Browse Topic: Education and training

Items (6,338)
Growing global warming and the associated climate change have expedited the need for adoption of carbon-neutral technologies. The transportation sector accounts for ~ 25 % of total carbon emissions. Hydrogen (H2) is widely explored as an alternative for decarbonizing the transport sector. The application of H2 through PEM Fuel Cells is one of the available technologies for the trucking industry, due to their relatively higher efficiency (~50%) and power density. However, at present the cost of an FCEV truck is considerably higher than its diesel equivalent. Hence, new technologies either enabling cost reduction or efficiency improvement for FCEVs are imperative for their widespread adoption. FCEVs have a system efficiency around 40-60% implying that around half of the input energy is lost to the environment as waste heat. However, recapturing this significant amount of waste heat into useful work is a challenge. This paper discusses the feasibility of waste heat recovery (WHR
P V, Navaneeth
Driver-in-the-Loop (DIL) simulators have become crucial tools across automotive, aerospace, and maritime industries in enabling the evaluation of design concepts, testing of critical scenarios and provision of effective training in virtual environments. With the diverse applications of DIL simulators highlighting their significance in vehicle dynamics assessment, Advanced Driver Assistance Systems (ADAS) and autonomous vehicle development, testing of complex control systems is crucial for vehicle safety. By examining the current landscape of DIL simulator use cases, this paper critically focuses on Virtual Validation of ADAS algorithms by testing of repeatable scenarios and effect on driver response time through virtual stimuli of acoustic and optical warnings generated during simulation. To receive appropriate feedback from the driver, industrial grade actuators were integrated with a real-time controller, a high-performance workstation and simulation software called Virtual Test
Sharma, ChinmayaBhagat, AjinkyaKale, Jyoti GaneshKarle, Ujjwala
Functional Mock-up Units (FMUs) have become a standard for enabling co-simulation and model exchange in vehicle development. However, traditional FMUs derived from physics-based models can be computationally intensive, especially in scenarios requiring real-time performance. This paper presents a Python-based approach for developing a Neural Network (NN) based FMU using deep learning techniques, aimed at accelerating vehicle simulation while ensuring high fidelity. The neural network was trained on vehicle simulation data and trained using Python frameworks such as TensorFlow. The trained model was then exported into FMU, enabling seamless integration with FMI-compliant platforms. The NN FMU replicates the thermal behavior of a vehicle with high accuracy while offering a significant reduction in computational load. Benchmark comparisons with a physical thermal model demonstrate that the proposed solution provides both efficiency and reliability across various driving conditions. The
Srinivasan, RangarajanAshok Bharde, PoojaMhetras, MayurChehire, Marc
For driver-automation collaborative driving, accurately monitoring driver state in smart cockpits is crucial for enhancing safety, comfort, and human-computer interactions. However, existing research lacks clarity regarding the relationships among driver states, and there is no consensus on the optimal physiological channels to reliably capture these states. This study examined three critical psychological constructs (i.e., perceived risk, trust in the automated driving system, and driver fatigue) using a 37-participant driving simulation experiment. We manipulated multiple factors to induce distinct driver states among participants and recorded subjective scale ratings, heart rate variability, galvanic skin response, and eye movement data. Subjective scale ratings were adopted as the ground truth to examine the corresponding measurement relationships between different physiological signals and the three targeted dimensions of driver states. Our results proved that perceived risk
Wang, ZhenyuanLi, QingkunWang, WenjunLiu, WeiminSun, ZhaocongCheng, Bo
This paper addresses the scarcity of training and testing data in autonomous driving scenarios. We propose a 3D reconstruction framework for autonomous driving scenes based on Neural Radiance Fields (NeRF). Compared to traditional multi-view geometry methods, NeRF offers superior scene representation and novel view synthesis capabilities but suffers from low training efficiency and limited generalization. To overcome these limitations, we integrate existing NeRF optimization techniques and introduce a scene-specific data reuse strategy tailored for autonomous driving, enabling continuous 3D reconstruction directly from 2D images without requiring elaborate calibration. This approach significantly improves reconstruction efficiency, achieving reliable reconstruction and real-time visualization in complex traffic environments. Furthermore, we develop an interactive scene editing plugin in Unreal Engine 5, supporting the addition, removal, and adjustment of static objects. This extension
Pan, DengZou, JieChen, YuhanMeng, ZhangjieLi, JieLi, Guofa
Lane change plays a critical role in autonomous driving and directly affects traffic safety and efficiency. Although deep learning-based lane-change decision-making frameworks have achieved promising results, they still face fundamental challenges in producing human-consistent and trustworthy behavior, mainly due to: 1) Inadequate psychology-informed personalization, as most frameworks focus on physical variables but neglect psychological factors (e.g., risk tolerance, urgency), limiting their ability to capture individual differences in lane-change motivations. 2) Limited holistic understanding of traffic context, most frameworks lack consideration of high-level and interpretable indicators (e.g., traffic pressure) in comprehensively assessing dynamic traffic scenarios, limiting their capacity for human-like contextual understanding. 3) Lack of transparent and interpretable decision logic, as many frameworks operate as black boxes with opaque reasoning processes, hindering human
Chen, YanboChen, JiaqiYu, HuilongXi, Junqiang
The characteristic representation and in-depth understanding of driver personalized driving behavior are fundamental to achieving human-like autonomous driving, enhancing the rationality of autonomous driving decisions, and meeting passengers’ personalized needs. [ADDED]Personalized driving behavior refers to individual-specific patterns in vehicle operation that emerge from drivers’ unique combinations of skills, risk tolerance, and habitual responses.However, current research lacks consideration of cluster analysis in the feature representation stage and ignores the time-varying contribution degree of time series values to low-dimensional features, which inhibits further utilization and development. This study adopts deep embedding clustering method and introduces attention mechanism to investigate driver personalized high-speed lane change behavior.[ADDED] Using a comprehensive driving simulator platform, we collected 15-channel time series data from 12 drivers performing 216 lane
Dong, HaominWang, WeiWang, YueLi, LunYue, YiTian, JiaxiaoHan, Jiayi
Perceiving the movement characteristics of specific body parts of a driver is crucial for determining their activity. Moreover, the driver’s body posture significantly impacts personnel safety during collision. This study investigates the creation of a dataset using Kinect depth camera for acquiring, organizing, annotating with skeleton tracking assistance, and optimizing interpolation. The pose recognition methods enhanced through an anchor regression mechanism, leading to the refinement of a lightweight anchor regression network capable of end-to-end learning ability from depth images. The improved backbone neck head structure offers advantages of reduced model parameters and enhanced accuracy. This engineering optimization makes it better suited for practical applications within vehicles with limited computational resources limitations and high real-time demands.
Xu, HailanLi, WuhuanLu, JunWang, XinHe, WenhaoChen, ZhenmingLiu, Yunjie
The need for high-quality simulation scenarios to verify the safety of autonomous driving systems is growing, but there are still obstacles to overcome, like the high cost and low efficiency of creating scenario files that satisfy simulation platform standards. To address the issues, this study suggests an automated approach for creating concrete autonomous driving simulation scenarios using a large language model. This approach enables the automated conversion of natural language input into standard scenario file output. The functional scenario generation stage uses the fine-tuned large language model for structured expression and improves the lightweight model deployment efficiency through knowledge distillation; the logical scenario generation stage involves mapping the standard parameter space and introducing constraint rules to ensure rationality; and the concrete scenario generation stage involves generating high-risk key parameters through data mining and generative adversarial
Li, JiweiWang, Runmin
In order to reduce traffic accidents and losses in long downhill sections of expressways, giving drivers reasonable prevention and control means of information induction can improve the safety of long downhill sections. The location of the accompanying information service of the driver's vehicle terminal and the rationality of the intervention information are worth studying. This study takes a high-speed long downhill road as an example, divides the risk level of the long downhill road based on the road safety risk index model, and verifies it with the help of driving behavior data. Secondly, three coverage schemes of sensing devices are designed according to the results of risk classification, and the HMI interface of accompanying information service is designed according to the different coverage degrees of sensing devices. Finally, a driving simulation experiment was carried out based on the driving simulator, and the speed control level, psychological comfort level, operational
Wang, YuejiaWeng, WenzhongLuan, SenDai, Yibo
Focusing on drivers in Hong Kong, this paper analyzes how social media usage contributes to inattentive driving and the associated safety consequences. Data were collected using a questionnaire-based survey and analyzed through chi-square tests, Fisher’s exact tests, and Cramér’s V effect size calculations to examine the relationships between demographic and driving-related factors—including gender, age group, education level, driving experience, and self-rated driving skills—and the level of high-risk perception. The findings reveal that gender, age, experience, and Self-assessed driving ability significantly influence drivers’ perception of high-risk situations. Furthermore, significant interaction effects were observed among these variables, indicating that they do not operate in isolation but rather interact to shape risk perception. For example, middle-aged and older female drivers with higher education levels and extensive driving experience demonstrated a heightened perception
Dong, JinhaiYe, HaochengCui, ZihengChen, Yang
In the context of the accelerating urbanization process, the problem of urban traffic congestion has become more severe. Rail transit, with its advantages of high efficiency, convenience, and environmental friendliness, has become a key force in alleviating urban traffic pressure. An in - depth exploration of passengers’ willingness to travel by rail transit is of great significance for optimizing urban traffic planning, improving the service quality of rail transit, and promoting the sustainable development of cities. This article starts from two dimensions: objective factors and passengers’ subjective perceptions, and comprehensively uses a variety of research methods to conduct an in - depth study on passengers’ willingness to travel by rail transit. In terms of objective factors, this article analyzes the differences in subjective perceptions among different passenger groups from the perspectives of gender, age, education level, and occupation. In terms of subjective perceptions
Wang, GangHuang, LeiYang, Yihao
In this article we will discuss the development and implementation of a computer vision system to be used in decision-making and control of an electro-hydraulic mechanism in order to guarantee correct functioning and efficiency during the logistics project. To achieve this, we have brought together a team of engineering students with knowledge in the area of Artificial Intelligence, Front End and mechanical, electrical and hydraulic devices. The project consists of installing a system on a forklift that moves packaged household appliances that can identify and differentiate the different types of products moved in factories and distribution centers. Therefore, the objective will be to process this identification and control an electro-hydraulic pressure control valve (normally controlled in PWM) so that it releases only the hydraulic pressure configured for each type of packaging/product, and thus correctly squeezing (compressing) the specific volume, without damaging it due to
Furquim, Bruno BuenoPivetta, Italo MeneguelloIbusuki, Ugo
This study explores how digital transformation in the automotive sector contributes to sustainability, particularly through the elimination of paper-based processes. Accelerated by the COVID-19 pandemic, the integration of digital technologies has optimized operations and reduced costs across the industry. The research focused on the impact of data digitalization on eliminating printed reports and documents, aligned with Sustainable Development Goals (SDGs) 8, 12, and 15. A mixed-methods approach was used, combining qualitative and quantitative techniques. Data were collected via questionnaires and descriptive research conducted with employees of a multinational automotive company in São Paulo. Findings revealed that the transition to digital solutions eliminated the company’s average of 842 monthly printouts, improved process efficiency by 12%, and reduced data loss and rework. Key initiatives included automating performance indicators, adopting electronic signatures, and promoting
Assis, Dioclécio SilveiraJussani, Ailton CondeIbusuki, Ugo
The concept of “quality feel” in automotive interiors relates to how consumers perceive a product’s quality through touch and feel. While subjective, it’s crucial for satisfaction and differentiation and is defined by engineering requirements like displacement, especially for interior components. Assessing this early in development is vital. Traditionally, this evaluation happens virtually using Computer Aided Engineering (CAE) simulations, which measure displacement and stiffness. However, conventional simulation methods, like Finite Element Method (FEM), can be time-consuming to set up. This work presents two case studies where the evaluation of an interior panel’s quality feel, using structural numerical simulations combined with the Simulation Driven Design (SDD) method was performed. SDD is an iterative process where simulation results guide design modifications, optimizing the component until it meets quality criteria, which are based on simulated human touch and resulting
Cunegatto, Eduardo Henrique TaubeCisco, Lenon AudibertSilva, Matheus RodriguesThums, EsmaelQuinelato, LeandroAraújo, Tomás Victor Gonçalves Pereira
2
Santana, JessicaCurti, GustavoLima, TiagoSarmento, MatheusCallegari, BrunaFolle, Luis
The integration of sensory stimuli in Virtual Reality remains a challenge in the automotive industry, especially regarding consumer perception and immersive experience. This study aims to examine the applications of virtual reality in the automotive industry, analyzing how the integration of sensory stimuli can impact consumer perception, the technological challenges involved, and the opportunities for innovation in the sector, contributing to the advancement of immersive automotive experiences. We adopted a literature-based analytical approach, involving the review of VR technologies applied to product design, consumer interaction, and sensory integration, with a focus on tactile, visual, and olfactory stimuli. The analysis considered technological, cultural, and market factors, ensuring a comprehensive understanding of the current state and challenges of VR adoption in the automotive context. As a result, we identified key benefits of VR in improving design, testing, training, and
Ramos, CatharinaThasla, YasmimRodrigues, DanielaAlfonso, MarcioLeite, RodrigoRibeiro, EuláliaWinkler, Ingrid
Vehicles powered by internal combustion engines play a crucial role in urban mobility and still represent the vast majority of vehicles produced. However, these vehicles significantly contribute to pollutant emissions and fossil fuel consumption. In response to this challenge, various technologies and strategies have been developed to reduce emissions and enhance vehicle efficiency. This paper presents the development of a solution based on optimized gear-shifting strategies aimed at minimizing fuel consumption and emissions in vehicles powered exclusively by internal combustion engines. To achieve this, a longitudinal vehicle dynamics model was developed using the MATLAB/Simulink platform. This model incorporates an engine combustion simulation based on the Advisor (Advanced Vehicle Simulator) tool, which estimates fuel consumption and emissions while considering catalyst efficiency under transient engine conditions. Based on these models, an optimization method was employed to
Da Silva, Vitor Henrique GomesCarvalho, Áquila ChagasLopez, Gustavo Adolfo GonzalesCasarin, Felipe Eduardo MayerDedini, Franco GiuseppeEckert, Jony Javorski
During the long-term service of steel-concrete composite beam bridges, the main beam structure is prone to sustain damage of varying severity due to such factors as sustained load effects and gradual degradation of material properties. The accurate identification of these damages and the implementation of timely maintenance measures are of crucial significance for guaranteeing the safe operation of bridges. This category of research not only holds substantial theoretical value but also can offer technical backing for engineering practices, thereby ensuring the long-term dependability of infrastructure facilities. For this reason, investigations into damage identification of bridges are conducted by means of vehicle-bridge coupling vibration analysis and wavelet packet analysis. Firstly, an analysis is carried out on the construction approach for the relative energy of wavelet packets; the relative energy curvature difference of wavelet packets is defined as the damage index (DI). To
Dou, Weihua
Pavement maintenance decision-making is the key to determining the maintenance program and ensuring the maintenance effect. Still, the existing pavement maintenance decision-making methods have problems, such as incomplete and inaccurate data. Based on this, this study develops an intelligent decision-making system for pavement maintenance on highways in Gansu Province by combining DeepSeek artificial intelligence technology with dynamic capability theory. The proposed framework integrates multi-source data fusion, predictive analytics, and organizational collaboration mechanisms to address the systematic challenges of resource allocation and decentralized decision-making. A spatio-temporal graph convolutional network enables accurate pavement performance modelling, while a redesigned decision-making process enhances cross-departmental coordination through game-theoretic optimization and blockchain-based traceability. The results show significant improvements in operational efficiency
Xie, ZilongLiu, ChunyaHuang, TaoKou, YujiaoXie, BingleiXue, Xue
Traffic flow prediction is the core challenge of transportation, and its key lies in effectively capturing the spatio-temporal dynamic dependencies. Aiming at the deficiencies of existing methods in modeling global temporal relations and dynamic spatial heterogeneity, this paper proposes a dynamic graph convolutional recurrent network (DGCRN) based on interactive progressive learning. First, the interactive progressive learning module (IPL) is designed to segment the input sequences through a tree structure, synchronize the extraction of spatiotemporal features using the interactive learning of parity subsequences, and adaptively capture the dynamic associations among nodes by combining with the dynamic graph convolutional recursive module (DGCRM). Secondly, a spatio-temporal embedding generator (STEG) is constructed to fuse temporal and spatial embedding to generate dynamic graph structures. Experiments validate the effectiveness of DGCRN on the PEMS04 and PEMS08 datasets with MAE
Su, JiangfengXie, ZilongLiu, ChunyaHe, LanKou, YujiaoXue, Xue
The paper examines how connected automated vehicles (CAVs) can navigate unsignalized intersections—especially those where major roads differ significantly from minor roads. The proposed method uses an improved incremental learning Monte Carlo Tree Search to quickly determine an optimal passing order for vehicles, adjusting in real time based on road conditions and vehicle states. Numerical experiments demonstrate that this approach achieves conflict-free, real-time cooperative, reducing average delays significantly compared to traditional traffic signal control. Compared to fully-actuated signal control, the proposed method achieves average delay reductions of 19.92s, 16.46s, and 15.47s for CAVs across varying demand patterns. The practical application of this research lies in its potential to enhance traffic efficiency in urban areas by replacing traditional signal-based control with intelligent, autonomous intersection management. This could lead to reduced congestion, lower fuel
Xue, YongjieGao, FengFeng, QiangCui, Shaohua
Traffic flow forecasting plays a pivotal role within intelligent transportation frameworks. Although existing methods combine graph neural networks and temporal models, there are still problems, such as static graph structure being challenging to characterize the dynamic associations between traffic nodes, insufficient ability to model long temporal dependencies, and low efficiency of fusion of complex spatio-temporal features, etc. Based on this, we propose a Transformer-based Temporal Representation Learning traffic flow prediction model (TRL-Trans). The proposed model employs Temporal Representation Learning (TRL) to derive contextual insights from heavily masked subsequences. It incorporates a Gated Temporal Convolutional Network (Gated TCN) coupled with an Adaptive Hybrid Graph Convolution Module (AHGCM) to effectively capture dynamic spatio-temporal characteristics. The AHGCM dynamically merges predefined adjacency matrices with implicit spatio-temporal relationships
Zhou, JianpingLu, ZongjiangWang, ZhongyuanHe, JinLiu, Chunya
Real-time traffic congestion prediction is essential for proactive traffic management, as it enhances the responsiveness of traffic systems, including route guidance, control, and enforcement. However, the heavy reliance on extensive historical data presents a significant challenge for real-time model updates. To overcome this limitation, this study proposes an advanced online learning framework that integrates a multi-head attention mechanism with LSTM-based ensemble learning. This approach incorporates traffic congestion factors as input features and employs average delay per kilometer as the predictive output. The experimental findings indicate that: 1) the proposed approach successfully enables real-time traffic congestion forecasting, and 2) it demonstrates strong adaptability in dynamic traffic environments.
Fu, ChuanyunLiu, JiamingLu, ZhaoyouWumaierjiang, AyinigeerLiu, HuahuaBai, Wei
Federated learning is an emerging distributed machine learning framework that allows edge devices to co-train global models without uploading their own data to a central server, which protects users’ data privacy. However, the problem of federated learning is that there is too much heterogeneity between users, including the size of the data, the different model structure, and the quality of the device. This problem leads to the need for more communication to train a better model, which also increases the cost of communication. To solve this problem, we developed the Fed-BNGC algorithm. First of all, the algorithm can perform the first screening according to the difference between the user’s system and the amount of data, and select the users with poor system evaluation value, and these users will not participate in this training. Secondly, the second screening is carried out according to the difference of the user’s model parameters, and the user with the greatest difference from other
Yang, ShuangyuKan, Zhongliang
With more 5G base stations coming into play, making an accurate assessment of RF-EMF exposure currently faces increasing demand to check if they meet regulatory requirements and ensure people’s safety. We present here PSF-Net, a novel deep learning network by uniting TabPFN’s meta-learned prior knowledge and SAINT’s dual attention structure; its use makes it particularly suitable to deal with applications like prediction of downlink power density and radiation level classification under different conditions within various kinds of 5G cell. A major component in the design of this approach is an uncertainty-aware gating block that determines the optimal weighting for each model output—TabPFN or SAINT—based on the estimated prediction variance as quantified via Monte Carlo sampling during training or the prediction variance calculated using inference-time dropout. In addition, a residual multi-layer perceptron (MLP) is also included to extract refined fused features and maintain a steady
Zhang, YanjinYu, Zefeng
.
Xie, DongxuanLi, DongyangZhang, YoukangZhao, YingjieHong, BaofengWang, Nan
In contemporary society, where Global Navigation Satellite Systems (GNSS) are utilised extensively, their inherent fragility gives rise to potential hazards with respect to the safety of ship navigation. In order to address this issue, the present study focuses on an ASM signal delay measurement system based on software defined radio peripherals. The system comprises two distinct components: a transmitting end and a receiving end. At the transmitting end, a signal generator, a first time-frequency synchronisation device, and a VHF transmitting antenna are employed to transmit ASM signals comprising dual Barker 13 code training sequences. At the receiving end, signals are received via software-defined radio equipment, a second time-frequency synchronisation device, a computing host, and a VHF receiving antenna. Utilising sliding correlation algorithms enables accurate time delay estimation. The present study leverages the high performance and low cost advantages of the universal
Li, HaoSun, XiaowenWang, TianqiZhou, ZeliangWang, Xiaoye
With the rapid development of Internet of Vehicles (IoV) and cyber-physical systems (CPS), connected autonomous vehicles (CAVs) have also developed rapidly. However, at the same time, in-vehicle networks also face more security challenges, mainly in terms of resource constraints, dynamic attacks, protocol heterogeneity, and high real-time requirements. Firstly, the trade-offs between lightweight encryption primitives and their software and hardware collaborative design in terms of performance, resource overhead, and security strength are analyzed. Secondly, the resource efficiency of AI-based intrusion detection system (IDS) is evaluated at the edge. Finally, we propose a dynamic adaptive collaborative defense framework (DACDF), which integrates federated learning with dynamic weight distillation, blockchain authentication with lightweight verifiable delay function (Light-VDF) and cross-domain IDS with hierarchical attention feature fusion to deal with collaborative attacks in resource
Zhou, YouZhang, JiguiDing, KaniYang, Guozhi
Recent advancements in energy efficient wireless communication protocols and low powered digital sensor technologies have led to the development of wireless sensor network (WSN) applications in diverse industries. These WSNs are generally designed using Bluetooth Low Energy (BLE), ZigBee and Wi-Fi communication protocol depending on the range and reliability requirements of the application. Designing these WSN applications also depends on the following factors. First, the environment under which devices operate varies with the industries and products they are employed in. Second, the energy availability for these devices is limited so higher signal strength for transmission and retransmission reduces the lifetime of these nodes significantly and finally, the size of networks is increasing hence scheduling and routing of messages becomes critical as well. These factors make simulation for these applications essential for evaluating the performance of WSNs before physical deployment of
Periwal, GarvitKoparde, PrashantSewalkar, Swarupanand
This paper presents a novel approach to automated robot programming and robot integration in manufacturing domain and minimizing the dependency on manual online/offline programming. Traditional industrial robots programming is typically done by online programing via teach pendants or by offline programming tools. This presents a major challenge as it requires skilled professionals and is a time-consuming process. In today’s competitive market, factories need to harness their full potential through smart and adaptive thinking to keep pace with evolving technology, customer demand, and manufacturing processes. This requires ability to manufacture multiple products on the same production line, minimum time for changeovers and implement robotic automation for efficiency enhancement. But each custom automation piece also demands significant human efforts for development and maintenance. By integrating the Robot Operating System (ROS) with vision-based 3D model generation systems, we address
Hepat, Abhijeet
Items per page:
1 – 50 of 6338