness. The ultimate goal is to advance the operational readiness of autonomous aerial refueling, laying the groundwork for the next generation of USN carrier-based aviation.

Keywords: Autonomy, Path Planning, Navigation
Abstract: This work derives two basic engagement zone models, describing regions of potential risk or capture for a mobile vehicle by a pursuer. The pursuer is modeled having turn- constraints rather than simple motion. Turn-only (C-Paths) and turn-straight (CS-Paths) paths are considered for the pursuer of limited range. Following the derivation, a simulation of a vehicle avoiding the pursuer’s engagement zone is provided.

Keywords: Autonomy, Path Planning, Simulation
Abstract: This paper proposes an optimal control-based rendezvous strategy for fixed-wing Unmanned Aerial Vehicles (UAVs) using a Linear Quadratic Regulator (LQR). The goal is precisely tracking a moving target while maintaining flight stability and avoiding predefined restricted areas. The controller optimally adjusts UAVs flight parameters to minimize trajectory errors and enhance robustness against environmental disturbances. A penalty-based method is integrated to prevent UAVs from entering restricted areas while ensuring smooth trajectory adaptation. The proposed approach has been tested in MATLAB simulations under multiple scenarios, demonstrating its effectiveness in achieving stable and efficient rendezvous maneuvers. The results confirm that LQR-based control and adaptive penalty mechanisms offer a practical solution for fixed-wing UAV operations in constrained environments.

Keywords: Energy Efficient UAS, Path Planning, Simulation
Abstract: Coverage Path Planning (CPP) is crucial for UAV applications such as inspection and surveying. While existing CPP methods often focus on minimizing distance or time, energy consumption remains a critical, relatively unexamined constraint, especially for multirotor drones. This paper proposes a novel CPP approach that directly incorporates an energy model into the path-planning process. By utilizing a Mixed Integer Linear Programming (MILP) framework and an energy model, the proposed method aims to minimize energy consumption while ensuring complete coverage of the target area. Simulations and experimental results demonstrate that the proposed approach gives optimal solutions, and using this richer heuristic reduces the processing time for the MILP problem, opening the door for faster online CPP planners.

Keywords: Navigation, Path Planning, Simulation
Abstract: The computation of a safe path between two target points for an omnidirectional drone is considered. The drone is equipped with eight fixed unidirectional thrusters, enabling full pose control. Given a priori knowledge of the environment map, a preliminary path is generated using a variant of RRT*. A corresponding trajectory is then fitted to this path and executed by the drone.

To enhance safety and efficiency, the velocity along the path is adaptively assigned, balancing caution near critical obstacles with minimizing travel time in open spaces. The adaptive velocity limits are proportional to the distance between the drone’s convex hull at various poses along the path and the surrounding environment. Distance computation is optimized by focusing on obstacles in the direction of motion, representing obstacle facets with axis-aligned voxels, and pruning distant obstacles before calculating the exact distance between the convex hull and the environment map.

The proposed approach is validated through simulation studies, demonstrating effective navigation through narrow gaps at odd angles while ensuring minimal travel time and maintaining required safety margins.

Keywords: Simulation, Path Planning, Training
Abstract: The utilization of simulations for the development of path planning algorithms for autonomous indoor multicopters is of primary importance. It offers a secure and cost-effective setting for the testing and optimization of algorithms. This article considers and examines the currently used simulation options with regard to their suitability for the development of path planning algorithms for autonomous indoor multicopters. The use of autonomous multicopters represents an innovative solution to simplify the process of layout recording and inventories. This article focuses on the voxel-based simulation VSim, developed and named by the author. In light of the extant literature, the article elucidates the simulation environments that are most commonly utilized. Subsequently, a selection of simulations is compared with VSim. The time efficiency and resource usage of the simulation environments are examined based on more than 1,500 test runs. Furthermore, the observations of the test executions are described in detail, and finally, the simulations with all investigated parameters are compared. Additionally, the potential for parallelization is explored and discussed.

Keywords: Air Vehicle Operations, Perception and Cognition, Sensor Fusion
Abstract: The knowledge of the precise 3D position of a target in tracking applications is a fundamental requirement. The lack of a low-cost single sensor capable of providing the three-dimensional position (of a target) makes it necessary to use complementary sensors together. This research presents a Local Positioning System (LPS) for outdoor scenarios, based on a data fusion approach for unmodified UAV tracking, combining a vision sensor and mmWave radar. The proposed solution takes advantage of the radar’s depth observation ability and the potential of a neural network for image processing. We have evaluated five data association approaches for radar data cluttered to get a reliable set of radar observations. The results demonstrated that the estimated target position is close to an exogenous ground truth obtained from a Visual Inertial Odometry (VIO) algorithm executed onboard the target UAV. Moreover, the developed system’s architecture is prepared to be scalable, allowing the addition of other observation stations. It will increase the accuracy of the estimation and extend the actuation area. To the best of our knowledge, this is the first work that uses a mmWave radar combined with a camera and a machine learning algorithm to track a UAV in an outdoor scenario.

Keywords: Navigation, Sensor Fusion, Multirotor Design and Control
Abstract: This paper presents an integrated navigation algorithm based on trident quaternions, an extension of dual quaternions. The proposed methodology provides an efficient approach for achieving precise and robust navigation by leveraging the advantages of trident quaternions. The performance of the navigation system was validated through experimental tests using a multi-rotor UAV equipped with two navigation computers: one executing the proposed algorithm and the other running a commercial autopilot.

Keywords: Sensor Fusion, Navigation, Perception and Cognition
Abstract: In autonomous multi-robot systems robot-to-{robot/object} localization methods can be utilized to increase the robustness and to achieve a precise and robust localization of the individuals. This paper investigates on the performance of two promising systems: UVDAR, a vision-based mutual localization in the UV spectrum, which has shown to be effective in swarm formation and leader-following tasks, and PoET, which is a deep learning-based visual relative object pose estimator. To evaluate these methods, we collected datasets in a controlled indoor environment equipped with a motion capture system for precise ground truth measurements. Our evaluation considers two key aspects: the absolute error between measured and true relative poses, and the consistency of the provided measurement uncertainty estimates with the actual errors. We introduce a novel framework for evaluating the consistency of relative pose measurements. This framework supports various error definitions and leverages spline-based trajectory representations to generate smooth, C2-continuous reference measurements. Both the UVDAR dataset and the evaluation framework are made publicly accessible to foster further research and development in this field.

Keywords: UAS Applications, Sensor Fusion
Abstract: This research presents a robust probabilistic framework for minefield localization, mapping, and avoidance, addressing a technological gap in the field of aerial countermine intelligence, while bypassing the well-established techniques of landmine detection. Our approach propagates the pose uncertainty matrix delivered by a drone's flight controller's Kalman filter to probabilistically estimate the location of detected mines. This probability map then seeds an artificial potential field path generator which creates a safe path for ground traversal by producing waypoints through the minefield. The system's performance is evaluated in simulations and validated through flight trials, demonstrating its potential to improve the efficiency and safety of UAV-assisted minefield navigation and threat avoidance.

Keywords: UAS Applications
Abstract: In this work a survey of the issues and difficulties for Unmanned Aerial Vehicles (UAVs) in underground environments, in particular tunnels, will be carried out. In addition to not having Global Navigation Satellite System (GNSS) signal or any other type of external positioning, this kind of environment will present a number of unique constraints that make a wide range of visual-inertial (VIO), or LiDAR-inertial (LIO),localization algorithms unusable. In addition, state-of-the-art algorithms will be validated with real flight data in a tunnel and possible solutions will be offered for achieving robust and reliable localization using only the on-board. In this way, the deployment of autonomous navigation tasks in these degraded environments will be pushed.