Browse Topic: Education and training

Items (6,356)
Find
Curvature-Based End-to-End Autonomous Vehicle Path Planning at Intersections2026-01-0045To be published on 04/07/2026
Autonomous vehicle navigation requires accurate prediction of driving path curvature to ensure smooth and safe trajectory planning. This paper presents an end-to-end approach to curvature prediction using deep neural networks trained on real-world driving data. We develop a comprehensive neural network architecture that directly maps high-dimensional sensor inputs to curvature predictions, eliminating the need for intermediate feature engineering steps. The model processes multi-modal inputs including vision features, vehicle state parameters, and environmental context through a deep learning pipeline. Our end-to-end approach demonstrates the feasibility of learning complex driving behaviors directly from raw sensor data, providing a more robust and generalization solution compared to traditional rule-based methods. The neural network architecture incorporates dropout regularization and adaptive learning rate scheduling to ensure stable training and optimal performance. Results show
Hajnorouzali, Yasaman, Wang, Hanchen, Li, Taozhe, Burch, Collin, Lee, Victoria, Tan, Lin, Arjmandzadeh, Ziba, Xu, Bin
Integrating Optimization and Model Fidelity Selection Methods for Real-Time Driver-in-the-Loop Vehicle Simulators2026-01-0621To be published on 04/07/2026
Automotive OEMs perform extensive prototype testing to configure vehicles for objective criteria (performance), and subjective criteria (handling and comfort). To reduce testing time and costs, OEMs rely on real-time Driver-In-the-Loop Simulators (DIL) running complex Multi-Body Dynamics (MBD) models. Recent advances in simulation technology have increased model accuracy but also operating costs, possibly limiting the viability of real-time DIL applications. Running high fidelity MBD models in real-time is computationally intensive and often requires re-configuration, CAE model de-contenting, solver setting optimization, which can introduce significant analysis errors. This presents a core challenge: selecting model fidelity levels that result in computationally efficient simulations, while maintaining sufficient predictive accuracy. This study introduces a methodology that integrates optimization algorithms with decision-making techniques to select the right fidelity within a
Balchanos, Michael, Emara, Mariam, Zarate Villazon, Angel, Mavris, Dimitri
HaloBus: Edge Computing‑Enabled Real‑Time Boarding and Exit Detection for Enhanced Transportation Safety Using Lightweight AI2026-01-0555To be published on 04/07/2026
This paper proposes HaloBus, an innovative, edge‑computing solution designed to mitigate this risk by detecting student boarding and exiting in real time using lightweight AI based methods. A persistent challenge in elementary school transportation is the issue of missing students after they exit their buses, which disproportionately impacts low-income households. Current safety systems are forced upon the individual households with their own methods. Common methods include applications on a personal device or a small tracker. However, not everyone can afford these options, and every parent deserves to feel like their child is safe. That is why HaloBus was invented. The system employs YOLOv5u—an Ultralytics‑enhanced, anchor‑free, split‑head architecture that offers a superior accuracy–speed tradeoff. By providing real-time, on-device alerts, HaloBus enables immediate intervention to prevent a student from being left behind, thereby shifting the focus from reactive post-incident
Getz, Grayson, Zadeh, Mehrdad, TAN, Teik-Khoon
Vehicle Test Platform with Experimentally Correlated Tire Model for Torque Vectoring Control2026-01-0622To be published on 04/07/2026
This paper presents a testing platform for torque vectoring controls utilizing a 10 degree of freedom (DOF) vehicle simulation and a ⅕ scale radio control test vehicle. These vehicle simulations or “Digital Twins” have been widely adopted throughout the automotive industry for their lower operating costs and ease of implementation. Virtual models are not perfect representations of reality, however, and physical testing is still necessary to validate systems for use in the real world. This is especially true when testing safety-critical features such as Advanced Driver Assist Systems (ADAS). As a result, a simulation environment working in conjunction with a test vehicle represents an optimal hybrid approach. In this work, a 1/5 scale radio controlled vehicle with torque vectoring capability is designed and assembled. A high fidelity vehicle model is then constructed in the Matlab/Simulink environment to model test vehicle behavior. The test vehicle features independent suspension for
Petersen, Nicholas Conner, Robinette, Darrell
Using Unreal Engine Software for Driving Studies: Developing Documentation to Support Collaboration2026-01-0517To be published on 04/07/2026
Context: A wide range of applications already support driving simulator studies, including CARLA, miniSim, VI-GRADE, SCANeR, and others, each with distinct strengths and limitations. However, many academic institutions are turning to free and accessible gaming platforms such as Unreal Engine and Unity. In the Human Factors Group at the University of Michigan Transportation Research Institute (UMTRI), a multidisciplinary team of 19 students is developing an Unreal Engine-based driving simulator as a research tool to investigate the difficulty of driving roads and for other purposes. Problem: Until recently, the absence of consistent documentation has created major obstacles, including errors in code management and steep learning curves for new contributors. To address the issue, the team initiated a development freeze and established documentation standards tailored to Unreal Engine’s Blueprint framework, a graphical node-based programming language that poses organizational and learning
Erturk, Selay, Stimec, Luka, Xin, Jared Hongyi, Tasmaan, Ashley, Mitani, Kate, Zhang, Luya, Green, Paul
Optimizing EV Battery Models for Full Vehicle Simulations2026-01-0389To be published on 04/07/2026
The increasing adoption of electric vehicles (EVs) demands accurate yet computationally efficient battery models that can be integrated into full vehicle simulations. At the cell level, mechanical battery models often employ fine-scale elements to capture localized deformation and failure phenomena. While such detailed discretization enables high-fidelity predictions, it also imposes significant computational costs that become prohibitive when scaling up to pack-level or full-vehicle crash and durability simulations. This research addresses the challenge by systematically simplifying cell-level mechanical models to reduce computational burden while preserving predictive accuracy. We propose an approach in which larger elements and reduced complexity representations are introduced without compromising the model’s ability to replicate experimentally observed behaviors. The methodology emphasizes model validation against targeted loading conditions, ensuring that the essential mechanics
Sahraei, Elham, Brar, Bavneet, Parmar, Dhruv, Muralidharan, Umachandran
A Real-time Capable, Three-dimensional, and Nonlinear Multibody Model of the Mercedes-Benz G-Class for an Efficient Assessment of Off-road Performance in Early Stages of Vehicle Development2026-01-0217To be published on 04/07/2026
This article deals with the development of a real-time capable, three-dimensional model of the Mercedes-Benz G-Class with flexible ladder frame that considers nonlinear suspension kinematics and force elements. The shift to new drivetrain technologies often results in a significant increase in vehicle weight and requires corresponding design modifications - also applying to off-road vehicles. These modifications result in changed stiffness of elements such as the ladder frame or anti-roll bar, which significantly affect vehicle dynamics and off-road performance. Therefore, strategic, efficient assessments must be made in early development stages, where no detailed information about individual systems and components is available yet, to detect and avoid potential massive, costly changes in later stages. This requires a “handmade” vehicle simulation model specifically tailored to this particular application, since the use of commercial multi-purpose simulation packages is not effective
Riebler, Sandro, Pernsteiner, Samuel, Granitz, Christina, Schabauer, Martin
A Sub Optimal Fuzzy Control Strategy for Balancing Driver Demand and Actuator Acceleration in Electrified Powertrains2026-01-0451To be published on 04/07/2026
Electrified powertrains—such as Power Splits, Series Hybrids, and EVs with Disconnect Actuators—enable flexible management of actuator acceleration and torque from shared power sources. In power-limited or high-demand conditions, the Hybrid Supervisor must balance available power to sustain performance and drivability; poor coordination can cause control imbalance, reduced actuator performance, and unintended motion. Conventional methods often favour a single control objective, compromising overall system efficiency. This paper introduces FLAIR (Fuzzy Learning Adaptive Integral Response) Control, a supervisory strategy for actuator speed profiling and driver demand tracking in SIMO systems. FLAIR integrates a integral of tracking error with fuzzy inferencing to dynamically weigh multiple control goals, adapting acceleration limits in real time while preserving driver power demand tracking. Unlike rigid approaches, it enables bi-directional power-flow decisions—allocating system power
Banuso, Abdulquadri, Sha, Hangxing, Shenoy, Aayush, Madireddy, Krishna Chaitanya
Development of a System for Regression Model Enhancement Utilizing Shape Generation AI2026-01-0499To be published on 04/07/2026
This study proposes a method to enhance regression models by shape generation AI. The approach focuses on automatically identifying regions within the design space where the model’s prediction accuracy is low. Once these regions are identified, new and diverse sample shapes are automatically generated by the shape generation AI and incorporated into the training dataset. The regression model is then retrained to improve its performance. By iteratively repeating this cycle of exploration, shape (FE mesh) generation, and model updating, the model’s reliability and accuracy across the entire design space are progressively enhanced. This method addresses data sparsity issues common in complex design tasks and enables better generalization to underrepresented regions. The effectiveness of the proposed system was demonstrated through a case study involving hood outer panels in automotive design. The results showed that adding AI-generated shapes improved prediction accuracy, particularly in
Taniguchi, Mashio
Energy Efficiency Analysis of U-Haul Truck and Trailer Systems: Impact of Tongue Weight and Load Variations2026-01-0466To be published on 04/07/2026
The demand for improved energy efficiency in real-world vehicle operations continues to grow with technology enhancement. When transporting large cargos with passenger pickup trucks and rental trailers, the interaction between vehicle payload, towing configuration, and fuel consumption becomes a key factor in overall system efficiency. Understanding how towing configurations and trailer loading influence fuel consumption and vehicle performance is critical for both consumer guidance and vehicle system design. This study investigates the energy efficiency of U-Haul truck and trailer systems, with a particular focus on the influence of trailer tongue weight. U-Haul truck and trailer simulation models were developed using AVL Vehicle Simulation Model (VSM) software, with an F-350 engine brake-specific fuel consumption (BSFC) map integrated to represent realistic engine performance. Two configurations with equal payload were evaluated: (1) a U-Haul truck alone, and (2) a U-Haul truck
Wang, Gang, Yang, Allan, Chen, Yan
Maintaining a Healthy Safety Culture in Autonomous Vehicle Development and Operations2026-01-0528To be published on 04/07/2026
The deployment of autonomous vehicles (AVs) requires not only technical excellence but also the cultivation of a robust organizational safety culture. While safety engineering standards and assurance processes provide essential structure, a culture that prioritizes learning, accountability, and continuous improvement is critical to ensuring public trust and operational resilience. This paper explores how UL 4600, the comprehensive safety standard for the evaluation of autonomous systems, and Safety Performance Indicators (SPIs) can be leveraged to build and sustain a Just Culture within an AV company. UL 4600 emphasizes systematic hazard identification, safety case construction, and ongoing evidence generation. When applied beyond compliance, it provides a framework for embedding safety considerations into day-to-day engineering and operational decision making. By mapping UL 4600 clauses into organizational processes and linking them with measurable SPIs—such as rates of system
Wagner, Michael, Gittleman, Michele
Physical Adversarial Infrastructure Attacks on Vision-Language Models for Autonomous Driving2026-01-0170To be published on 04/07/2026
Vision-language models (VLMs) offer a promising end-to-end approach for autonomous driving, but their robustness to physical adversarial attacks remains an unaddressed gap for safety-critical deployment. This paper introduces a systematic framework for evaluating these attacks using the Dolphins VLM and CARLA simulator. We employ Natural Evolution Strategies (NES), a black-box optimization method, to generate adversarial patches without internal model access. Our approach uses semantic similarity loss and Expectation over Transformation (EoT) to ensure physical realizability under varying viewing conditions. Patches are strategically placed on realistic advertising infrastructure (bus shelter panels and highway billboards), reflecting a plausible threat model. We establish two complementary scenarios: crosswalk pedestrian detection suppression and highway steering manipulation. Our evaluation reveals critical vulnerabilities. Adversarial patches achieved a 76.0% overall attack success
Fernandez, David, MohajerAnsari, Pedram, Salarpour, Amir, Pese, Mert D.
Adaptive Eco-Driving Feedback for Battery Electric Vehicles: A Reinforcement Learning Approach Using Context-Aware Policy Optimization2026-01-0165To be published on 04/07/2026
Energy efficiency and range optimization remain critical challenges to the widespread adoption of battery electric vehicles (BEVs). As a result, there is a growing demand for intelligent driver assistance systems that can extend the operating range and reduce range anxiety. This paper presents an adaptive eco-feedback and driver rating system based on proximal policy optimization (PPO) reinforcement learning, designed to support drivers with the target to reduce energy consumption and maximize driving range. The system processes real-time driving data, such as velocity, acceleration and powertrain status. Map data of high quality is used to anticipate traffic events, including but not limited to speed limits, curves, gradients, preceding vehicles and traffic lights. This contextual awareness allows the system to continuously assess driving behavior and provide personalized, context-aware visual feedback alongside a dynamic driving behavior rating. A PPO agent learns optimal feedback
Stocker, Christoph, Hirz, Mario, Martin, Michael, Kreis, Alexander, Stadler, Severin
Benchmarking Driver Responses in Head-On Conflicts: Toward an Objective Protocol for Human and AV Evaluation2026-01-0534To be published on 04/07/2026
Head-on emergency conflicts present a unique challenge for evaluating driver and automated vehicle (AV) performance. Unlike most emergency scenarios that follow a direct stimulus–response sequence, head-on encounters are characterized by a stimulus–wait–response pattern in which time to contact (TTC) strongly shapes driver behavior. Drawing on naturalistic and simulator data, this study quantified human responses to head-on conflicts. When the opposing vehicle crossed the centerline with more than 2 seconds of TTC, drivers delayed braking until an average of 1.3 seconds (SD = 0.8) before impact, regardless of the timing of the intrusion. By contrast, when TTC was less than 2 seconds, braking was initiated only 0 to 1.0 second before impact. As a result, many drivers applied the brakes less than half a second before collision. These findings provide a meta-analytically grounded benchmark for comparing human behavior to AV decision-making processes and demonstrate the need for conflict
Muttart, Jeffrey, Dinakar, Swaroop, Maloney, Tim, Adikhari, Bikram, Gernhard-Macha, Suntasty
Machine Learning Modeling for Compressive Property Prediction of Foams2026-01-0512To be published on 04/07/2026
Foam material models for automotive structural analysis typically require tensile and compressive data at multiple strain rates. The testing is costly and may require a long time to complete. For many applications, foams of similar chemistry are used and the foam structural responses, such as stiffness and compression force deflection, are controlled by the foam density. In such cases, Machine Learning (ML) lends itself as an ideal tool to detect the trends in material response based on density and strain rate. In this paper, five microcellular polyurethane (PU) foams of different densities were tested at four strain rates ranging from 0.01/s to 100/s. A ML model capable of predicting compressive stress-strain response for a range of densities was developed. The model demonstrated good prediction capability for intermediate strain rates at all foam densities and in extrapolating stress-strain curves at higher densities at all strain rates. The strain rate trends for a density outside
M, Gokula Krishnan, Kavimani, Harish, Muppana, Sai Siddhartha, Savic, Vesna, Chavare, Sudeep, V S, Rajamanickam
Lateral stability and energy-saving integrated control of distributed drive vehicles with four wheel hub motors2026-01-0635To be published on 04/07/2026
Abstract: In order to improve the lateral stability and energy optimization of four-wheel hub motor distributed drive vehicles under complex road conditions, a layered control strategy for yaw stability is proposed. The upper controller is designed based on the sliding mode control principle to create a yaw moment controller, establishing both a two-degree-of-freedom model and a seven-degree-of-freedom model for the vehicle, tracking the desired yaw rate, desired center of mass side slip angle, actual yaw rate, and actual center of mass side slip angle to obtain the corresponding additional yaw moment. Moreover, the state of the vehicle is analyzed using the phase plane method of the center of mass side slip angle and yaw rate, and the total additional yaw moment for the vehicle is computed based on weighted calculations according to the state. Additionally, an unscented Kalman filter observer is established to enhance the tracking accuracy of the actual yaw rate and actual center of
shi, cheng'ao, liu, bingsen, Zou, Xiaojun, Wang, Tao, Zhang, Ming
NN FMU: Deep Learning Models for Next-Gen xiL Vehicle Simulation2026-26-04521/16/2026
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, Rangarajan, Ashok Bharde, Pooja, Mhetras, Mayur, Chehire, Marc
Optimizing System Design Performance and Its Accuracy Using Feature Importance2026-26-04211/16/2026
With advancements in model accuracy and computational power, system simulation is increasingly integrated into development tools as a “virtual test bed” alongside experimental testing. However, virtual vehicle and powertrain thermal models still face challenges, particularly in ensuring accuracy across systems developed by various internal and external sources. These models, often built using different software platforms, are difficult to validate consistently, especially when integrated in a Co-simulation environment. This integration can degrade the overall accuracy of the Vehicle Simulation Platform, reducing the return on investment in model development. To address these limitations, this paper proposes the use of machine learning-based feature importance techniques at the vehicle-level simulation stage. Feature importance helps identify the most influential variables affecting system outputs. By focusing calibration and validation efforts on these key variables, the approach aims
Srinivasan, Rangarajan, Sarapalli Ramachandran, Raghuveeran, Ashok Bharde, Pooja, Saravanan, Vivek
Implementation of New Educational Technologies for Training Personnel for the Transport Industry2026-26-02411/16/2026
The article is devoted to a comprehensive analysis of the digital transformation of education using the example of a project to train engineering personnel for the innovative transport industry in Russia. Special attention is paid to the introduction of hybrid formats, digital platforms, inclusivity, issues of digital inequality, as well as the experience of the National Research Center of the Russian Federation FSUE NAMI and interaction with leading universities in the country. A comparative analysis with foreign initiatives, including modern AI solutions for inclusive education, is presented, as well as the impact of the project to create educational and methodological centers on the professional motivation of teachers.
Shishanov, Sergei, Kurmaev, Rinat, Revenok, Svetlana
Driver-in-the-Loop Optimization of Tire-Vehicle Dynamics for Variant Application through Physical Tire Model2026-26-00991/16/2026
Today due to time to market requirements, Original Equipment Manufacturers (OEM) prefers platform modularity for Product Development in Automotive Domain. Money and time being main constraint we need to focus on single platform which can give flavors of different category just by changing Ride height and Tyre and some extra tunable. Taking this as challenge still tyre development for new variant demands lot of time and iterations which can lead to delays in time to market. This study provides a virtual development process using driver in loop Simulator and Multi body dynamics simulation which are real time capable and integrating physical tire models. The proposed alteration introduces ride height changes, weight distribution changes, and center of gravity changes from existing vehicle design. The proposed new vehicle variant also introduces tire change from highway terrain type to all-terrain type as it was intended to deliver some off-roading capabilities, thereby vehicle dynamics
Shrivastava, Apoorv, Asthana, Shivam
Boosting the Development of a BEV Rear Twist Beam Suspension Through a Pioneering Approach: ADAMS Real Time on Driving Simulator2026-26-03971/16/2026
Twist beam suspensions are widely utilised in passenger vehicles because of their simplicity and cost-efficiency, yet they provide engineers with a complex challenge as their performance depends entirely upon the structural properties of the beam itself. Traditional methodologies rely on the generation of Modal Neutral Files (MNF) based upon vehicle dynamics requirements and packaging constraints, which is a highly time-consuming process that starts failing to fulfil the demands of a market where development times are being exponentially reduced. Besides this, part of flexible body’s real behaviour might be lost in the process of converting multibody models into parametric ones, which, in turn, presents difficulties in modifying compliant-related items. Thanks to a novel approach followed jointly by Applus+ IDIADA & Mahindra, quick identification and optimisation of key tuneable items is achieved by employing a hybrid solution that combines full flexible and FE elements in Hexagon
Osorio, Alejandro García, Prabhakara Rao, Vageesh, Asthana, Shivam, Rasal, Shraddhesh
Lightweight AI Deployment for Legacy Automotive ECUs: A Practical Optimization Approach2026-26-06631/16/2026
Automotive systems are increasingly adopting data-driven and intelligent functionality in the areas of predictive maintenance, virtual sensors and diagnostics. This has led to a need for the AI models to be directly run on vehicle ECUs. However, most of these ECUs – especially those in cost-sensitive or legacy platforms lack the computational capacity and parallel processing support required for standard AI implementations. Given the stringent real-time and reliability requirements in automotive environments, deploying such models presents a unique challenge. This paper proposes a practical methodology to optimize both the training and deployment phases of AI models for low-computation ECUs that operate without parallelism. Designing lightweight model architectures, using pruning and quantization techniques to minimize resource utilization, and putting in place a strategy appropriate for single-threaded execution are the three main objectives of the developed approach. The goal is to
Sharma, Sahil, Mathew, Melvin John
Waste Heat Recovery Evaluation in FCEV Truck on Different Drive-Cycles2026-26-02591/16/2026
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
Conceptual Crash Analysis in Automotive Applications with Reduced Computational Effort2026-26-04511/16/2026
In the realm of automotive safety engineering, the demand for efficient and accurate crash simulations is ever-increasing. As finite element (FE) modeling of components becomes increasingly detailed and the availability of advanced material models improves, crash simulations for full vehicles can become time-consuming. Evaluating the crash performance of any vehicle subsystem requires structural simulations at different levels. While the design and configuration phase deals with a local simulation in representative load cases, full vehicle simulations are required later for a final digital proof of achieved requirements and development targets. This paper introduces a novel methodology for replacing full vehicle crash simulations, as required for a local view on the structural load path development, through segment-models. By adapting segment-model simulations, a significant reduction in computational time and resource usage is achieved, thereby optimizing CPU cluster performance and
Moncayo, David, Malipatil, Anand, Prasad, Rakesh, Kunnath, Allwin
Multi-Band Frequency Approach to Correlate Proving Ground and Road Simulator for an Electric Two-Wheeler2026-26-05561/16/2026
Real-world usage subjects two-wheelers to complex and varying dynamic loads, necessitating early-stage durability validation to ensure robust product development. Conducting a full life-cycle durability testing on proving grounds is time-consuming, extremely difficult for the riders involved, and costly, which is why accelerated testing using rigs such as the road simulator system have become a preferred approach. The use of road simulators necessitates, accurately measured inputs and precise simulation to ensure proper actuation of the rig, thereby enabling realistic representation of road undulations. This paper covers two important aspects essential for achieving an accurate and clear representation of road simulation in a 4-DOF road simulator, encompassing both longitudinal and vertical simulations at the front and rear of the vehicle. The first aspect involves the development of an instrumentation strategy for the two-wheeler, with careful identification of directionally sensitive
Ganju, Shubham, V, Vijayamirtharaj, Prasad, Sathish, R S, Mahenthran
Simulation Based Optimization of the NVH Characteristics in Modern High Speed Engine During Development Phase2026-26-03261/16/2026
Engine noise mitigation is paramount in powertrain development for enhanced performance and occupant comfort. Identifying NVH problems at the prototype stage leads to costly and time-consuming redesigns and modifications, potentially delaying the product launch. NVH simulations facilitate identification of noise and vibration sources, informing design modifications prior to physical prototyping. Early detection and resolution of NVH problems through simulation can significantly shorten the overall development cycle and multiple physical prototypes and costly redesigns. During NVH simulations, predicting and optimizing valvetrain and timing drive noise necessitates transfer of bearing, valve spring, and contact forces to NVH simulation models. Traditional simulations, involved continuous force data export and NVH model evaluation for each design variant, pose efficiency challenges. In this paper, an approach for preliminary assessment of dB level reductions across design iterations is
Rai, Ankur, Deshpande, Ajay Mahadeo, Yadav, Rakesh
Virtual Validation of ADAS Algorithms Using Driver-in-the-Loop Simulation2026-26-00501/16/2026
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, Chinmaya, Bhagat, Ajinkya, Kale, Jyoti Ganesh, Karle, Ujjwala
Prediction of REESS Factor for SOC Correction in Hybrid Vehicles2026-26-04711/16/2026
The regulatory mechanisms to measure emissions from automobiles have evolved drastically over the years. Certification of CO2 emissions is one of them. It is not only critical for environmental protection but can also invite heavy fines to OEMs, if not complied with. In homologation test of a Hybrid Vehicle, it is necessary to correct the measured CO2 to account for deviations in measurement from failed Start-Stop phase and difference between start and end State of Charge (SOC) of battery. The correction methodology is also applicable for vehicle simulation in Software-in-Loop environment and for analyzing vehicle test data for CO2 emissions with programmed digital tools. The focus of this paper is on the correction of CO2 derived from SOC delta in the WLTP homologation drive cycle. The battery energy delta due to difference in SOC between start and end of drive cycle should be converted to corresponding CO2 expended from Internal Combustion Engine. The resulting correction factor is
Gopinath, Shravanthi Poorigali, Khatod, Krishna
Correlation of Power Rating for Battery Electric Vehicles: Simulation vs. Test Validation in Accordance with Regulatory Compliance2026-26-05751/16/2026
Accurate power and energy assessment in Battery Electric Vehicles (BEVs) requires high-fidelity simulation models that reflect real-world performance. This study presents a power rating correlation of the BEV model in compliance with the GTR 21[1] standard, validating the simulation’s accuracy against physical test data. Simulations were conducted using Matlab and Simulink based Simulation tool to estimate Electric Drive Module (EDM) power at the motor output and gearbox input under standardized conditions. The operating parameters were shared with the testing team to ensure consistency; however, the initial test results deviated by approximately 4% to 5% from the simulation target. To address this delta, EDM speed and vehicle speed were optimized, achieving a close alignment with the simulation and meeting the power rating targets. The results demonstrate a strong correlation between the simulation and test data, confirming the model’s accuracy and reliability. This study underscores
Mahajan, Prasad, Kesarkar, Sidhesh, Ali, Shoaib
Adoptive Safety Solutions in Road Simulators for Commercial Vehicle Structural Validation2026-26-05331/16/2026
Road Simulators used to carry out accelerated structural durability validation of a vehicle. As a commercial vehicle manufacturer, for our commercial vehicles structural validation, we are using 8 poster road simulators. We use road load data, torture track data, synthetic profiles or road events as the input test data. From a mini 4 wheeler trucks to high capacity 8 wheeler truck, and any bus variant is being tested at road simulator. All the vehicle variants are tested with prescribed road and load conditions for the pre-determined life. Each wheel of the vehicle is positioned on the wheel pan of the hydraulic actuators so that each actuator excites the corresponding vibration data. The vehicle is being restrained as per the manufacturers recommendation. Manufacturer recommendations widely addresses the risks associated with the test rigs. In addition to that there are risks associated with the vehicle running, vehicle handling, vehicle positioning. For example, when durability test
Arumugam, Paramasivam, N, Gopi Kannan, N, Mahendra, Muthu kumar, Pandurangan, Singh, Laxman, Tiwari, Manish, V, Subash
Overview of Automotive Policies, Evolution of Automotive Regulations, and Striking a Balanced Approach for Harmonization2026-26-02421/16/2026
The automotive regulatory landscape in India is evolving rapidly, driven by a dynamic policy intervention by GOI, striking push for sustainable mobility, safety, technological advancements, dEnvironmentally soundeeper localization, energy self-reliance, product quality control and simplified registration process. Key regulations cover areas like vehicle safety norms, emission norms, fuel economy norms, BIS QCO, the promotion of EVs and alternative fuel vehicles, R & D roadmaps, ELVs, incentive policies and vehicle registration reforms. India has been keeping a close eye on the automotive regulatory progress in the Europe as well as other developed countries as a cornerstone for technical harmonization, cross learning, gauge benefits and economic implications. India is progressively aligning its automotive regulations with global standards, particularly with UN Regulations and GTRs, while also considering unique Indian driving and environmental conditions. This alignment is crucial for
Patil, Dharmarayagouda
Methodical Approach to Preparedness of India Specific Automotive Database Matrix with Example of AEB Scenarios2026-26-06511/16/2026
The purpose of this report is to identify systematic approach of formation of India specific automotive database matrix. At first the paper reviews the practices used to prepare automotive dataset catalogue with established pattern to showcase automotive dataset from which appropriate data clusters can be picked up judiciously in order to train ADAS algorithms. The work applies this framework which helps to establish strategy to build a grid in which Indian automotive dataset can be contoured and selection of serviceable data bunches can be picked. This would make sure prompt selection of database aiming model training with valid input. This serves the purpose of implementation and evaluation of varied ADAS levels in India which insist upon good quality of distinguished dataset pertaining to Indian scenarios. The paper describes the approach with the example of AEB scenarios and present appropriate matrix readiness comprising of relevant data objects excluding unnecessary junk data
Behere, Sayali Rajendra, Karle, Manish, Karle, Ujjwala
Optimizing Tire NVH Performance in Electric Vehicles: A Comprehensive Approach Using Benchmarking, Simulation, and Validation2026-26-06051/16/2026
The present study enumerates the effectiveness of using Foam-inside Tyres (FIT) for attenuating the in-cabin noise due to tire-road interaction in Internal Combustion Engines (ICE) converted Electric SUVs (E-SUV). Due to the elimination of the ICE Prime movers in (E-SUV), the Tyre booming, Tyre cavity, and rumbling noise in the structure-borne region are significantly audible in the driver’s & passenger's ears globally for E-SUVs. Foam tyres reduce tyre cavity resonance. However, the effectiveness of the acoustic foam is predominant between 180 to 240 Hz only. In the present study, In Cabin Noise (ICN) measurement was completed on the comfort testing track, and the results of structure-borne in-cabin noise up to 500 Hz were analysed. These measurements identified the vehicle in-cabin sensitive frequencies, which are affected by the tyre and wheel assembly. To analyse the contribution of the Tyre design parameters and to predict the ICN performance in the whole vehicle simulation, CD
Singh, Ram Krishnan, Deivasigamani Purushothaman, Balakrishnan, Paua, Ketan, Ahire, Manoj, Adiga, Ganesh N
Simulation Driven Design of Crank-train Systems for Elevated In-Cylinder Combustion Pressures for Existing Architecture2026-26-04001/16/2026
The work demonstrating a novel approach to the optimization of crankshaft design for heavy-duty commercial vehicle engines, specifically targeting non-automotive applications with elevated power ratings. The research focuses on a 6-cylinder, 5.6-litre diesel engine, originally rated at 160 kVA and upgraded to 200 kVA, where the challenge was to enhance the crank-train system’s robustness within existing packaging constraints. By fundamentally altering the crankshaft’s geometry and structural parameters, the new design achieves higher load-bearing capacity while inherently mitigating torsional vibrations, thereby eliminating the need for viscous dampers traditionally used in place of rubber dampers. Advanced simulation tools, notably AVL Excite, employed to iterate and evaluate the balance between crankshaft balance ratio, weight, and torsional behavior. The optimized design then validated through both simulation and physical vibration trials, with sixth-order angular displacement
Khandelwal, Meha, Kaundabalaraman, Kaarthic, Rathi, Hemantkumar
An Integrated Digital Platform for Wiring Harness Testing2026-26-05031/16/2026
This article describes an enhanced, more efficient way to build and test wire harnesses. The wire harness is a complex, organized bundle of wire found in virtually every motorized vehicle, machinery and equipment. Manual work is usually performed in assembling such harnesses, which is time-consuming and error-prone. Workers usually rely on printed diagrams and basic tools, which can be tiring and tricky to follow, especially when the designs change often. The new system solves many of these issues by combining a smart testing machine called Quad 64 with a large digital display workbench. Instead of looking at paper drawings, workers can now see the full wire layout directly on a screen, life-sized and clear. This makes it easier to understand where each wire goes and what to do next. What’s really helpful is that the system can spot mistakes right away. If a connector is omitted or a wire is placed wrongly, the system will report the error immediately and show it and the remedy. It
Sancheti, Rahul Madanlal
Simulation of EV Range Estimation for Different Payload of Vehicle2026-26-03891/16/2026
The electrification of transportation is revolutionizing the automotive and logistics sectors, with electric vehicles (EVs) assuming an increasingly pivotal role in both passenger mobility and commercial activities. As the adoption of EVs rises, the necessity for precise range estimation becomes essential, especially under diverse operational circumstances, including vehicle and battery characteristics, driving conditions, environmental influences, vehicle configurations, and user-specific behaviors. Among the varying factors, a key fluctuating one is user behavior—most notably, increased payload, which significantly affects EV range. A key business challenge lies in the significant variability of EV range due to changes in vehicle load, which can affect performance, operational efficiency, and cost-effectiveness—especially for fleet-based services. This research aims to tackle the technical deficiency in forecasting electric vehicle (EV) range under various payload conditions
Khatal, Swaraj, Gupta, Anjali, Krishna, Thallapaka
Testing and Validation of Future Mobility Vehicles using Realistic Digital Twin of Road Corridors and Tires2026-26-05801/16/2026
The automotive industry is rapidly evolving with technologies such as vehicle electrification, autonomous driving, Advanced Driver Assistance Systems (ADAS), and active suspension systems. Testing and validating these technologies under India’s diverse and complex road conditions is a major challenge. Physical testing alone is often impractical due to variability in road surfaces, traffic patterns, and environmental conditions, as well as safety constraints. Virtual testing using high-fidelity digital twins of road corridors offers an effective solution for replicating real-world conditions in a controlled environment. This paper highlights the representation of Indian road corridors as digital twins in ASAM OpenDRIVE and OpenCRG formats, emphasizing the critical elements required for realistic simulation of vehicle, tire, and ADAS performance. The digital twin incorporates detailed 3D road profiles (X-Y-Z coordinates), capturing the geometry and surface variations of Indian roads. The
Joshi, Omkar Prakash, Shinde, Vikram, Pawar, Prashant R
Establishing a Scalable Virtual Framework for ADAS Validation Traffic Jam Pilot with Real-World Scene Integration2026-26-05061/16/2026
Advanced Driver Assistance Systems (ADAS) are instrumental in improving road safety and minimizing traffic-related incidents. However, their development and validation processes are resource-intensive, requiring substantial time, cost, and domain-specific expertise. Moreover, real-world testing introduces significant safety challenges. To address these issues, virtual simulation platforms offer high-fidelity environments for the secure and efficient testing of ADAS functions. This research presents a virtual validation framework for a Traffic Jam Pilot (TJP) algorithm utilizing such simulators. The framework features detailed models of camera and radar sensors, capturing essential parameters like detection range and field of view, alongside a vehicle plant model and road infrastructure modeling that includes elements such as curvature, slope, banking angles, and varying lane widths. A perception stack is developed using synthetic sensor data and is integrated with the TJP control
Agrawal, Mridul, Ithape, Avinash, Sharma, Prashant, Trivedi, Abhishek
Simulation Driven Virtual Road Load and Accelerated Duty Cycle Generation for 3-Speed eAxle Systems2026-26-04011/16/2026
The transition from Internal Combustion Engine (ICE) vehicles to Battery Electric Vehicles (BEVs) introduces significant challenges in drivetrain development, particularly when historical road load data (RLD) is unavailable This study presents a methodology for virtually generating and processing road load data (RLD) to assess the durability of a new 3-speed electric axle (eAxle) design before building a physical prototype. Using AVL Route Studio, we simulated a range of driving conditions including urban, highway, and mixed-terrain routes, covering diverse global scenarios. These simulations produced high-frequency torque and speed data representative of real-world operation. Given that the raw dataset contained millions of points, direct use for fatigue assessment was impractical. To address this, the data was imported into Romax, where it was condensed into an accelerated duty cycle while preserving the cumulative fatigue damage patterns from the original dataset. Unlike
Ligade, Pratik, Khan, Nuruzzama Mehadi, Koona, Rammohan Rao
SAE TOMORROW TODAY - An Inside Look at the 2026 Detroit Auto Show135491/2/2026
From surprise unveilings to one-of-a-kind experiences, excitement is building for the 2026 Detroit Auto Show. But it's about more than just horsepower. This year, SAE International is co-sponsoring Media and Industry Days, where OEMs, suppliers, tech leaders, and students come together for vehicle debuts, industry insights, and future-focused conversations. Listen in as Sam Klemet, Executive Director of the Detroit Auto Dealers Association, discusses what visitors can expect this year, including new STEM-driven, career-focused activities designed to inspire future engineers. He also highlights the show's multi-million-dollar philanthropic and economic impact, and how its growing emphasis on education, talent development, and innovation continues to reflect the true spirit of the Motor City. We'd love to hear from you. Share your comments, questions and ideas for future topics and guests to podcast@sae.org. Don't forget to take a moment to follow SAE Tomorrow Today--a podcast where we
Patterson, Lori
An Interpretable Deep Learning Decision-Making Framework for Autonomous Lane-Change Inspired by Human Driving Experiences2025-01-733912/31/2025
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, Yanbo, Chen, Jiaqi, Yu, Huilong, Xi, Junqiang
Detection of Dangerous Driving Postures Based on Depth Images Using an Anchor Regression Method2025-01-734312/31/2025
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, Hailan, Li, Wuhuan, Lu, Jun, Wang, Xin, He, Wenhao, Chen, Zhenming, Liu, Yunjie
Automating Concrete Simulation Scenario Generation for Autonomous Driving with Large Language Models2025-01-731812/31/2025
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, Jiwei, Wang, Runmin
Deconstructing Driver State in Smart Cockpits: Physiological Validation of Perceived Risk, Trust, and Fatigue during Automated Driving2025-01-734512/31/2025
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, Zhenyuan, Li, Qingkun, Wang, Wenjun, Liu, Weimin, Sun, Zhaocong, Cheng, Bo
Driver Personalized Lane Change Behavior Analysis Based on Attention Deep Embedding Clustering2025-01-734712/31/2025
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, Haomin, Wang, Wei, Wang, Yue, Li, Lun, Yue, Yi, Tian, Jiaxiao, Han, Jiayi
Research and Implementation of a Neural Radiance Fields-Based 3D Reconstruction Method for Autonomous Driving Scenes2025-01-731012/31/2025
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, Deng, Zou, Jie, Chen, Yuhan, Meng, Zhangjie, Li, Jie, Li, Guofa
Research on Passengers’ Willingness to Travel by Rail Transit Based on Objective Factors and Subjective Perceptions2025-99-025112/23/2025
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, Gang, Huang, Lei, Yang, Yihao
Risk Identification and Accompanying Information Service Design of Long Downhill Road Section2025-99-025012/23/2025
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, Yuejia, Weng, Wenzhong, Luan, Sen, Dai, Yibo
Investigating the Impact of Social Media on Driving Safety: A Case Study in Hong Kong2025-99-025412/23/2025
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, Jinhai, Ye, Haocheng, Cui, Ziheng, Chen, Yang
Development of a Localized Heat Treatment Route for Stamped Automotive Parts2025-36-008912/18/2025
2
Santana, Jessica, Curti, Gustavo, Lima, Tiago, Sarmento, Matheus, Callegari, Bruna, Folle, Luis
Items per page:
1 – 50 of 6356