Browse Topic: Unmanned aerial vehicles
Unmanned Aerial Systems (UAS) pose a growing threat on the modern battlefield, demanding rapid detection and characterization capabilities for the warfighter. Existing single-model solutions are inadequate for Counter-UAS (C-UAS), as they struggle across varying ranges and cannot provide detailed contextual information beyond bounding boxes. We present ZEUS (Zero-shot Explainable Universal Segmentation), a multi-model detection and recognition system that integrates several machine learning approaches. ZEUS employs a high-performance UAS detector trained on synthetic, internally collected, and open-source datasets, with real-time capability demonstrated on edge hardware across both electro-optical and infrared modalities. For classification, ZEUS uses a zero-shot approach: detected UAS are segmented and compared against a library of 3D reference models rendered at various poses, enabling identification of new UAS types without retraining. This methodology additionally provides UAS pose and range estimates critical for threat assessment and engagement decisions.
This paper details the development of an intelligence and inspection platform consisting of an attritable sub-250g UAV, a ground control station, and a visualization interface for users. The UAV architecture combines onboard obstacle detection and avoidance along with simultaneous localization and mapping to have full autonomous navigation inside of complicated GPS-denied environments. The ROS 2-to-Unreal Engine data pipeline allows for sensor fusion, data cleansing, and initial analysis as well as creation of a high-fidelity real-time 3D digital twin. The visualization interface allows users to easily identify critical features and turn data into intelligence to support decision making by soldiers and first responders.
Shrike Nano provides forward observers and small unmanned aerial system (sUAS) operators with an integrated solution to enhance target prosecution using sUAS video feeds and indirect fire systems. Operable within the Android Tactical Assault Kit (ATAK) ecosystem, Shrike Nano functions as a software plugin that interacts seamlessly with existing tools, including UAS Tool, Robot Picker, and Network Monitor. By utilizing either aided threat recognition (AiTR) or manual targeting workflows, along with passive single-camera geolocation, operators can nominate targets and correct shot placement via digital messaging to enterprise fires terminals such as the Advanced Field Artillery Tactical Data System (AFATDS). The system offers key advantages, including operator standoff capabilities, accurate geolocation, and streamlined fires messaging workflows, all while leveraging low-observable platforms. Shrike Nano seeks to bridge gaps in traditional targeting processes by providing a cohesive and efficient sensor-to-shooter workflow that reduces cognitive load and enables faster, more reliable fire missions at the tactical edge.
This paper presents a generalizable geometric framework for rapid on-demand generation of multi-UAV formations with arbitrary 2D geometries and user-specified scalable scales. First, vertices, edge intersections and edges are extracted from a user-defined formation template to enable parametric description of both simple and composite formation geometries. Second, boundary interpolation, edge expansion and recursive internal expansion are integrated to synthesize hierarchical multi-layer UAV deployment point sets under a controllable expansion ratio. Third, a geometric distortion metric is proposed to optimize UAV node indexing and formation reconstruction while preserving inter-node topological consistency. Algorithmic derivations, complexity analysis and simulation assumptions are further elaborated. Simulation results verify that the proposed method preserves geometric fidelity of target formations while delivering superior scalability and spatial coverage, rendering it well-suited for emergency transport, aerial surveying and low-altitude cooperative missions in dense urban environments.
With the complexity of chemical warfare threats and the diversification of battlefield environments, traditional toxic agent detection methods are facing bottlenecks such as response delays, coverage blind spots, and personnel safety risks. This research focuses on the application of unmanned aerial vehicle (UAV) carried toxic agent sensor systems, aiming to analyze the methods of mounting and deploying the sensors on the UAVs, and to construct a rapid response, high-precision, and highly resistant toxic agent monitoring system. Its significance lies in two aspects: 1. Tactical value: It breaks through the time and space limitations of manual reconnaissance, realizes real-time dynamic perception and early warning of toxic agent contamination, and provides key decision-making support for battlefield command; 2. Application expansion: The research results can be transferred to counter-terrorism, nuclear, biological, and chemical emergency response fields, providing theoretical support and engineering paradigms for the development of unmanned and intelligent chemical defense equipment.
New technologies, advanced materials, evolving mission profiles and fast-changing requirements are forcing the aerospace and defense (A&D) industry to dramatically increase the speed of engineering. Companies must design, validate and bring more complex products to market faster than ever, even as software, electronics and autonomy continue to reshape what aircraft, spacecraft and defense systems can do. At the same time, a growing production challenge is emerging. Workforce shortages, supply chain disruption and pressure to reduce cost and cycle time are converging with new demands for greater volume and flexibility. Defense programs are seeing increasing need for larger quantities of lower-cost systems such as drones, while commercial aerospace companies continue to work through backlogs and reinforce their fleets. To keep pace, the industry must accelerate innovation while also scaling production with greater speed, resilience and adaptability.
This paper presents the design, implementation, and validation of an aerial-launch FPV (First-Person View) drone system that was developed to provide a complex environment with flexible deployment and precise delivery capabilities. The integrated system is composed of a hybrid VTOL carrier aircraft, a number of FPV drones, and an aerial mounting / release equipment. Using the AYK-250 platform, the carrier has a vertical take-off and landing function and long-time endurance. In terms of the FPV drones, it is built upon the high performance MARK4 5-inch frame that has high agility and high payload. The release module uses a single-hook point structure with a limit stop. The FPV drones are released stably, and the separation is reliable in flight. Comprehensive flight tests proved all workflows completely, involving carrier take-off, cruise with drones mounted, sequential aerial launch, and subsequent autonomous attitude recovery and route tracking by the FPV drones. The test results confirm the system’s capability for reliable launch from an aerial platform coupled with precise guidance, establishing a credible technical solution for expanding the practical applications of FPV drones in distributed tasks. Results show that our system can be launched via an aerial platform with an accurate guide and is a viable technological solution to spread FPF Drones for operational strategies in a more distributed way.
Aerodynamicists around the globe are developing mechanisms and structures inspired by nature that enable variable camber morphing (VCM) for aerodynamic surfaces. The implementation of the VCM mechanism in an airplane wing enhances the performance and stability during various flight segments. The present review article is focused mainly on the up-to-date VCM methods in a qualitative as well as quantitative approach that are specific to Aircraft/unmanned aerial vehicle (UAV) wing configurations. Initial literature discussions are confined to the conventional mechanisms that enable VCM in different aircraft configurations and the added aerodynamic advantages such as lift enhancement, drag reduction, boundary layer separation, and flow control. However, those designs need either external shape optimization or internal structural refinements to ensure the factor of safety (FoS). The modern aviation industry is also focused on bioinspired technology because of the adaptive flying capabilities and stall-delay characteristics. Therefore, a review of bioinspired VCM methods that are assessed based on the aerodynamic potentials is sequentially organized in the article. Additionally, considerations are motivated by the application of various compliant structural patterns for VCM in the aircraft industry. The discussion indicates the prospective benefits of morphing toward the future of the Green Aviation industry.
This paper proposes a UAV combat simulation method integrating AFSIM and DoDAF to address the complexity of UAV combat systems. DoDAF establishes a multi-view architecture mode to clarify logical relationships between UAVs and weapon systems, laying a structured foundation. AFSIM implements dynamic simulation of combat processes by mapping DoDAF’s static architecture to its dynamic elements, simulating UAV maneuver, situation awareness, and strikes. A UAV search-and-strike mission scenario test shows the method accurately simulates collaborative behavior in target searching, tracking, and engaging. This method features a high degree of standardization and normalization, providing a foundation for the evaluation of UAV combat effectiveness and strategy optimization.
This paper, for the first time, applies the Divine Religions Algorithm (DRA) to three-dimensional UAV path planning. Targeting the complex terrain of urban-mountain mixed environments, we propose a novel method that incorporates multiple enhancements, including A* initialization, single-point disturbance mutation, and adaptive weighting. First, the A* algorithm is employed to generate high-quality initial paths, serving as the skeleton of the population. Innovative mechanisms such as terrain-adaptive disturbances and dynamic weight adjustment are integrated to achieve both efficiency and robustness in path optimization. Comparative experiments with Genetic Algorithm (GA) and Crowned Porcupine Optimization (CPO) show that the improved DRA algorithm exhibits significant advantages in terms of path length, safety margin, average altitude variation, average turning angle, and overall cost function. It consistently obtains superior paths and achieves faster convergence. The results demonstrate that the proposed approach provides an efficient, adaptive, and practical intelligent optimization tool for UAV path planning in urban-mountain mixed or similarly complex environments, offering promising prospects for engineering applications.
When quadrotor unmanned aerial vehicles (UAVs) operate in urban low-altitude airspace, especially within complex environments, their sensor perception signals are highly susceptible to blockages, deviations, and the inclusion of high-frequency noise. These factors, in turn, induce nonlinear variations in the UAVs’ flight mechanical properties, giving rise to abnormal flight stability issues such as attitude jitter, altitude fluctuations, and trajectory deviations. To address these challenges, this paper puts forward a method aimed at enhancing the positional accuracy of quadrotor UAVs, which is based on Extended Kalman Filter (EKF) multi-sensor fusion. In conjunction with the redundant configuration of sensors, a proportional-integral controller is specifically designed to allow optical flow sensors to compensate for the speed data generated by inertial sensors. Building on the EKF method, a comprehensive data fusion model is established, encompassing both position and speed states. Leveraging the MATLAB platform, trajectory flight simulations are conducted, utilizing multi-sensor data fused via EKF, with the sensor suite including GPS, IMU, Optical Flow sensors, and Barometers. The simulation results demonstrate that this proposed method can effectively mitigate the adverse impacts of environmental interference and sensor noise on the positional accuracy of quadrotors. By continuously correcting position information and accurately estimating position states, it significantly improves the UAVs’ flight position accuracy. This research outcome lays a robust and theoretically sound foundation for in-depth investigations on critical issues related to general aviation applications, such as the safe and efficient autonomous flight, adaptive and reliable intelligent navigation, and ultra-precise and mission-critical operations of quadrotor UAVs, thereby significantly contributing to the sustained and innovative advancement of the field.
Multi-UAV cooperative localization can utilize information fusion between nodes to improve localization accuracy and performance on the target. Distributed state fusion estimation methods have been heavily studied in recent years, but the final estimates in the research results do not converge towards the global optimum. This paper aims to make the state estimates of each individual in the UAV formation for the target converge and converge to reliable values. In this paper, we study a multi-UAV cooperative tracking method based on adaptive weighted fusion, which first evaluates the importance of each node in the UAV formation and the reliability of the local filtering estimation results, and then assigns the weights according to the reliability of the UAV’s local state estimation of the target in the whole at the current moment. Finally, this paper verifies through simulation experiments that the method can not only accomplish the state tracking of the target, but also that the state estimates of each node in the network converge to more accurate state estimates.
Aiming at the problems of model uncertainty, external disturbances and high-frequency chattering of traditional sliding mode control in complex working conditions for quadrotor unmanned aerial vehicles, this paper proposes a control strategy based on fractional-order sliding mode. The quadrotor UAV control system has problems such as parameter uncertainty, multi-input multi-output, and sensitivity to internal and external disturbances. Traditional PID control has certain limitations. Sliding mode control has the advantages of strong robustness and simple implementation. Fractional-order calculus has hereditary and memory properties. The combination of the two has better control performance for nonlinear systems. To further improve the trajectory tracking performance of quadrotor UAVs, a fractional-order sliding mode controller is designed based on fractional-order theory and traditional sliding mode control. Finally, multiple experiments are conducted in Matlab/Simulink, including trajectory tracking, parameter perturbation, and anti-interference simulation experiments. The control results of various controllers are compared and analyzed to verify the effectiveness of the fractional-order sliding mode control method designed in this paper.
Rigorous validation of SAE Levels 3 and 4 autonomous systems increasingly relies on simulation. However, the simulation-reality gap remains a challenge for human-in-the-loop assessments. This study empirically quantifies the behavioral fidelity of the Car-Learning-to-Act (CARLA) simulator by recreating specific real-world traffic scenarios using the high-precision exiD drone dataset. Twenty-five participants performed a series of maneuvers, including lane changes and time-critical cut-ins. Their performance was analyzed using Dynamic Time Warping (DTW), driver profiling, and Time-to-Collision (TTC) metrics. The findings reveal a clear distinction between relative and absolute behavioral validity. In strategic decision-making tasks, the simulation demonstrated remarkably high temporal fidelity. DTW analysis explained 94% of the trajectory variance. Participants initiated lane changes with an average lag of -9 frames (0.36 s) compared to naturalistic references. These results indicate that, despite the absence of peripheral optical flow, the simulator successfully elicits temporally correlated decision-making patterns suitable for assessing strategic driver intent. However, physical execution in reactive scenarios revealed significant absolute discrepancies. Although the high Pearson correlation (r ≈ 0.89) in velocity profiles proves that drivers recognize and react to hazards with realistic timing, their physical inputs were exaggerated. Participants displayed digital, over-modulated braking responses and maintained a negative safety bias of -11.26 m, a deviation attributed to the lack of vestibular g-force feedback and geometric minification. Furthermore, distinct driver profiles emerged. Risk-oriented participants exhibited a gaming effect by neglecting safety margins. In conclusion, while CARLA is highly valid for testing the temporal logic of driver interactions, absolute dynamics require calibration functions, such as force-feedback (pedal) tuning and visual deceleration cues like camera shake, to compensate for sensory limitations before it can be used for safety-critical validation.
Labor shortages and supply chain volatility are putting additional pressure on warehouse operations to be faster and more adaptable. “In this environment, real-time visibility becomes foundational. Physical AI enables warehouses to operate with a continuously updated understanding of their environment, allowing them to respond quickly to disruptions and optimize performance,” Joseph Mirabile, Vice President of Operations at Gather AI, a Pittsburgh-based startup developing drone-powered inventory solutions.
In the two months since Microvision bought Luminar and acquired key tech and talent, the sensor company has been busy. In that time, they've merged key lidar units from each company and created a perception software stack to run it in a convincing demo of its ADAS and autonomous capabilities. The company is also pushing innovative lidar tech into the defense drone and antidrone markets, already working with a German defense supplier that works with NATO member countries.
Items per page:
50
1 – 50 of 1416