This SAE Information Report classifies and defines a harmonized set of safety principles intended to be considered by ADS and ADS-equipped vehicle development stakeholders. The set of safety principles herein is based on the collection and analysis of existing information from multiple entities, reflecting the content and spirit of their efforts, including: SAE ITC AVSC Best Practices CAMP Automated Vehicle Research for Enhanced Safety - Final Report RAND Report - Measuring Automated Vehicle Safety: Forging a Framework U.S. DOT: Automated Driving Systems 2.0 - A Vision for Safety Safety First for Automated Driving (SaFAD) UNECE WP29 amendment proposal UNECE/TRANS/WP.29/GRVA/2019/13 On a Formal Model of Safe and Scalable Self-Driving Cars (Intel RSS model) SAE J3018 This SAE Information Report provides guidance for the consideration and application of the safety principles for the development and deployment of ADS and ADS-equipped vehicles. This SAE Information Report is not intended to

On-Road Automated Driving (ORAD) committee

Taxonomy and Definition of Safety Principles for Automated Driving System (ADS)

J3206_202107-TEST-REC (Historical)07/07/2021

On-Road Automated Driving (ORAD) committee

Detection & Tracking of Multi-Scenic Lane Based on Segnet-LSTM Semantic Split Network

2021-01-008304/06/2021

Lane detection is an important component in automatic pilot system and advanced driving assistance system (ADAS). The stability and precision of lane detection will directly determine precision of control and lane plan of vehicles. Traditional mechanical vision lane detection approaches in complicated environment have the deficiencies of low precision and feature semantic description disabilities. But the lane detection depending on deep learning, e.g. SCNN network, LaneNet network, ENet-SAD network have imbalance problems of splitting precision and storage usage. This paper proposes an approach of high-efficiency deep learning Segnet-LSTM semantic segmentation network. This network structure is composed with encoding network and corresponding decoding networks. First, convolution and maximum pooling. The proposal extracts texture details of five images and stores searching position of maximum pooling. Meanwhile, it will implement interpolate processing to the lost points. Then, by up

Ye, Meng, Tan, Gangfeng, Tang, Jingning, Feng, Jiaming, Huang, Xin, Sun, Wenchao

High-Definition Map Based Motion Planning, and Control for Urban Autonomous Driving

2021-01-009804/06/2021

This paper presents motion planning and control algorithm for urban automated driving using high-definition(HD) map. Many automakers have developed and commercialized advanced driver assistance system(ADAS) based on vision-only lane extraction in motorway environments. Compared to the motorway environments where the lane is continuous and clearly visible, however, in urban roads, degradation of the lane quality such as lane occlusion and lane loss occurs frequently. This leads to the poor quality of the local guide path for the autonomous vehicles with vision-only lane extraction. Global HD map is used to provide the lane information continuously instead of vision-only lane extraction. With the existence of global position of host vehicle and the HD map, the proposed sequential algorithm performs the lane keeping and lane changing decision and control with safety margin in multi-vehicle situation. The perceived surrounding vehicles are classified according to their road belonging and

Yoon, Youngmin, Chae, Heungseok, Yi, Kyongsu

Simulation Study to Evaluate Robustness of the Lane Centering Feature

2021-01-010904/06/2021

The advances in automotive technology continue to deliver safety and driving comfort benefits to the society. The Automated Driving Assistance System (ADAS) technology is at the forefront of this evolution. Today, various vehicle models on the road have features like lane keeping assist, lane centering, automated emergency braking, adaptive cruise control, traffic jam assist etc. During early development, such feature algorithms often assume ideal environmental and vehicle conditions while doing a performance evaluation. This study focuses on the use of simulation platform to evaluate robustness of the lane centering ADAS feature in presence of various factor variations. The feature considered here is an end-to-end feature, i.e., from camera sensor output to steering actuation. The use of closed-loop simulation tools is well recognized in automotive industry for early requirements validation as well as robustness study. However, it has been traditionally used mainly for vehicle

Varunjikar, Tejas, Awathe, Arpit, Kushwaha, Pushpendra, Chen, Chao

Simulation Based Virtual Testing for Safety of ADAS Algorithms - Case Studies

2021-01-011404/06/2021

Automated Driving Systems (ADS) make the driving experience safer, more efficient, and comfortable by performing complex maneuvers, preempting potential risky situations, or taking over the driver’s tasks in critical situations. Innovation acceptance research for Advanced Driver Assistance Systems (ADAS) illustrates the increasing demand for safety and comfort as the two prime movers of the ADAS market. Since ADAS technologies have significant impact on human lives, extensive testing and validation throughout the design process is indispensable. Due to complexity of systems, cost of testing, and safety of test engineers, a significant chunk of ADAS calibration and validation needs to be done virtually. Although simulation-based verification and validation (V&V) is not new, the test descriptions, modeling and simulation framework are not yet well established. Off-the-shelf software tools have different architectures, simulation procedures, data standardizations, and tradeoffs. The

Singh, Harnarayan, Midlam-Mohler, Shawn, Tulpule, Punit

Putting Safety of Intended Functionality SOTIF into Practice

2021-01-019604/06/2021

The increase of autonomy demand in the automotive industry made the usage of AI models inevitable. However, such models introduce a variety of threats to automobile safety and security. ISO/PAS 21448 SOTIF is a safety standard that is designed to deal with risks due to non-electrical and non-electronic failures. In this paper we put SOTIF into practice. In our work we introduce a conceivable safety critical scenario that targets the lane keep assist function. We use the suggested modelling techniques in the SOTIF standard to analyze the scenario and extract the trigger event. In result, we propose a contextual based predictive ML model to monitor the intervention between the driver and lane keep assist system. Our approach followed the SOTIF verification and validation guidelines. Empirically, we use a real safety critical scenario dataset as well as an augmented dataset. Our results show a high precision/recall values that exceed 90% by an increase of more than 150% in f1 score

Abdulazim, Amr, Elbahaey, Moustafa, Mohamed, Abduallah

Deep Learning Based Real Time Vulnerability Fixes Verification Mechanism for Automotive Firmware/Software

2021-01-018304/06/2021

Software vulnerability management is one of the most critical and crucial security techniques, which analyzes the automotive software/firmware across the digital cockpit, ADAS, V2X, etc. domains for vulnerabilities, and provides security patches for the concerned Common Vulnerabilities and Exposures (CVE). The process of automotive SW/FW vulnerability management system between the OEMs and vendors happen through a channel of fixing a certain number of vulnerabilities by 1st tier supplier which needs to be verified in front of OEMs for the fixed number and type of patches in there deliverable SW/FW. The gap of verification between for the fixed patches between the OEMs and 1st tier supplier requires a reliable human independent intelligent technique to have a trustworthiness of verification. Hence, in this regard, a novel machine learning based intelligent verification technique is proposed which is free from human intervention to verify the certain number and type of vulnerabilities

Ansari, Asadullah, Ameen Alimohideen, Mohamed, P.C., Karthik

Coalesce of Artificial Intelligence into ADAS Hardware-In-the-Loop Testing

2021-01-019304/06/2021

Automotive industry is inclined towards connected, comfortable, environment friendly, efficient and smarter systems. Advanced Driver Assist System (ADAS) technology assist drivers to achieve a safer as well as better ride by automation and improvisation of the vehicular systems. With the advent of ADAS system, there is a significant focus not only in the development of Electronic Control Units (ECUs) and its features to cater to the emerging market but also on the information that could be displayed to meet the functional as well as safety requirements. This ADAS information display ensures timely notification to the driver with unique alerts that can be acoustic or visual. These systems should be tested thoroughly to ensure reliability as failures may impose severe risk on the OEM. Hardware in the loop testing has been largely adopted by industry against manual testing in lieu of the testing constraints imposed by the latter. This paper discusses on the existing test methods for ADAS

Krishnamoorthy, Bharathi, Nammalwar, Giri, Wulf, Torsten, Pazhur, Nandini

Correlation between Sensor Performance, Autonomy Performance and Fuel-Efficiency in Semi-Truck Platoons

2021-01-006404/06/2021

Semi-trucks, specifically class-8 trucks, have recently become a platform of interest for autonomy systems. Platooning involves multiple trucks following each other in close proximity, with only the lead truck being manually driven and the rest being controlled autonomously. This approach to semi-truck autonomy is easily integrated on existing platforms, reduces delivery times, and reduces greenhouse gas emissions via fuel economy benefits. Level 1 SAE fuel studies were performed on class-8 trucks operating with the Auburn Cooperative Adaptive Cruise Control (CACC) system, and fuel savings up to 10-12% were seen. Enabling platooning autonomy required the use of radar, global positioning systems (GPS), and wireless vehicle-to-vehicle (V2V) communication. Poor measurements and state estimates can lead to incorrect or missing positioning data, which can lead to unnecessary dynamics and finally wasted fuel. This is especially an issue if deceleration is applied in response to a bad

Adam, Cristian, Lakshmanan, Sridhar, Richardson, Paul, Stegner, Evan, Ward, Jacob, Hoffman, Mark, Bevly, David M.

Object Segmentation and Augmented Visualization Based on Panoramic Image Segmentation

2021-01-008904/06/2021

Panoramic images can provide critical information for Advanced Driving Assistance Systems (ADAS), such as parking spaces and surrounding vehicles. However, the vehicle in the bird's-eye view image is severely distorted and incomplete, and the visual information becomes very blurred in some illumination insufficient environments. If the driver cannot see the surrounding environment information, the risk of collision will increase, especially during parking. To better percept the local environment with the help of panoramic images, we use panoramic image segmentation results to construct a virtual surround view monitoring system to provide drivers with clearer perception information. Firstly, a lightweight segmentation network is redesigned based on SegNet, which will improve the accuracy of the segmentation without increasing the model’s inference time. Secondly, we build an augment visualization around view monitor (AV-AVM) system with regards to the segmentation results. All necessary

Liao, Jiacai, Cao, Libo, Gong, Yipeng, Zhao, Junjie, Chen, Zhen, Chen, Kai

Research on Photobiological Safety of Automotive Active Infrared Detection System

2021-01-007204/06/2021

The automotive active infrared detection system is usually applied to the night driver assistance system or the diver attention monitoring system. However, the infrared light emitted by the active infrared detection system can cause damage to retina, cornea and eye crystals. This paper has studied the photobiological safety of the infrared light source used in the automotive active infrared detection system. Although it has been already have the general requirements of photobiological safety in international standards, there is not any requirements for automotive active infrared detection system. The range of the active infrared detection system depends on the radiation intensity of the infrared light source, but too much radiation intensity will cause harm to retina, cornea and eye lens when the infrared light source is too close to eyes. Based on the international standards, this paper has analyzed the retinal thermal hazard and the harm to skin and eyes caused by infrared radiation

Hu, Yue, Zhu, Tong, Li, Qian, Yang, Xiong

New Leak Detection Methodology to Protect against Microscopic Leaks and Water Ingress in Battery Cells, Battery Packs and ADAS Sensors

2021-01-075404/06/2021

Ingress protection standards published by the International Electrotechnical Commission (IEC) classify and rate the degree of protection provided by mechanical casings and electrical enclosures against intrusion, dust, accidental contact and water and may be insufficient. The IP 67 or European EN 60529 test duration is 30 minutes during which time “water ingress in a harmful quantity will not be possible". What is a “harmful quantity” is not stated, nor is the test designed to predict future leak tightness for battery packs for electric and hybrid vehicles, sensors for ADAS (Advanced Driver Assistance Systems), fuel cell stacks, cooling circuits and other automotive electronics where long-term exposure to moisture can cause significant issues. This paper will provide empirical results to show leak sizes that allow either water ingress or egress at typical operating pressures and translate these results into test gas leakage rates.

Blaufuss, Marc, Wetzig, Daniel

Impact of Fog Particles on 1.55 μm Automotive LiDAR Sensor Performance: An Experimental Study in an Enclosed Chamber

2021-01-008104/06/2021

To achieve full automation in self-driving vehicles, environmental perception sensing accuracy is critically important. However, ambient particles in adverse weather like foggy, rainy, or snowy conditions can significantly scatter the incident laser beam, and therefore contaminate the intensity and accuracy of light detection and ranging (LiDAR) sensors. Especially compared to the rapidity of technology development in self-driving vehicles, there is a significant lack of documented research on LiDAR systems with wavelength longer than 1 μm for application in Advanced Driver-Assistance Systems. In this work, experimental studies were performed with a state-of-the-art 1.55 μm wavelength automotive-grade LiDAR system in a controlled laboratory fog chamber. The goal of the research is to correlate laser attenuation and the optical properties of fog particles. In this work, a thorough multistep procedure for LiDAR data analysis is presented including spatial averaging of the object

Zhan, Lu, Northrop, William F.

Multi-Sensor Fusion in Slow Lanes for Lane Keep Assist System

2021-01-008404/06/2021

Implementing Advanced Driver Assistance Systems (ADAS) features that are available in all road scenarios and weather conditions is a big challenge for automotive companies and considered key enablers to achieve autonomous Level 4 (L4) vehicles. One important feature is the Lane Keep Assist System (LKAS). Most LKAS systems are based on lane line detection cameras and lane coefficient estimations by the camera is the key point for LKAS where the camera recognizes the lane lines using edge detection. But when the lane markers are not available due to high traffic and slow driving on the roads, another source of data for the lane lines needs to be available for the LKAS. In this paper a multi-sensor fusion approach based on camera, Lidar, and GPS is used to allow the vehicle to maintain its lateral location within the lane. The lateral distances of the lane lines are measured by LiDAR detection of the markers based on the intensity and fused with lane line information from the HD Map after

Alrousan, Qusay, Matta, Sherif, Tasky, Tom

Vehicular Visual Sensor Blinding Detection by Integrating Variational Autoencoders with SVM

2021-01-014404/06/2021

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. One of these major mechanisms on the visual camera sensors includes blinding of the camera, which is done either deliberately by cyber

S M, Sarala, Karki, Maya

Fuzzy Control Model of Intelligent Lane-Changing Decision Based on Genetic Algorithm Optimization

2021-01-501703/09/2021

Based on the fuzzy inference system, it constructs a discretionary lane-changing decision model for different types of preceding vehicles and compares and analyzes the parameter differences of their input membership functions. According to the driver questionnaire survey, the model uses three parameters that drivers can easily percept as the model input—preceding vehicle distance in the current lane, preceding vehicle distance in the target lane, and following-vehicle distance in the target lane—uses Next-Generation Simulation (NGSIM) vehicle trajectory data to optimize the input membership functions of models based on genetic algorithm according to different vehicle lane-changing trajectory data to analyze the impact of the preceding vehicle type before lane change to the intelligent lane-changing decision. Results show that the membership function parameters of fuzzy control systems are quite different under different preceding vehicle sizes, that is, when the driver makes a lane

Yan, Zhou, Dong, Liu Yuan, Peng, Qin Xun

1.1.201 - A Context Aware Automatic Image Enhancement Method Using Color Transfer

SAE-PP-0021602/01/2021

Advanced Driver Assistance Systems (ADAS) have become an inevitable part of most of the modern cars. Their use is mandated by regulations in some cases; and in other cases where vehicle owners have become more safety conscious. Vision / camera based ADAS systems are widely in use today. However, it is to be noted that the performance of these systems is depends on the quality of the image/video captured by the camera. Low illumination is one of the most important factors which degrades image quality. In order to improve the system performance under low illumination, it is required to first enhance the input images/frames. In this paper, we propose an image enhancement algorithm that would automatically enhance images to a near ideal condition. This is accomplished by mapping features taken from images acquired under ideal illumination conditions on to the target low illumination images/frames. The proposed method consists of four steps a) Pre- processing b) a coarse level segmentation

Mutagaana, Festo

Magna execs warns on impending EV complexities

21AUTP02_1002/01/2021

The industry's transition to electrified - and ultimately, fully electric vehicles (EVs) is bringing far greater overall complexity in product development and technology-management, according to Magna Powertrain executives speaking in an online media session during mid-January's CES 2021 virtual trade show. Magna's traditional strengths in lightweight structures, driver-assistance sensor technologies, active aerodynamic systems, powertrain/drivelines and full-vehicle assembly serve as the foundation for the company as it moves further into vehicle electrification and automated-driving solutions, noted Sherif Marakby, the company's recently hired executive VP. Markaby is a veteran leader of Ford's hybrid and EV programs and headed the automaker's Team Edison autonomous R&D group before joining Magna.

Brooke, Lindsay

Tire pressure's impact on EV driving range

20AUTP11_0311/01/2020

A new study shows that tighter control of tire-pressure loss can lead to marked improvement in electric-vehicle efficiency. Electric-vehicle development teams have made great advances in improving vehicle range, mitigating “range anxiety” for the end customer. While much focus has been on advances in battery technology, controls and vehicle aerodynamics, EV driving range also is significantly affected by tires. Energy-inefficient tire construction, sub-optimal inflation and other factors can adversely impact EV range. Tires lose a certain amount of air on a continuous basis. An underinflated tire is less stiff and its deformation is much higher, leading to a larger amount of heat dissipation and ultimately higher rolling resistance and poor range efficiency.

Tang, Lamei, Wei, Sheng, Valentage, Jeffrey, Li, Zheng, Nair, Sujith

Driver Drowsiness and Fatigue in the Safe Operation of Vehicles - Definition of Terms and Concepts

J3198_202010 (Current)

10/26/2020

This SAE Information Report provides definitions and discussions of key terms concerning driver drowsiness and fatigue, and basic information on measuring drowsiness and fatigue. It also includes information and concepts for driver drowsiness as they relate to the safe operation of a vehicle. The key driver drowsiness and fatigue causal factors include the following: (1) sleep quality and quantity, (2) time of day, (3) time awake, (4) time on task (modulated by characteristics of the driving task), (5) task-related fatigue (variations of arousal levels related to task underload and overload), and (6) combinations of these factors. Medical conditions, medication, alcohol, or drugs exacerbate drowsiness; however, the discussion in this report is limited to fatigue concepts. This report has two primary outputs: (1) definitions and discussions of key terms concerning driver drowsiness and fatigue, and (2) basic information on measuring drowsiness and fatigue and its effects on the safe

Driver Metrics, Performance, Behaviors and States Committee

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

EPR2020007

06/03/2020

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.Yet, data-sharing can be developed – as a technology, culture, and business – and allow for rapid generation and testing of the billions of possible scenarios that are needed to prove practicality and safety of an ADS – resulting in lower research

Khalkhali, Mohsen, Khalighi, Yaser