Search Results (246)

This paper presents an electromagnetic levitation system that stabilizes a magnetic body using an array of electromagnets controlled by a Hall-effect sensor array and TinyML-based position detection. Departing from conventional optical tracking methods, the proposed design combines finite-element-optimized electromagnets with a microcontroller-optimized neural network that processes sensor data to predict the levitated object’s position with 0.0263–0.0381 mm mean absolute error. The system employs both quantized and full-precision implementations of a supervised multi-output regression model trained on spatially sampled data (40 × 40 × 15 mm volume at 5 mm intervals). Comprehensive benchmarking demonstrates stable operation at 850–1000 Hz control frequencies, matching optical systems’ performance while eliminating their cost and complexity. The integrated solution performs real-time position detection and current calculation entirely on-board, requiring no external tracking devices or high-performance computing. By achieving sub 30 μm accuracy with standard microcontrollers and minimal hardware, this work validates machine learning as a viable alternative to optical position detection in magnetic levitation systems, reducing implementation barriers for research and industrial applications. The complete system design, including electromagnetic array characterization, neural network architecture selection, and real-time implementation challenges, is presented alongside performance comparisons with conventional approaches. Full article

As the demand for high-speed space-borne data transmission grows, CubeSat-based Free-Space Optical Communication (FSOC) offers a viable solution for achieving a Gbps-speed optical intersatellite link on low-cost platforms. The Very-High-Speed Intersatellite Optical Link System Using an Infrared Optical Terminal and Nanosatellite (VISION) mission aims to establish these high-speed laser crosslinks, which require a precise pointing and relative positioning system at relative distances up to 1000 km. A real-time relative navigation system was developed based on dual-frequency GPS pseudorange and carrier-phase measurements, incorporating an adaptive Kalman filter which uses innovation-based covariance matching to dynamically adjust process noise covariance. Hardware-integrated testing with GPS signal generators and onboard receivers validated its performance under realistic conditions, consistently achieving sub-meter positioning accuracy across baselines up to 1000 km. An integrated orbit–attitude simulation further evaluated the feasibility of the Pointing, Acquisition, and Tracking (PAT) system by combining real-time relative navigation outputs with an attitude control system. Simulation results showed that the PAT system maintained a total pointing error of 274.3 μrad, sufficient to sustain stable high-speed optical links. This study demonstrates that the VISION relative navigation and pointing systems, integrated within the PAT framework, enable precise real-time optical intersatellite communication using CubeSats. Full article

The high operational velocities of high-speed trains present constraints on their onboard track intrusion detection systems for real-time capture and analysis, encompassing limited computational resources and motion image blurring. This emphasizes the critical necessity of track perimeter intrusion monitoring systems. Consequently, an intelligent monitoring system employing trackside cameras is constructed, integrating weakly supervised video anomaly detection and unsupervised foreground segmentation, which offers a solution for monitoring foreign objects on high-speed train tracks. To address the challenges of complex dataset annotation and unidentified target detection, weakly supervised learning detection is proposed to track foreign object intrusions based on video. The pretraining of Xception3D and the integration of multiple attention mechanisms have markedly enhanced the feature extraction capabilities. The Top-K sample selection alongside the amplitude score/feature loss function effectively discriminates abnormal from normal samples, incorporating time-smoothing constraints to ensure detection consistency across consecutive frames. Once abnormal video frames are identified, a multiscale variational autoencoder is proposed for the positioning of foreign objects. A downsampling/upsampling module is optimized to increase feature extraction efficiency. The pixel-level background weight distribution loss function is engineered to jointly balance background authenticity and noise resistance. Ultimately, the experimental results indicate that the video anomaly detection model achieved an AUC of 0.99 on the track anomaly detection dataset and processes 2 s video segments in 0.41 s. The proposed foreground segmentation algorithm achieved an F1 score of 0.9030 in the track anomaly dataset and 0.8375 on CDnet2014, with 91 Frames per Second, confirming its efficacy. Full article

This paper proposes a distributed model predictive control (DMPC) framework integrating an event-triggered mechanism and an adaptive alternating direction method of multipliers (ADMM) to address the challenges of constrained computational resources and stringent real-time requirements in distributed vehicle platoon control systems. Firstly, the longitudinal dynamic model and communication topology of the vehicle platoon are established. Secondly, under the DMPC framework, a controller integrating residual-based adaptive ADMM and an event-triggered mechanism is designed. The adaptive ADMM dynamically adjusts the penalty parameter by leveraging residual information, which significantly accelerates the solving of the quadratic programming (QP) subproblems of DMPC and ensures the real-time performance of the control system. In order to reduce unnecessary solver invocations, the event-triggered mechanism is employed. Finally, numerical simulations verify that the proposed control strategy significantly reduces both the computation time per optimization and the cumulative optimization instances throughout the process. The proposed approach effectively alleviates the computational burden on onboard resources and enhances the real-time performance of vehicle platoon control. Full article

BDS-3 faces challenges in achieving precision orbit determination (POD) due to the difficulty of establishing a globally uniform distribution of independently operated ground tracking stations. The use of onboard BDS-3 observations collected by low Earth orbit (LEO) satellites can partially mitigate this limitation. However, these observations introduce additional parameters, such as receiver clock offsets and carrier-phase ambiguities, which substantially increase the computational burden. Therefore, the capability of achieving real-time (RT) joint POD for BDS-3 and LEO satellites, relying solely on independently operated tracking stations, is greatly constrained. Currently, the inter-satellite links (ISLs) of BDS-3 have been successfully demonstrated to be effective for POD of BDS-3 satellites. In the future, ISLs of LEO satellites will also be incorporated as a measurement technique. Compared to traditional BDS-3 onboard observations, POD using ISLs involves almost no additional parameters other than the orbital states. Therefore, this paper proposes a method that combines onboard BDS-3 receivers on a subset of LEO satellites with LEO ISL observations to achieve rapid high-precision joint POD for BDS-3 and the full LEO constellation. To validate the proposed approach, measured BDS-3 data from regional ground stations in China are employed, together with simulated onboard BDS-3 data and simulated LEO ISL observations. All datasets were obtained over a three-day period, corresponding to days 131–133 of the year 2025. Firstly, it is demonstrated that, when relying solely on regional ground stations, the 24 MEO and 3 IGSO satellites of BDS-3 cannot achieve high-precision POD, with 1D RMS orbit accuracies of only 11.6 cm and 26.9 cm, respectively. Incorporating onboard BDS-3 data from LEO satellites significantly improves orbit determination accuracy, with 1D RMS accuracies reaching 4.9 cm for MEO and 6.4 cm for IGSO satellites, while LEO satellites themselves achieve orbit accuracy better than 5 cm. Subsequently, the computational burden introduced by onboard BDS-3 data from LEO satellites in joint POD is further assessed. On average, incorporating onboard BDS-3 data from 10 LEO satellites adds approximately 6780 parameters to be estimated, substantially increasing computation time. When onboard BDS-3 data from 20 LEO satellites are included, the achieved BDS-3 orbit accuracy shows negligible degradation compared to using data from all LEO satellites, with 1D RMS accuracies of 4.9 cm and 6.7 cm for MEO and IGSO, respectively. Meanwhile, the processing time for a single batch least squares (BLSQ) solution decreases dramatically from 27.0 min to 5.7 min. Increasing the number of LEO satellites to 30 further improves BDS-3 orbit accuracy, mainly due to the enhanced orbit precision of the LEO satellites. After incorporating LEO ISLs, LEO satellites achieve orbit accuracy in the 1D direction of approximately 1 cm, regardless of whether their onboard BDS-3 data are used. In summary, the proposed approach significantly reduces computational burden while ensuring orbit determination accuracy for both BDS-3 and LEO satellites. This approach is more likely to realize real-time joint POD of BDS-3 and LEO satellites based on large-scale LEO constellations. Full article

Autonomous ground vehicles (AGVs) are of major importance in exploration missions since they perform difficult tasks in changing or harmful environments. Mapping and exploration is crucial in hazardous areas, or areas inaccessible to humans, demanding autonomous navigation. This paper proposes a lightweight, low-cost AGV platform, which will be used in resource-constrained situations and aimed at scenarios like exploration missions (e.g., cave interiors, biohazard environments, or fire-stricken buildings) where there are serious security threats to humans. The proposed system relies on simple ultrasonic sensors when navigating and applied traversal algorithms (e.g., BFS, DFS, or $A^{*}$) during path planning. Since on-board microcomputers have limited memory, the traversal data and direction decisions are stored in a file located on an SD card, which supports long-term, energy-saving navigation and risk-free backtracking. A fish-eye camera set on a servo motor captures three photos ordered from left to right and stores them on the SD card for further off-line processing, integrating each frame into a low-frame-rate video. Moreover, when the battery level falls below 50%, the exploration path does not extend further and the AGV returns to the base station, thus combining a secure backtracking procedure with energy-efficient decisions. The resultant platform is low-cost, modular, and efficient at augmenting; thus it is suitable for exploring missions with applications in search and rescue, educational robotics, and real-time applications in low-infrastructure environments. Full article

Unmanned Aerial Vehicles (UAVs) integrated with lightweight deep learning models represent an effective solution for image-based rapid post-earthquake damage assessment. UAVs, equipped with cameras, capture high-resolution aerial imagery of disaster-stricken areas, providing essential data for evaluating structural damage. When paired with light eight Convolutional Neural Network (CNN) models, these UAVs can process the captured images onboard, enabling real-time, accurate damage level predictions that might with potential interest to orient efficiently the efforts of the Search and Rescue (SAR) teams. This study investigates the use of the MobileNetV3-Small lightweight CNN model for real-time post-earthquake damage level prediction using UAV-captured imagery. The model is trained to classify three levels of post-earthquake damage, ranging from no damage to severe damage. Experimental results show that the adapted MobileNetV3-Small model achieves the lowest FLOPs, with a significant reduction of 58.8% compared to the ShuffleNetv2 model. Fine-tuning the last five layers resulted in a slight increase of approximately 0.2% in FLOPs, but significantly improved accuracy and robustness, yielding a 4.5% performance boost over the baseline. The model achieved a weighted average F-score of 0.93 on a merged dataset composed of three post-earthquake damage level datasets. It was successfully deployed and tested on a Raspberry Pi 5, demonstrating its feasibility for edge-device applications. This deployment highlighted the model’s efficiency and real-time performance in resource-constrained environments. Full article

This study introduces YOLOv13-Cone-Lite, an enhanced algorithm based on YOLOv13s, designed to meet the stringent accuracy and real-time performance demands for traffic cone detection in autonomous formula racing cars on enclosed tracks. We improved detection accuracy by refining the network architecture. Specifically, the DS-C3k2_UIB module, an advanced iteration of the Universal Inverted Bottleneck (UIB), was integrated into the backbone to boost small object feature extraction. Additionally, the Non-Maximum Suppression (NMS)-free ConeDetect head was engineered to eliminate post-processing delays. To accommodate resource-limited onboard terminals, we minimized superfluous parameters through structural reparameterization pruning and performed 8-bit integer (INT8) quantization using the TensorRT toolkit, resulting in a lightweight model. Experimental findings show that YOLOv13-Cone-Lite achieves a mAP₅₀ of 92.9% (a 4.5% enhancement over the original YOLOv13s), a frame rate of 68 Hz (double the original model’s speed), and a parameter size of 8.7 MB (a 52.5% reduction). The proposed algorithm effectively addresses challenges like intricate lighting and long-range detection of small objects and offers the automotive industry a framework to develop more efficient onboard perception systems, while informing object detection in other closed autonomous environments like factory campuses. Notably, the model is optimized for enclosed tracks, with open traffic generalization needing further validation. Full article

Wire Arc Additive Manufacturing holds promise for on-board metal part production in maritime settings, yet its implementation remains limited due to the vibrational instability inherent to shipborne environments. This study addresses this critical technological barrier by analyzing the effects of marine vibrations on process stability and proposing an integrated solution based on adaptive process control, gyrostabilized platforms, and real-time monitoring systems. The research establishes specific technical requirements for WAAM instrumentation under maritime conditions and evaluates the capabilities and limitations of existing hardware and software tools. A set of engineering recommendations is presented for improving digital modeling, thermal–mechanical monitoring, and feedback control systems. Additionally, the study highlights material-related challenges by examining the influence of alloy properties on print quality under dynamic loads. The proposed approach enhances WAAM process resilience, laying the groundwork for reliable, high-quality additive manufacturing at sea. These findings are particularly relevant to shipboard maintenance, repair, and remote fabrication tasks, marking a significant step toward the industrial adoption of WAAM in marine engineering. Full article

AUVs offer the potential for in situ MP detection at constant, pre-set depths in marine environments. By carrying onboard MP detectors, AUVs can serve as alternatives to traditional methods of sample collection, processing, and analysis, while also addressing the inefficiencies and complexities associated with conventional detection procedures. This study conducts a comprehensive review of existing and potential MP detection methods that can be integrated with AUVs for in situ detection. In particular, guided by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework, this review analyzes selected studies on MP detection using AUVs. It finds that real-time, in situ MP detection via AUVs or multi-AUV systems remains underdeveloped. Key challenges include deep-sea communication, sensor integration, and underwater durability. The review highlights the current advances, research gaps, and future directions for AUV-based MP detection technologies. Full article

Onboard the MetOp satellite series, Infrared Atmospheric Sounding Interferometer (IASI) is a Fourier Transform spectrometer based on the Michelson interferometer. IASI acquires interferograms, which are processed to provide high-resolution atmospheric emission spectra. These spectra enable the derivation of temperature and humidity profiles, among other parameters, with exceptional spectral resolution. In this study, we evaluate a novel, rapid retrieval approach in the interferogram domain, aiming for near-real-time (NRT) analysis of large spectral datasets anticipated from next-generation tropospheric sounders, such as MTG-IRS. The Partially Sampled Interferogram (PSI) method, applied to trace gas retrievals from IASI, has been sparsely explored. However, previous studies suggest its potential for high-accuracy retrievals of specific gases, including CO, CO₂, CH₄, and N₂O at the resolution of a single IASI footprint. This article presents the results of a study based on retrieval in the interferogram domain. Furthermore, the optical pathway differences sensitive to the parameters of interest are studied. Interferograms are generated using a fast Fourier transform on synthetic IASI spectra. Finally, the relationship to the total column of carbon monoxide is explored using three different algorithms—from the most intuitive to a complex neural network approach. These algorithms serve as a proof of concept for interferogram classification and rapid predictions of surface temperature, as well as the abundances of H₂O and CO. IASI spectra simulations were performed using the LATMOS Atmospheric Retrieval Algorithm (LARA), a robust and validated radiative transfer model based on least squares estimation. The climatological library TIGR was employed to generate IASI interferograms from LARA spectra. TIGR includes 2311 atmospheric scenarios, each characterized by temperature, water vapor, and ozone concentration profiles across a pressure grid from the surface to the top of the atmosphere. Our study focuses on CO, a critical trace gas for understanding air quality and climate forcing, which displays a characteristic absorption pattern in the 2050–2350 ${\mathrm{cm}}^{-1}$ wavenumber range. Additionally, the study explores the potential of correlating interferogram characteristics with surface temperature and H₂O content, aiming to enhance the accuracy of CO column retrievals. Starting with intuitive retrieval algorithms, we progressively increased complexity, culminating in a neural network-based algorithm. The results of the NN study demonstrate the feasibility of fast interferogram-domain retrievals, paving the way for operational applications. Full article

With advancements in remote sensing technology and very-large-scale integration (VLSI) circuit technology, the Earth observation capabilities of spaceborne synthetic aperture radar (SAR) have continuously improved, leading to significantly increased performance demands for on-board SAR real-time imaging processors. Currently, the low data access efficiency of traditional direct memory access (DMA) engines remains a critical technical bottleneck limiting the real-time processing performance of SAR imaging systems. To address this limitation, this paper proposes a dedicated instruction set for spaceborne SAR data transfer control, leveraging the memory access characteristics of DDR4 SDRAM and common data read/write address jump patterns during on-board SAR real-time imaging processing. This instruction set can significantly reduce the number of instructions required in DMA engine data access operations and optimize data access logic patterns. While effectively reducing memory resource usage, it also substantially enhances the data access efficiency of DMA engines. Based on the proposed dedicated instruction set, we designed a DMA engine optimized for efficient data access in on-board SAR real-time imaging processing scenarios. Module-level performance tests were conducted on this engine, and full-process imaging experiments were performed using an FPGA-based SAR imaging system. Experimental results demonstrate that, under spaceborne SAR imaging processing conditions, the proposed DMA engine achieves a receive data bandwidth of 2.385 GB/s and a transmit data bandwidth of 2.649 GB/s at a 200 MHz clock frequency, indicating excellent memory access bandwidth and efficiency. Furthermore, tests show that the complete SAR imaging system incorporating this DMA engine processes a 16 k × 16 k SAR image using the Chirp Scaling (CS) algorithm in 1.2325 s, representing a significant improvement in timeliness compared to existing solutions. Full article

This study proposes and implements a dual-processor FPGA-ARM architecture to resolve the critical contradiction between massive data volumes and real-time processing demands in UAV-borne hyperspectral imaging. The integrated system incorporates a shortwave infrared hyperspectral camera, IMU, control module, heterogeneous computing core, and SATA SSD storage. Through hardware-level task partitioning—utilizing FPGA for high-speed data buffering and ARM for core computational processing—it achieves a real-time end-to-end acquisition–storage–processing–display pipeline. The compact integrated device exhibits a total weight of merely 6 kg and power consumption of 40 W, suitable for airborne platforms. Experimental validation confirms the system’s capability to store over 200 frames per second (at 640 × 270 resolution, matching the camera’s maximum frame rate), quick-look imaging capability, and demonstrated real-time processing efficacy via relative radio-metric correction tasks (processing 5000 image frames within 1000 ms). This framework provides an effective technical solution to address hyperspectral data processing bottlenecks more efficiently on UAV platforms for dynamic scenario applications. Future work includes actual flight deployment to verify performance in operational environments. Full article

This paper presents a distributed measurement system intended to effectively monitor the health status of switchgears under varying temperature conditions. In particular, thermocouples are deployed as temperature sensors for the continuous monitoring of a medium-voltage (MV) switchgear. Then, by integrating a low-cost microcontroller unit, the proposed system can implement previously trained unsupervised learning techniques for health status evaluation. This approach enables the early detection of potential faults by identifying anomalous temperature patterns, thus supporting predictive maintenance and extending the lifespan of switchgears. The results show strong clustering performance with low execution times, highlighting the suitability of the method for resource-constrained hardware. Furthermore, onboard temperature processing eliminates the need for data transmission to remote servers, reducing latency and communication overhead while improving system responsiveness. The paper includes a numerical analysis on synthetic data as well as a validation on real measurements. Overall, the presented distributed measurement system offers a scalable and cost-effective solution to enhance the reliability and safety of MV switchgears. Full article

Unmanned Aerial Vehicles (UAVs) have rapidly grown into different essential applications, including surveillance, disaster response, agriculture, and urban monitoring. However, for UAVS to steer safely and autonomously, the ability to detect obstacles and nearby aircraft remains crucial, especially under hard environmental conditions. This study comprehensively analyzes the recent landscape of obstacle and aircraft detection techniques tailored for UAVs acting in difficult scenarios such as fog, rain, smoke, low light, motion blur, and disorderly environments. It starts with a detailed discussion of key detection challenges and continues with an evaluation of different sensor types, from RGB and infrared cameras to LiDAR, radar, sonar, and event-based vision sensors. Both classical computer vision methods and deep learning-based detection techniques are examined in particular, highlighting their performance strengths and limitations under degraded sensing conditions. The paper additionally offers an overview of suitable UAV-specific datasets and the evaluation metrics generally used to evaluate detection systems. Finally, the paper examines open problems and coming research directions, emphasising the demand for lightweight, adaptive, and weather-resilient detection systems appropriate for real-time onboard processing. This study aims to guide students and engineers towards developing stronger and intelligent detection systems for next-generation UAV operations. Full article