Your Selections

Cartography
Show Only

Collections

File Formats

Content Types

Dates

Sectors

Topics

Authors

Publishers

Affiliations

Committees

Events

Magazine

   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Using Reinforcement Learning and Simulation to Develop Autonomous Vehicle Control Strategies

Amazon Web Services-Sahika Genc, Premkumar Rangarajan
PolySync Technologies-Anthony Navarro
  • Technical Paper
  • 2020-01-0737
To be published on 2020-04-14 by SAE International in United States
While machine learning in autonomous vehicles development has increased significantly in the past few years, the use of reinforcement learning (RL) methods has only recently been applied. Convolutional neural networks (CNNs) became common for their powerful object detection and identification and even provided end-to-end control of an autonomous vehicle. However, one of the requirements of a CNN is a large amount of labeled data to inform the neural network. While data is becoming more accessible, these networks are still sensitive to the format and collection environment which makes the use of others’ data more difficult. In contrast, RL develops solutions in a simulation environment by trial and error without labeled data. Our research expands upon previous research in RL and proximal policy optimization (PPO) and the application of these algorithms to 1/18th scale cars by expanding the application of this control strategy to a full-sized passenger vehicle. By using this method of unsupervised learning, our research demonstrates the ability to learn new control strategies while in a simulation environment without the need for large amounts…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Numerical Investigation of Friction Material Contact Mechanics in Automotive Clutches

FCC Co., Ltd.-Masatoshi Miyagawa, Takahiro Tsuchiya, Shinji Nakamura, Matthew Wendel
Ford Motor Company-Hiral Haria, David Popejoy, Rachel Divinagracia, Yuji Fujii
  • Technical Paper
  • 2020-01-1417
To be published on 2020-04-14 by SAE International in United States
A wet clutch model is required in automotive propulsion system simulations for enabling robust design and control development. It commonly assumes Coulomb friction for simplicity, even though it does not represent the physics of hydrodynamic torque transfer. In practice, the Coulomb friction coefficient is treated as a tuning parameter in simulations to match vehicle data for targeted conditions. The simulations tend to deviate from actual behaviors for different drive conditions unless the friction coefficient is adjusted repeatedly. Alternatively, a complex hydrodynamic model, coupled with a surface contact model, is utilized to enhance the fidelity of system simulations for broader conditions. The theory of elastic asperity deformation is conventionally employed to model clutch surface contact. However, recent examination of friction material shows that the elastic modulus of surface fibers significantly exceeds the contact load, implying no deformation of fibers. This article investigates the friction material contact mechanics through numerical simulations. A surface model is constructed based on microscopic examination of material topography and properties. An FEM simulation is conducted to examine the interactions between surface fibers…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Automotive Dimensional Quality Control with Geometry Tree Process

FCA US LLC-James Cole, Yuqin Wang, Robert Bertucci
  • Technical Paper
  • 2020-01-0480
To be published on 2020-04-14 by SAE International in United States
Geometry Tree is a term describing the product assembly structure and the manufacturing process for the product. The concept refers to the assembly structure of the final vehicle (the Part Tree) and the assembly process and tools for the final product (the Process Tree). In the past few years, the Geometry Tree-based quality process was piloted in the FCA NAFTA region and has since evolved into a standardized quality control process. In the Part Tree process, the coordinated measurements and naming convention are enforced throughout the different levels of product sub-assemblies and measurement processes. The Process Tree, on the other hand, includes both prominently identified assembly tools and the mapping of key product characteristics to key assembly tools. The benefits of directly tying critical customer characteristics to actual machine components that have a high propensity to influence them is both preventive and reactive. This article describes the integrated Geometry Tree quality process and how it has been implemented at the FCA vehicle assembly plants and in the dimensional data management system.
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Assessing Fit and Finish Design Sensitivity By Mapping Measurements to VNM Utility

FCA US LLC-Christopher Slon, Xiaona LI, Vita Valetchikov
Oakland University-Vijitashwa Pandey
  • Technical Paper
  • 2020-01-0600
To be published on 2020-04-14 by SAE International in United States
In the automotive industry “fit and finish” is the term applied to the perceived quality of the alignment of one part to another. Fit and finish gives the buyer a sense of the overall quality of the vehicle purely from an aesthetic perspective. Fit and finish is usually evaluated by the manufacturer through dimensional measurements of the “gap” and “flush” conditions between panels. Since variation in the measurements increases the probability that a vehicle will result in poor fit and finish, relatively arbitrary limits are put on these measurements to define whether a gap or flush condition is acceptable or not. It is suspected that the relationship between the appropriate measurement limits and the customer’s perception of quality is highly influenced by the design of the interface between panels. This paper proposes a method to evaluate the sensitivity of the perceived quality of the designed interface to variation in the measurements of gap and flush. The novelty is in the application of the concept of von Neumann-Morgestern utility to fit and finish. The significance is…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

The Investigation of the Structure and Origins of Gasoline Direct Injection (GDI) Deposits.

Innospec-J Barker J Reid, S Mulqueen
University of Sheffield-J Castle
  • Technical Paper
  • 2019-01-2356
Published 2019-12-19 by SAE International in United States
The legislative pressures on environmental targets combined with fuel economy requirements have led to the GDI engine enjoying a renaissance. This is because the technology is considered to be the leader in meeting those requirements. However it is also recognized that the engine suffers from injector deposits (ID) and that understanding the formation of and characterization of such deposits is required. This study will deal with the characterization and morphology of injector deposits as well as the fuel constituents leading to such deposits. A number of analytical techniques were used to undertake this such as Scanning Electron microscopy and X-ray Fluorescence (SEM/EDS) mapping with Fourier Transform Infra-red mapping, in conjunction with mass spectrometry studies. Further, work will be described regarding new deposit control additives (DCAs) for GDI which are more effective than traditional DCAs.
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Mapping Canada - Centimeter by Centimeter

Autonomous Vehicle Engineering: December 2019

Sebastian Blanco
  • Magazine Article
  • 19AVEP11_05
Published 2019-11-01 by SAE International in United States

A Montreal-based company leverages artificial intelligence to take on the task of developing high-definition maps of Canada.

Fully-automated vehicles will only be as smart as the datasets they use to determine their driving pathways. Jakarto Cartographie 3D, a young company based in Montreal, Canada, is working on artificial-intelligence (AI)-powered, high-definition (HD) maps that it claims offer 2-3 cm (.787- to 1.2-inch) absolute precision and relative precision measured in millimeters. In other words, better maps that will allow for better automated vehicles (AVs).

Annotation ability available

Nondestructive Measurement of Residual Strain in Connecting Rods Using Neutrons

SAE International Journal of Materials and Manufacturing

Honda R&D Co., Ltd., Japan-Tomohiro Ikeda, Ryuta Motani, Hideki Matsuda, Tatsuya Okayama
Oak Ridge National Laboratory, USA-Bunn R. Jeffery, Christopher M. Fancher
  • Journal Article
  • 05-12-03-0018
Published 2019-10-15 by SAE International in United States
Increasing the strength of materials is effective in reducing weight and boosting structural part performance, but there are cases where the residual strain generated during the process of manufacturing of high-strength materials results in a decline of durability. It is therefore important to understand how the residual strain in a manufactured component changes due to processing conditions. In the case of a connecting rod, because the strain load on the connecting rod rib sections is high, it is necessary to clearly understand the distribution of strain in the ribs. However, because residual strain is generally measured by using X-ray diffractometers or strain gauges, measurements are limited to the surface layer of the parts. Neutron beams, however, have a higher penetration depth than X-rays, allowing for strain measurement in the bulk material. The research discussed within this article consists of nondestructive residual strain measurements in the interior of connecting rods using the Second Generation Neutron Residual Stress Mapping Facility (NRSF2) at Oak Ridge National Laboratory (ORNL), measuring the Fe (211) diffraction peak position of the ferrite…

Mobile Rugged Displays for Situational Awareness

  • Magazine Article
  • TBMG-35280
Published 2019-10-01 by Tech Briefs Media Group in United States

With the constant emergence of new display technologies in the consumer sector, it is important for program managers and engineers in the military markets to be aware of how several of these advances can be incorporated into new military programs to achieve maximum benefit. Additionally, as older programs present themselves for technological refreshes, it is imperative to understand the difference in display specifications from previous decades and how updated technology provides avenues for their evolution and continued progress.

Bringing Human-Like Reasoning to Driverless Car Navigation

  • Magazine Article
  • TBMG-34772
Published 2019-07-01 by Tech Briefs Media Group in United States

With the aim of bringing more human-like reasoning to autonomous vehicles, MIT researchers have created a system that uses only simple maps and visual data to enable driverless cars to navigate routes in new, complex environments.

   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Global Temperature Mapping and Crystallization Analysis of Supercooled Water Droplet Freezing Using Luminescent Imaging Technique

University of Notre Dame-Wesley Chad Patterson, Hirotaka Sakaue
Published 2019-06-10 by SAE International in United States
A prominent environmental phenomenon that greatly affects many industries including automotive, aeronautics, energy transmission, etc. is icing. One mechanism by which this occurs and plagues our machines and infrastructures that are exposed to the atmosphere is the icing of supercooled water droplets on a surface - either by impact against a surface or spontaneous nucleation and crystallization of a droplet at rest. The process by which nucleation propagates during the liquid-to-solid phase change and the thermodynamic implications in regards to latent heat generation and transfer are not fully understood on the single droplet scale. An attempt to better resolve these unknowns in both spatial and temporal domains has been made here. Previous efforts have implemented a unique temperature sensing technique utilizing luminescent dyes. A thermally sensitive luminescent paint coated onto the surface of interest allows direct mapping of the heat transfer from the supercooled liquid droplet undergoing freezing to the surface. This technique also provides insight into the nucleation propagation speed along the droplet-substrate interface. This, in conjunction with a high-speed color camera and an…
Annotation ability available