The SAE MOBILUS platform will continue to be accessible and populated with high quality technical content during the coronavirus (COVID-19) pandemic. x

Your Selections

Artificial intelligence (AI)
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.

A Diagnostic Technology of Powertrain Parts that Cause Abnormal Noises using Artificial Intelligence

Hanyang University-Kyoungjin Noh, Joon-Hyuk Chang
Hyundai Motor Company-Insoo Jung, Dongchul Lee, Dongkyu Yoo, Kibeen Lim
  • Technical Paper
  • 2020-01-1565
To be published on 2020-06-03 by SAE International in United States
In general, when a problem occurs in a component, various phenomena appear, and abnormal noise is one of them. The service technicians diagnose the noise through the analysis using hearing and equipment. Depending on their experiences, the analysis time and diagnosis accuracy vary widely. The newly developed AI-based diagnostic technology diagnoses parts that cause abnormal noises within seconds when a noise is input to the equipment. To create a learning model for diagnosis, we collected as many abnormal noises as possible from various parts, and selected good and bad data. This process is very important in the development of diagnostic techniques. Artificial intelligence was learned by deep learning with selected good data. This paper is about the technology that can diagnose the abnormal noises generated from the engine, transmission, drivetrain and PE (Power Electric) parts of the eco-friendly vehicle through the diagnosis model composed of various methods of deep learning.
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Safety assurance concepts for automated driving systems

University of Melbourne-Stuart Ballingall, Majid Sarvi, Peter Sweatman
  • Technical Paper
  • 2020-01-0727
To be published on 2020-04-14 by SAE International in United States
Automated Driving Systems (ADSs) for road vehicles are being developed that can perform the entire dynamic driving task without a human driver in the loop. However, current regulatory frameworks for assuring vehicle safety may restrict the deployment of ADSs that can use machine learning to modify their functionality while in service. A review was undertaken to identify and assess key initiatives and research relevant to the safety assurance of adaptive safety-critical systems that use machine learning, and to highlight assurance concepts that could benefit from further research. The primary objective was to produce findings and recommendations that can inform policy and regulatory reform relating to ADS safety assurance. Due to the almost infinite number and combination of scenarios that an ADS could encounter, the review found much support for concepts that involve the use of simulation data as virtual evidence of safety compliance, with suggestions of a need to assure simulation tools and models. Real-world behavioural competency testing was also commonly proposed, although noting this concept has its limitations. The concept of whole-of-life assurance was…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Data-Driven Confidence Model for ADAS Object Detection

Dong Feng Engineering & Technical Center-Hang Yang, Darui Zhang, Daihan Wang, Jianguang Zhou
  • Technical Paper
  • 2020-01-0695
To be published on 2020-04-14 by SAE International in United States
The majority of road accident is due to human error. Advanced Driver Assistance System (ADAS) has the potential to reduce human error and improve driving safety. Customers have shown a growing acceptance for ADAS technology. With the rising demand for safety and comfortable driving experience, the global market for ADAS is expected to grow to $67 billion by 2025.A reliable ADAS system requires an accurate and robust object-detection system. There is often a trade-off in tuning the system. On one hand, miss-detection can cause accidents; on the other hand, false-detection can result in ghost-braking and harm the driving experience. The ADAS system can access various information from different sources. However, a unified confidence model, which combines different indicators, has not been much studied in the literature. In this paper, we propose a data-driven method, which utilizes the features from radar, camera and the tracking system to produce a high-level confidence model. In addition, different regions regarding the ego vehicle usually have different emphases for detection error based on the system design requirements. And therefore, we…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Heterogeneous Machine Learning on High Performance Computing for End to End Driving of Autonomous Vehicles

National Renewable Energy Laboratory-Xiangyu Zhang, Peter Graf
Oak Ridge National Laboratory-Robert Patton, Shang Gao, Spencer Paulissen, Nicholas Haas, Brian Jewell
  • Technical Paper
  • 2020-01-0739
To be published on 2020-04-14 by SAE International in United States
Current artificial intelligence techniques for end to end driving of autonomous vehicles typically rely on a single form of learning or training processes along with a corresponding dataset or simulation environment. Relatively speaking, success has been shown for a variety of learning modalities in which it can be shown that the machine can successfully “drive” a vehicle. However, the realm of real-world driving extends significantly beyond the realm of limited test environments for machine training. This creates an enormous gap in capability between these two realms. With their superior neural network structures and learning capabilities, humans can be easily trained within a short period of time to proceed from limited test environments to real world driving. For machines though, this gap is guarded by at least two challenges: 1) machine learning techniques remain brittle and unable to generalize to a wide range of scenarios, and 2) effective training data that enhances generalization and generates the desired driving behavior. Further, each challenge can be computationally intensive on its own thereby exasperating the gap. Moreover, is has…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

ROBUST SENSOR FUSED OBJECT DETECTION USING CONVOLUTIONAL NEURAL NETWORKS FOR AUTONOMOUS VEHICLES

Kettering University-Jungme Park, Sriram Jayachandran Raguraman, Aakif Aslam, Shruti Gotadki
  • Technical Paper
  • 2020-01-0100
To be published on 2020-04-14 by SAE International in United States
Nowadays, the proliferation of research on the autonomous vehicles and the Advanced Driver Assistance System (ADAS) has resulted from the need for intelligent and safer mobility. Environmental perception is considered as an essential module for autonomous driving and ADAS. In the object detection problem, deep Convolutional Neural Networks (CNNs) become the State-of-the-Art with various different architectures. However, the performances of the existing CNNs have dropped when detecting small objects in distance. To deploy the environmental perception system in real world applications, it is important that the perception system achieves the high accuracy regardless the obstacle sizes, the distances, and weather conditions. In this paper, a sensor fused system for object detection, tracking and classification is proposed by utilizing the advantages of both vision sensor and automotive radar sensor. Data from on-vehicle radar sensor and camera sensor are processed in real time simultaneously. The proposed system consists of three modules: 1) the Coordinate Conversion module converts the radar coordinates into the image coordinate system. 2) Multi Level-Multi Region detection system based on the deep CNNs. The…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Process-Monitoring-for-Quality — A Step Forward in the Zero Defects Vision

General Motors LLC-Carlos Escobar, Jorge Arinez
Tecnologico de Monterrey-Ruben Morales-Menendez
  • Technical Paper
  • 2020-01-1302
To be published on 2020-04-14 by SAE International in United States
More than four decades ago the concept of zero defects was coined by Phillip Crosby. At that time it was only a vision, but today with the introduction of Artificial Intelligence in manufacturing it has become attainable. Since most mature manufacturing organizations have merged traditional quality philosophies and techniques, their processes generate only a few defects per million of opportunities. Therefore, detecting these rare quality events is one of the modern intellectual challenges posed by this industry. Process Monitoring for Quality is a big data-driven quality philosophy aimed at defect detection and empirical knowledge discovery. Detection is formulated as a binary classification problem, where the right machine learning, optimization and statistics techniques are applied to develop an effective predictive system. Manufacturing-derived data sets for binary classification of quality tend to be highly/ultra unbalanced, making it very difficult for the learning algorithms to learn the minority (defective) class. In this paper, the learning and deployment paradigm of Process Monitoring for Quality is presented, a discussion of how it interacts with traditional quality philosophies to enable the…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Effect of Space Weather on Autonomous Vehicle Navigation

University Of Detroit Mercy-Alan Hoback
  • Technical Paper
  • 2020-01-0140
To be published on 2020-04-14 by SAE International in United States
Autonomous vehicle systems integrate multiple information systems. Navigation is reliant on Global navigation satellite systems (GNSS) such as the global positioning systems (GPS) which are supported by a satellite network. However, satellites and radio signals are subject to interference from sunspots. Sunspots happen on regular cycles at varying strengths but their occurrence can’t be exactly predicted. The likelihood of a severe solar event is roughly twelve percent per decade; consequently, solar events are likely to impair navigation. Results will show the probability of each event and its impact on autonomous vehicle navigation. In the worst case scenario, satellites could even be permanently damaged by severe sunspots. As autonomous vehicles become a more significant portion of the economy, it is necessary that they have resilience to operate in extreme conditions. Alternative navigation procedures are proposed to enhance the resiliency of autonomous vehicles. Artificial intelligence related to place identification with relative geographic navigation and storage of most common routes is an option.
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

A Study of Driver's Driving Concentration Based on Computer Vision Technology

Chongqing University-Guan Lin, Zhenfei Zhan, Xiangjun Peng, Huijie Xu, Yue Fu, Ling Jiang
  • Technical Paper
  • 2020-01-0572
To be published on 2020-04-14 by SAE International in United States
Driving safety is an eternal theme of the transportation industry. In recent years, with the rapid growth of car ownership, traffic accidents have become more frequent, and the harm it brings to human society has become increasingly serious. In this context, car safety assisted driving technology has received widespread attention. As an effective means to reduce traffic accidents and reduce accident losses, it has become the research frontier in the field of traffic engineering and represents the trend of future vehicle development. However, there are still many technical problems that need to be solved. With the continuous development of computer vision technology, face detection technology has become more and more mature, and applications have become more and more extensive. This article will use the face detection technology to detect the driver's face, and then analyze the changes in driver's driving focus. Firstly, the problem of detecting the eyes and mouth status of the driver is discussed. The purpose is to capture the driver's long-term closed eyes and yawning and other actions closely related to the…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Driving Safety Performance Assessment Metrics for ADS-Equipped Vehicles

Exponent Inc., Arizona State University-Jeffrey Wishart, Steven Como
Intel-Maria Elli, Jack Weast
  • Technical Paper
  • 2020-01-1206
To be published on 2020-04-14 by SAE International in United States
The driving safety performance of automated driving system (ADS)-equipped vehicles (AVs) must be quantified using metrics in order to be able to assess the driving safety performance and compare it to that of human-driven vehicles. In this research, driving safety performance metrics and methods for the measurement and analysis of said metrics are defined and/or developed.A comprehensive literature review of metrics that have been proposed for measuring the driving safety performance of both human-driven vehicles and AVs was conducted. A list of proposed metrics, including novel contributions to the literature, that collectively, quantitatively describe the driving safety performance of an AV was then compiled, including proximal surrogate indicators, driving behaviors, and rules-of-the-road violations. These metrics, which include metrics from on- and off-board data sources, allow the driving safety performance of an AV to be measured in a variety of situations, including crashes, potential conflicts, and near misses. These measurements enable the evaluation of temporal flows and the quantification of key aspects of driving safety performance. The identification and exploration of metrics focusing explicitly on AVs…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Bridging the Gap Between ISO 26262 and Machine Learning: A Survey of Techniques for Developing Confidence in Machine Learning Based Systems.

Critical Systems Labs Inc.-Jose Serna, Simon Diemert, Laure Millet, Jeffrey Joyce
General Motors LLC-Rami Debouk, Ramesh S
  • Technical Paper
  • 2020-01-0738
To be published on 2020-04-14 by SAE International in United States
Machine Learning (ML) based technologies are increasingly being used to fulfill safety-critical functions in autonomous and advanced driver assistance systems (ADAS). This change has been spurred by recent developments in ML and Artificial Intelligence techniques as well as rapid growth of computing power. It is clear that ML-enabled systems can deliver value as part of a production ADAS program. However, demonstrating that ML-based systems are capable of achieving the necessary level of safety integrity remains a challenge. Current research and development work focused on establishing the reliable and safe operation of ML-based systems is disjoint and typically presents individual techniques that might be used to gain confidence in these systems. As a result, there is minimal guidance for adapting an established ISO 26262 compliant automotive engineering program to enable the development of ML-based systems. This paper presents a literature survey of recent ML literature to identify techniques and methods that can contribute to meeting ISO 2626 requirements. The surveyed literature is mapped onto the ISO 26262 V-model and the applicability of individual techniques and methods…