Browse Topic: Education and training

Items (1,753)
Find
SAE TOMORROW TODAY - Scalable AV Deployment Starts with Fewer Close Calls1351305/01/2025
The hallmark of exceptional autonomous driving technology isn't just how it reacts in a crisis but how it avoids one altogether. That's the vision behind May Mobility: a world where self-driving cars confidently navigate busy intersections, unexpected detours, and pedestrian-filled crosswalks with the instincts of a seasoned human driver. At the core of May Mobility's technology platform is its patented Multi-Policy Decision Making (MPDM) system. This breakthrough technology uses real-time, in-situ AI to interpret data, continuously learning and adapting to new, complex, and unpredictable driving conditions. By learning on the fly--much like a human driver--May Mobility's AVs can be deployed faster and more cost-effectively than traditional systems. To explore how May Mobility is scaling its AV technology, we spoke with Ed Olson, CEO and Founder, about the company's city-wide AV deployments, strategic partnerships with Toyota and NTT, and its entrance into the rideshare market through
Hineman, Marcie
Podcast
Study on Motorcycle Rider Model Using Reinforcement Learning - Learning Examples Including Following Target Velocity and Basic Research on Rider Proficiency2024-32-002804/18/2025
In this study, an initial approach using deep reinforcement learning to replicate the complex behaviors of motorcycle riders was presented. Three learning examples were demonstrated: following a target velocity, maintaining stability at low speeds, and following a target trajectory. These examples serve as a starting point for further research. Additionally, the proficiency of the constructed models was examined using rider proficiency evaluation methods developed in previous studies. Initial results indicated that the models have the potential to mimic real rider behaviors; however, challenges such as differences between the model’s output and what humans can produce were also identified for future work.
Mitsuhashi, Yasuhiro, Momiyama, Yoshitaka, Yabe, Noboru
Technical Paper
System Configuration and Validation of Hybrid-Based Six Degrees of Freedom Motion Platform for Vehicle Dynamic Testing2025-01-502103/27/2025
Scenario-based testing has become one of the important elements to evaluate the performance of automated vehicle systems before deploying on actual road. There are several approaches that can be used to conduct scenario-based testing via simulation approach. One of the important aspects in scenario-based safety testing is the driver-in-the-loop (DiL) simulation where it involves integration of hardware and human interaction. Therefore, motion platform-based vehicle driving simulators are commonly used for the DiL simulation for scenario-based testing. Generally, a high degree of freedom driving simulator is used for scenario-based testing such as 6 degrees of freedom (DoF) to achieve high accuracy to represent an actual vehicle response. Moreover, most of the motion platforms are designed using hexapod configuration, which also contributes to 6-DoF. However, this type of design requires large space to conduct the testing because the field of motion (FoM) is high in three axes and high
Kleolee, KahOnn, Aparow, Vimal Rau, Cheok, Jun Hong, de Boer, Niels, Jamaluddin, Hishamuddin
Technical Paper
Intelligent Courier Delivery Scheduling Based on XGBoost Feature Selection and Reinforcement Learning: A Case Study Using Chongqing Cainiao Express Data2025-01-717602/21/2025
This study tackles the issue of order delays in logistics using XGBoost for feature analysis and reinforcement learning for intelligent courier scheduling. Pickup order data from May 1 to October 31, 2023, in Chongqing is analyzed using spatio-temporal statistical methods. Key findings include that order placement peaks at 9:00 a.m., delays peak at 10:00 a.m., and the delay rate is 8.6%. A significant imbalance exists between the regional daily average of dispatchable couriers and order volumes.XGBoost is employed to predict order delays, revealing that pickup location is the most influential factor (27%), followed by courier pickup location (22%). These factors and their relationships are identified as key drivers of delays.To address these issues, a reinforcement learning-based courier scheduling optimization model is developed. The model defines courier location, current time, and pending orders as state variables and adopts an epsilon-greedy strategy for action selection
Wang, Manjun, Yu, Xinlian
Technical Paper
SAE TOMORROW TODAY: Launching Human Space Travel with a Luxury Balloon1349801/23/2025
Imagine a six-hour journey to outer space that includes a world-class meal, cocktail service, Wi-Fi, and unprecedented views of Earth. This experience could soon become reality. Space Perspective, the world's first carbon-neutral spaceflight experience company, is commercializing space travel with Spaceship Neptune, a pressurized capsule propelled by a giant SpaceBalloon(TM). The experience is designed to be gentle and accessible with no rockets, weightlessness, heavy g-forces, or training required. Alongside world-class meal and cocktail service, space travelers will also enjoy views through the largest windows ever flown to space, Wi-Fi, and a proper restroom. To learn more, we sat down with Taber MacCallum, Founder and Chief Technology Officer, Space Perspective, to discuss the technical development of the SpaceBalloon(TM) and how the company is unlocking the market for space travel in a new and innovative way. We'd love to hear from you. Share your comments, questions and ideas for
Hineman, Marcie
Podcast
Vehicle-Level Control Systems Framework for Use in Create-GV Vehicle Dynamics Simulations2024-01-410709/16/2024
Abstract This paper presents a software framework developed for the simulation of vehicle-level control systems for modern (existing or conceptual) ground vehicles, targeted for high-performance platforms (Linux clusters). The framework augmented existing ground vehicle simulation environments (such as CREATE-GV MERCURY or other object-oriented software packages) making it possible to perform a comprehensive evaluation of a ground vehicle’s performance when equipped with vehicle level controllers to determine the effectiveness of the control systems on the vehicle. The framework, implemented as part of the PACE (Powertrain Analysis Computational Environment), was comprised of software components (a C++ objects library) simulating various vehicle-level controllers, an Application Programming Interface for the development of new components to be used within the framework, and C++ code for integrating these components into simulations of control systems within a ground vehicle simulation
Jelinek, Bohumir, Henley, Greg, Card, Angela, Hannis, Tyler, Gibson, Michael, Priddy, Jody, Boyle, Sara, Figueroa-Santos, Miriam, Mange, Jeremy
Technical Paper
Casting Equipment Engineering GuideB-ASM-05603/01/2024
Casting Equipment Engineering Guide is an essential resource covering engineering details of casting equipment, their design features, applications, capabilities, and selection guidelines. This book is written for mechanical engineers, practicing engineers, engineering students, and metallurgists specializing in casting technology.
Book
Generation of tire digital twin for virtual MBD simulation of vehicles for durability, NVH and handling evaluation2024-26-030101/16/2024
With the recent development in virtual modelling and vehicle simulation technology, many OEM's worldwide are using digital road profiles in virtual environment for vehicle durability load prediction and virtual design evaluation. For precise simulation results, it is important to have the tire digital twin which is the realistic representation of tire in the virtual environment. The study comprises of discussion about different types of tire models such as empirical, solid model, rigid ring model and flexural ring models such as Pacejka, MF Swift, CD tire, F tire etc. and also the complexity involved in development of these tire models. Generation of virtual tire model requires highly sophisticated test rigs as well as vehicle level testing with Wheel Force transducers and other vehicle dynamics sensors. The large number of data points generated with testing are converted in standard TYDEX format to be further processed in various software tool for virtual model generation. Thus, a
Bakal, Nikhil
Technical Paper
Model Based NVH Simulator for Virtual Development2025-01-005905/05/2023
For mature virtual development, enlarging coverage of performances and driving conditions comparable with physical prototype is important. The subjective evaluation on various driving conditions to find abnormal or nonlinear phenomenon as well as objective evaluation becomes indispensable even in virtual development stage. From the previous research, the road noise had been successfully predicted and replayed from the synthesis of system models. In this study, model based NVH simulator dedicated to virtual development have been implemented. At first, in addition to road noise, motor noise was predicted from experimental models such as blocked force and transfer function of motor, mount and body according to various vehicle conditions such as speed and torque. Next, to convert driver’s inputs such as acceleration and brake pedal, mode selection button and steering wheel to vehicle condition, 1-D performance model was generated and calibrated. Finally, the audio and visual feedback
Park, Sangyoung, Dirickx, Tom, Kang, Yeon June, Nam, Jeong Min
Technical Paper
Simulation of in-vehicle tire noise performance from single-tire test stand2025-01-006105/05/2023
A test and signal processing strategy was developed to allow a tire manufacturer to predict vehicle-level interior response based on component-level testing of a single tire. The approach leveraged time-domain Source-Path-Contribution (SPC) techniques to build an experimental model of an existing single tire tested on a dynamometer and substitute into a simulator vehicle to predict vehicle-level performance. The component-level single tire was characterized by its acoustic source strength and structural forces estimated by means of virtual point transformation and a matrix inversion approach. These source strengths and forces were then inserted into a simulator vehicle model to predict the acoustic signature, in time-domain, at the passenger’s ears. This approach was validated by comparing the vehicle-level prediction to vehicle-level measured response. The experimental model building procedure can then be adopted as a standard procedure to aid in vehicle development programs.
Nashio, Hiroshi, Kajiwara, Kohei, Rinaldi, Giovanni, Sakamoto, Yumiko
Technical Paper
Leveraging user feedback to optimize the tuning of EVSE models2025-01-002005/05/2023
The implementation of active sound design models in vehicles requires precise tuning of synthetic sounds to harmonize with existing interior noise, driving conditions, and driver preferences. This tuning process is often time-consuming and intricate, especially facing various driving styles and preferences of target customers. Incorporating user feedback into the tuning process of Electric Vehicle Sound Enhancement (EVSE) offers a solution. A user-focused empirical test drive approach can be assessed, providing a comprehensive understanding of the EVSE characteristics and highlighting areas for improvement. Although effective, the process includes many manual tasks, such as transcribing driver comments, classifying feedback, and identifying clusters. By integrating driving simulator technology to the test drive assessment method and employing machine learning algorithms for evaluation, the EVSE workflow can be more seamlessly integrated. But do the simulated test drive results
Hank, Stefan, Kamp, Fabian, Gomes Lobato, Thiago Henrique
Technical Paper
Leveraging Vision Language Models for Automated NVH Analysis2025-01-012705/05/2023
Optimizing Noise, Vibration, and Harshness (NVH) is crucial in the automotive industry. Traditional analysis methods, including time series analytics and frequency spectrum analysis, as well as advanced techniques like time-frequency spectrogram analysis, are often time-consuming and rely heavily on expert interpretation. This research explores the potential of Vision Language Models (VLMs) specifically LLaMA 3.2 Vision, GPT-4o, and Microsoft Phi-3 vision for automating noise spectrogram analysis. By employing techniques such as few-shot learning and fine-tuning these models on a curated dataset of spectrograms paired with expert interpretations, we aim to facilitate rapid and accurate NVH assessments and report generation. The proposed approach includes assembling a dataset derived from vibration sensors and expert analyses to inform model training. Furthermore, we will evaluate the accuracy and reliability of the trained models to ensure robust performance. The techniques discussed
CHANDRASEKARAN, BALAJI, Cury, Rudoniel
Technical Paper
Development and Evaluation of Comfort Assessment Approaches for Passengers in Autonomous Vehicles2023-01-078804/11/2023
Passenger comfort is a critical factor in user acceptance of autonomous vehicles (AVs). Despite existing methods for passenger comfort assessment, new approaches to assessing passenger comfort in AVs may be valuable to the automotive industry. In this paper, continuous pressing-based and discrete smartphone-based approaches for comfort assessment were designed and implemented in a user study. Participants used the two approaches to evaluate their comfort levels in an experimental study based on a high-fidelity autonomous driving simulator. Performances of the two approaches in assessing comfort levels were analyzed and compared. In general, the discrete approach showed better measurement repeatability and lower measurement bias than the continuous approach. The performance gap of the continuous approach could be reduced with proper post-processing measures. Discussions on the potential uses of the approaches were also raised.
Su, Haotian, Brooks, Johnell, Jia, Yunyi
Technical Paper
This is a course with a really long, verbose title with special characters; testing the ingestion process and display on the website. The limit in Docebo is 255 characters, although I don't believe we have one longer than 200 characters in real life. Wow!ZWB1319.LA02/10/2023
Description Text goes here. Do we have a really long overview/description? non-breaking-space-start-here end-here each word separated by non-breaking space non-breaking space at each end and normal space between each word 'Single ascii quote' ‘Single MSWord quote’ "Double ascii quote" “Double MS Word Quote” regular dash - endash – emdash — Three Umlaut Characters ä, ö, ü MS Word’s Apostrophe string of special things GreaterThan > LessThan < StuffInBraces (xxxxx) BackSlashN \n BackSlashR \r ParagraphSymbol ¶ Misc8CharactersFromDotToBeta ·¸¹º»¼Ýβ Chinese 机械 Misc Characters ßà®–½— X¹‘ "<sup>1</sup> h's & Japanese お世話 Russian машин Korean 기계 ElasticSearch Special Characters that need escaped + - && || ! ( ) { } ~ * ? : \ non-breaking-space-start-here end-here each word separated by non-breaking space non-breaking space at each end and normal space between each word 'Single ascii quote' ‘Single MSWord quote’ "Double ascii quote" “Double MS Word Quote” regular dash - endash – emdash — Three
eLearning
The Electric Vehicle Infrastructure: New Opportunities in Learning, Certification and Human Development in the EV Charging IndustryWP-001409/30/2022
Menchaca, Frank
White Paper
Enhancing Meta Model of the Brake Pad Friction Coefficient using the Explainable Machine Learning2022-01-117509/19/2022
As increasing system complexity and various customer demands result in the need for highly efficient vehicle development processes. Once the brake torque is predicted accurately during the driving scenario in the earlier stage, it will be able to prevent the changing the vehicle or brake system design to satisfy the legal regulation and customer requirement. As brake torque performance target allocate brake pad friction coefficient level and characteristic, the accurate friction coefficient prediction should be preceded for accurate prediction for brake torque. Generally, the friction coefficient of the brake pad is known to vary nonlinearly depending on the physical properties of the disc and the pad, as well as the rotational speed of the brake disc, the disc temperature, and the hydraulic pressure. Furthermore, it varies depending on the driving scenario even the same condition. Therefore, there was a need for a new method : machine learning to solve this problem. A Mixed Effect
Cho, Sunghyun, Bang, Sunghoon, Jang, Jiwoo, Kim, Youngjae
Technical Paper
Virginia Tech College of EngineeringTBMG-4651109/01/2022
Founded in 1872, Virginia Tech is a public land-grant research university with its main campus in Blacksburg, VA. From artificial intelligence, cybersecurity, and manufacturing to health sciences, robotics, and more, the Virginia Tech College of Engineering offers an advanced engineering curriculum.
Magazine Article
SAE TOMORROW TODAY: Reinventing the Wheel with Carbon Fiber1323808/05/2022
The team at Carbon Revolution is going against some age-old advice -they're reinventing the wheel. And they're seeing results. Back in 2004, Dr. Ashley Denmead, Chief Technology Officer and Founder of Carbon Revolution, was part of the Formula SAE team at Deakin University in Australia. After building a too-heavy car the year prior, Ashley and his engineering team looked to save weight in the wheels. Their idea? Build them out of carbon fiber. Thus, the journey of Carbon Revolution began. Today, the company designs and manufactures some of the world's most technically advanced and highest performing wheels on the planet, and one of the most advanced lightweight technologies on any car. There are more than 50,000 Carbon Revolution wheels on the road today, including on vehicles such as the Ford GT and the Ferrari F8 Spider. From four guys in a garage to 550 people in a 10,000 square-foot facility with Ford, Ferrari and General Motors among its customers, Carbon Revolution proves
Hineman, Marcie
Podcast
SAE TOMORROW TODAY: Using AI to Scale Autonomous Vehicles1322906/03/2022
A driving school for self-driving vehicles? It's here and proving to be a game-changer. Waabi World is the most scalable, highest fidelity, closed-loop simulator for autonomous vehicles. Powered by AI, it's an immersive and reactive environment that can design tests, assess skills, and teach the self-driving "brain" to learn to drive on its own. This technology significantly reduces the need to test drive in the real world resulting in a safer, more affordable solution. When AI trailblazer & CEO Raquel Urtasun founded Waabi, she set out to scale one of the most important technologies of our generation. By taking an AI-first approach, Raquel and her team are unlocking the potential of self-driving technology and accelerating the commercial deployment of autonomous vehicles. And their work is changing the world for the better.
Hineman, Marcie
Podcast
An Artificial Intelligence System to Identify Objects in Cluttered ScenesTBMG-4595606/01/2022
Robotic vision has come a long way, reaching a level of sophistication with applications in complex and demanding tasks, such as autonomous driving and object manipulation. However, it still struggles to identify individual objects in cluttered scenes where some objects are partially or completely hidden behind others. Typically, when dealing with such scenes, robotic vision systems are trained to identify the occluded object based only on its visible parts. But such training requires large datasets of objects and can be tedious.
Magazine Article
Toward a Machine Learning Development Lifecycle for Product Certification and Approval in Aviation01-15-02-000905/26/2022
This article presents a new machine learning (ML) development lifecycle which will constitute the core of the new aeronautical standard on ML called AS6983, jointly being developed by working group WG-114/G34 of European Organisation for Civil Aviation Equipment (EUROCAE) and SAE. The article also presents a survey of several existing standards and guidelines related to ML in aeronautics, automotive, and industrial domains by comparing and contrasting their scope, purpose, and results. Standards and guidelines reviewed include the European Union Aviation Safety Agency (EASA) Concept Paper, the DEEL (pendable andxplainableearning) white paper “Machine Learning in Certified Systems”, Aerospace Vehicle System Institute (AVSI) Authorization for Expenditure (AFE) 87 report on Machine Learning, Guidance on the Assurance of Machine Learning for use in Autonomous Systems (AMLAS), Laboratoire National de Metrologie et d’Essais (LNE) Certification Standard of Processes for AI, the Underwriters
Kaakai, Fateh, Dmitriev, Konstantin, Adibhatla, Sridhar (“Shreeder”), Baskaya, Elgiz, Bezzecchi, Emanuele, Bharadwaj, Ramesh, Brown, Barclay, Gentile, Giacomo, Gingins, Corinne, Grihon, Stephane, Travers, Christophe
Journal Article
A study of driving performance prediction using integrated objective and subjective index for concept design stage2022-01-110403/29/2022
Over the recent years with a strong focus on optimizing its early performance prediction capabilities, vehicle manufacturers around the world are reviewing their virtual development processes with the intent to address the vehicle attributes that are most important to its customers during the early stages of development. However, reliable performance prediction through simulation in the concept development phase for new technologies and new entries in different vehicle segments is a very challenging task. Furthermore, the strong need for increased vehicle energy efficiency requires a precise balancing with the driving performance. Therefore, in order to respond quickly to a rapidly changing market and customer preferences, the development of a robust process to reliably evaluate vehicle concepts is absolutely mandatory. This paper is focused on the prediction of vehicle driving attributes (more specifically handling, and lap time) through the application of various objective and
Jeong, Pilyoung, Lee, Jaekil, OSWALD, MARIO, Ecker, Joachim, KELLNER, STEFAN, Kogler, Manfred
Technical Paper
Active Learning Optimization for Boundary Identification Using Machine Learning-Assisted Method2022-01-094603/29/2022
Identifying edge cases for designed algorithms is critical for functional safety in autonomous driving deployment. In order to find the feasible boundary of designed algorithms, simulations are heavily used. However, simulations for autonomous driving validation are expensive due to the requirement of visual rendering, physical simulation, and AI agents. In this case, common sampling techniques, such as Monte Carlo Sampling, become computationally expensive due to their sample inefficiency. To improve sample efficiency and minimize the number of simulations, we propose a tailored active learning approach combining the Support Vector Machine (SVM) and the Gaussian Process Regressor (GPR). The SVM learns the feasible boundary iteratively with a new sampling point via active learning. Active Learning is achieved by using the information of the decision boundary of the current SVM and the uncertainty metric calculated by the GPR. The optimal sampling point is selected through multi
Ryu, Joonjae, Wei, Yifan
Technical Paper
A constant equivalence ratio multi-zone approach for a detailed and fast prediction of performances and emissions in CI engines2022-01-045503/29/2022
The paper illustrates and validates a novel predictive combustion model for the estimation of in-cylinder performances and pollutant production in CI engines. The numerical methodology was developed by the authors for near real-time and / or control-oriented applications, while aiming at an accurate description of the air mixing process by means of a multi-zone approach of the air-fuel mass. Charge stratification is estimated via a 2D representation of the fuel spray distribution that is numerically derived by an axial one-dimensional control-volume description of the direct injection. The radial coordinate of each control volume is reconstructed a posteriori by means of a local distribution function. Fuel mass clustered in each zone is further split in ‘liquid’, ‘unburnt’ and ‘burnt’ sub-zones, given the local properties of the fuel spray control volumes with respect to space-time location of modelled ignition delay, liquid length, and flame lift-off. Multiple injections are described
Tamborski, Matteo, D'Errico, Gianluca, Lucchini, Tommaso, Cerri, Tarcisio, Onorati, Angelo
Technical Paper
A driving simulator for UNECE 157 homologation activities2022-01-010803/29/2022
UNECE 157 Regulation is devoted to the homologation of SAE Level 3 automated vehicles. The research and development activities related with the Regulation may require an extensive usage of driving simulators. Developing a sickness-free driving simulator is crucial for extensive tests to be performed with ordinary drivers. The paper presents the technical features of the new driving simulator of the Politecnico di Milano. A number of biometric set of signals is recorded, namely, forces and moments at each single hand at the steering wheel, heart rate variability, skin resistance potential, eye tracking. A matching of the objective monitoring of the driver is compared with the subjective psychological status. An initial population of 30 subjects has been investigated. The new driving simulator has shown a good acceptance by ordinary drivers. Both objective and psychologic subjective assessment agree to state that the new driving simulator may be used to test ordinary driver behavior in a
Gobbi, Massimiliano, Mastinu, Giampiero, Melzi, Stefano, Previati, Giorgio, Sabbioni, Edoardo, Ronconi, Luca
Technical Paper
Development of an Integrated Co-Simulation Environment to Model and Test Advanced DAT Features Utilizing MIL and HIL2022-01-010303/29/2022
The widespread deployment of Connected and Automated Vehicles (CAVs) in the future will bring major changes in the automotive industry and the vehicle features it will offer. Currently, technology and infrastructure are not ready to test and develop CAV features fully in real traffic. Simulators are becoming popular to develop CAVs and assisted automated driving features for all levels of automation to overcome the infrastructural needs of the automotive industry. Simulators allow researchers to design CAV algorithms safely, quickly, and efficiently, and test these algorithms for various metrics. A co-simulation environment, where a vehicle simulator like CarSim and a traffic simulator like Simulation of Urban Mobility (SUMO) feed into each other, is an invaluable tool, allowing CAV features to be tested in a realistic traffic environment. This paper presents a co-simulation environment, where the vehicle simulator CarSim and the traffic simulator SUMO share data. The paper follows the
Kavas-Torris, Ozgenur, cai, Xiaolin, Joshi, Adit, Mittal, Archak, Djavadian, Shadi, Fishelson, James
Technical Paper
Virtual EET for Combat Robotic Vehicles: Integrating Qualitative and Quantitative Analyses in Autonomous Vehicle Simulation2022-01-043203/29/2022
Spurred on by the constraints of the COVID-19 pandemic, virtual testing is becoming an increasingly essential method for validation and verification of autonomous ground vehicle simulation tools. The Mobility Systems Branch (MSB) of the US Army Corps of Engineers Engineering Research and Development Center (ERDC) Geotechnical and Structures Laboratory (GSL) has developed a new approach in physics-based virtual testing of autonomous ground vehicle systems through the incorporation of both qualitative and quantitative data in congruency with MSB's Simulation-in-the-Loop laboratory. Virtual testing of autonomous vehicles combines simulation tools consisting of vehicle and sensor models represented in a virtual scene, performer observations, and modeling and simulation observations. The first iteration of a Virtual Engineering Evaluation Test (V-EET) for Simulation Tools for Combat Robotic Vehicles took place in 2021 at the ERDC GSL in Vicksburg, Mississippi. Virtual testing took place
Lyons, Jessica W., Jackson, Rebekah, Richards, James, Gates, Burhman, Fairley, Josh, Price, Stephanie
Technical Paper
Mixed Reality Driving Simulator as a Training Tool for Autonomous Vehicles2022-01-097303/29/2022
While manufacturers have invested billions of dollars in the self-driving car technology, little has been done to prepare drivers to this paradigm shift in transportation. According to a recent survey published by PAVE (Partners for Automotive Vehicle Education, 2020) of 1,200 adult drivers, 48% of American drivers say they “would never get into a taxi or ride-share vehicle that was driven autonomously”. To overcome these issues and to address this problem, we developed a highly immersive driving simulator which provides a safe platform for drivers of all ages and abilities to get a first hand experience of a self-driving vehicle. The proposed system provides a highly innovative use of mixed reality and can be easily retrofitted to any vehicle to provide mechanical immersion. Visual immersion is obtained through a mixed reality experience delivered through a Head Mounted Display. In this paper we will discuss the various mixed reality techniques that were implemented during the
Loeb, Helen S.
Technical Paper
Effects of combined Phone use and Alcohol-impaired Driving Behaviours among Female Drivers; A Driving Simulator Study2022-01-097203/29/2022
Driver behavior and passenger safety remain one of the foremost axes developed for investigative research in driving simulator studies. However, a plethora of studies on driver’s behaviour using driving simulators has seen the underrepresentation of female participants whose characteristics have scarcely been investigated. More tellingly, the responsibility of female drivers for road traffic accidents with respect to cell phone use and alcohol-impaired behaviours is overlooked. Using a driving simulator experiment, this study thematically modelled and analysed the combined upshot of cell phone use and alcohol-impaired tasks among 15 female driver participants. The experiment was carried out in an urban simulated environment to extract discrete responses from these intoxicated drivers at four different levels of blood alcohol concentration (BAC) (0%, 0.02%, 0.05%, and 0.08%). Vehicle telematic variables such as acceleration (m/s2), vehicle speed (m/s), angular velocity (rad/s2) and RPM
Frimpong, Justice Alex, Prince PhD, Owusu-Ansah, Agyeman, Philip, Arhin, Ebenezer, Fayzullayevich, Jamshid
Technical Paper
Construction of Personalized Driver Models based on LSTM using Driving Simulator.2022-01-098103/29/2022
The purpose of this study is to construct personalized driver models using Long Short-Term Memory (LSTM). The driver model is used for automated driving systems and driver assistance systems and is expected to control longitudinal and lateral directions of vehicles. For example, driver models including the individual driving characteristics adapt the control of systems, which can reduce discomfort and nuisance to drivers. The LSTM models in this study enable the time series data processing. In some previous studies, LSTM models have been used to investigate pedestrian behaviors. However, there are few studies of driver behavior models based on LSTM. In this study, we measured the data of the driver's driving operation using a Driving Simulator (DS). DS consists of a visual display and a motion display, of which motion functions consist of a 6-axis motion device and a turntable. DS has a cockpit using an actual body of a vehicle, and a visual information projected on a cylindrical
Hamada, Ayaka, Oikawa PhD, Shoko, Hirose, Toshiya
Technical Paper
A Novel Method For Displaying Systems Datums Based On "Cognitive Load"2022-01-096903/29/2022
Operator attention has been a focus of human factors research. This research has defined how electronic devices and other stimuli can become distractions when included in the operator environment. Distracted driving occurs when a stimulus interrupts the essential cognitive processes of operating a vehicle. Attention is the most often mentioned of this loosely ordered sequence of processes that also includes perception, memory, cognition, and planful behaviors. These processes are the “cognitive demands” of vehicle operation. There is another issue, similar to “distracted driving,” that may cause an operator to fail to respond appropriately. That issue is the “cognitive load” of human-machine interface devices, including instrument clusters. The present paper explores the effects of cognitive load on the speed of operator responses. It describes a novel method for displaying systems datums that is designed to manage cognitive load. The paper describes a pilot study where participants
Havins, William
Technical Paper
Controller design for path tracking of autonomous vehicle incorporating four-wheel steering system2022-01-034603/29/2022
This research aims to model and assess autonomous vehicle controller while including a four-wheel steering and longitudinal speed control. Such a modeling process simulates human driver behavior with consideration of real vehicle dynamics’ characteristics during standard maneuvers. However, a four-wheel steering control improves vehicle stability and maneuverability as well. A two-degree of freedom bicycle model, lateral deviation and yaw angle, is constructed to describe vehicle dynamics’ behavior. Moreover, a comprehensive traction model is implemented which includes an engine, automatic transmission, and non-linear magic formula tire model for simulation of vehicle longitudinal dynamics. A combination of PID longitudinal controller and fuzzy lateral controller are implemented simultaneously to track the desired vehicle path while minimizing lateral deviation and yaw angle errors. Then, A LQR based rear steering controller is introduced to represent a performance improvement over
Gafar, Ibrahim, Oraby, Walid, Aly, Mahmoud Atef
Technical Paper
Numerical simulation of Vehicle Dynamics performance of a Formula 1 Car based on 2022 regulations with integrated Power Unit2022-01-044503/29/2022
The Formula One World Championship gathers the best of engineering to produce the safest and the fastest cars in straight lines and corners. The new FIA budget restrictions and the cost of testing push the teams to use numerical simulations for the development of their car, aiming to reproduce the behaviours of the vehicle on different racetracks. Current published models use a rigid body representation of the chassis to describe the motion of the car. This omits the influence of the powertrain, in particular by not fully representing the action of the Motor Generator Unit-Kinetic (MGUK) system acting on braking. The aim of this work is to predict the vehicle dynamics performance of a Formula One car from a powertrain perspective on three circuits of the Formula One Championship race Calendar. The vehicle model developed on GT-Suite and which complies with the FIA 2022 technical regulations, includes the main elements for predicting vehicle dynamics, such as the vehicle body, wheels
Praneuf, Valentin, Samuel, Stephen
Technical Paper
AS13100 Quality Foundations Learning AssessmentC2112.LA02/15/2022
.
eLearning
Learning How Docebo Works...PW202202/03/2022
This course blah blah blah....blabitty blah blah blah.. Learn about donuts CEUs
Instructor Led
Prediction of Lane Change on the Expressway Based on Logistic Regression2021-01-703212/15/2021
In autonomous driving system, lane change decision-making plays an important role as the front-end of lateral control. However, the current prediction methods of lane change are typically performed by using basic variables as the features of model without deep processing, which reduces the accuracy of the prediction. Therefore, we propose a binary logistic regression method to solve the lane change decision problem under expressway conditions, which treat quantified willingness and risk as the inputs. Firstly, we design Lane Changing Willingness function and Lane Changing Risk function with the minimum safety spacing theory and traffic environment factors. Secondly, a binary logistic regression method for predicting lane change behavior is proposed. Thirdly, we develop the driving simulation platform with low latency data collecting tools and design the experiments. After training the model with the experiment data, the proposed method predicts the lane change decision with 94.02
Sun, Weiqi, Bai, Jie, Huang, Libo, Chang, Liang, Dong, Lianfei, Luo, Zhengang
Technical Paper
SAE TOMORROW TODAY: SAE: Forging a New Mobility Ecosystem - Part 11317111/12/2021
Think you know SAE? These episodes will have you thinking again. The next mobility revolution is upon us. Connected, automated and electrified transportation can provide equity of access to jobs, education, health care and beyond - but the future comes with challenges as innovators consider sustainability, resiliency and scalability of production. In part one of this special two-part series, SAE International's own Chief Growth Officer, Frank Menchaca, discusses the ways SAE is meeting the changing needs of 21st-century transportation and mobility, the organization's partnership with Argo AI and Clemson University to build the new Robotics Bootcamp, why SAE's J3016 Levels of Driving Automation was created, and the launch of SAE's Office of Sustainable Energy. Intrigued? Meet Pete. Meet Skylar. And meet Violet.
Hineman, Marcie
Podcast
Aerospace Safety Engineers (ASE) Training for the FAAC211311/03/2021
160 Hours 16.0 CEUs
eLearning
SAE TOMORROW TODAY: Traffic21 Modernizes Pittsburgh with Smart Mobility1316409/24/2021
Once a steel titan, Pittsburgh is now a burgeoning tech hub - and Traffic21 has helped place it at the forefront of the intelligent transportation field, improving the economy and attracting new businesses along the way. Stan Caldwell, Executive Director of Carnegie Mellon University Traffic21 Institute, discusses the latest research from Traffic21 and how cities like Pittsburgh are uniquely equipped to develop the smart cities of tomorrow through collaboration between educational leaders, tech giants and policymakers. Stay up to date on the latest research innovations by visiting https://traffic21.heinz.cmu.edu/. During this conversation, Caldwell refers to the work of two previous SAE Tomorrow Today guests. Check out their episodes to continue the conversation: Ep.62 PennDOT, Ep.71 Locomation. Stay tuned for Ep.79 with Karina Ricks, Director of Mobility and Infrastructure for the City of Pittsburgh.
Hineman, Marcie
Podcast
Pedestrian Safety Performance Prediction Using Machine-Learning Techniques2021-26-002609/22/2021
As per WHO 2018 report, pedestrian fatalities accounts for 23% of world road accident fatalities. Every day 850 pedestrians lose their lives in the world. As per MoRTH 2018 report, 16% of road accident fatalities are of pedestrians in India. Everyday 64 pedestrians lose their lives in India. Based on accident data, one of the most common reason for the pedestrian fatality is head injury due to primary contact from vehicle front-end structure. Pedestrian head injury performance is highly depended on front-end styling, bonnet stiffness, clearance with aggregates underneath the bonnet and hard contact points. During concept stage of vehicle development, safety recommendation on front-end design is provided based on geometric assessment of the class A surface, as the maturity of the geometry is insufficient to carryout CAE simulations. This paper presents the novel approach of using machine-learning algorithms to predict the head injury performance at the early stage of the vehicle design
Kaushik, Bharat, Daphal, Pratap, Khare, Pratyush, Koralla, Sivaprasad, Bera, Satadru
Technical Paper
Implementation of Lean Operation User ManualJ4001_202109 (Current)09/21/2021
SAE J4001 provides instruction for evaluating levels of compliance to SAE J4000. Component text (Sections 4 to 9) from SAE J4000 is included for convenience during the evaluation process. Applicable definitions and references are contained in SAE J4000. SAE J4000 tests lean implementation within a manufacturing organization and includes those areas of direct overlap with the organization’s suppliers and customers. If applied to each consecutive organizational link, an enterprise level evaluation can be made. SAE J4001 relates the following approximate topic percentages to the implementation process as a whole: SAE J4001 is to be applied on a specific component basis. Each of the 52 components tests part of, one, or multiples of the specific requirements of lean implementation. Implementation throughout an organization may be measured by evaluating all of the components. The level of compliance for each component relative to best practice may be used as a reference by an organization to
Automotive Quality and Process Improvement Committee
Recommended Practice
Implementation of Lean Operation User ManualJ4001_202109-TEST-REC (Historical)09/21/2021
SAE J4001 provides instruction for evaluating levels of compliance to SAE J4000. Component text (Sections 4 to 9) from SAE J4000 is included for convenience during the evaluation process. Applicable definitions and references are contained in SAE J4000. SAE J4000 tests lean implementation within a manufacturing organization and includes those areas of direct overlap with the organization’s suppliers and customers. If applied to each consecutive organizational link, an enterprise level evaluation can be made. SAE J4001 relates the following approximate topic percentages to the implementation process as a whole: SAE J4001 is to be applied on a specific component basis. Each of the 52 components tests part of, one, or multiples of the specific requirements of lean implementation. Implementation throughout an organization may be measured by evaluating all of the components. The level of compliance for each component relative to best practice may be used as a reference by an organization to
Automotive Quality and Process Improvement Committee
Recommended Practice
Full Vehicle Global Modal Identification Based on Deep Neural Network2021-01-111308/31/2021
Full vehicle modal identification is a major challenge for both experimental and simulated modal results. A global modal is usually masked by nearby local modes, so that even well-experienced engineers have difficulty to identify vehicle modes efficiently. Besides different vehicle configurations e.g. SUV, MPV and hatchback can make the challenge even greater, since the same modal for them will present different characteristics. This paper proposes a deep neural network for vehicle modal identification. This method takes advantage of the deep learning method which has achieved outstanding performance in language translation, computer vision and image processing. It also has the potentiality to improve modal identification efficiency. In general commercial neural network applications, a large number of data is available for training to achieve a robust output. However, the training data for a vehicle modal identification is always limited, as a result, training the network becomes
Lee, Zhen
Technical Paper
Utilizing Engine Dyno Data to Build NVH Simulation Models for Early Rapid Prototyping2021-01-106908/31/2021
As the move to decrease physical prototyping increases the need to virtually prototype vehicles become more critical. Assessing NVH vehicle targets and making critical component level decisions is becoming a larger part of the NVH engineer’s job. To make decisions earlier in the process when prototypes are not available companies need to leverage more both their historical and simulation results. Today this is possible by utilizing a hybrid modelling approach in an NVH Simulator using measured on road, CAE, and test bench data. By starting with measured on road data from a previous generation or comparable vehicle, engineers can build virtual prototypes by using a hybrid modeling approach incorporating CAE and/or test bench data to create the desired NVH characteristics. This enables the creation of a virtual drivable model to assess subjectively the vehicles acoustic targets virtually before a prototype vehicle is available. This approach can also be used with, but not limited to
Thom, Brian, Singh, Vinod, Newton, Gary, Rengarajan, Revathi, Radic, Nebojsa
Technical Paper
SAE TOMORROW TODAY: Qualcomm is Changing the World with C-V2X Technology1315207/06/2021
Just in time for the rollout of 5G, Qualcomm is connecting vehicles to networks, the cloud, other vehicles, pedestrians and more through C-V2X technology. Jim Misener, Senior Director of Product Management, Automotive, joins us to dig into how this technology is improving autonomy and safety. Misener, a pioneer in vehicle-highway automation and vehicle safety communication, also serves as SAE's C-V2X Technical Committee Chair. His commitment to innovation and STEM is apparent through Qualcomm's three-year commitment to provide experiential, project-based STEM learning to children through the SAE Foundation. Read about Qualcomm's STEM education investment to learn more about how you can invest in young minds and make a difference. Volunteer, donate or become a corporate partner and inspire the next generation of innovators through the SAE Foundation.
Hineman, Marcie
Podcast
Simulation Framework for Testing Autonomous Vehicles in a School for the Blind Campus2021-01-011804/06/2021
With the advent of increasing autonomous vehicles on public roads, the safety of vulnerable road users such as pedestrians, cyclists, etc. has never been more important. These especially include Blind or Visually Impaired (BVI) pedestrians who face difficulty in making confident decisions in road crossings without the help of accessible pedestrian signals (APS). This paper addresses some of the safety measures that can be taken to improve and assess the safety of BVI pedestrians in a controlled environment like a BVI school campus where autonomous vehicles are operated. The majority of research on autonomous vehicle safety does not consider the edge cases of encounters with BVI pedestrians. Based on this motivation, requirements and characteristics of Non-BVI and BVI pedestrians have been stated along with the motion models used to predict their future movements. Existing tools based on Bayesian multi-model filters were used for pedestrian tracking and motion predictions. These can be
Kalidas, Karthik, Gelbal, Sukru Yaren, Aksun Guvenc, Bilin
Technical Paper
Visual SLAM in Long-Range Autonomous Parking Application Based on Instance-Aware Semantic Segmentation via Multi-Task Network Cascades and Metric Learning Scheme2021-01-007704/06/2021
Long-range Autonomous Parking is becoming an attractive application in terms of demands. The vehicle is capable of driving autonomously into the appointed parking slot when the driver leaves it at the drop-off spot. In this application, the ability of accurate localization has become a key issue, especially in GPS-denied environments. This paper proposes a method of localization and mapping for Long-range Autonomous Parking, which is achieved by Visual SLAM based on deep learning algorithms. Firstly, we propose an instance segmentation via multi-task network cascades, and even in a complex visual environment, the main roadway instances of interest in the parking lot IPM image can be detected, such as parking corners, speed bumps. Then we combine the information of wheel encoders to build a global semantic map of the parking lot. Vehicles can often rely on semantic map matching to achieve high-precision localization. However, without a good initial position, it is difficult to infer an
Yan, Yixiong, Hang, Yang, Hu, Tianren, Yu, Hao, Lai, Feng
Journal Article
Object Detection Method of Autonomous Vehicle Based on Lightweight Deep Learning2021-01-019204/06/2021
Object detection is an important visual content of the autonomous vehicle, the traditional detecting methods usually cost a lot of computational memory and elapsed time. This paper proposes to use lightweight deep convolutional neural network (MobilenetV3-SSDLite) to carry out the object detection task of autonomous vehicles. Simulation analysis based on this method is implemented, the feature layer obtained after h-swish activation function in the first Conv of the 13th bottleneck module in MobilenetV3 is taken as the first effective feature layer, and the feature layer before pooling and convolution of the antepenultimate layer in MobilenetV3 is taken as the second effective feature layer, and these two feature layers are extracted from the MobilenetV3 network. The two output effective feature layers of MobilenetV3 are used to replace the two output feature layers of VGG16 in the SSD network, and the rest convolutions of SSD was replaced by lightweight separable convolutions and
Guo, Rong, Xie, Xin
Technical Paper
A Real-Time Intelligent Speed Optimization Planner Using Reinforcement Learning2021-01-043404/06/2021
As connectivity and sensing technologies become more mature, automated vehicles can predict future driving situations and utilize this information to drive more energy-efficiently than human-driven vehicles. However, future information beyond the limited connectivity and sensing range is difficult to predict and utilize, limiting the energy-saving potential of energy-efficient driving. Thus, we combine a conventional speed optimization planner, developed in our previous work, and reinforcement learning to propose a real-time intelligent speed optimization planner for connected and automated vehicles. We briefly summarize the conventional speed optimization planner with limited information, based on closed-form energy-optimal solutions, and present its multiple parameters that determine reference speed trajectories. Then, we use a deep reinforcement learning (DRL) algorithm, such as a deep Q-learning algorithm, to find the policy of how to adjust these parameters in real-time to
Lee, Woong, Han, Jihun, Zhang, Yaozhong, Karbowski, Dominik, Rousseau, Aymeric, Kim, Namwook
Technical Paper
Using Deep Learning to Predict the Engine Operating Point in Real-Time2021-01-018604/06/2021
The engine operating point (EOP), which is determined by the engine speed and torque, is an important part of a vehicle's powertrain performance and it impacts FC, available propulsion power, and emissions. Predicting instantaneous EOP in real-time subject to dynamic driver behaviour and environmental conditions is a challenging problem, and in existing literature, engine performance is predicted based on internal powertrain parameters. However, a driver cannot directly influence these internal parameters in real-time and can only accommodate changes in driving behaviour and cabin temperature. It would be beneficial to develop a direct relationship between the vehicle-level parameters that a driver could influence in real-time, and the instantaneous EOP. Such a relationship can be exploited to dynamically optimize engine performance. In this work, we investigate deep learning methods to correlate vehicle-level vectors, including parameters which define driving behaviour, with
Kolachalama, Srikanth, Lakshmanan, Sridhar
Technical Paper
Items per page:
1 – 50 of 1753