Search Results (53)

With the rise in motor vehicles, driving safety is a major concern, and autonomous driving technology plays a key role in enhancing safety. Vision-based lane departure warning systems are essential for accurate navigation, focusing on lane line detection. This paper reviews the development of such systems and highlights the limitations of traditional image processing. To improve lane line detection, a dataset from Roboflow Universe will be used, incorporating techniques like priority pixels, least squares fitting for positioning, and a Kalman filter for tracking. YOLOv5 will be enhanced with a di-versified branch block (DBB) for better multi-scale feature extraction and an improved segmentation head inspired by YOLACT (You Only Look At CoefficienTs) for precise lane line segmentation. A multi-scale feature fusion mechanism with self-attention will be introduced to improve robustness. Experiments will demonstrate that the improved YOLOv5 outperforms other models in accuracy, recall, and mAP@0.5. Future work will focus on optimizing the model structure and enhancing the fusion mechanism for better performance. Full article

Traditional unmanned aerial vehicle (UAV) detection and tracking methods have long faced the twin challenges of high cost and poor efficiency. In real-world battlefield environments with complex backgrounds, occlusions, and varying speeds, existing techniques struggle to track small UAVs accurately and stably. To tackle these issues, this paper presents an enhanced YOLOv8N-Drone-based algorithm for improved target tracking of small UAVs. Firstly, a novel module named C2f-DSFEM (Depthwise-Separable and Sobel Feature Enhancement Module) is designed, integrating Sobel convolution with depthwise separable convolution across layers. Edge detail extraction and multi-scale feature representation are synchronized through a bidirectional feature enhancement mechanism, and the discriminability of target features in complex backgrounds is thus significantly enhanced. For the feature confusion problem, the improved lightweight Context Anchored Attention (CAA) mechanism is integrated into the Neck network, which effectively improves the system’s adaptability to complex scenes. By employing a position-aware weight allocation strategy, this approach enables adaptive suppression of background interference and precise focus on the target region, thereby improving localization accuracy. At the level of loss function optimization, the traditional classification loss is replaced by the focal loss (Focal Loss). This mechanism effectively suppresses the contribution of easy-to-classify samples through a dynamic weight adjustment strategy, while significantly increasing the priority of difficult samples in the training process. The class imbalance that exists between the positive and negative samples is then significantly mitigated. Experimental results show the enhanced YOLOv8 boosts mean average precision (Map@0.5) by 12.3%, hitting 99.2%. In terms of tracking performance, the proposed YOLOv8 N-Drone algorithm achieves a 19.2% improvement in Multiple Object Tracking Accuracy (MOTA) under complex multi-scenario conditions. Additionally, the IDF1 score increases by 6.8%, and the number of ID switches is reduced by 85.2%, indicating significant improvements in both accuracy and stability of UAV tracking. Compared to other mainstream algorithms, the proposed improved method demonstrates significant advantages in tracking performance, offering a more effective and reliable solution for small-target tracking tasks in UAV applications. Full article

Autonomous earthwork machinery is gaining traction as a means to boost productivity and safety on space-constrained urban sites, yet the fast-growing literature has not been fully integrated. To clarify current knowledge, we systematically searched Scopus and screened 597 records, retaining 157 peer-reviewed papers (2015–March 2025) that address autonomy, integrated control, or risk mitigation for excavators, bulldozers, and loaders. Descriptive statistics, VOSviewer mapping, and qualitative synthesis show the output rising rapidly and peaking at 30 papers in 2024, led by China, Korea, and the USA. Four tightly linked themes dominate: perception-driven machine autonomy, IoT-enabled integrated control systems, multi-sensor safety strategies, and the first demonstrations of fleet-level collaboration (e.g., coordinated excavator clusters and unmanned aerial vehicle and unmanned ground vehicle (UAV–UGV) site preparation). Advances include centimeter-scale path tracking, real-time vision-light detection and ranging (LiDAR) fusion and geofenced safety envelopes, but formal validation protocols and robust inter-machine communication remain open challenges. The review distils five research priorities, including adaptive perception and artificial intelligence (AI), digital-twin integration with building information modeling (BIM), cooperative multi-robot planning, rigorous safety assurance, and human–automation partnership that must be addressed to transform isolated prototypes into connected, self-optimizing fleets capable of delivering safer, faster, and more sustainable urban construction. Full article

In many applications, including underwater robotics, the coverage problem requires an autonomous vehicle to systematically explore a defined area while minimizing redundancy and avoiding obstacles. This paper investigates coverage path-planning strategies to enhance the efficiency of underwater gliders particularly in maximizing the probability of detecting a radioactive source while ensuring safe navigation. We evaluate three path-planning approaches: the Traveling Salesman Problem (TSP), Minimum Spanning Tree (MST), and the Optimal Control Problem (OCP). Simulations were conducted in MATLAB R2020a, comparing processing time, uncovered areas, path length, and traversal time. Results indicate that the OCP is preferable when traversal time is constrained, although it incurs significantly higher computational costs. Conversely, MST-based approaches provide faster but fewer optimal solutions. These findings offer insights into selecting appropriate algorithms based on mission priorities, balancing efficiency and computational feasbility. Full article

Pedestrian safety at crosswalks remains a critical concern as traffic accidents frequently result from drivers’ failure to yield, leading to severe injuries or fatalities. In response, various jurisdictions have enacted pedestrian priority laws to regulate driver behavior. Nevertheless, intersections lacking clear traffic signage and environments with limited visibility continue to present elevated risks. The scarcity and difficulty of collecting data under such complex conditions pose significant challenges to the development of accurate detection systems. This study proposes a CyclicGAN-based loop-learning framework, in which the learning process begins with a set of manually annotated images used to train an initial labeling model. This model is then applied to automatically annotate newly generated synthetic images, which are incorporated into the training dataset for subsequent rounds of model retraining and image generation. Through this iterative process, the model progressively refines its ability to simulate and recognize diverse contextual features, thereby enhancing detection performance under varying environmental conditions. The experimental results show that environmental variations—such as daytime, nighttime, and rainy conditions—substantially affect the model performance in terms of F1-score. Training with a balanced mix of real and synthetic images yields an F1-score comparable to that obtained using real data alone. These results suggest that CycleGAN-generated images can effectively augment limited datasets and enhance model generalization. The proposed system may be integrated with in-vehicle assistance platforms as a supportive tool for pedestrian-crossing detection in data-scarce environments, contributing to improved driver awareness and road safety. Full article

Forest fires have a great destructive impact on the Earth’s ecosystem; therefore, the top priority of current research is how to accurately and quickly monitor forest fires. Taking into account efficiency and cost-effectiveness, deep-learning-driven UAV remote sensing fire detection algorithms have emerged as a favored research trend and have seen extensive application. However, in the process of drone monitoring, fires often appear very small and are easily obstructed by trees, which greatly limits the amount of effective information that algorithms can extract. Meanwhile, considering the limitations of unmanned aerial vehicles, the algorithm model also needs to have lightweight characteristics. To address challenges such as the small targets, occlusions, and image blurriness in UAV-captured wildfire images, this paper proposes an improved UAV forest fire detection model based on YOLOv8. Firstly, we incorporate SPDConv modules, enhancing the YOLOv8 architecture and boosting its efficacy in dealing with minor objects and images with low resolution. Secondly, we introduce the C2f-PConv module, which effectively improves computational efficiency by reducing redundant calculations and memory access. Thirdly, the model boosts classification precision through the integration of a Mixed Local Channel Attention (MLCA) strategy preceding the three detection outputs. Finally, the W-IoU loss function is utilized, which adaptively modifies the weights for different target boxes within the loss computation, to efficiently address the difficulties associated with detecting small targets. The experimental results showed that the accuracy of our model increased by 2.17%, the recall increased by 5.5%, and the mAP@0.5 increased by 1.9%. In addition, the number of parameters decreased by 43.8%, with only 5.96M parameters, while the model size and GFlops decreased by 43.3% and 36.7%, respectively. Our model not only reduces the number of parameters and computational complexity, but also exhibits superior accuracy and effectiveness in UAV fire image recognition tasks, thereby offering a robust and reliable solution for UAV fire monitoring. Full article

This study introduces a novel approach for traffic control systems by using Large Language Models (LLMs) as traffic controllers. The study utilizes their logical reasoning, scene understanding, and decision-making capabilities to optimize throughput and provide feedback based on traffic conditions in real time. LLMs centralize traditionally disconnected traffic control processes and can integrate traffic data from diverse sources to provide context-aware decisions. LLMs can also deliver tailored outputs using various means such as wireless signals and visuals to drivers, infrastructures, and autonomous vehicles. To evaluate LLMs’ ability as traffic controllers, this study proposed a four-stage methodology. The methodology includes data creation and environment initialization, prompt engineering, conflict identification, and fine-tuning. We simulated multi-lane four-leg intersection scenarios and generated detailed datasets to enable conflict detection using LLMs and Python simulation as a ground truth. We used chain-of-thought prompts to lead LLMs in understanding the context, detecting conflicts, resolving them using traffic rules, and delivering context-sensitive traffic management solutions. We evaluated the performance of GPT-4o-mini, Gemini, and Llama as traffic controllers. Results showed that the fine-tuned GPT-mini achieved 83% accuracy and an F1-score of 0.84. The GPT-4o-mini model exhibited a promising performance in generating actionable traffic management insights, with high ROUGE-L scores across conflict identification of 0.95, decision making of 0.91, priority assignment of 0.94, and waiting time optimization of 0.92. This methodology confirmed LLMs’ benefits as a traffic controller in real-world applications. We demonstrated that LLMs can offer precise recommendations to drivers in real time including yielding, slowing, or stopping based on vehicle dynamics. This study demonstrates LLMs’ transformative potential for traffic control, enhancing efficiency and safety at intersections. Full article

As modern vehicles continue to evolve, advanced technologies are integrated to enhance the driving experience. A key enabler of this advancement is the Controller Area Network (CAN) bus, which facilitates seamless communication between vehicle components. Despite its widespread adoption, the CAN bus was not designed with security as a priority, making it vulnerable to various attacks. In this paper, we propose CANGuard, an Intrusion Detection System (IDS) designed to detect attacks on the CAN network and identify the originating node in real time. Using a simulated CAN-enabled system with four nodes representing diverse vehicle components, we generated a dataset featuring Denial-of-Service (DoS) attacks by exploiting the arbitration feature of the CAN bus, which prioritizes high-criticality messages (e.g., engine control) over lower-criticality ones (e.g., infotainment). We trained and evaluated several machine learning models for their ability to detect attacks and pinpoint the responsible node. Results indicate that Gradient Boosting outperformed other models, achieving high accuracy in both attack detection and node identification. While the Multi-Layer Perceptron (MLP) model demonstrated strong attack detection performance, it struggled with node identification, achieving less than 50% accuracy. These findings underscore the potential of tree-based models for real-time IDS applications in CAN-enabled vehicles. Full article

LLC resonant converters have emerged as essential components in DC charging station modules, thanks to their outstanding performance attributes such as high power density, efficiency, and compact size. The stability of these converters is crucial for vehicle endurance and passenger experience, making reliability a top priority. However, malfunctions in the switching transistor or current sensor can hinder the converter’s ability to maintain a resonant state and stable output voltage, leading to a notable reduction in system efficiency and output capability. This article proposes a fault diagnosis strategy for LLC resonant converters utilizing a reduced-order interval sliding mode observer. Initially, an augmented generalized system for the LLC resonant converter is developed to convert current sensor faults into generalized state vectors. Next, the application of matrix transformations plays a critical role in decoupling open-circuit faults from the inverter system’s state and current sensor faults. To achieve accurate estimation of phase currents and detection of current sensor faults, a reduced-order interval sliding mode observer has been designed. Building upon the estimation results generated by this observer, a diagnostic algorithm featuring adaptive thresholds has been introduced. This innovative algorithm effectively differentiates between current sensor faults and open switch faults, enhancing fault detection accuracy. Furthermore, it is capable of localizing faulty power switches and estimating various types of current sensor faults, thereby providing valuable insights for maintenance and repair. The robustness and effectiveness of the proposed fault diagnosis algorithm have been validated through experimental results and comparisons with existing methods, confirming its practical applicability in real-world inverter systems. Full article

This review investigates the ship emission measurements using multirotor unmanned aerial vehicles (UAVs). The monitoring of emissions from shipping is a priority globally, because of the necessity to reduce air pollution and greenhouse gas emissions. Moreover, there is widespread global effort to extensively measure vessel fuel sulfur content (FSC). The majority of studies indicate that more commonly used methods for measuring ship emission with UAVs is the sniffing method. Most of the research is concerned with determining the fuel sulfur content. Fuel sulfur content can be determined by the ratio of CO₂ and SO₂ concentration in the exhaust gas plume. For CO₂, the non-dispersive infrared (NDIR) method is used, the most common measuring range reaches 0–2000 ppm, the overall measuring range 0–10,000 ppm, and detection accuracy is ±5–300 ppm. For SO₂, the electrochemical (EC) method is used, the measuring range reaches 0–100 ppm, and the detection accuracy is ±5 ppm. Common UAV characteristics, used in measurement with ships, involve the following: 8–10 m/s of wind resistance, 5–6 kg maximum payload, and a flight distance ranging from 5 to 10 km. This can change in the near future, since a variety of emission measuring devices that can be mounted on UAVs are available on the market. The range of available elements differs from device to device, but available ranges are allowed and the accuracy provides good possibilities for wider research into ship emissions. Full article

The rise in autonomous vehicles further impacts road networks and driving conditions over the road networks. Cameras and sensors allow these vehicles to gather the characteristics of their surrounding traffic. One crucial factor in this environment is the appearance of emergency vehicles, which require special rules and priorities. Machine learning and deep learning techniques are used to develop intelligent models for detecting emergency vehicles from images. Vehicles use this model to analyze regularly captured road environment photos, requiring swift actions for safety on road networks. In this work, we mainly developed a Generative Adversarial Network (GAN) model that generates new emergency vehicles. This is to introduce a comprehensive expanded dataset that assists emergency vehicles detection and classification processes. Then, using Convolutional Neural Networks (CNNs), we constructed a vehicle detection model demonstrating satisfactory performance in identifying emergency vehicles. The detection model yielded an accuracy of 90.9% using the newly generated dataset. To ensure the reliability of the dataset, we employed 10-fold cross-validation, achieving accuracy exceeding 87%. Our work highlights the significance of accurate datasets in developing intelligent models for emergency vehicle detection. Finally, we validated the accuracy of our model using an external dataset. We compared our proposed model’s performance against four other online models, all evaluated using the same external dataset. Our proposed model achieved an accuracy of 85% on the external dataset. Full article

Path planning and obstacle avoidance are fundamental problems in unmanned ground vehicle path planning. Aiming at the limitations of Deep Reinforcement Learning (DRL) algorithms in unmanned ground vehicle path planning, such as low sampling rate, insufficient exploration, and unstable training, this paper proposes an improved algorithm called Dual Priority Experience and Ornstein–Uhlenbeck Soft Actor-Critic (DPEOU-SAC) based on Ornstein–Uhlenbeck (OU noise) and double-factor prioritized sampling experience replay (DPE) with the introduction of expert experience, which is used to help the agent achieve faster and better path planning and obstacle avoidance. Firstly, OU noise enhances the agent’s action selection quality through temporal correlation, thereby improving the agent’s detection performance in complex unknown environments. Meanwhile, the experience replay is based on double-factor preferential sampling, which has better sample continuity and sample utilization. Then, the introduced expert experience can help the agent to find the optimal path with faster training speed and avoid falling into a local optimum, thus achieving stable training. Finally, the proposed DPEOU-SAC algorithm is tested against other deep reinforcement learning algorithms in four different simulation environments. The experimental results show that the convergence speed of DPEOU-SAC is 88.99% higher than the traditional SAC algorithm, and the shortest path length of DPEOU-SAC is 27.24, which is shorter than that of SAC. Full article

Track smoothness has become an important factor in the safe operation of high-speed trains. In order to ensure the safety of high-speed operations, studies on track smoothness detection methods are constantly improving. This paper presents a track irregularity identification method based on CNN-Bi-LSTM and predicts track irregularity through car body acceleration detection, which is easy to collect and can be obtained by passenger trains, so the model proposed in this paper provides an idea for the development of track irregularity identification method based on conventional vehicles. The first step is construction of the data set required for model training. The model input is the car body acceleration detection sequence, and the output is the irregularity sequence of the same length. The fluctuation trend of the irregularity data is extracted by the HP filtering (Hodrick Prescott Filter) algorithm as the prediction target. The second is a prediction model based on the CNN-Bi-LSTM network, extracting features from the car body acceleration data and realizing the point-by-point prediction of irregularities. Meanwhile, this paper proposes an exponential weighted mean square error with priority inner fitting (EIF-MSE) as the loss function, improving the accuracy of big value data prediction, and reducing the risk of false alarms. In conclusion, the model is verified based on the simulation data and the real data measured by the high-speed railway comprehensive inspection train. Full article

Advances in information and signal processing, driven by artificial intelligence techniques and recent breakthroughs in deep learning, have significantly impacted autonomous driving by enhancing safety and reducing the dependence on human intervention. Generally, prevailing ADASs (advanced driver assistance systems) incorporate costly components, making them financially unattainable for a substantial portion of the population. This paper proposes a solution: an embedded system designed for real-time pedestrian and priority sign detection, offering affordability and universal applicability across various vehicles. The suggested system, which comprises two cameras, an NVIDIA Jetson Nano B01 low-power edge device and an LCD (liquid crystal system) display, ensures seamless integration into a vehicle without occupying substantial space and provides a cost-effective alternative. The primary focus of this research is addressing accidents caused by the failure to yield priority to other drivers or pedestrians. Our study stands out from existing research by concurrently addressing traffic sign recognition and pedestrian detection, concentrating on identifying five crucial objects: pedestrians, pedestrian crossings (signs and road paintings separately), stop signs, and give way signs. Object detection was executed using a lightweight, custom-trained CNN (convolutional neural network) known as SSD (Single Shot Detector)-MobileNet, implemented on the Jetson Nano. To tailor the model for this specific application, the pre-trained neural network underwent training on our custom dataset consisting of images captured on the road under diverse lighting and traffic conditions. The outcomes of the proposed system offer promising results, positioning it as a viable candidate for real-time implementation; its contributions are noteworthy in advancing the safety and accessibility of autonomous driving technologies. Full article

This study investigates an energy utilization optimization strategy in a smart home for charging electric vehicles (EVs) with/without a vehicle-to-home (V2H) and/or household energy storage system (HESS) to improve household energy utilization, smooth the load profile, and reduce electricity bills. The proposed strategy detects EV arrival and departure time, establishes the priority order between EV and HESS during charge and discharge, and ensures that the EV battery state of energy at the departure time is sufficient for its travel distance. It also ensures that the EV and HESS are charged when electricity prices are low and discharged in peak hours to reduce net electricity expenditure. The proposed strategy operates in different modes to control the energy amount flowing from the grid to EV and/or HESS and the energy amount drawn from the HESS and/or EV to feed the demand to maintain the load curve level within the average limits of the daily load curve. Four different scenarios are presented to investigate the role of HESS and EV technology in reducing electricity bills and smoothing the load curve in the smart house. The results demonstrate that the proposed strategy effectively reduces electricity costs by 12%, 15%, 14%, and 17% in scenarios A, B, C, and D, respectively, and smooths the load profile. Transferring valley electricity by V2H can reduce the electricity costs better than HESS, whereas HESS is better than EV at flattening the load curve. Transferring valley electricity through both V2H and HESS gives better results in reducing electricity costs and smoothing the load curve than transferring valley electricity by HESS or V2H alone. Full article