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.

Drivable area detection and vehicle location based on multi-sensor information fusion

Suzhou Haomibo Technology Co. Ltd.-Panpan Tong
Tongji University-Jie Bai, Sen Li, Jinzhu Wang, Libo Huang, Lianfei Dong
  • Technical Paper
  • 2020-01-1027
To be published on 2020-04-14 by SAE International in United States
Multi-sensor information fusion framework is the eyes for unmanned driving and Advanced Driver Assistance System (ADAS) to perceive the surrounding environment. In addition to the perception of the surrounding environment, real-time vehicle location is also the key and difficult point of unmanned driving technology. The disappearance of high-precision GPS differential signal and the defect of lane line will bring much more difficult for vehicle self-locating. In this paper, a road boundary feature extraction algorithm is proposed based on multi-sensor information fusion of automotive radar and vision to realize the auxiliary locating of vehicles. Firstly, we designed a 79GHz (78-81GHz) Ultra Wide Band(UWB)millimeter wave radar, which can obtain the point cloud information of road edge features such as guardrail or green belt and so on. Secondly, the pixel semantic information of the drivable area of road can be obtained by the pixel semantic segmentation of image information through deep learning. Then, the road boundary equation in vehicle coordinate system is obtained by clustering and fusion of the road boundary point cloud information and the boundary semantic…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

The Design of Safe-Reliable-Optimal Performance for Automated Driving Systems on Multiple Lanes with Merging Features

Honda Motor Co., Ltd.-Kaijiang Yu
  • Technical Paper
  • 2020-01-0122
To be published on 2020-04-14 by SAE International in United States
Safety function for automated driving systems including advanced driver assistance systems and autonomous vehicle systems is very important. Inside safety function, predictive judge sub-function should be designed with the consideration of more and more penetration of automated driving vehicles. This paper presents the design on multiple lanes with merging features based on the author's previous Patent JP2019-147944. In the author's previous work (Model Predictive Control for Hybrid Electric Vehicle Platooning Using Slope Information-Published on IEEE transactions on Intelligent Transportation Systems), a model predictive control framework was designed. Due to the difficulty to detail the sub-safety function deeply with merging features, few works are found to deal with sensor platforms focusing on rear side, and situations of merging lane side with the consideration of relative relation variations with other vehicles and road border markers. However, performance enhancement is needed assuring 100% safety-reliability-optimality and single-objectivity. Also, the detailed platform of on-board sensors including side and rear view is needed to deal with false negative operations and false positive operations. The optimal operation line model of human factors…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Data-driven Object Detection Confidence Model for ADAS

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) have the potential to reduce human error and therefore improve driving safety and comfort. Object-detection is a critical task for the ADAS perception system. On one hand, false-negative can cause accidents; on the other hand, false-positive can result in ghost-braking and harm the driving experience. Different sensors, such as radar and camera, are typically combined to achieve higher robustness and accuracy. Using large amount of information from different sources to create a confidence mode and determine the validity of the detected-objects have not been much studied in the literature. In this paper, we propose a data-driven method which combines various information, such as radar reflection power and camera detection quality, to produce a unified confidence model. In addition, different region regarding the ego vehicle usually has different requirements for detection error based on ADAS functions. And thus, different confidence thresholds are used base the region of interest. The proposed method was validated with real-world driving data and shown a higher…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Optimization of Fuel Economy using Optimal Controls on regulatory and real-world driving cycles.

BorgWarner-Sara Mohon, Philip Keller, John Shutty, Nithin Kondipati
Gamma Technologies LLC-Dhaval Lodaya, Jonathan Zeman, Marcin Okarmus
  • Technical Paper
  • 2020-01-1007
To be published on 2020-04-14 by SAE International in United States
In recent years, electrification of vehicle powertrains has become more mainstream to meet regulatory fuel economy and emissions requirements. Amongst the many challenges involved with powertrain electrification, developing supervisory controls and energy management of hybrid electric vehicle powertrains involves significant challenges due to multiple power sources involved. Optimizing energy management for a hybrid electric vehicle largely involves two sets of tasks: component level or low-level control task and supervisory level or high-level control task. In addition to complexity within powertrain controls, advanced driver assistance systems and the associated chassis controls are also continuing to become more complex. However, opportunities exist to optimize energy management when a cohesive interaction between chassis and powertrain controls can be realized. To optimize energy management along a given route, certain information such as the projected vehicle route, driver behavior, and battery charge level should be considered. In this paper, simulation models of a parallel P0P4 hybrid electric vehicle are presented, which optimize powertrain controls using the Dynamic Programming approach. This virtual vehicle model is exercised through the EPA 5-Cycle Fuel…
   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.

Decision making and trajectory planning of a novel vehicle lane-changing control method inspired by automatic parallel parking

Tsinghua University-Liangyao Yu, Ze Ru, Zhenghong Lu, Guanqun Liang, Cenbo Xiong, Abi Lanie, Ruyue Wang
  • Technical Paper
  • 2020-01-0134
To be published on 2020-04-14 by SAE International in United States
With the development of automation technology in automobiles, lane-changing systems have been developed and applied to improve environmental adaptability of advanced driver assistant system (ADAS) as well as driver comfort. Lane-changing control consists of three steps: decision making, trajectory planning and trajectory tracking. Decision making and trajectory planning are usually integrated in recent studies, where decision making is related to potential trajectories so that environmental adaptability is improved. However, current methods are not perfect due to weaknesses like high computation cost, low robustness to uncertainties, etc. In this paper, a novel lane changing control method is proposed, where lane-changing behavior is analogized to parallel parking behavior. The focus of this study lies on decision making and trajectory planning. In the perspective of host vehicle with lane-changing intention, the space between vehicles in the target adjacent lane can be regarded as dynamic parking space. A decision making and trajectory planning algorithm of parallel parking is adapted to deal with lane-changing condition. The adopted algorithm is based on rules which checks lane-changing feasibility and generates desired path…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

ROS and XCP in Traditional ECU Development

ETAS Inc.-Tobias Gutjahr, Matthew Roddy
  • Technical Paper
  • 2020-01-1367
To be published on 2020-04-14 by SAE International in United States
Originally developed for the service robot industry, the Robot Operating System (ROS) has lately received a lot of attention from the automotive sector with use cases, especially, in the area of advanced driver assistance systems and autonomous driving (ADAS/AD). Introduced as communication framework on top a of a host operating system, the value proposition of ROS is to simplify the software development in large-scale heterogeneous computing systems. Developers can focus on the application layer and let ROS handle the discovery of all participants in the system and establish communication in-between them. Despite the recent success of ROS, standardized automotive communication protocols such as the Universal Measurement and Calibration Protocol (XCP) are still dominant in the electronic control unit (ECU) development of traditional vehicle subsystems like engine, transmission, braking system, etc. XCP guarantees that common measurement and calibration tools can be used across different vehicles with ECUs from multiple suppliers. With the advancing area of ADAS/AD, we also expect the presence of ROS-based modules in the development of new vehicle platforms to increase. In this paper,…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Effect of Adherent Rain on the Performance of Image-Based Algorithms in Automotive Domain

University of Michigan - Dearborn-Yazan Hamzeh, Zaid El-Shair, Samir A. Rawashdeh
  • Technical Paper
  • 2020-01-0104
To be published on 2020-04-14 by SAE International in United States
Adverse weather conditions degrade the quality of images used in vision-based advanced driver assistance systems (ADAS) and autonomous driving algorithms. Adherent rain drops onto a vehicle’s windshield occlude parts of the input image and blur background texture in regions covered by them. Rain also changes image intensity and disturbs chromatic properties of color images. In this work, we collected a dataset using a camera mounted behind a windshield at different rain intensities. The data was processed to generate a set of distorted images by adherent raindrops along with ground truth data of clear images (just after a windshield wipe). We quantitatively evaluated the amount of distortion caused by the raindrops, using the Normalized Cross-Correlation (NCC) and structural similarity (SSIM) methods. While most prior work in the field of rain detection and removal focuses on the image restoration aspects, they typically do not provide quantitative measures to the effect of degradation of input image quality on the performance of image-based algorithms. We quantitatively evaluated the effect of raindrop distortion on deep-learning-based object detection algorithms by comparing…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Experimental Evaluation of Longitudinal Control for Connected and Automated Vehicles through Vehicle-in-the-Loop Testing

Argonne National Laboratory-Miriam Di Russo, Simeon Iliev, Kevin M. Stutenberg, Eric Rask
Wayne State University-Jerry Ku
  • Technical Paper
  • 2020-01-0714
To be published on 2020-04-14 by SAE International in United States
Automated driving functionalities delivered through Advanced Driver Assistance System (ADAS) have been adopted more and more frequently in consumer vehicles. The development and implementation of such functionalities pose new challenges in safety and functional testing and the associated validations, due primarily to their high demands on facility and infrastructure. This paper presents a rather unique Vehicle-in-the-Loop (VIL) test setup and methodology compared those previously reported, by combining the advantages of the hardware-in-the-loop (HIL) and traditional chassis dynamometer test cell in place of on-road testing, with a multi-agent real-time simulator for the rest of test environment. Details associated with applying the proposed VIL for testing adaptive cruise control (ACC), in conjunction with approaches for creating a virtual lead vehicle, as well as results of energy consumption analysis for a 2017 Toyota Prime with stock and improved longitudinal control algorithm, are reported to illustrate the effectiveness of low-infrastructure-demand test setup and the potential in applying the setup and methodology to other ADAS functionalities
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Development of a Procedure to Correlate, Validate and Confirm Radar Characteristics of Surrogate Targets for ADAS testing.

Dynamic Research Inc.-Jordan Silberling, John Lenkeit
Michigan Technological University-William Buller
  • Technical Paper
  • 2020-01-0716
To be published on 2020-04-14 by SAE International in United States
Surrogate targets are used throughout the automotive industry to safely and repeatably test Advanced Driver Assistance Systems and will likely find similar applications in tests of driving automation systems. For those test results to be applicable to real-world scenarios, the surrogate targets must be representative of the real-world objects that they emulate. Early target development efforts were generally divided into those that relied on sophisticated radar measurement facilities and those that relied on ad-hoc measurements using automotive grade equipment. This situation made communication and interpretation of results between research groups, target developers and target users difficult. SAE J3122-1, ”Test Target Correlation – Radar Characteristics”, was developed by the SAE Active Safety Systems Standards Committee to address this and other challenges associated with target development and use. It describes standardized equipment and procedures for making various types of calibrated radar measurements using automotive grade equipment, with minimal measurement site restrictions. It also defines a correlation procedure that is used to define validity regions and properties for targets that are representative of real-world objects, a validation procedure…