Your Selections

Driver assistance systems
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.
new

Virtual Assessment of Automated Driving: Methodology, Challenges, and Lessons Learned

SAE International Journal of Connected and Automated Vehicles

BMW Group, Germany-Korbinian Groh
BMW of North America, USA-Thomas Kühbeck
  • Journal Article
  • 12-02-04-0020
Published 2019-12-18 by SAE International in United States
Automated driving as one of the most anticipated technologies is approaching its market release in the near future. Since several years, the research in the automotive industry is largely focused on its development and presents well-engineered prototypes. The many aspects of this development do not only concern the function and its components itself, but also the proof of safety and assessment for its market release. It is clear that previous methods used for the release of Advanced Driver Assistance Systems are not applicable. In contrast to already released systems, automated driving is not restricted to a certain field of application in terms of driving scenarios it has to take action in. This results in an infeasible amount of required testing and unforeseeable scenarios the function can face throughout its lifetime. In this article, we show a scenario-based approach that promises to overcome those challenges. In contrast to previous methods, it includes virtual test domains in a verified way to diminish the demand for real-world testing. Local verification of certain scenarios from real-world testing enables virtual…
Annotation ability available
Open Access
new

Pedestrian Collision Avoidance System for Autonomous Vehicles

SAE International Journal of Connected and Automated Vehicles

Virtual Vehicle Research Center and Graz University of Technology, Austria-Daniel Watzenig
Virtual Vehicle Research Center, Austria-Markus Schratter, Michael Hartmann
  • Journal Article
  • 12-02-04-0021
Published 2019-12-18 by SAE International in United States
Advanced driver assistance systems (ADAS) are state of the art in modern vehicles (SAE level 1-2). They support the driver and improve thereby the vehicle safety during manual driving. In critical situations, collision avoidance systems warn the driver or trigger an autonomous emergency braking maneuver to mitigate or avoid a collision. Also, automated driving vehicles (SAE level 3+) must be able to avoid critical situations and must be more capable than currently available systems. During automated driving, the vehicle is responsible for the driving task instead of the driver. Therefore, safe automated driving requires robust algorithms to avoid collisions with other traffic participants in every situation, especially in critical situations with pedestrians and a limited perception ability. In this work, we investigate how automated driving vehicles can handle critical situations with pedestrians on multilane roads with an emergency braking or evasion maneuver. We focus in detail on very critical situations, where pedestrians are crossing behind an occluded area, e.g. from behind a parked car on the side of the road. In these critical situations, a…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.
new

Road Parameter-Based Driver Assistance System for Safe Driving

SAE International Journal of Connected and Automated Vehicles

Indian Institute of Information Technology (IIIT) Sri City, India-Sai Charan Addanki, J. Sowmya Vasuki, Hrishikesh Venkataraman
  • Journal Article
  • 12-02-04-0019
Published 2019-12-17 by SAE International in United States
One of the key aspects of Advanced Driver Assistance Systems (ADAS) is ensuring the safety of the driver by maintaining a safe drivable speed. Overspeeding is one of the critical factors for accidents and vehicle rollovers, especially at road turns. This article aims to propose a driver assistance system for safe driving on Indian roads. In this regard, a camera-based classification of the road type combined with the road curvature estimation helps the driver to maintain a safe drivable speed primarily at road curves. Three Deep Convolutional Neural Network (CNN) models viz. Inception-v3, ResNet-50, and VGG-16 are being used for the task of road type classification. In this regard, the models are validated using a self-created dataset of Indian roads and an optimal performance of 83.2% correct classification is observed. For the calculation of road curvature, a lane tracking algorithm is used to estimate the curve radius of a structured road. The road type classification and the estimated road curvature values are given as inputs to a simulation-based model, CARSIM (vehicle road simulator to estimate…
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.

Q&A

SAE Truck & Off-Highway Engineering: December 2019

Ryan Gehm
  • Magazine Article
  • 19TOFHP12_13
Published 2019-12-01 by SAE International in United States

Together with its many partners, ZF supplies camera and radar technology and advanced components for both the passenger car and commercial truck markets, the latter being especially suited for the move to more complex driver-assistance systems, according to Dan Williams, director of ADAS & Autonomy at ZF. “The business case in commercial vehicle for reduction in driver hours of service, fuel cost reduction and safety have strong economic incentives to adopt ADAS/automated driving technology. Additionally, the regulations placed on the industry will require our customers to utilize certain solutions,” he said.

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

A Personalized Lane-Changing Model for Advanced Driver Assistance System Based on Deep Learning and Spatial-Temporal Modeling

SAE International Journal of Transportation Safety

Jianghan University, China-Jun Gao, Jiangang Yi
University of Michigan-Dearborn, USA-Yi Lu Murphey
  • Journal Article
  • 09-07-02-0009
Published 2019-11-14 by SAE International in United States
Lane changes are stressful maneuvers for drivers, particularly during high-speed traffic flows. However, modeling driver’s lane-changing decision and implementation process is challenging due to the complexity and uncertainty of driving behaviors. To address this issue, this article presents a personalized Lane-Changing Model (LCM) for Advanced Driver Assistance System (ADAS) based on deep learning method. The LCM contains three major computational components. Firstly, with abundant inputs of Root Residual Network (Root-ResNet), LCM is able to exploit more local information from the front view video data. Secondly, the LCM has an ability of learning the global spatial-temporal information via Temporal Modeling Blocks (TMBs). Finally, a two-layer Long Short-Term Memory (LSTM) network is used to learn video contextual features combined with lane boundary based distance features in lane change events. The experimental results on a -world driving dataset show that the LCM is capable of learning the latent features of lane-changing behaviors and achieving significantly better performance than other prevalent models.
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Weighted Distance Metrics for Data Association Problem in Multi-Sensor Fusion

Dongfeng Motor Corporation Technical Center-Darui Zhang, Ning Bian, Daihan Wang, Hang Yang, Xinjuan Tuo
Published 2019-11-04 by SAE International in United States
Traffic accidents are the world's leading threat to human safety. The majority of traffic accidents are due to human error. Advanced Driver Assist Systems (ADAS) can reduce human error, therefore has the potential to effectively improve the safety of road traffic. The perception module in an ADAS understands the surrounding environment of the subject vehicle and therefore is the prerequisite for planning and control. Due to the limitation of computational constrain of Electronic Control Units, ADAS system commonly uses object-leveled multi-sensor fusion, in which raw data is processed to detect objects at the sensory level. In multi-sensor fusion, the task of assigning new observations to the existing tracks, known as Data Association problem, requires distance metrics to present the similarity between tracks. In the literature, metrics, such as standardized Euclidean distance and Mahalanobis distance has been used. Though accounting for the scale and correlation of the data, the existing metrics cannot account for the importance of each feature in predicting their dissimilarity. As a result, weighting factors are added to the distance metrics and they…
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

An Outer Loop of Trajectory and an Inner Loop of Steering Angle for Trajectory Tracking Control of Automatic Lane Change System

Tongji University-Yang Yang Wang, Yuan Xing Jiang, Zhi Guang Liu, Guang Da Chen
Published 2019-11-04 by SAE International in United States
Automatic Lane Change (ALC) function is an important step to promote the currently popular Advanced Driver Assistance Systems (ADAS) within a single lane. The key issue for ALC is accurate steering angle and trajectory tracking during the lane changing process. In this paper, an MPC controller with a receding horizon is designed to track the desired trajectory. During the tracking process, other objectives such as safety and smoothness are considered. Considering of the practical mechanism and parameter uncertainties, an SMC controller is designed to track the target steering angle. For validation, a Hardware-in-the-Loop (HIL) experiment platform is established, and experiments of different control algorithms under different conditions are carried out successively. Comparisons of the experiment results of MPC+SMC and PID+SMC schemes indicate that both the trajectory error and the steering angle error of the former combination are smaller. Specifically, the peak trajectory error in Y direction of MPC+SMC is by about 50% smaller under velocity from 60km/h to 80km/h, and lane change duration is also shorter than the PID+SMC scheme. And compared to the servo…
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Adaptive Design of Driver Steering Override Characteristics for LKAS

JTEKT Corporation-Yosuke Nishimura, Atsushi Ishihara, Kazuya Ando
Tongji University-Quyi Liu, Hui Chen, Jiachen Chen
Published 2019-11-04 by SAE International in United States
Lane Keeping Assistance System (LKAS) is a typical lateral driver assistance system with low acceptance. One of the main reasons is that fixed parameters cannot satisfy individual differences. So LKAS adaptive to driver characteristics needs to be designed. Driver Steering Override (DSO) process is an important process of LKAS. It happens when contradiction between driver’s intention and system behavior occurs. As feeling of overriding will affect the overall experience of using LKAS, the design of DSO characteristics is worthy of attention. This research provided an adaptive design scheme aiming at DSO characteristics for LKAS by building Driver Preference Model (DPM) based on simulator test data from preliminary experiments. The DPM was to represent the relationship between driver characteristics indices and driver preferred system characteristics indices. So that new drivers’ preference can be predicted by DPM based on their own daily driving data with LKAS switched off. The inputs of DPMs are 27 lane changing driver characteristics indices which were extracted based on natural lane changing data. Principal Component Analysis (PCA) and correlation analysis were used…
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Study on Robust Motion Planning Method for Automatic Parking Assist System Based on Neural Network and Tree Search

Tongji University-Fengwei Hu, Hui Chen, Jiren Zhang
Published 2019-11-04 by SAE International in United States
Automatic Parking Assist System (APAS) is an important part of Advanced Driver Assistance System (ADAS). It frees drivers from the burden of maneuvering a vehicle into a narrow parking space. This paper deals with the motion planning, a key issue of APAS, for vehicles in automatic parking. Planning module should guarantee the robustness to various initial postures and ensure that the vehicle is parked symmetrically in the center of the parking slot. However, current planning methods can’t meet both requirements well. To meet the aforementioned requirements, a method combining neural network and Monte-Carlo Tree Search (MCTS) is adopted in this work. From a driver’s perspective, different initial postures imply different parking strategies. In order to achieve the robustness to diverse initial postures, a natural idea is to train a model that can learn various strategies. As artificial neural network has outstanding potential in representing and learning knowledge, a neural network is utilized to provide prior knowledge, which is trained through supervised learning by a novel method that imitates human learning style. However, the training accuracy…
This content contains downloadable datasets
Annotation ability available