General simulation platform for vision based UAV testing

This paper introduces a virtual reality (VR)-based unmanned aerial vehicle (UAV) simulator designed to support immersive training and early-stage human factors evaluations in rescue and emergency mission contexts. The system simulates a leader-follower UAV configuration, where a human operator controls a lead drone through a VR headset and joystick, while autonomous drones maintain any geometric formations using onboard sensing and dynamic obstacle avoidance [1]. This swarm-based coordination reflects real-world search and rescue scenarios, where rapid decision-making, spatial awareness, and teamwork are essential.The simulator is developed with a focus on human-in-the-loop design, providing an immersive teleoperation experience that places the user in high-pressure environments with dynamic spatial constraints. Visual and auditory feedback, along with the ability to switch between multiple drone perspectives, is intended to support situational awareness, mission control, and error recovery in complex terrain.From a human factors perspective, the simulator serves as a flexible testbed for evaluating cognitive and ergonomic variables in safety-critical tasks. It allows the assessment of operator workload, interface usability, attention allocation, and situation awareness under realistic but controlled conditions. Subjective evaluation tools such as the NASA Task Load Index (NASA-TLX) and the Situation Awareness Rating Technique (SART) [2] can be embedded directly within the VR experience. At the same time, objective data from head and hand movement, control inputs, and UAV performance are recorded to gain insight into operator behavior.The simulator integrates high-fidelity UAV dynamics using closed-loop reference model adaptive controllers [3], and can be equipped with tools such as eye tracking, physiological sensors for workload estimation, and visual attention assessment methods like ATTENDO [4]. These additions support deeper analysis of how operators acquire information, prioritize tasks, and shift attention during mission-critical events.Overall, the VR-based UAV simulator addresses a growing need to evaluate and enhance human performance in multi-agent control systems used in emergency operations. It offers a scalable, immersive environment that supports both training and cognitive engineering. Its modular structure allows for future integration of real UAVs, digital mapping capabilities, and adaptive interfaces, making it a valuable platform for advancing human-centered UAV system design.

Unmanned Aerial Vehicles (UAVs) have become essential tools in various industries for tasks such as inspection, maintenance, and surveillance. An Online Impedance Adaptive Controller (OIAC) is proposed for the online modulating of UAV control gains to obtain better performance and stability of tracking curved trajectories than the traditional methods, Model Reference Adaptive Controller (MRAC) and Proportional–Integral–Derivative (PID). Two UAV path planners with minimal jerk and snap were integrated into OIAC, MRAC, and PID. These six controllers were implemented and compared in a simulated UAV with perceptional noise, which follows curved pipelines and avoids obstacles. Experimental results show that the OIAC controller achieves at least an 80% improvement over the PID controller across all trajectory types in terms of the trajectory tracking error. Additionally, OIAC demonstrates an over 20% improvement in jerk trajectories and a more than 30% improvement in snap trajectories when compared to the MRAC controller. These results indicate that OIAC offers enhanced trajectory tracking accuracy and robustness against perceptual noise. Our work presents an advanced controller of a UAV and its preliminary validation in accurate and robust path tracking.

The interest of open source software in order to empower the capabilities of Unmanned Aerial Vehicles (UAVs) is growing rapidly into various business applications. In this paper, a complete, multi-layered, and open source flight architecture is proposed. This architecture includes an integrated flight stack, which comprises two side stacks: the UAV side stack and the Ground Control Station (GCS) side stack. Furthermore, a communication layer is used for managing the communication between the two side stacks. The proposed architecture is evaluated on a simulated UAV, and it envisions to be a software stack that will facilitate the development of more complex UAV concepts such as Flying Ad-hoc Networks (FANETs).

Unmanned Aerial Vehicles (UAV) may lose control and collide with other objects in the air, thus causing serious flight safety accidents. In this paper, the impact load and damage mechanism of 4.78 kg quad rotor UAV were studied. First, the accurate numerical model of UAV was established in the explicit dynamic analysis software LS-DYNA. Then the overall drop simulation and test of UAV with two different heights were carried out. Finally, the results were compared and analyzed. The high coincidence of experimental results and simulation results showed that the calculation method and simulation model are reasonable. On this basis, the impact load and damage of UAV in different speeds, heading angles and pitch angles were simulated and analyzed. The results revealed that the heading angle, pitch angle and velocity of UAV during collision have a significant effect on the impact load between UAV and the impacted object. It also affected the damage degree of UAV itself. In the collision, the arm of the UAV tended to break at the position joined to the fuselage. The battery hanging on the fuselage was also liable to separate from the fuselage. The research results of this paper have a certain guiding significance for the formulation of UAV safe flight airworthiness regulations.

In many applications, there is a need to compare multiple simulation models or parameter configurations in order to choose the model(s) whose output best resembles the historical data available from the system under study. This paper presents a novel framework that enables such analysis for multidimensional output statistics such as those found in weather/climate, epidemic, swarm/crowd control, social systems, communication networks, and other simulation applications with spatial output statistics that are distributed across various locations or geographical regions. The proposed framework uses the Wasserstein distance from the target data as the primary performance metric and statistically compares the models to determine the best-performing candidate(s). The efficacy of the proposed framework is illustrated through three examples related to random walk of swarm particles on a two-dimensional space, Monte Carlo simulation with correlated bivariate output, and a realistic engineering application involving simulation of unmanned aerial vehicle (UAV) communication systems with spatial output.

The traditional reinforcement learning (RL) methods can solve Markov Decision Processes (MDPs) online, but these learning methods cannot effectively use a priori knowledge to guide the learning process. The exploration of the optimal policy is time-consuming and does not employ the information about specific issues. To tackle the problem, this paper proposes heuristic function negotiation (HFN) as an online learning framework. The HFN framework extends MDPs and introduces heuristic functions. HFN changes the state-action dual layer structure of traditional RL to the triple layer structure, in which multiple heuristic functions can be set to meet the needs required to solve the problem. The HFN framework can use different algorithms to let the functions negotiate to determine the appropriate action, and adjust the impact of each function according to the rewards. The HFN framework introduces domain knowledge by setting heuristic functions and thus speeds up the problem solving of MDPs. Furthermore, user preferences can be reflected in the learning process, which improves the flexibility of RL. The experiments show that, by setting reasonable heuristic functions, the learning results of the HFN framework are more efficient than traditional RL. We also apply HFN to the air combat simulation of unmanned aerial vehicles (UAVs), which shows that different function settings lead to different combat behaviors.

This paper investigates the general problem of comparing multidimensional simulation output with a given data set (e.g., real-world historical data). This problem frequently arises in verification, validation, and calibration of simulation models with spatial output statistics as in weather/climate, epidemic, swarm/crowd, social systems, communication networks, and many other applications where the simulation output is distributed across various locations or geographical regions. In the case of univariate simulation output, two-sample statistical hypothesis tests such as the t -test are commonly used. For simulation models with multidimensional and spatial output statistics, the Hotelling’s two-sample test is widely used as the benchmark method in the simulation literature. However, the Hotelling’s test assumes that the two samples come from multivariate Gaussian distributions with equal covariance matrices, which may not be the case in many applications. To address this gap, this paper proposes a double-bootstrap method based on the Wasserstein distance for comparing two multidimensional samples. Unlike the Hotelling’s test and other parametric approaches, the proposed method does not require restrictive distributional assumptions, enabling a wider range of applications and contributing to verification, validation, and calibration of simulation models with multidimensional output. Computational experiments are performed to assess the test power, and the results indicate that the proposed method outperforms the Hotelling’s test and various other approaches. The proposed method’s applicability is illustrated through two examples related to random walk of swarm particles on a two-dimensional space and a realistic engineering application involving simulation of unmanned aerial vehicle (UAV) communication systems.

The interest of social scientists in dynamic and far from equilibrium processes, the need for efficient methods to analyse complex business systems, and the availability of new computational tools, are the reasons for the growing interest in agent-based simulation models (ABMs). One of the applications of ABMs in economic and business field is the study of geographical clusters. Using simulation, various authors have tried to validate specific hypotheses about emergent features and performances of these systems. Nevertheless, the analyses of their dynamic behaviour are in part, lacking. The aim of this paper is to investigate, using a quite general AB simulation platform, the drivers of their evolutionary trajectories: origin, growth, maturity and death or transformation. After some references on the state of the art and on the use of the ABMs in business systems dynamics, the principal building criteria of a quite general simulation platform are described. In the conclusions, some preliminary results and research agenda are synthesised.

The applications of Unmanned aerial vehicle (UAV) in both civil and military fields have become increasingly widespread. There are many limitations for traditional experimental verification methods such as high trial-and-error costs, low efficiency and difficulty in troubleshooting. This paper proposes a UAV simulation and test method by Gazebo simulator and Robot Operating Systems (ROS2). In this paper, it uses the PX4 flight controller as the core control unit, and uses Gazebo to build a UAV model and physical environment. In order to implement the control algorithm and communication architecture, it adopts ROS2 method and achieve the path planning and flight control through the simulation way. This method can effectively simulate the flight characteristics of UAV in the real flight environment, and reduce the development costs, and improve the efficiency of algorithm verification. This paper provides an effective simulation and testing research approach for UAV flight simulation in complex environments.

In response to the issue of low positioning accuracy and insufficient robustness in small UAVs (unmanned aerial vehicle) caused by sensor noise and cumulative motion errors during flight in complex environments, this paper proposes a multisource, multimodal data fusion method. Initially, it employs a multimodal data fusion of various sensors, including GPS (global positioning system), an IMU (inertial measurement unit), and visual sensors, to complement the strengths and weaknesses of each hardware component, thereby mitigating motion errors to enhance accuracy. To mitigate the impact of sudden changes in sensor data, a high-fidelity UAV model is established in the digital twin based on the real UAV parameters, providing a robust reference for data fusion. By utilizing the extended Kalman filter algorithm, it fuses data from both the real UAV and its digital twin, and the filtered positional information is fed back into the control system of the real UAV. This enables the real-time correction of UAV positional deviations caused by sensor noise and environmental disturbances. The multisource, multimodal fusion Kalman filter method proposed in this paper significantly improves the positioning accuracy of UAVs in complex scenarios and the overall stability of the system. This method holds significant value in maintaining high-precision positioning in variable environments and has important practical implications for enhancing UAV navigation and application efficiency.

Local and asymmetrical potential field approach to leader tracking problem in rigid formations of fixed-wing UAVs

This paper presents a method to increase the reliability of Unmanned Aerial Vehicle (UAV) sensor Fault Detection and Identification (FDI) in a multi-UAV context. Differential Global Positioning System (DGPS) and inertial sensors are used for sensor FDI in each UAV. The method uses additional position estimations that augment individual UAV FDI system. These additional estimations are obtained using images from the same planar scene taken from two different UAVs. Since accuracy and noise level of the estimation depends on several factors, dynamic replanning of the multi-UAV team can be used to obtain a better estimation in case of faults caused by slow growing errors of absolute position estimation that cannot be detected by using local FDI in the UAVs. Experimental results with data from two real UAVs are also presented.

Inspecting overhead cables using autonomous Unmanned Aerial Vehicles (UAVs) is an affordable and promising future solution for providing a clear picture of the energy infrastructure. However, most of today's UAVs for powerline inspection are designed to use the Global Navigation Satellite System (GNSS) to follow the power pylons which compromises the detection accuracy. In this paper, we provide an overview of the current state-of-the-art in sensors that can be used to remotely detect power lines using UAVs. The work compares 20+ low-cost, low-power, and light-weight sensors. The performance of 6 different kinds of sensors is evaluated thoroughly in a real outdoor powerline test setup using a custom UAV. The sensor data is obtained and analyzed using Robot Operating System (ROS) and is provided openly.

This paper proposes a complete-information-based principal component analysis (CIPCA)-back-propagation neural network (BPNN)_ fault prediction method using real unmanned aerial vehicle (UAV) flight data. Unmanned aerial vehicles are widely used in commercial and industrial fields. With the development of UAV technology, it is imperative to diagnose and predict UAV faults and improve their safety and reliability. The data-driven fault prediction method provides a basis for UAV fault prediction. A UAV is a typical complex system. Its flight data is a kind of typical high-dimensional large sample dataset, and traditional methods cannot meet the requirements of data compression and dimensionality reduction at the same time. The method used interval data to compress UAV flight data, used CIPCA to reduce the dimensionality of the compressed data, and then used a back propagation (BP) neural network to predict UAV failure. Experimental results show that the CIPCA-BPNN method had obvious advantages over the traditional principal component analysis (PCA)-BPNN method and could accurately predict a failure about 9 s before the UAV failure occurred.

Unmanned aerial vehicles (UAVs) have become an important technology for acquiring high-resolution remote sensing images. Because most space optical imaging systems of UAVs work in environments affected by vibrations, the optical axis motion and image plane jitter caused by these vibrations easily result in blurring of UAV images. In the paper; we propose an advanced UAV image deblurring method based on a discriminative model comprising a classifier for blurred and sharp UAV images which is embedded into the maximum a posteriori framework as a regularization term that constantly optimizes ill-posed problem of blind image deblurring to obtain sharper UAV images. Compared with other methods, the results show that in image deblurring experiments using both simulated and real UAV images the proposed method delivers sharper images of various ground objects.