Browse Topic: Sensors and actuators

Items (8,250)
Spacecraft with chemical propellant engines, especially spacecraft for exploring extraterrestrial objects, need to carry out plume tests on the ground in order to determine the influence of engine plumes on spacecraft. An important purpose of the plume test is to accurately measure the pressure field in key parts of the spacecraft. In this paper, according to the pressure measurement requirements of the spacecraft plume test, the design of a pressure measurement system is carried out, which mainly includes a pressure measurement sensor, a pressure difference measurement sensor, a pipeline, a cable, a measuring instrument, a data acquisition instrument, upper measurement software, and so on. The designed pressure measurement system was successfully applied to the plume impact test of Chang'e VII, which provided important technical support for the development of the spacecraft.
Wu, YueGuo, QinliangWu, DongliangLiu, XiaoningTao, DongxingLin, BoyingXie, ZhengWei, XiNiu, Tong
The adjustment process for multi-link retractable hatches has long relied on personal experience, making it difficult to achieve precise and quantitative length adjustments. This limitation has consistently constrained the efficiency of the adjustment process. This paper aims to analyze the risks and shortcomings in the existing flush adjustment process, simplify the flush adjustment process into a mathematical model, and calculate the required adjustment amount of the actuator length. By simplifying the flush adjustment process and steps, the risk associated with the adjustment process can be reduced, and the efficiency of door step difference adjustment can be improved.
Deng, QinwenShen, YingdongWang, ZhihaiLi, YixiaoWei, XingxuGao, Haosen
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.
Cui, NanLiu, WenzhiLiu, HanqiWang, JingruiWang, ZhizhongZhi, Haonan
The development of remote tower systems in aviation and the resurgence of multi-display interfaces and virtual environments have dramatically influenced ATC, increasing both controllers’ visual demands and their ergonomic needs. This study uses the Visual Ergonomics to study the impact of screen luminance level, along with color temperature, on trainees’ visual performance, fatigue, and physical discomfort in the control rooms of the Remote Tower. By combining a simulated remote control system with spectrometer measurements, PVT alertness tests, VMT (Visual Memory Test) measurements, and subjective evaluations, COST B21 can build up a multi-dimensional ergonomic assessment framework. Eight levels of display luminance (and color temperature) were tested, including two illuminance levels (300 lx and 400 lx) and four color temperature ranges (6000 K–9000 K). Using the Analytic Hierarchy Process (AHP), these parameters were assigned weights to derive a Visual Ergonomics (VE) scoring model, and the ideal visual performance was observed at 400 lx illuminance and 8000 K CCT. The results clearly illustrate the significant impact of display parameters on operational performance in remote tower systems and provide both practical data and a theoretical basis for the human factors design and fatigue reduction research on RTSs.
Zhong, LinfengHu, RuohuiLuo, PeilinZuo, QinghaiZhong, QingweiAi, Yi
This study presents a full-envelope attitude-stabilisation and trajectory-tracking strategy for morphing flying-wing UAVs operating in highly nonlinear and strongly coupled conditions. The approach integrates fuzzy C-means (FCM) envelope partitioning with L1 adaptive control. Small-disturbance linear models are first generated at multiple altitude–Mach trim points; the FCM algorithm then performs unsupervised clustering in the state space, yielding representative subintervals that capture local flight-dynamic characteristics. The optimal cluster number and fuzziness exponent are selected using the partition coefficient, partition index, partition entropy, and Xie–Beni indices. For each sub-interval, an LQR baseline controller is designed and augmented by an L1 adaptive compensator, where a low-pass filter decouples adaptation from robustness to guarantee specified transient-performance bounds under matched/unmatched uncertainties, actuator saturation, and external disturbances. A feed-forward pre-filter realises online decoupling of the multi-input multi-output channels, thereby enhancing adaptability to variable sweep angles and large aerodynamic variations. Simulations covering low-speed/small-sweep and high-speed/large-sweep scenarios demonstrate that the proposed method sustains robust stability across the clustered envelope, outperforming conventional control schemes and confirming its engineering applicability.
Tang, LonghaoSun, XiaoxuLiu, Changlin
This paper proposes a multi-source dynamic error compensation algorithm for the transfer alignment of airborne optoelectronic payloads. This method addresses performance limitations of micro-inertial navigation systems (micro-INS) in complex dynamic environments, specifically those arising from accumulated device noise and the inability to perform static alignment due to installation errors. The algorithm’s core is the Extended Kalman Filter (EKF) technology. By constructing a “velocity + attitude” matching model between the UAV’s master inertial navigation system (MINS) and the optoelectronic payload’s slave inertial navigation system (SINS), it leverages high-precision MINS navigation information to correct SINS errors. Utilizing a 21-dimensional state space equation and measurement equation, the algorithm achieves real-time estimation and compensation of various errors, including attitude misalignment angles, sensor biases, installation errors, and flexure deformation. Simulation results demonstrate significant alignment accuracy improvement. Post-lever arm effect compensation, velocity errors are stably controlled within 0.01 m/s. Concurrently, flexure deformation angle compensation substantially reduces misalignment angle fluctuations across all directions, enhancing system stability and maintaining low misalignment angles. These findings validate the proposed error compensation strategy’s effectiveness.
Zhang, LuLi, MaoWang, ShiyongLei, Chao
This study develops an end-to-end load analysis scheme for flap and slat actuators, which comprise the aircraft’s high-lift system, and the analysis results are directly integrated into hardware optimization. Because they shoulder heavy responsibilities during the takeoff and landing phases, whether they can remain rock-solid under complex aerodynamic conditions or even remain unmoved in emergencies is directly related to their overall safety performance. This work process is closely linked and includes three major links. First of all, according to the CCAR-25.301 standard, the load envelope under normal working conditions is sorted out, and the limit cases of abnormal faults are exhausted. Subsequently, ANSYS Workbench pulled silk and peeled off the cocoons to capture the peak stress at the engagement between the output shaft and the gear. In the end, the closed-loop verification of the customized test bench made the theoretical calculations and the hardware-measured data exactly the same. The entire package provides designers with hardcore data support, and always uses airworthiness, not convenience, as the criterion when improving actuator performance.
Xu, Yuanze
It is very hard to position helicopters in complex environments, and this severely limits their ability to navigate on their own. This paper proposes a navigation algorithm that uses a combination of different sensors and deep learning. It uses a special type of deep learning called ResNet50 and a special type of machine learning called LSTM. This algorithm extracts features of the environment and uses a Kalman filter to estimate the state of the system. The system is made more robust by merging information from multiple levels. The algorithm’s ability to maintain stable navigation in the face of faulty sensors is noteworthy, as is its use of an adaptive inference strategy that dynamically adjusts computational load. This strategy strikes a balance between performance and resource consumption. Experiments show that the plan works well in places where GPS is not available. This makes it much better for the helicopter to fly by itself, and it can be used in places like the army, for looking at places from the sky, and for helping people in danger.
Yang, Ming
This paper focuses on autonomous drone landing scenarios. Addressing the core requirements of accurate landing site assessment and intuitive visual presentation, it conducts in-depth research on the application of 3D LiDAR (TOF technology) point cloud data. LiDAR captures point cloud data containing 3D coordinates and reflection intensity values. While sparse, non-uniform, and disordered, its high measurement accuracy and strong anti-interference capabilities make it a key sensor for landing terrain perception. Based on a review of recent research results from related teams, this study designed and implemented a comprehensive technical solution: First, raw point cloud data is acquired via the UDP protocol combined with an SDK interface. Preprocessing is then performed using voxel grid filtering (downsampling) and radius filtering (denoising). The assessment area is then divided into a row-by-column grid. A sliding window method is used to calculate the elevation difference, empty grid ratio, flatness, and slope of each grid. Based on these attributes, the grids are classified into six categories: Risk, Warning, Blank, Unknown, No Landing, and Landing. Finally, a grid attribute coloring method and OpenGL 3D rendering are used to generate the visual scene. Through the development of verification programs and moving obstacle experiments, it has been proven that the solution can efficiently process point cloud data and accurately identify safe landing areas, providing key technical support for the engineering realization of the autonomous landing function of drones, and also laying the foundation for the intelligent development of drone landing decisions in complex environments.
Guo, HangyuShi, Zhe
A comprehensive solution integrating advanced sensor technology, structural dynamics models, and intelligent control algorithms is proposed to address the shortcomings of traditional flight testing techniques in monitoring and controlling aircraft structures under complex flight conditions. By establishing precise aircraft structural dynamic equations through fiber optic sensors, an accurate description of the dynamic characteristics of the aircraft structure can be achieved. A distributed structural monitoring system is constructed through FBG to monitor the physical quantities, such as strain and temperature, of key parts of the aircraft in real time during flight testing. Based on the real-time monitoring data, the structural state of the aircraft can be predicted, and the structural response can be actively adjusted by controlling the actuator. The experimental results show that this technology system effectively improves the accuracy of structural monitoring and the effectiveness of control during aircraft flight testing, providing strong guarantees for the safety and reliability of aircraft flight testing, and laying a solid foundation for aircraft structural design optimization and flight performance improvement.
Gao, Sheng
This paper presents an innovative study in exploring, evaluating, and implementing deep-learning architectures for the calibration of multimodal sensor systems. The aim of this paper is to leverage the use of sensor fusion to achieve dynamic, real-time alignment between 3D LiDAR and 2D camera sensors. Static calibration methods are tedious and time-consuming, which is why we propose utilizing conventional neural networks (CNNs) coupled with geometrically informed learning to solve this issue. We leverage the foundational principles of extrinsic LiDAR–camera calibration tools such as RegNet, CalibNet, and LCCNet by exploring open-source models that are available online and compare our results with their corresponding research papers. Requirements for extracting these visual and measurable outputs involved tweaking source code, fine-tuning, training, validation, and testing of each of these frameworks for equal comparisons. This approach aims to investigate which of these advanced networks produces the most accurate and consistent predictions. Through a series of experiments, we reveal some of their shortcomings and areas for potential improvements. We find that LCCNet yields the best results among all the models that we validated.
Karramreddy, Venkat Sai RaxitMitchell, Liam
With the rapid development of China’s civil aviation industry, the problem of airport noise has attracted widespread social attention. The requirement for the real-time monitoring and evaluation of acoustic environment around airports is becoming more and more intense. The identification of aircraft noise events in the complex acoustic environment surrounding the airport is the most critical technical problem in airport noise monitoring. However, the traditional noise source identification technology is difficult to be widely used in real-time monitoring system due to its large errors and complex deployment conditions. This paper presented an aircraft noise source identification technique based on a single acoustic vector sensor. The azimuth parameters of the noise source were estimated by the three-dimensional spatial positioning algorithm of sound pressure and particle vibration velocity combined with information processing, and the three-dimensional footprint of the noise event in the complex acoustic environment was described. Finally, the event was judged as an aircraft noise event by matching the noise footprint with the aircraft flight path. By monitored and analyzed the actual noise events of aircraft departure, the results show that this method can only use a single acoustic vector sensor to locate the aircraft noise source and distinguish the aircraft noise event from the background noise event, which provide a new lightweight method for the real-time airport noise monitoring system to locate the noise source and identify the aircraft noise event
Hou, JiayuHe, TianlunZhu, LinChen, YingLiu, YinhuiLv, LeiWang, YuhaoChen, Da
This paper puts forward a Privacy-Preserving UAV-Based Traffic Data Acquisition Platform to address 1) privacy leakage, 2) limited scenario coverage, and 3) low traffic data utilization efficiency in urban traffic monitoring environments. Our system integrates three innovations: 1) Dynamic Privacy Masking (DPM) and Dual-Track acquisition (DTC), which hides sensitive information (e.g., faces, license plates or LPL) in real-time while preserving critical traffic data (e.g., vehicle density, speed), 2) traffic data Localization (DL) and Privacy-Enhanced Federated Learning (FEFL), enabling cross-regional collaboration without raw traffic data sharing by perturbing neural network updates with differential privacy (DP), and 3) Ground-Air Collaboration (GAC) and VPF (VPF), combining UAVs with ground sensors and digital twins (DTs) to cover blind spots (e.g., tunnels, extreme weather). Experimented on UA-DETRAC and CitySim traffic data-sets, the platform achieves 92% privacy compliance (GDPR/PIPL), 87.5% mAP accuracy, and 85% road network coverage, outperforming other methods (e.g., FedUAV, static blurring). It supports applications such as traffic flow optimization, accident prevention, and regulatory alignment.
Zhang, ShilinYan, Ming
Hemisphere resonant gyroscope (HRG) is a new type of vibration gyroscope with high precision, high reliability, and long lifespan. Improving the temperature stability of a hemispherical resonant gyroscope (HRG) has profound implications for navigation and guidance systems as well as airborne sensor technology. By optimizing temperature compensation algorithms or improving material thermal properties, the angular velocity measurement error caused by temperature drift can be significantly reduced, thereby improving the long-term positioning reliability of navigation systems in extreme temperature fluctuation scenarios. This article starts with the structure of the hemispherical resonant gyroscope, studies the temperature characteristics of the hemispherical resonator through formula theory, verifies and analyzes the temperature characteristics of the hemispherical resonant gyroscope through experiments, and designs a temperature compensation scheme. Through experimental data analysis, the root mean square error of hemispherical gyroscope drift was reduced from 1.451066 ° /h to 0.383937 ° /h after temperature compensation. This compensation scheme can effectively improve the output accuracy of the hemispherical resonant gyroscope and reduce the output drift under the condition of gyroscope temperature changes.
Wang, JiachenChen, PuYao, ZhiqiangZhang, YiBai, Fan
The collection of road high-frequency data often involves inputs from multiple sensors, such as stress and strain, and sampling of these data features a high sampling rate of up to 2,000 Hz. High-frequency sampling enables capturing of the internal stress and strain of the pavements when vehicles are passing and facilitates the analysis of the pavement structure and prediction of its long-term service performance. However, while the sensors are continuously collecting data, the time the vehicles pass is discrete and unpredictable, resulting in a large number of low information density or irrelevant data. Even when the massive high-frequency data are collected, challenges remain in data transmission, storage, and analysis—the challenges are attributable not only to the massive quantity and complexity of data from multiple sensors, but also to the inconsistent data formats, misaligned timestamps, and multi-sensor data fusion difficulties. In response to the challenges specified above, a new approach combining traditional road observation data with deep learning models is proposed here to efficiently process and analyze massive sensor data. This method not only improves the data processing efficiency but also provides new insights into innovation of road engineering technologies.
Gang, JianZhang, YueChen, YinghaoZheng, XiaoyanWang, TaojieLiu, YilinGuan, WeiWu, Jiangfeng
This study investigates the feasibility of identifying individual e-bike riders based on CAN data using machine learning techniques. Datasets from 12 test riders performing various predefined cycling tasks on a dynamometer test bench are collected and used to ensure controlled and reproducible conditions. The recorded CAN data includes various sensor signals, such as power output, cadence, torque, and the used support mode. After pre-processing, two different methods of feature extraction are tested and compared, one based on snapshots of the data and one based on driving events such as braking and accelerating, measured by calculating statistics of the riding data over sliding windows. A range of machine learning models is employed to classify riders based on their distinct riding patterns using the extracted features. The evaluated models comprise KNN, Random Forest and Naïve Bayes. The findings demonstrate the efficacy of machine learning in differentiating riders, with Random Forest and KNN achieving the highest and most robust accuracy among the tested models. The KNN-model achieves up to 99% accuracy, the Random Forest up to 75%. The paper analyzes the influence of different signals, feature extraction methods and model parameterizations on the results. The results show that machine learning-based rider identification using CAN data is a viable approach for enhancing e-bike security, authentication, and personalization. Potential applications include theft prevention, automatic user recognition for personalized assistance settings, and access control. Future research could include the exploration of the impact of additional sensor data, real-world outdoor conditions, and deep learning approaches, with the aim to further enhance identification accuracy and efficiency.
Simmann, GabrielRauch, YannickBeißert, FlorianKriesten, Reiner
The detection of free space plays a fundamental role in ensuring the safe and efficient operation of heavy-duty vehicles, particularly in environments where the available area to maneuver is severely constrained, such as construction zones, rest areas, or loading docks. An accurate estimation of free space is essential to prevent collisions, maintaining operational continuity and minimizing vehicle downtime. As observed from the reviewed literature, despite the large number of proposed free-space detection methods, there is no concise and established definition about how free space should be determined, represented, and inferred, nor agreement on the semantic classes to be considered. This heterogeneity complicates systematic comparison and benchmarking across approaches. This paper presents a structured survey and methodological analysis of recent free-space detection and semantic segmentation approaches across automotive LiDAR-, camera-, and radar-based perception systems, as well as multimodal sensor fusion. The review spans classical geometric and occupancy-based techniques together with deep-learning methods, along with datasets commonly used for evaluation. The main contributions are (i) a structured taxonomy and comparative analysis of existing free-space definitions and detection strategies, categorized by their assumptions, representation forms, and sensing modalities; and (ii) a unified and application-independent definition of free space together with the required semantic classes. These contributions aim to provide a consistent conceptual foundation to support future research and to aid the systematic evaluation of upcoming free-space detection systems.
Martinez, CristianPeters, Steven
The UMV Peoplemover 2+2 is part of a modular vehicle family (Urban Modular Vehicle) that includes derivatives for passenger and cargo transport in urban environments. The platform supports automated movers as well as conventionally controlled vehicles with a human driver, ensuring high flexibility across applications. The modular platform enables the extensive use of common parts, allowing the efficient and cost-effective realization of multiple vehicle variants. The increased share of common parts also improves sustainability by reducing derivative-specific parts, material usage, and production complexity. A drivable demonstrator of the UMV Peoplemover 2+2 has already been realized. The vehicle is designed for the automated transport of up to four occupants in a 2+2 vis-à-vis seating arrangement and is targeted at demand-oriented shuttle services. While the drivable demonstrator validated the proof of concept, it lacked the core Level 4 hardware and software stack for automated driving functions. To address this limitation, we deployed a software-defined vehicle architecture to the concept. This paper introduces the novel e/e-architecture and software stack enabling the Peoplemover 2+2 to initiate its first shuttle service at the German Aerospace Center (DLR e.V.) in Stuttgart. We further detail the deployed multi-modal sensor suite, comprising modern solid-state LiDARs and a 4D imaging radar, which were carefully selected to meet the operational design domain requirements while also serving as a versatile research platform for future advanced perception studies. Finally, we analyze the SDV-based modular software stack, which facilitates rapid application development through straightforward switching between commercial, open-source, and in-house software domains, and supports parallel execution of domain-specific functions across all three software sources.
Pohl, EricSchmid, FabianMünster, MarcoSiefkes, TjarkStuebler, TillmannMohammed, Shawan
This paper investigates the integration of Artificial Intelligence (AI) within radar-based perception for Advanced Driver Assistance Systems (ADAS) under safety considerations aligned with ISO 26262 [1] for functional safety and ISO 21448 (SOTIF) [2] for performance-related safety of the intended functionality. The study evaluates a hybrid architecture in which AI-based perception modules are combined with deterministic supervisory mechanisms to maintain safety compliance. A simulation-based case study using CARLA with radar sensor modeling is presented to compare a deterministic radar perception pipeline with an AI-enhanced approach under nominal and degraded environmental conditions. Performance is evaluated using precision, recall, and F1 score metrics. Results indicate improved recall and F1 score under adverse scenarios for the AI-based perception module, accompanied by a moderate increase in false positives. The paper discusses architectural constraints required to limit non-deterministic behavior, including confidence gating, deterministic supervision, and scenario-based validation. The findings are limited to simulation and are intended to provide preliminary insights into the technical and safety implications of incorporating AI-based radar perception within ISO 26262-compliant ADAS architectures.
Jain, Yesha
Ultrasonic sensors are widely deployed in automotive driver assistance systems for near-range environment perception and provide safety-relevant inputs for functions such as parking assistance and automated parking. With increasing vehicle automation, the integrity and availability of ultrasonic sensor data become more critical, as compromised measurements may lead to incorrect vehicle decisions and hazardous behavior. While prior research has extensively studied physical attacks on ultrasonic sensors, a structured cybersecurity risk analysis in accordance with automotive cybersecurity standards, combined with experimental validation, is largely missing. In particular, the communication interface between ultrasonic sensors and control units has received limited attention despite its relevance as a potential attack surface. This paper presents a systematic security analysis of an automotive ultrasonic sensing system based on a demonstrator setup. The work applies a Threat Analysis and Risk Assessment methodology aligned with ISO/SAE 21434 and HEAVENS 2.0 to identify security-relevant assets, threat scenarios, and attack paths. Risk levels are derived by evaluating potential impact and attack feasibility. To validate the risk assessment, a structured test strategy is developed using the ISTQB test process and translated into laboratory experiments. Both digital attacks targeting the sensor communication interface, with DSI3 selected as the representative protocol, and physical manipulations of the sensor environment are examined. Experimental results show that selected communication-level attacks can be realized with moderate effort and can cause controlled falsification or loss of measurement data. Physical environmental manipulations significantly degrade signal quality but do not fully suppress object detection in the evaluated configuration. The findings largely confirm the initial risk assessment while enabling refinement of attack feasibility parameters. The results provide a validated linkage between automotive cyber-security risk assessment methods and practical testing of ultrasonic sensing systems and underline the importance of jointly addressing communication interfaces and physical effects in future security concept development.
Gahm, SebastianHaller, JonathanKriesten, Reiner
Level-3 and higher automated driving systems require longitudinal speed strategies that remain consistent with both physical stopping feasibility and realistic sensing constraints. This paper presents a route-based, sensor-aware speed planning method that supports safety validation and explicitly couples longitudinal driving strategy with sensor field-of-view coverage. Based on a concrete route extracted from digital maps and enriched with fleet data, point-wise maximum speeds are computed considering road curvature, speed limits, and comfort constraints. From the resulting drivable speed profile, physically consistent stopping paths and their endpoints are calculated for each route position, accounting for friction limits, scenario-dependent deceleration capabilities, and system delays between perception and braking. The set of stopping paths is aggregated into a region of interest (ROI) representing the spatial area that must be reliably perceived to guarantee safe stopping. This ROI is overlaid with the geometric fields of view of camera, radar, and lidar sensors, enabling the definition of a compact and interpretable key performance indicator (KPI) based on the number of sensor modalities covering critical regions. Rather than evaluating a specific sensor configuration, the proposed KPI establishes a geometric interface between braking-based perception requirements and multi-modal sensing coverage. The approach reveals the structural sensitivity of perception demands to route geometry and braking assumptions and provides a systematic basis for perception-aware speed release decisions. The method is applicable to highways, interchanges, and other route types, and contributes a modular geometric framework for sensor-aware safety analysis in Level-3 and higher automated driving systems.
Kohler, Paul LeonhardResch, Michael
Trajectory tracking control and vehicle state estimation are core functionalities of highly automated vehicles and must operate reliably under strict real-time constraints as well as in the presence of model uncertainties and limited sensor availability. This paper presents an integrated, real-time capable framework for trajectory tracking control and vehicle state estimation, developed within the UShift II research project and implemented on the highly automated vehicle platform. The framework combines nonlinear model predictive control (NMPC) for trajectory tracking with an extended Kalman filter (EKF) for multi-sensor state estimation within a modular system architecture. The NMPC is based on a vehicle model designed for low-speed automated driving maneuvers and explicitly accounts for actuator constraints. Trajectories are tracked based on local planned reference trajectories while ensuring smooth and physically feasible control inputs for underlying control. The EKF fuses measurements from global navigation satellite system (GNSS), inertial sensors, and wheel-speed-based odometry, providing consistent estimates of the vehicle states under varying sensor availability. Particular emphasis is placed on robustness and computational efficiency in order to meet the real-time execution requirements on the target hardware. The complete framework is implemented on automotive-grade real-time hardware and validated on the U-Shift II vehicle platform. Experimental results demonstrate reliable localization performance, smooth and accurate trajectory tracking, and deterministic real-time execution, confirming the suitability of the proposed approach for practical low-speed automated driving applications.
Fuchs, SörenNeubeck, JensWagner, Andreas
The aim of this work is to develop a modular, real-time-capable digital twin of an electric powertrain based on machine learning (ML)-based model structures and a systematic, component-oriented architecture with a focus on efficiency estimation in test bench environments. The further goal here is to enable virtual testing, which can be used for frontloading and thus both prevent errors and increase the speed of product development. Based on a comprehensive set of measured and derived test bench data, a multi-stage procedure is implemented that integrates data acquisition, physically informed feature selection, modeling at the component and subsystem level, and hybrid coupling strategies. The digital twin captures inverter, electric machine, and mechanical transmission stages and generates consistent predictions of key variables such as torque, speed, power factors, and subsystem as well as overall drivetrain efficiency. The methodology enables a systematic comparison of black box, dark grey box, grey box, and bright grey box architectures with respect to prediction accuracy, information content, and real-time capability. The methodology provided uses new model structures that explicitly integrate physical dependencies while also using ML models to map nonlinear effects. The hybrid architectures presented have been shown to significantly reduce the measurement effort while achieving nearly identical model quality and surpassing purely physics-based models in terms of accuracy, robustness, and real-time capability. For the final bright grey-box architecture, average relative efficiency errors below 1 % are achieved while maintaining real-time execution rates. The study shows that bright grey box-models in particular offer a best-case compromise between the requirements of information content, error quality, and synchronization rate, thus representing a methodological advance over conventional digital twins, which are often created at the component level. The shown methodology provides an implementable framework for digital twins of electric powertrains in industrial test environments.
Kopp, LennartProksch, DanielOckert, NielsKarthaus, CarstenKley, Markus
Sound source localization is a fundamental capability for environmental awareness in a wide range of applications, including automotive or automated vehicles. Microphone-array-based signal processing techniques are widely used for this task. However, achieving sufficient localization accuracy often requires a large number of microphones and wide array apertures, which can be incompatible with limited installation space and cost constraints. Moreover, standard array-processing methods often rely on free-field transfer functions. In environments with reflections, diffraction, and scattering, particularly under non-line-of-sight conditions, this mismatch can degrade both accuracy and interpretability. This paper presents a methodology for sound source localization in partially known environments that addresses these challenges by combining two ideas. First, the method reduces sensor requirements by exploiting sequential pressure measurements acquired at different spatial locations along a moving receiver trajectory. Second, environmental effects are incorporated through an approximate acoustic model derived from rough geometric cues assumed to be retrievable from visual sensing modalities. Geometric and acoustic parameters are treated as unknowns and estimated jointly with the source location, reducing the need for precise prior environmental knowledge. Numerical simulations validate the approach in two representative scenarios: (i) a single source in the presence of a wall with unknown absorbing properties and unknown distance, and (ii) a T-junction configuration where the source is not in direct line of sight. The case studies establish proof-of-concept feasibility and highlight the potential of jointly leveraging single or dual sequential measurements and approximate environmental information while maintaining low modeling and computational complexity.
Pirro, Giovanni BattistaNijman, EugeneDeckers, ElkeDenayer, Hervé
Gyroscopic effects split circumferential traveling-wave resonances of rotating structures into forward and backward branches. This work first analyzes the splitting in the co-rotating (Lagrangian) frame to provide physical intuition for the evolution of the two branches with spin speed. A transformation to the inertial (Eulerian) frame is then derived, showing that the observed frequencies are shifted by a kinematic Doppler-like term that acts with opposite sign on the forward and backward waves, leading to different Campbell-diagram slopes depending on the observation frame. The resulting framework is validated experimentally on a freely rotating, unloaded tire using two complementary sensing modalities: wireless on-tire accelerometers (co-rotating view) and a scanning laser Doppler vibrometer (inertial view). A frequency-domain SVD-based identification (FDD/ODS-SVD) is used to extract poles and deformation patterns over a range of spin speeds, enabling Campbell diagrams in both frames. The application of the proposed transformation maps the co-rotating branches onto the inertial observations, yielding consistent forward/backward splitting between the two measurement systems.
del Fresno Zarza, JavierNaets, Frank
Neural Network Enabled Synthetic Air Data System: Development and Validation2026-26-07206/1/2026
Synthetic Air Data System (SADS) provides a smart solution that can be used to predict critical air data parameters in the absence of conventional air data sensors. Traditional air data sensors, such as pitot-static tubes and vanes, are generally expensive, require regular maintenance, and can fail in harsh weather conditions. In addition, these sensors, along with their processor and computers, add weight to the aircraft. To address these issues, a synthetic air data system is proposed using a Recurrent Neural Network (RNN). Several flight variables were checked for Pearson correlation coefficient with respect to the angle-of-attack and angle-of-sideslip, and thereafter, input features were selected based on the thresholding technique. The proposed neural network has two hidden layers and regularization technique was implemented by adding two dropout layers to each hidden layer to prevent overfitting of the model. The neural network was trained using actual flight test data, supplemented with simulated data wherever gaps were observed in the entire flight envelope. The RNN model is trained to predict the aerodynamic flow angles, viz., angle-of-attack and angle-of-sideslip. The proposed model was found to be able to predict the aerodynamic angles with a degree of accuracy. The accuracy was also checked with several complementary actual flight data to check the fidelity of the trained neural network model.
Sahu, SanjuC, PoornimaKaliyari, DushyantTK, Khadeeja NusrathHebbar, Archana
Modern aircraft depend on extensive electrical wiring networks for power distribution, avionics, and control systems; however, these wiring systems are vulnerable to wear, insulation degradation, and arcing over time, leading to safety risks and costly unscheduled maintenance. This paper introduces an advanced Electric Health-Monitoring Wiring (E-Wiring) system that integrates temperature, current, insulation, vibration, and environmental sensors directly into aircraft wiring harnesses to enable continuous monitoring and intelligent fault detection. Data from these embedded sensors are processed through a distributed edge AI network, forming an Electrical Health Monitoring System (EHMS) capable of real-time diagnostics, predictive maintenance, and fault localization. The architecture comprises smart cable segments with sensor nodes, local harness gateways for edge processing, aircraft-level EHMS integration via AFDX/Ethernet, and cockpit or maintenance displays linked to ground-based cloud analytics for fleet-wide insights. We have an existing method to detect by using acoustic sensing method which can detect ongoing insulation chafing or a cut, they are limited in identifying pre-existing damages and by adding multiple acoustics in the existing wire harnesses it’ll add extra load to the aircraft. To overcome this, the system incorporates Time Domain Reflectometry (TDR) technology to detect both existing and potential wiring faults. The TDR circuitry interfaces with onboard devices, injecting test signals into wiring to pinpoint insulation anomalies or conductor breaks without adding significant weight or complexity. The proposed E-Wiring and EHMS solution enhances aircraft safety, reduces maintenance costs, and improves operational availability, offering a scalable approach for both retrofit and new-generation aircraft.
Tammana, Bala Sai Sri RohitMurthy, HarshaMendu, HarikaSivaniSunandha
Passenger comfort within vehicles and aerospace cabins relies on finely tuned management of temperature, air quality, and energy use. This paper proposes an integrated HVAC framework that combines zonal climate control, intelligent airflow distribution, and real-time sensor data to maintain thermal balance across different cabin zones. Leveraging predictive thermal load modelling and machine learning, the system anticipates environmental changes—such as sudden shifts in external temperature or passenger load—and proactively adjusts heating and cooling outputs. Simultaneously, air quality is enhanced through a multistage filtration system, active air purification technologies, and dynamic CO₂ concentration monitoring. Comfort assessment integrates PMV (Predicted Mean Vote) and PPD (Predicted Percentage Dissatisfied) indices to adapting environmental conditions. Simulations and early-stage prototypes improve energy savings and improve occupant comfort and air quality. The proposed HVAC approach is a promising avenue for enhancing passenger experience and operational efficiency in both ground and air mobility platforms.
Mudavath, Lehitha SaiPatil, AshishSaha, Sudipta
This novel method deals with emulation of Strain of a Structural Measurement System which includes software validation, acceptance tests and training. Current methods for simulating strain and force data for developing and verifying data acquisition (DAQ) software typically rely on costly electronic simulators or specialized hardware, making it challenging and expensive for developers, researchers, and small organizations to test their solutions under realistic conditions. To verify DAQ software, multiple specialized hardware solutions are deployed, that include Electronic Simulators, Commercial DAQ Modules and Hydraulic/Pneumatic test rigs. These technologies pose a challenge with limited flexibility and scalability options for small-scale prototyping, especially in budget-constrained scenarios. The sensors on these equipment may or may not be company approved inducing acceptance challenges. Our invention is an inexpensive, scalable, and mechanically simple alternative. Using a 3D-printed structure combined with standard cantilever load cells and easily accessible weights, it enables realistic and customizable strain simulations without the need for expensive electronic simulation equipment. All platforms namely NI based, Dewesoft, VTI and others can be integrated into a unified test framework in this method which otherwise needs to be simulated on suitable equipment individually.
Murthy, HarshaBhat Venkatesh, AditiK Padmanabhan, RahulMadhu, SheetalGarag, Naveen
Emergency evacuation slides (EVAC slides) are critical safety devices used on aircraft to enable rapid egress during emergencies. While these slides provide a quick and reliable escape route, communication between separated slides during evacuation remains a challenge. Often, during raft deployment over water, slides may drift apart impeding communication among evacuees and rescue personnel potentially compromising safety. Existing aircraft EVAC systems lack integrated wireless communication relying on visual or voice signals that are unreliable in chaotic conditions. This paper explores the integration of wireless IoT technology into EVAC slide systems to facilitate inter-slide communication and monitor critical parameters such as slide air pressure and the floating weight of stranded passengers through embedded sensors. It proposes the adoption of Long Range (LoRa) modulation technology for wireless communication chosen for its low-power, long-range performance and license-free operation in emergency evacuation scenarios. In addition, the usage of this proposed technology can be further extended to locate the aircraft when other existing locating mechanisms fail.
Sengodan, RajkumarTalore, Suresh
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.
Clonts, Chris
Researchers at the University of California, Irvine, and New York’s Columbia University have embedded transistors in a soft, conformable material to create a biocompatible sensor implant that monitors neurological functions through successive phases of a patient’s development.
Using an inexpensive electrode coated with DNA, MIT researchers have designed disposable diagnostics that could be adapted to detect a variety of diseases, including cancer or infectious diseases such as influenza and HIV.
Robot Arm Tracking Control refers to the control of robot end effectors following a prescribed trajectory as their movement in robotic systems. The work presents a combination of Kalman Filter Based Dynamic System Tracking with Reinforcement Learning Based Trajectory Planning. These two aspects of tracking and planning help the robotic manipulator dynamically track a target that is located on an arbitrary moving path. In particular, by using Kalman filtering to estimate the position of a moving target and to compensate for sensor noise and sparse sampling, we take high-precision estimation values of each point’s coordinates along the target trajectory as a reliable basis to build a policy network using reinforcement learning. Based on it, the robot manipulator could produce effective motion planning under its own dynamic capabilities and physical constraint limit. Comprehensive simulation results illustrate advantages of the new algorithm against the classical control method, confirm that the novel technique achieves better performance both in accuracy and computation efficiency. Also, this mixed control system can deal with complex moving path for track target object. Even when meet different obstacle and not sure measurement, it still works well with other moving obstacle in many conditions. This can be strong to face other dynamic obstacle even if have different situation with changing obstacle and uncertain data. It shows that this paper works as an attempt toward optimal solution to combine the model-based technique together with data-driven approach aiming to support real-time, highly accurate, adaptive prediction is based control technique, promising applications into industry and promoting more improved works related.
Yu, JingzeWang, YujiaLi, JunshenChen, CongXu, Peng
End-to-end autonomous driving in urban environments faces three core challenges. First, camera and LiDAR sensor heterogeneity causes cross-modal perception inconsistencies and sensor fusion instability. Second, diffusion models suffer from training instability due to scale variance and distribution changes, which limits generalization. Third, traditional trajectory decoders lack structured interaction with semantic elements, thereby undermining planning rationality. To address these issues, CMFPNet introduces an integrated framework with three key modules. The HGCF-Backbone integrates LiDAR and camera features using channel focus, deformable cross-focus, and state space modeling to enhance semantic alignment. The NST module maps physical trajectories to normalized space, employing truncated diffusion sampling for stable generation in just 2–4 steps. The NDA models trajectory generation as a semantic narrative, utilizing a six-stage semantic attention flow incorporating BEV context, interactive dynamics, and self-states. Experiments on the NAVSIM dataset demonstrate CMFP Net’s superiority over existing baselines, showing outstanding generalization and trajectory stability in challenging scenarios. Notably, the truncated sampling strategy achieves an 8–10× acceleration during inference while maintaining decision accuracy and reducing computational costs. CMFPNet provides a scalable, semantically consistent solution for diffusion-based autonomous driving with significant potential in both research and practical deployment.
Qu, YanweiMo, Hangjie
In response to the problems of urban traffic congestion and the limited expansion of infrastructure, this paper conducts two core research focusing on the intelligent chassis system of split-type flying vehicle. Firstly, an autonomous navigation strategy for the intelligent chassis module is proposed based on chassis module Navigation 2 architecture, which fuses LIDAR and IMU positioning to plan paths using the A* global planning algorithm on a global cost map, and update the local cost map in real time with sensor data. It is orchestrated by the BT Navigator using a behavior tree, with failures handled by the Recovery Server, to achieve autonomous driving across multiple waypoints. In simulation and closed-field experiments, the system can stably reach the preset target points. The positioning accuracy and trajectory tracking performance can meet the design requirements. Secondly, a mechanical slide rail-type docking structure adapted to the split flying vehicle architecture is designed. Deformation analysis under the representative working conditions are evaluated through finite element software. The test results show that the maximum deformation of this docking structure under typical load is significantly lower than the docking tolerance and positioning repeatability requirements. The structural stiffness and stability meet the design indicators. The above work indicates that the proposed autonomous navigation strategy and the docking structure for the intelligent chassis can effectively support the modular operation of “air trunk & ground terminal” mode, providing a scientific basis for the functional integration and system reliability research of split-type flying vehicles.
Zhao, WenyuShi, QinJiang, CongHe, Zejia
The analysis of wear particles within machinery lubricants constitutes a critical methodology for assessing equipment health and enabling the early identification of potential failures. However, conventional inductive abrasive particle sensors typically exhibit lower detection sensitivity compared to other sensing technologies, limiting their practical application in precision condition monitoring. To address this limitation, this paper introduces an inductive abrasive particle sensor with enhanced sensitivity and throughput, employing rectangular coils, together with a custom-designed signal conditioning circuit. The sensor features two symmetrically arranged rectangular excitation coils and two symmetrically arranged rectangular sensing coils, with their respective axes mutually perpendicular. This unique spatial configuration not only ensures strong magnetic field intensity within the detection region but also significantly enhances magnetic field utilization efficiency. The sensing coils are connected in a differential output configuration to improve the common-mode rejection ratio, thereby enhancing the sensor's immunity to environmental interference. Furthermore, a specifically designed compensation circuit effectively counteracts the inherent unbalanced output of the probe, ensuring stable sensor operation. Subsequent the signal conditioning circuit successfully extracts weak particle signals from the sensor output while effectively suppressing noise interference and improving the signal-to-noise ratio. This paper also develops a comprehensive mathematical model for the proposed sensor, providing theoretical validation of the structural superiority. Experimental results reveal that the sensor can reliably detect ferromagnetic particles as small as 130 μm and non-ferromagnetic particles as small as 184 μm within a flow conduit of 7.2 mm equivalent diameter, maintaining high sensitivity while providing substantial flow throughput of 4.88 L/min.
Jiang, ZiyangQian, MinHuang, HonglianLu, YanluZhang, JunjianPan, Chengliang
If wear particles generated during the operation of automobile engines are not monitored in time, they will contaminate the lubricating oil, leading to system failures or even accidents. Therefore, real-time wear particle monitoring is crucial for the stable operation of engines. Among mainstream wear particle monitoring sensors, the three-coil inductive sensor demonstrates significant application potential due to its ability to distinguish wear particle materials and strong resistance to environmental interference. However, its insufficient sensitivity to small-diameter wear particles limits further performance improvement. This paper takes the three-coil inductive wear particle monitoring sensor as the research object. First, a mathematical model of the sensor’s operation is established based on the law of electromagnetic induction, clarifying the relationship between structural parameters (such as channel radius, turns, coil spacing, and length) and the peak induced voltage. Subsequently, Multiphysics simulation software is employed to quantitatively analyze the influence of each structural parameter on the induced voltage, identifying directions for parameter optimization. Furthermore, orthogonal experiments are conducted to optimize discrete parameters, determining optimal levels for key parameters such as channel radius and coil spacing. Then, the simulated annealing algorithm is applied to achieve precise optimization of continuous parameters, ultimately obtaining the optimal combination of coil structural parameters. Experimental validation based on the optimized parameters shows that the peak-to-peak induced voltage for 1000 μm wear particles measured by the sensor optimized with the simulated annealing algorithm reaches 2.43 V, which is approximately 41 times higher than the 0.06 V observed before optimization. Additionally, the optimization effect of the simulated annealing algorithm further improves by 38.86% compared to the orthogonal experiment. In addition, experimental tests were also carried out on small-diameter abrasive particles of 100 μm, with the peak-to-peak value of the induced voltage reaching 0.38 V. The results confirm that this coil structural parameter optimization method effectively enhances the sensor’s sensitivity to small-diameter wear particles, providing a theoretical basis and technical support for the structural design and performance improvement of three-coil inductive wear particle monitoring sensors.
Yin, HaoZhao, LijunShen, Yitao
The outwash flow of a VTOL aircraft in near-ground operation is a serious risk for surrounding objects or personnel, and has been investigated for a long time. The current paper contributes to this topic by revisiting quantitative outwash measurement techniques and evaluation strategies suitable for full-scale flight experiments. An array of purpose-built ultrasonic anemometers, a pitot tube rake, and fiber-film sensors were applied during outwash tests with a hovering Eurocopter EC135, complemented by accompanying numerical simulations with the Vorticity Transport Model (VTM). A focus is set on an analysis of the flow unsteadiness, revealing large fluctuations at low frequencies which require careful data post-processing. The fluctuations limit the application of pitot tubes to measure the mean flow due to their angular sensitivity, and ultrasonic anemometers are recommended as a particularly suitable and convenient measurement method with a sufficient frequency response. Furthermore, the experimental and numerical results are compared to semi-empirical outwash models, and the importance of simultaneous measurements of the ambient wind conditions is demonstrated.
Wolf, Claus ChristianBrown, RichardGardner, Anthony DonaldWeise, Till SilasSchwalbe, JulienBraukmann, Johannes Niklas
The present work develops a computational framework for simulating the two-way coupled ship-helicopter dynamic interface using large-eddy simulation. The Simple Frigate Shape 2 geometry is modeled using the immersed boundary method, and baseline simulations under both uniform inflow and neutral atmospheric boundary layer (ABL) conditions are validated against wind tunnel measurements for two wind-over-deck angles. Rotor modeling techniques, including the actuator line model (ALM) and actuator disk model (ADM), are verified and validated across several configurations: the Knight and Hefner rotor, ONERA HAD-1 propeller, and NASA Dragonfly Phase B* coaxial rotor. The lower-fidelity ADM captures wake characteristics consistent with the ALM with up to a 9× speedup. The ADM maintains strong agreement with experimental and numerical results for integrated performance metrics and is suitable for two-way coupled simulations. The developed framework is applied to a rotor-obstacle configuration based on a GARTEUR 22 experimental survey and subsequently to a fully-coupled ship-rotor-ABL system.
Tyagi, DivyaSchmitz, Sven
This paper presents two distinct Lagrangian models developed for efficient rotorcraft inflow prediction: an Extended Vortex Ring Wake (EVRW) model and a Viscous Vortex Particle Method Actuator Disk (VVPM-AD). The EVRW model represents wake vorticity as circular rings with a harmonic distribution of bound circulation, thereby avoiding explicit coordinate-by-coordinate calculations. In contrast, the VVPM-AD discretizes shed vorticity into an independent Lagrangian particle cloud. This formulation naturally captures wake roll-up and viscous effects via a meshless Large Eddy Simulation solver, eliminating the need for empirical core-radius formulations. Validated against experimental data, these separate modeling tracks provide a scalable toolkit that balances computational speed with simulation fidelity.
Yurt, KursatAli, SaadYavrucuk, IlkaySubramaniam, Navarajah
In September 2025 a test was conducted at the NASA Ames Research Center's Outdoor Aerodynamics Research Facility to characterize the outwash flow from a hovering rotor. The studied configurations included variations in rotor height above the ground plane as well as variations in rotor speed, thrust, and trim state. Outwash flow was measured using a rake of hot-film anemometers mounted to a semi-autonomous instrumentation cart. Flow measurements were conducted for a single rotor azimuth at distances between 0.6 and 4.0 diameters from the rotor center. In addition to hot-film anemometry, additional flow data was captured using a Background Oriented Schlieren Velocimetry technique that provides a detailed measurement over time of flow velocity in an image plane upstream of the hot-film sensors. The downwash and outwash produced by a lifting rotor in the presence of a ground plane can pose significant risks to life and property in the area of operations. Rotor wake interactions exhibited by modern, multi-rotor aircraft designs can amplify these flows and increase the risk. The rotorcraft community is therefore motivated to better understand rotor downwash and outwash to establish safe operating limits in the vertiport environment.
Romander, EthanAnderson, AlynaYamauchi, GloriaSmith, NathanialDominguez, MichelleCummings, HaleySheikman, AlexGileadi, AvrahamKallstrom, KristenShirazi, DorsaRadotich, Michael
This study develops an efficient framework coupling the Lattice Boltzmann Method with the Actuator Line Method to evaluate the unsteady downwash/outwash of eVTOL aircraft. By incorporating a modified Prandtl loss function with geometric smearing correction, the framework accurately predicts velocity profiles and preserves unsteady vortices at lower computational costs than conventional RANS-based simulations. Analyzing three distinct eVTOL configurations sized for identical payload missions reveals that higher disk loading and multi-rotor interactions generate highly asymmetric, localized jet-like outwash structures, contrasting with the symmetric ground-level footprint of single rotor designs. Utilizing a 95th percentile velocity metric, transient peak hazards breach the regulated vertiport Safety Area boundary, extending up to 1.65 times the prescribed baseline limit. These findings demonstrate that time-averaged metrics underestimate physical hazards, highlighting the necessity for future guidelines to mandate configuration specific evaluations utilizing high-resolution unsteady flow data and robust statistical processing.
Lim, JuneyoungYee, Kwanjung
Full state feedback offers theoretically guaranteed multi-axis stability, making it superior to conventional PID controllers. There is however one drawback, a full state controller has a mathematical difficulty if the B matrix is not square and thus not invertible. This is the case for helicopters with 6 degrees of freedom and 4 inceptors. Variations of linear quadratic regulators are a work around, however complexity dramatically increases. Best would be a direct solution to the original problem. This is the breakthrough result of this paper. This paper documents an approach which removes the analysis roadblock by partitioning the 6 x 6 system "A" matrix into two groups of 4 x 4 matrices. The 4x4 matrices are individually stabilized with full state gain matrices. One matrix is designated “Driver Matrix” which provides actuator commands. The other matrix is designated "Reference Matrix" which provides references. The two matrices are coupled together by requiring that the driver matrix follow references generated by the reference matrix. With each matrix individually stabilized, the coupled combination is also stabilized. Computation of flight dynamics states (u, v, w, p, q, r) is shared between the matrices. Initial results are very encouraging, showing an originally sluggish, heavy lift helicopter having now concise decoupled responses to pitch and roll commands. Stability derivatives are recomputed during flight allowing coverage over the whole flight envelope. A handling qualities task has been defined to relocate a 40 ft standard seaborne container directed by a pilot in a ground control station. Cooper Harper ratings of this task have demonstrated favorable Level 1 handling qualities if use is made of an automated lateral repositioning command.
Mouritsen, StephenPiasecki, Fred
This paper introduces a robust supervised machine learning framework for estimating helicopter gross weight during the takeoff phase. The methodology leverages high-fidelity datasets from Airbus's global in-service fleet to ensure a reliable training foundation. At the core of the approach is a long short-term memory recurrent neural network, supported by a patented data-curation pipeline designed to maintain high data integrity. To align with rigorous aviation safety standards, the study outlines a learning assurance process compliant with EASA guidelines, specifically addressing safety assessment objectives for machine learning. A central innovation is the characterization and monitoring of the model's operational design domain through multidimensional functional principal component analysis. By projecting high-dimensional, non-linear sensor data into a manageable tabular subspace, this approach enables the definition of safety envelopes using explainable and efficient classical methods. Validated against diverse real-world flight profiles, the framework demonstrates high predictive accuracy, marking a significant milestone toward deploying the model on airborne targets for safety-critical functions such as condition-based maintenance.
Mechouche, AmmarFabre, LouisValot, Nicolas
Vehicle maneuver data are essential for perception and planning in advanced driver-assistance systems (ADAS) and automated driving systems (ADS). While high-quality annotations improve machine-learning performance, existing maneuver datasets remain fragmented, labor-intensive to annotate, and inconsistent in semantic richness. Challenges persist in scalability, interpretability, and contextual labeling. This article establishes a structured framework for maneuver data analysis by combining a systematic review of existing resources with the development of a new multimodal dataset. First, we conduct a systematic review of publicly available datasets such as HDD, KITTI, BDD-X, D2CAV, Brain4Cars, DrivingDojo, and the Driving Behavior Database. We further evaluate the data modality and sensor configurations including event data recorders, onboard logging systems, and smartphone sensing. We then propose the Matt3r Data Collection System with modern metadata management, which integrates video, GPS, and IMU signals into temporally coherent clips. Next, we outline the limitations of traditional annotation approaches, which rely on manual labeling and rule-based methods. To address the limitations of traditional manual and semi-automated labeling, we propose a Vision–Language Model (VLM)–driven annotation pipeline. VLMs generate maneuver categories and causal explanations through prompt-based reasoning, with selected outputs refined through human-in-the-loop verification. Finally, we propose an annotation quality evaluation based on accuracy, inter-annotator agreement, credibility, consistency, and efficiency gain. In summary, this article bridges the gap between the environment perception requirements of existing ADAS and ADS systems and the developing capabilities of generative artificial intelligence. By providing a novel and scalable research approach for AI-driven maneuver data annotation and analysis, this article supports data engineering efforts for both research and practical applications aimed at enhancing vehicle safety.
Bai, LingYuan, ChongyuOsman, IslamLin, ZiruiMirab, GhazalSaheb, AmirParnian, NedaShapiro, EvgenyShehata, Mohamed S.Liu, Zheng
This article surveys the most recent data-driven methods of lithium-ion (Li-ion) battery state of health (SOH) estimation methods and dataset resources utilized in electrified vehicles (EV) and their potential adoption for automotive battery management systems. These include regression-based models, ensemble learners, deep neural networks, and physics-informed hybrid methods. The review describes estimation methods found in articles published between 2023 and 2025, and investigates their differences in terms of estimation accuracy, data requirement, interpretability, and real-time deployment ability. The article traverses the dataset space, focusing on laboratory aging datasets, vehicle field–based datasets, telematics-derived records, and synthetic or augmented datasets, to underline that model performance in the estimation of SOH cannot be disentangled from the quality of the data, the operating coverage, and the transfer conditions. Apart from the model design, this work reviews the large-scale estimation pipeline, which involves preprocessing under sensor noise and irregular timestamps, feature extraction from incremental capacity, differential voltage, relaxation response and impedance-related indicators, and uncertainty handling for diagnostics and safety-based decision support. Practical constraints to the deployment of embedded BMS are covered. Such as ECU memory and computing limits, communication overhead, calibration effort, update approach, and functional-safety requirements. The review determines that the distance between laboratory validation and field robustness is large raising a need for more work in this area and also, that domain adaptation, federated learning, and improving benchmarking practice turn out to be promising directions for improving generalization and reproducibility. The article concludes that future advances in automotive SOH estimation will not only rely on better learning algorithms but also on improvement in the availability of realistic and field representative data, the application of robust evaluation mechanisms, and methods that are developed under real BMS constraints.
Nyachionjeka, KumbirayiBayoumi, Ehab H.E.
The emergence of AI-driven autonomy in modern vehicles marks a pivotal evolution in transportation, but it also introduces deep system-level vulnerabilities that span from sensor interface tampering to compute unit compromise and untrusted communication links. Autonomous vehicles (AVs) operate as distributed intelligent systems, relying on real-time data exchange between zonal gateways, AI compute platforms, and safety-critical electronic control units (ECUs). These interactions must be protected from hardware-based attacks that could compromise functional safety, system integrity, or operational availability. The deployment of AI-driven AVs introduces unprecedented levels of complexity. Sensors, AI compute clusters, and actuators communicate over multiple interfaces including Ethernet, PCIe, and MIPI, exposing vehicles to potential cybersecurity attacks. This paper proposes a unified, layered hardware security architecture tailored for AI-powered automated vehicles. Grounded in current automotive Ethernet and zonal architectures, it provides end-to-end trust using hardware interface security, accelerated- cryptography, and SRAM PUF-based key provisioning. All security primitives are anchored to hardware root of trust, delivering cryptographic identity, secure boot enforcement, and trusted key storage across the entire vehicle lifecycle.
C Suriyanarayanan, PavIacob, Radu
Items per page:
1 – 50 of 8250