Mobile Vehicle Research Articles

Comparing YOLOv5 and YOLOv8 Performance in Vehicle License Plate Detection

The number of mobile vehicles on the roads in Indonesia is increasing every year. Therefore, it is essential to verify the identities of these vehicles for a variety of reasons, including locating stolen vehicles, enforcing traffic laws, managing car parks, and collecting tolls. Nevertheless, inspecting these vast numbers of vehicles manually is a challenging task. Motor vehicle number plate detection and recognition play a crucial role in intelligent transport systems. Generally, the detection and recognition of number plates on motor vehicles entail three main stages. Machine learning-based object detection, which encompasses a range of algorithms that can automatically identify and locate objects in images or videos, is the first stage. These models leverage multiple layers of processing units to extract intricate features from input data, thereby enhancing overall efficiency for object detection purposes. The YOLO algorithm is a popular object detection algorithm that can detect objects from images or videos in real-time using custom dataset. In this study, we directly compared YOLOv5 and YOLOv8 models which underwent equal training epochs, achieved stability, and utilized hyperparameters with an image size 640, 100 epochs, val 200, and batch 16. The YOLOv8 gets the best performance with almost 97.5% mAP and 69.4% mAP50-95. Keywords: Plate Number, YOLOv5, YOLOv8, Object Detection, Custom Dataset

Enhancing Driving Safety of Personal Mobility Vehicles Using On-Board Technologies

Accidents involving electric wheelchairs are a growing concern, with users frequently encountering obstacles that lead to collisions, tipping, or loss of balance. These incidents underscore the need for advanced safety technologies tailored to electric wheelchair users. This research addresses this need by developing a driving assistance system to prevent accidents and enhance user safety. The system incorporates ultrasonic sensors and a front-facing camera to detect obstacles and provide real-time warnings. The proposed system operates independently of stable server communication and employs embedded hardware for fast object detection and environmental recognition, ensuring immediate guidance in various scenarios. In this research, we utilized the existing yolov8 model as is. But we attempted to improve performance by hardware acceleration of convolutional neural networks, supporting various layers such as convolution, deconvolution, pooling, batch normalization, and others. Thus, the YOLO model was accelerated during inference on the specialized hardware in our experiments. Performance was evaluated in diverse environments to assess its usability. Results demonstrated high accuracy in detecting obstacles and providing timely warnings. Leveraging hardware acceleration for YOLOv8 delivers faster, scalable, and robust object detection, making it a great platform for enhancing driving safety on edge and embedded devices. These findings provide a strong foundation for future advancements in safety assistance systems for electric wheelchairs and other mobility devices. Future research will focus on enhancing system performance and integrating additional features to create a safer environment for electric wheelchair users.

Tractive performance of rigid wheel in granular media using coarse-scale DEM models

Understanding interactions between wheel and granular media in variable loading conditions is critical for prediction of mobility of wheeled vehicles in off-road environments. The discrete element method (DEM) is routinely used for modeling vehicle off-road performance, but the method’s accuracy is often not fully established.In this work, the DEM modeling accuracy is assessed by the comparison of ten DEM soil models with laboratory soil-bin measurements of net traction, gross traction, and sinkage of a wheel operating in sand. Laboratory soil-bin measurements, serving as reference for DEM simulations, were taken from physical experiments by Shinone et al. (2010), examining a 165/60R13 wheel with circumferential velocity of 97.6 mm/s and vertical contact load of 980 N in varying slip conditions.The set of ten DEM models was selected from the Generic EDEM Material Model database from Altair®’s EDEM™ software package, choosing the materials matching the bulk density and angle of repose for dry sand.Given the large particle size and no additional calibration of the DEM models, finding overall reasonable match with the gross traction from lab measurements and identifying a material predicting the net traction with a satisfiable accuracy encourages further use, refinement, and calibration of the DEM-based soil models.

A Decision Tree-Based Pattern Classification and Regression for a Mobility Support Scheme in Industrial Wireless Sensor Networks

Industrial wireless sensor networks (IWSNs) are exploited to achieve various purposes, including enhancing productivity and reducing cost in a variety of industries, and they require low-delay and high-reliability packet transmission. To achieve these requirements, a network manager is responsible for constructing a graph, allocating resources, and determining the transmission cycle and path of each node in advance. However, this approach is inadequate for exploiting mobile devices that constantly change network topology because frequent graph reconstruction and resource reallocation are required. In other words, despite the increasing reliance on mobile devices in a variety of industries, existing schemes cannot adequately respond to path failures due to device movement and subsequent packet loss during recovery. For example, real-time tracking of mobile vehicles in mining operations is crucial for safety and efficiency, where path failures and packet loss can lead to significant issues. To solve this problem, we propose a mobility support scheme to prevent packet loss caused by device mobility. In the proposed scheme, we first classify mobility patterns based on the decision tree and then apply regression to predict their trajectories. By leveraging this predictive information, the network manager could preemptively adjust graph construction and resource allocation to accommodate topology changes. Performance evaluation results show that the predicted mobility patterns closely match the actual patterns, achieving a high packet delivery ratio compared to conventional schemes, while also enabling efficient resource management.

The possibility of reducing the anthropogenic load of diesel engines on the environment by changing the compression ratio

The article is devoted to solving environmental problems arising from the operation of mobile energy vehicles with diesel engines in the agro-industrial sector and installed on cars, tractors, combines. Contrary to all forecasts, the use of environmentally friendly engines capable of competing with piston engines is limited in agricultural production, therefore, solving the problem of reducing harmful emissions from exhaust gases of diesel engines used in agriculture is very important and relevant. The research is aimed at solving one of the key tasks of our time – reducing the anthropogenic load from harmful emissions of diesel engines on the environment by changing the compression ratio. As a result of the test, it was found that an increase in the compression ratio from 13.5 to 15.5 leads to a decrease in emissions from exhaust gases of solid particles (PM), hydrocarbons (CxHy) and carbon monoxide (CO), however, over the entire load characteristic from Pe =0 to Pe=1.24 MPa at 1900 min-1 emissions of nitrogen oxides (NOx) increases. Emissions of particulate matter from exhaust gases are reduced from 0.122 to 0.063. When the compression ratio changes from 13.5 to 15.5, the estimated values change: for nitrogen oxides – by 1.88 times; for carbon monoxide – by 1.22 times; for hydrocarbons – by 1.35 times; for solid particles – by 1.15 times. The evaluation results showed that the values of the anthropogenic load were Htn = 78.31 ut/g with serial configuration at = 13.5 and Htn = 90.4 ut/g at = 14.5. This indicates a decrease of 1.15 times with a decrease to 13.5. In order to obtain the best results in reducing the anthropogenic load on the environment, it is recommended to use complex methods, for example, simultaneous changes in the degree of compression and catalytic neutralization.

The Prediction Method and Application of Off-Road Mobility for Ground Vehicles: A Review

The Prediction Method and Application of Off-Road Mobility for Ground Vehicles: A Review

Introducing digital air-traffic controllers for urban-air mobility to ensure safe and energy-efficient flight operations

Abstract Facing the continued growth of cities, the introduction of urban-air mobility intends to reduce traffic congestion and improve the quality of services such as on-demand-transport, reduced travel times and increased connectivity. Nevertheless, its integration into existing air-traffic flows remains one of the biggest challenges ahead, especially once controlled airspace overlaps with urban-air mobility areas, such as at airport control zones. Here, air-traffic control needs to coordinate amobng urban-air mobility vehicles and conventional air traffic. In 2022, DLR conducted a human-in-the-loop simulation with ten air-traffic controllers to validate previously developed workflows for that coordination task applied for Hamburg airport. The simulation results revealed that additional urban-air mobility traffic increases controllers’ experienced workload up to 30% while slightly reducing their perceived situation awareness. Thus, a majority of controllers participating in the trials suggested to introduce an additional controller working position to exclusively control airtaxis and traffic following visual flight rules. This option is assessed as owning a high potential as cost intensive adaptions of regulations and procedures can be omitted. Nevertheless, the feasibility of this option is rather low due to the limited availability of endorsed human controllers. This study proposes a concept for a digital controller taking the responsibility of guidance for airtaxis under visual flight rules traffic (abbr. VFR) within a control zone. This digital controller is named “UAM digital controller” (abbr. UDC) and based on algorithms calculating slots and trajectories which have been validated in previous DLR projects. The UDC coordinates with the human controller once a potential conflict is detected. Within the study, first the concept of the digital controller is defined, following existing work. As a second step, a theoretical evaluation based on an air-traffic control task model and an operational concept for airtaxi integration will analyze the task load reduction for the human controller. Last but not least, the expected energy saving of flight operations by the digital controllers will be assessed.

Head and neck injuries from personal motorised vehicles in the United States

BackgroundThe use of personal electric vehicles in the United States has increased head and neck injuries. This study analyses the types, frequencies, demographics and management of these injuries across motorised...

The optimal control law of the power supplied to the wheeled vehicle in case of curvilinear movement

INTRODUCTION: Highly mobile wheeled vehicles are designed to move on roads and terrain in various road and soil conditions, which is accompanied by frequent and significant changes in traction forces and rolling resistance forces. In this regard, in order to maintain vehicle mobility and ensure low energy costs when performing transport tasks, it is necessary to continuously change the operating mode during movement from completely locked to differential in the case of a mechanical transmission. At the same time, the transmission operating mode selected by the driver is not always rational. Thus, the development of a law for controlling the power supplied to the propulsion system, ensuring minimal energy losses while maintaining vehicle mobility in widely varying road conditions, is an urgent task. PURPOSE OF THE STUDY: Increasing the energy efficiency of highly mobile wheeled vehicles by applying a control law for the power supplied to the propulsion system, adaptive to driving conditions. METHODOLOGY AND METHODS: Increasing the energy efficiency of movement can be achieved by reducing losses due to wheel slipping by controlling the power supplied to the propulsion unit. It is advisable to obtain the control law as a result of solving an optimization problem, where the loss power is chosen as the objective function, and the traction forces developed on each of the wheels are chosen as the varied values. At the same time, in order to maintain the possibility of vehicle movement, it is necessary to take into account that the total traction force on all wheels must be determined by external conditions and provided by the power plant. To solve the optimization problem, the Lagrange multiplier method was used. RESULTS AND SCIENTIFIC NOVELTY: The studies carried out made it possible to obtain in analytical form a unified law of adaptive control of the power supplied to the propulsors, applicable in a wide range of road conditions in both straight and curved motion, providing a close to optimal distribution of moments across the driving wheels of the machine, obtained as a result of numerical optimization. PRACTICAL SIGNIFICANCE: The application of the developed law for controlling the power supplied to the propulsors, based on the use in the process of movement of information only about the longitudinal and vertical forces, rotational speeds and angles of rotation of the wheels (trajectory radius), will improve the efficiency of performing transport tasks when moving a vehicle in continuously changing road conditions due to reducing the load on the driver in terms of controlling differential locks in comparison with a manual transmission both in straight and curved motion.

Research on Electric Vehicle Mobility: A Bibliometric Review and Research Agenda

Research on Electric Vehicle Mobility: A Bibliometric Review and Research Agenda

AN IN-DEPTH ASSESSMENT OF THE EXISTING LEGAL FRAMEWORK REGULATING UNMANNED AERIAL SYSTEMS (UAS) ACTIVITIES IN MALAYSIA

The rapid growth of the Unmanned Aircraft System (UAS) industry, with significant increases projected for commercial unmanned aircraft, urban air mobility vehicles, cargo delivery drones, inspection drones, and hobby drones, necessitates a comprehensive approach to UAS regulations. While the Civil Aviation Authority of Malaysia (CAAM) has made strides in developing regulations for UAS operations, the current rules, mainly the Civil Aviation Regulations (CAR) 2016 are insufficient to address the challenges posed by emerging UAS technologies and their unique operational concepts. Innovations such as Advanced Air Mobility (AAM), international operations of Remotely Piloted Aircraft Systems (RPAS), swarm drones, and autonomous UAS operations are outpacing existing regulations. The aim of this study was to identify and address the shortcomings of the current regulatory framework for UAS operations in Malaysia and compared the global renowned regulatory bodies. To achieve these goals, a multi-faceted research methodology was employed. This involved an in-depth analysis of international regulatory frameworks and a comprehensive survey to gather necessary data and insights. In summary, this research presented a comprehensive and transformative approach to UAS operations in Malaysia. The findings and recommendations of this study provided valuable insights for policymakers, regulators, and UAS operators in Malaysia and other countries facing similar regulatory challenges.

Bio-Inspired Algorithms for Efficient Clustering and Routing in Flying Ad Hoc Networks.

The high mobility and dynamic nature of unmanned aerial vehicles (UAVs) pose significant challenges to clustering and routing in flying ad hoc networks (FANETs). Traditional methods often fail to achieve stable networks with efficient resource utilization and low latency. To address these issues, we propose a hybrid bio-inspired algorithm, HMAO, combining the mountain gazelle optimizer (MGO) and the aquila optimizer (AO). HMAO improves cluster stability and enhances data delivery reliability in FANETs. The algorithm uses MGO for efficient cluster head (CH) selection, considering UAV energy levels, mobility patterns, intra-cluster distance, and one-hop neighbor density, thereby reducing re-clustering frequency and ensuring coordinated operations. For cluster maintenance, a congestion-based approach redistributes UAVs in overloaded or imbalanced clusters. The AO-based routing algorithm ensures reliable data transmission from CHs to the base station by leveraging predictive mobility data, load balancing, fault tolerance, and global insights from ferry nodes. According to the simulations conducted on the network simulator (NS-3.35), the HMAO technique exhibits improved cluster stability, packet delivery ratio, low delay, overhead, and reduced energy consumption compared to the existing methods.

Assessment of atmospheric volatile organic compounds at two crude oil production plants in Southeastern Türkiye.

Ambient Volatile Organic Compounds (VOCs) were investigated to determine their characteristics, Ozone Formation Potentials (OFPs), and health risks in two crude oil production plants (Nusaybin and Egil plants) in southeastern Türkiye. Benzene, toluene, ethylbenzene, m + p xylene, o xylene, and 1,3,5-trimethylbenzene were measured at eight passive sampling points in each plant. Samples were analyzed using gas chromatography coupled with a flame ionization detector and a thermal desorption. The concentration of ranged from 5.03 to 88.43μg/m3 in the Nusaybin Plant and from 7.70 to 154.35μg/m3 in the Egil Plant. Toluene and xylenes were predominant in both plants. In the Nusaybin Plant, VOCs were mainly associated with crude oil production, while in the Egil Plant, they were associated with a combination of crude oil production and mobile vehicle activities. The OFP of was 297.47μg/m3 in the Nusaybin Plant, and 249.25μg/m3 in the Egil Plant. M + p xylene, toluene, and 1,3,5-trimethylbenzene together contributed 86% and 84% of the total OFP in the Nusaybin and Egil plants, respectively. Benzene exposure posed a possible cancer risk to oil workers in both plants. Non-cancer health risk was at a potential level in the Egil Plant but negligible in the Nusaybin Plant. This study is expected to enhance knowledge regarding the effects of crude oil production plants on air quality and workplace exposure.

Understanding Emission Trends, Regional Distribution Differences, and Synergistic Emission Effects in the Transportation Sector in Terms of Social Factors and Energy Consumption

China’s transportation sector plays a significant role in reducing carbon dioxide (CO2) and air pollution. Previous studies have predominantly utilized scenario analysis to forecast emissions for the next 30 to 50 years based on coefficients from a base year. To elucidate the current state of gas emissions in the transportation sector, this study employed panel data for 10 types of gas emissions from 2001 to 2020, analyzing their emission characteristics, tendencies, and synergistic effects. Utilizing the Kaya equation and the logarithmic mean division index (LMDI) decomposition method, we developed a model of pollutant emissions that considers the synergistic effects, pollution emission intensity, energy mix, energy consumption intensity, and population. The results show that all pollutants in the transportation sector decreased except for NH3 and CO2. There was a synergistic effect between air pollutants and CO2 emissions, but the reduction was not significant. From 2013 to 2020, the transportation sector shifted from a high emission intensity with low synergy to a low emission intensity with high synergy. The results indicate that off-road mobile vehicles, on-road diesel vehicles, and motorcycles became the main source of emissions from transportation in certain provinces, and a key area requiring attention in policy development. Gasoline consumption was identified as the primary contributor to the significant increase in synergistic emission variability in the transportation sector. These results provide policymakers with practical ways to optimize emission reduction pathways.

Autonomous Navigation for Personal Mobility Vehicles Considering Passenger Tolerance to Approaching Pedestrians

Autonomous Navigation for Personal Mobility Vehicles Considering Passenger Tolerance to Approaching Pedestrians

Optimizing Age of Information in Internet of Vehicles over Error-Prone Channels.

In the Internet of Vehicles (IoV), age of information (AoI) has become a vital performance metric for evaluating the freshness of information in communication systems. Although many studies aim to minimize the average AoI of the system through optimized resource scheduling schemes, they often fail to adequately consider the queue characteristics. Moreover, vehicle mobility leads to rapid changes in network topology and channel conditions, making it difficult to accurately reflect the unique characteristics of vehicles with the calculated AoI under ideal channel conditions. This paper examines the impact of Doppler shifts caused by vehicle speeds on data transmission in error-prone channels. Based on the M/M/1 and D/M/1 queuing theory models, we derive expressions for the age of information and optimize the system's average AoI by adjusting the data extraction rates of vehicles (which affect system utilization). We propose an online optimization algorithm that dynamically adjusts the vehicles' data extraction rates based on environmental changes to ensure optimal AoI. Simulation results have demonstrated that adjusting the data extraction rates of vehicles can significantly reduce the system's AoI. Additionally, in the network scenario of this work, the AoI of the D/M/1 system is lower than that of the M/M/1 system.

A Fully‐Integrated Diamond Nitrogen‐Vacancy Magnetometer with Nanotesla Sensitivity

AbstractEnsemble diamond nitrogen‐vacancy (DNV) centers have emerged as a promising platform for precise earth‐field vector magnetic sensing, particularly in applications that require high mobility. Nevertheless, integrating all control utilities into a compact form has proven challenging, thus far limiting the sensitivity of mobile DNV magnetometers to the ‐level. This study introduces a fully integrated DNV magnetometer that encompasses all the essential components typically found in traditional platforms, while maintaining compact dimensions of approximately 13 cm 26 cm. In contrast to previous efforts, these challenges are successfully addressed by integrating a high‐power laser, a lock‐in amplifier, and a digitally‐modulated microwave source. These home‐made components show comparable performance with commercial devices under the circumstance, resulting in an optimal sensitivity approaching 2.14 nT ()−1. The limitations in this system as well as possible future improvements are discussed. This work paves the way for the use of DNV magnetometry in cost‐effective, mobile unmanned aerial vehicles, facilitating a wide range of practical applications.

Lidar Simultaneous Localization and Mapping Algorithm for Dynamic Scenes

To address the issue of significant point cloud ghosting in the construction of high-precision point cloud maps by low-speed intelligent mobile vehicles due to the presence of numerous dynamic obstacles in the environment, which affects the accuracy of map construction, this paper proposes a LiDAR-based Simultaneous Localization and Mapping (SLAM) algorithm tailored for dynamic scenes. The algorithm employs a tightly coupled SLAM framework integrating LiDAR and inertial measurement unit (IMU). In the process of dynamic obstacle removal, the point cloud data is first gridded. To more comprehensively represent the point cloud information, the point cloud within the perception area is linearly discretized by height to obtain the distribution of the point cloud at different height layers, which is then encoded to construct a linear discretized height descriptor for dynamic region extraction. To preserve more static feature points without altering the original point cloud, the Random Sample Consensus (RANSAC) ground fitting algorithm is employed to fit and segment the ground point cloud within the dynamic regions, followed by the removal of dynamic obstacles. Finally, accurate point cloud poses are obtained through static feature matching. The proposed algorithm has been validated using open-source datasets and self-collected campus datasets. The results demonstrate that the algorithm improves dynamic point cloud removal accuracy by 12.3% compared to the ERASOR algorithm and enhances overall mapping and localization accuracy by 8.3% compared to the LIO-SAM algorithm, thereby providing a reliable environmental description for intelligent mobile vehicles.

Evaluation of collision detection and avoidance methods for urban air mobility through simulation

AbstractUrban Air Mobility is a new concept of regional aviation that has been growing in popularity as a solution to the issue of ever-increasing ground traffic. Electric vehicles with vertical take-off and landing capabilities are developed by numerous market companies as a result of the push toward environmentally sustainable aviation. The next stage in this development process would be to define the concept of operation of these conceptual aircraft and then to integrate them with the existing airspace once they are airborne. In addition to coordinating with conventional air traffic and other Urban Air Mobility vehicles, collision avoidance with uncooperative airspace users has to be addressed. Birds and drones of all sizes pose a serious risk to these low-flying aircraft. Innovative collision detection and avoidance techniques need to be employed due to the non-cooperative nature of these airspace users and different performance characteristics of Urban Air Mobility vehicles compared to classical fixed-wing aircraft. The aim of this study is to evaluate the concept of one such system by means of fast-time simulations. This system builds, similarly to the Airborne Collision Avoidance System, on safety envelopes and rule-based collision avoidance to prevent collisions with non-cooperative airspace members. The system is designed to work with all aircraft configurations used for Urban Air Mobility operations. To assess its influence on safety and capacity, different scenarios are modeled by varying parameters, such as intruder type, location, flight path. The parameters assessed are differences in flight time and closest point of approach with and without the collision avoidance system in place. Moreover, the influence of different configurations of Urban Air Mobility aircraft on these parameters is analyzed. The results show that the separation between the ownship and intruder is increased substantially which leads to safe operations at bearable delay costs.

Dear: vehicle mobility prediction using diffusion-expanded attention network based on IoV trajectory data

Dear: vehicle mobility prediction using diffusion-expanded attention network based on IoV trajectory data