Refine Your Search

Topic

Author

Affiliation

Search Results

Research Report

Unsettled Issues Regarding Autonomous Vehicles and Open-source Software

2021-04-21
EPR2021009
Unsettled Issues Regarding Autonomous Vehicles and Open-source Software introduces the impact of software in advanced automotive applications, the role of open-source communities in accelerating innovation, and the important topic of safety and cybersecurity. As electronic functionality is captured in software and a bigger percentage of that software is open-source code, some critical challenges arise concerning security and validation.
Technical Paper

xEV Propulsion System Control-Overview and Current Trends

2021-04-06
2021-01-0781
Propulsion system control algorithms covering the functional needs of xEV propulsion (‘x’ donates P0-P4 configurations) systems are presented in this paper. The scope and foundation are based on generic well-established HEV controller architectures. However, unlike conventional HEV (series, parallel and power split) powertrains, the next generation of integrated electric propulsion configurations will utilize a single micro controller that supports multiple control functions ranging from the electric machines, inverters, actuators, clutch solenoids, coolant pumps, etc. This presents a unique challenge to architect control algorithms within the AUTOSAR framework while satisfying the complex timing requirements of motor/generator-inverter (MGi) control and increased interface definitions between software components to realize functional integration between the higher level propulsion system and its sub-systems.
Technical Paper

Adopting Aviation Safety Knowledge into the Discussions of Safe Implementation of Connected and Autonomous Road Vehicles

2021-04-06
2021-01-0074
The development of connected and autonomous vehicles (CAVs) is progressing fast. Yet, safety and standardization-related discussions are limited due to the recent nature of the sector. Despite the effort that is initiated to kick-start the study, awareness among practitioners is still low. Hence, further effort is required to stimulate this discussion. Among the available works on CAV safety, some of them take inspiration from the aviation sector that has strict safety regulations. The underlying reason is the experience that has been gained over the decades. However, the literature still lacks a thorough association between automation in aviation and the CAV from the safety perspective. As such, this paper motivates the adoption of safe-automation knowledge from aviation to facilitate safer CAV systems.
Technical Paper

Implementation Methodologies for Simulation as a Service (SaaS) to Develop ADAS Applications

2021-04-06
2021-01-0116
Over the years, the complexity of autonomous vehicle development (and concurrently the verification and validation) has grown tremendously in terms of component-, subsystem- and system-level interactions between autonomy and the human users. Simulation-based testing holds significant promise in helping to identify both problematic interactions between component-, subsystem-, and system-levels as well as overcoming delays typically introduced by the default full-scale on-road testing. Software in Loop (SiL) simulation is utilized as an intermediate step towards software deployment for autonomous vehicles (AV) to make them reliable. SiL efforts can help reduce the resources required for successful deployment by helping to validate the software for millions of road miles. A key enabler for accelerating SiL processes is the ability to use Simulation as a Service (SaaS) rather than just isolated instances of software.
Technical Paper

Streamlined Process for Cloud Based Diagnostics Using Amazon Web Services

2021-04-06
2021-01-0159
In the age of 5G, the cloud constitutes a massive computational resource. Such capability is greatly underutilized, especially for the purpose of vehicle diagnostics and prognostics. Diagnostics and prognostics run mostly in the limited and cost sensitive electronic module of the vehicle. Utilizing vehicle connectivity, along with the massive capability of the cloud would allow the deployment of smarter algorithms that provide improved vehicle performance and operation management. In this paper, a streamlined process to develop and deploy off-board diagnostics is presented. The process included developing multiphysics digital twins and running the diagnostics off-board. It was demonstrated on a fleet of virtual Hybrid Electric Vehicles (HEV). The Digital Twin replica was created using Simulink® and Simscape®. The microcontroller used to demonstrate the diagnostic is a Raspberry Pi hardware running in real time.
Technical Paper

Vehicular Visual Sensor Blinding Detection by Integrating Variational Autoencoders with SVM

2021-04-06
2021-01-0144
The advancements of autonomous vehicles or advanced driver assistance systems in terms of safety, driving experience, and comfort against manual driving results in extensive adoption of them across the modern automotive sector. The autonomous vehicles are equipped with numerous sensing and actuating components both inside as well as outside the vehicles to perceive the environment, perform path planning, and intelligently control the autonomous vehicles. The perception mechanism includes fused information of multiple sensors such as camera, RADAR, and LiDAR to effectively understand all the dynamic driving environments. Some of the intentional and unintentional mechanisms such as cyber-attacks and natural variations of the environment, etc., across the sensor's external interface with the environment cause the degradation of the perception mechanism.
Technical Paper

Building Responsibility in AI: Transparent AI for Highly Automated Vehicle Systems

2021-04-06
2021-01-0195
Replacing a human driver is an extraordinarily complex task. While machine learning (ML) and its’ subset, deep learning (DL) are fueling breakthroughs in everything from consumer mobile applications to image and gesture recognition, significant challenges remain. The majority of artificial intelligence (AI) learning applications, particularly with respect to Highly Automated Vehicles (HAVs) and their ecosystem have remained opaque - genuine “black boxes.” Data is loaded into one side of the ML system and results come out the other, however, there is little to no understanding at how the decision was arrived at. To make these systems accurate, these AI systems require lots of data to crunch and the sheer computational complexity of building these DL based AI models also slows down the progress in accuracy and the practicality of deploying DL at scale.
Technical Paper

Zero-Day Attack Defenses and Test Framework for Connected Mobility ECUs

2021-04-06
2021-01-0141
Recent developments in the commercialization of mobility services have brought unprecedented connectivity to the automotive sector. While the adoption of connected features provides significant benefits to vehicle owners, adversaries may leverage zero-day attacks to target the expanded attack surface and make unauthorized access to sensitive data. Protecting new generations of automotive controllers against malicious intrusions requires solutions that do not depend on conventional countermeasures, which often fall short when pitted against sophisticated exploitation attempts. In this paper, we describe some of the latent risks in current automotive systems along with a well-engineered multi-layer defense strategy. Further, we introduce a novel and comprehensive attack and performance test framework which considers state-of-the-art memory corruption attacks, countermeasures and evaluation methods.
Technical Paper

Technical Trends of the Intelligent Connected Vehicle and Development Stage Division for Freeway Traffic Control

2020-12-30
2020-01-5134
It is deemed that currently the intelligent connected vehicle (ICV) is in its early stage of development, and it will go through multiple development stages in the future to realize its final goal—autonomous driving. Based on the existing ICV researches, this paper believes that ICV can be used to improve the efficiency and safety of freeway. The current research of ICV has two main directions: one focuses on the traffic flow characteristics of vehicles with different attributes, the other is concerned with using ICV to reduce congestion. From the policies issued by countries around the world and the development plans promoted by major vehicle manufacturers, the future development trends and challenges of ICV are analyzed. ICV must overcome all the shortcomings to achieve its final goal, including insufficient hardware capabilities or excessive cost, and the degree of intelligence that needs to be improved.
Technical Paper

Service Analysis of Autonomous Driving

2020-12-30
2020-01-5194
Autonomous driving represents the ultimate goal of future automobile development. As a collaborative application that integrates vehicles, road infrastructure, network and cloud, autonomous driving business requires a high-degree dynamic cooperation among multiple resources such as data, computing and communications that are distributed throughout the system. In order to meet the anticipated high demand for resources and performance requirements of autonomous driving, and to ensure the safety and comfort of the vehicle users and pedestrians, a top concern of autonomous driving is to understand the system requirements for resources and conduct an in-depth analysis of the autonomous driving business. In this context, this paper presents a comprehensive analysis of the typical business for autonomous driving and establishes an analysis model for five common capabilities, i.e. collection, transmission, intelligent computing, human-machine interaction (HMI), and security.
Research Report

Unsettled Topics Concerning Human and Autonomous Vehicle Interaction

2020-12-18
EPR2020025
This report examines the current interaction points between humans and autonomous systems, with a particular focus on advanced driver assistance systems (ADAS), the requirements for human-machine interfaces as imposed by human perception, and finally, the progress being made to close the gap. Autonomous technology has the potential to benefit personal transportation, last-mile delivery, logistics, and many other mobility applications enormously. In many of these applications, the mobility infrastructure is a shared resource in which all the players must cooperate. In fact, the driving task has been described as a “tango” where we—as humans—cooperate naturally to enable a robust transportation system. Can autonomous systems participate in this tango? Does that even make sense? And if so, how do we make it happen?
Research Report

Unsettled Topics Concerning Autonomous Public Transportation Systems

2020-10-30
EPR2020020
With billions of dollars of investment and events like DARPA’s Grand Challenges automated driving technology has been making its way toward commercialization. While the enabling technology for SAE Level 4 and 5 automated vehicles (AV) has not yet matured, specific restricted-use models such as “robo-taxis” and automated truck convoying show great promise. Now, cities are across the world are looking to AVs to solve their public transportation issues. With low speeds and fixed route, public transportation is an ideal application for AVs. From a business angle, AVs could leverage existing public transport models and infrastructure while providing superior quality of service for disadvantaged communities. Yet, dense urban environments—which would benefit from automated transportation the most—present unique challenges and public sector requirements. This SAE EDGE™ Research Report by Dr.
Research Report

Unsettled Issues Regarding Policy Aspects of Automated Driving Systems

2020-08-31
EPR2020016
Automated driving systems (ADS) represent an area of considerable investment and activity within the transportation sphere. The potential impact of ADS on safety, efficiency, and user experience are extremely significant. To get the most from the technology, it is important to ensure that policies are developed to support the balance between achieving public sector objectives and supporting private sector innovation. This SAE EDGE™ Research Report explores the policy aspects related to ADS technology, explains the key stakeholders, identifies unsettled issues, and proposes a number of steps to move forward and improve the current situation. It is hoped that the report will provide a valuable resource to those involved in the definition of ADS policy from both public and private perspectives. It is also intended to serve as a resource for those involved in ADS planning and development and public sector staff involved in other aspects beyond ADS policy.
Research Report

Unsettled Issues Facing Automated Vehicles and Insurance

2020-08-05
EPR2020015
This SAE EDGE™ Research Report explores how the deployment of automated vehicles (AVs) will affect the insurance industry and the principles of liability that underly the structure of insurance in the US. As we trade human drivers for suites of sensors and computers, who (or what) is responsible when there is a crash? The owner of the vehicle? The automaker that built it? The programmer that wrote the code? Insurers have over 100 years of experience and data covering human drivers, but with only a few years’ worth of information on AVs – how can they properly predict the true risks associated with their deployment? Without an understanding of the nature and risks of AVs, how can the government agencies that regulate the insurance industry provide proper oversight? Do the challenges AVs present require a total reworking of our insurance and liability systems, or can our current structures be adapted to fit them with minor modifications?
Research Report

Unsettled Topics Concerning User Experience and Acceptance of Automated Vehicles

2020-06-29
EPR2020012
This SAE EDGE Research Report addresses the unsettled topic of user acceptance of automated driving, analyzing the user experience for a more intuitive and safe driving experience. Unsettled Topics Concerning User Experience and Acceptance of Automated Vehicles examines the requirements for safer driver/user engagement with driving for the various SAE automation levels. It analyzes consumer sentiment toward automated driving - both consumer excitement about the perceived benefits and dislikes or concerns about the technology. The findings from surveys about drivers' experience with advanced driving assistance technologies and its application to automated driving is also brought to the surface of the discussion, together with driver profiles observed during a user-centric experience in an immersive automated driving cockpit.
Research Report

Unsettled Topics in Automated Vehicle Data Sharing for Verification and Validation Purposes

2020-06-03
EPR2020007
Unsettled Topics in Automated Vehicle Data Sharing for Verification and Validation Purposes discusses the unsettled issue of sharing the terabytes of driving data generated by Automated Vehicles (AVs) on a daily basis. Perception engineers use these large datasets to analyze and model the automated driving systems (ADS) that will eventually be integrated into future “self-driving” vehicles. However, the current industry practices of collecting data by driving on public roads to understand real-world scenarios is not practical and will be unlikely to lead to safe deployment of this technology anytime soon. Estimates show that it could take 400 years for a fleet of 100 AVs to drive enough miles to prove that they are as safe as human drivers.
Research Report

Unsettled Topics in the Application of Satellite Navigation to Air Traffic Management

2020-05-27
EPR2020010
Contemporary air traffic management (ATM) challenges are both (1) acute and (2) growing at rates far outpacing established ways for absorbing technological innovation. Lack of timely response will guarantee failure to meet demands. Immediately that creates a necessity to identify means of coping and judging new technologies based on possible speed of adoption. Paralleling the challenges are developments in capability, both recent and decades old. Some steps (e.g., Global Positioning System (GPS) backup) are well known and, in fact, should have progressed further long ago. Others (e.g., sharing raw measurements instead of position fixes) are equally well known and, if followed by further flight tests initiated (and successful) years ago, would have produced a wealth of in-flight experience by now if development had continued. Other possibilities (e.g., automated pilot override) are much less common and are considered largely experimental.
Technical Paper

An Integrated View on Automotive SPICE, Functional Safety and Cyber-Security

2020-04-14
2020-01-0145
This increases the attractiveness of an attack on vehicles and thus introduces new risks for vehicle cybersecurity. Thus, just as safety became a critical part of the development in the late 20th century, the automotive domain must now consider cybersecurity as an integral part of the development of modern vehicles. ...Thus, just as safety became a critical part of the development in the late 20th century, the automotive domain must now consider cybersecurity as an integral part of the development of modern vehicles. Aware of this fact, the automotive industry has, therefore, recently taken multiple efforts in designing and producing safe and secure connected and automated vehicles. ...As the domain geared up for the cybersecurity challenges, they leveraged experiences from many other domains, but must face several unique challenges.
X