Technical Paper collections have been re-named for better clarity and alignment.x

Your Selections

Education and training
Show Only

Collections

File Formats

Content Types

Dates

Sectors

Topics

Authors

Publishers

Affiliations

Committees

Events

Magazine

Series

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

Improving robotic accuracy through iterative teaching

The University of Sheffield - AMRC-Daniela Sawyer, Lloyd Tinkler, Nathan Roberts, Ryan Diver
  • Technical Paper
  • 2020-01-0014
To be published on 2020-03-10 by SAE International in United States
Industrial robots have been around since the 1960s and their introduction into the manufacturing industry has helped in automating otherwise repetitive and unsafe tasks, while also increasing the performance and productivity for the companies that adopted the technology. As the majority of industrial robotic arms are deployed in repetitive tasks, the pose accuracy is much less of a key driver for the majority of consumers (e.g. the automotive industry) than speed, payload, energy efficiency and unit cost. Consequently, manufacturers of industrial robots often quote repeatability as an indication of performance whilst the pose accuracy remains comparatively poor. Due to their lack in accuracy, robotic arms have seen slower adoption in the aerospace industry where high accuracy is of utmost importance. However if their accuracy could be improved, robots offer significant advantages, being comparatively inexpensive and more flexible than bespoke automation. Extensive research has been conducted in the area of improving robotic accuracy through re-calibration of the kinematic model. This approach is often highly complex, and seeks to optimise performance over the whole working volume or…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Delivery of Mixed Reality Tools Training in the Modern Production Environment

Boeing Co.-Mark Friesen, Lorrie Sivich
  • Technical Paper
  • 2020-01-0052
To be published on 2020-03-10 by SAE International in United States
Since the early development of Mixed Reality (MR) technologies for the gaming industry, Boeing Research and Technology has been a leader in applying the technology to the production environment. Mixed Reality technologies have matured in size reduction and cost enabling a wide variety of visualization tools into the factory today. They include: tablets, Microsoft’s HoloLens, Google Glasses, Vive, and Oculus to name a few. These digital productivity tools allow the factory worker to perform work through installation, quality inspection, and trouble shooting.
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.
new

Fundamentals of Geometric Dimensioning and Tolerancing 2018: Using Critical Thinking Skills

  • Book
  • PD0220019-CB00
Published 2019-12-31 by SAE International in United States

The Fundamentals of Geometric Dimensioning and Tolerancing 2018 Using Critical Thinking Skills by Alex Krulikowski reflects the technical content found in the latest release of the ASME Y14.5-2018 Standard.

This book includes several key features that aid in the understanding of geometric tolerancing. Each of the textbook's 26 chapters focuses on a major topic that must be mastered to be fluent in the fundamentals of GD&T. Each topic includes a goal that is defined and supported by a set of performance objectives that include real-world examples, verification principles and methods, and chapter summaries. There are more than 260 performance objectives that describe specific, observable, measurable actions that the student must accomplish to demonstrate mastery of each goal. Learning is reinforced by completing three types of exercise problems, along with critical thinking questions that promote application of GD&T on the job. It's the most practical and easy-to-use GD&T text on the market.

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

Improvement of motor calibration by using deep learning

Toyota Motor Corporation-Toshiki Terabe, Toshio Watari, Hiroshi Yoshimoto, Kenji Yamada
  • Technical Paper
  • 2019-01-2310
Published 2019-12-19 by SAE International in United States
Knowledge of experts is necessary for judging motor current waveforms. Here, we develop an automatic judgement system for motor current waveform by establishing an AI model trained by knowledge of experts and CAE technology.
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.
new

Diesel Engine Combustion Control with Onboard Calibration by Using Feedback Error Learning

Department of Mechanical Engineering, University of Tokyo-Motoki Takahashi, Yudai Yamasaki, Shigehiko Kaneko
School of Integrated Design Engineering, Graduate school of-Makoto Eguchi, Naoki Fukuda, Hiromitsu Ohmori
  • Technical Paper
  • 2019-01-2318
Published 2019-12-19 by SAE International in United States
In this paper, we propose an onboard calibration method based on the feedback error learning (FEL). This controller is 2 degree of freedom controller. We use a cerebellar model articulation controller (CMAC) as the feedforward controller. By using this, fast learning will be possible. Due to the online learning of this controller, it becomes possible to correspond to changes in the environment such as aging. In this paper, we constructed FEL considering the premixed diesel combustion with dual peak heat release rate under transient operation. To confirm the effectiveness of this control system, experimental results will be shown.
This content contains downloadable datasets
Annotation ability available
Open Access
new

Autonomous Vehicles Scenario Testing Framework and Model of Computation

SAE International Journal of Connected and Automated Vehicles

Florida Polytechnic University, USA-Ala Jamil Alnaser, Mustafa Ilhan Akbas, Arman Sargolzaei, Rahul Razdan
  • Journal Article
  • 12-02-04-0015
Published 2019-12-18 by SAE International in United States
Autonomous Vehicle (AV) technology has the potential to fundamentally transform the automotive industry, reorient transportation infrastructure, and significantly impact the energy sector. Rapid progress is being made in the core artificial intelligence engines that form the basis of AV technology. However, without a quantum leap in testing and verification, the full capabilities of AV technology will not be realized. Critical issues include finding and testing complex functional scenarios, verifying that sensor and object recognition systems accurately detect the external environment independent of weather conditions, and building a regulatory regime that enables accumulative learning. The significant contribution of this article is to outline a novel methodology for solving these issues by using the Florida Poly AV Verification Framework (FLPolyVF).
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.
new

Finding Diverse Failure Scenarios in Autonomous Systems Using Adaptive Stress Testing

SAE International Journal of Connected and Automated Vehicles

University of Illinois at Urbana-Champaign, USA-Peter Du, Katherine Driggs-Campbell
  • Journal Article
  • 12-02-04-0018
Published 2019-12-18 by SAE International in United States
Identifying and eliminating failure scenarios is critical in the development of autonomous vehicle (AV) systems. However, finding such failures through real-world vehicle-level testing is a difficult task as system disengagements and accidents are rare occurrences. Simulation approaches have been proposed to supplement vehicle-level testing and reduce the costs associated with operating large fleets of autonomous test vehicles. While one can run more vehicles in simulation than in the real world, applying traditional Monte Carlo sampling techniques to find failures still yields an unguided search and a large waste of computing resources. A more directed method than random sampling is needed to identify failure scenarios in a computationally efficient manner. Adaptive Stress Testing (AST) is a method that uses reinforcement learning (RL) paradigms to efficiently find failure scenarios in stochastic sequential decision-making systems. Through iteratively exploring the action space and collecting rewards, AST aims to establish an optimal policy that generates a set of high-probability failure trajectories. However, the trajectories obtained through AST tend to lack diversity and converge to similar failure states. Due to the…
This content contains downloadable datasets
Annotation ability available
new

Application Study of Blind Spot Monitoring System Realized by Monocular Camera with CNN Depth Cues Extraction Approach

SAE International Journal of Connected and Automated Vehicles

Jiangsu Chaoli Electric Co., Ltd., China-Chuyo Kaku
Tokyo Institute of Technology, Japan-Yuxiang Guo, Itsuo Kumazawa
  • Journal Article
  • 12-02-04-0016
Published 2019-12-17 by SAE International in United States
The image from monocular camera is processed to detect depth information of the obstacles viewed by the rearview cameras of vehicle door side. The depth information recognized from a single, two-dimensional image data can be used for the purpose of blind spot area detection. Blind spot detection is contributing to enhance the vehicle safety in scenarios such as lane-change and overtaking driving. In this article the depth cue information is inferred from the feature comparison between two image blocks selected within a single image. Convolutional neural network model trained by deep learning process with good enough accuracy is applied to distinguish if an obstacle is far or near for a specified threshold in the vehicle blind spot area. The application study results are demonstrated by the offline calculations with real traffic image data.
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Caterpillar launches next-gen mini hydraulic excavator, skid steer and compact track loaders

SAE Truck & Off-Highway Engineering: December 2019

Jennifer Shuttleworth
  • Magazine Article
  • 19TOFHP12_12
Published 2019-12-01 by SAE International in United States

Covering about 2.5 million ft2 and including roughly 2,800 exhibitors, the triennial ConExpo-Con/Agg event boasts an evenlarger footprint for 2020 with the addition of the Festival Grounds. As one of the major exhibitors at North America's largest construction tradeshow, taking place March 10-14 in Las Vegas, Caterpillar will have a fairly significant footprint of its own, filled with new equipment featuring the company's latest technology developments. A few of the machines likely to be on display were revealed at an October 2019 press event in Clayton, NC.

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

Electrification System Modeling with Machine/Deep Learning for Virtual Drive Quality Prediction

General Motors Technical Center India-Brijesh Borkar, John Bosco Maria Francis, Pankaj Arora
  • Technical Paper
  • 2019-28-2418
Published 2019-11-21 by SAE International in United States
A virtual 'model' is generally a mathematical surrogate of a physical system and when well correlated, serves as a basis for understanding the physical system in part or in entirety. Drive Quality (DQ) defines a driver's 'experience' of a blend of controlled responses to an applied input. The 'experience' encompasses physical, biological and bio- chemical perception of vehicular motion by the human body. In the automotive domain, many physical modeling tools are used to model the sub-components and its integration at the system level. Physical Modeling requires high domain expertise and is not only time consuming but is also very 'compute-resource' intensive. In the path to achieving 'vDQP (Virtual Drive Quality Prediction)' goal, one of the requirements is to establish 'well-correlated' virtual environments of high fidelity with respect to standard test maneuvers. This helps in advancing many developmental activities from a Analysis, Controls and Calibration standpoint. Recently, machine/deep learning have proven to be very effective in pattern recognition, classification tasks and human-level control to model highly nonlinear real world systems. This paper investigates the effectiveness…
This content contains downloadable datasets
Annotation ability available