Your Selections

Radar
Show Only

Collections

File Formats

Content Types

Dates

Sectors

Topics

Authors

Publishers

Affiliations

Committees

Events

Magazine

Series

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

Autonomous Vehicle Multi-Sensors Localization in Unstructured Environment

FEV North America Inc.-Qusay Alrousan, Hamzeh Alzu'bi, Andrew Pfeil, Tom Tasky
  • Technical Paper
  • 2020-01-1029
To be published on 2020-04-14 by SAE International in United States
Autonomous driving in unstructured environments is a significant challenge due to the inconsistency of important information for localization such as lane markings. To reduce the uncertainty of vehicle localization in such environments, sensor fusion of LiDAR, Radar, Camera, GPS/IMU, and Odometry sensors is utilized. This paper discusses a hybrid localization technique developed using: LiDAR based Simultaneous Localization and Mapping (SLAM), GPS/IMU and Odometry data, and object lists from Radar and Camera sensors. An Extended Kalman Filter (EKF) is utilized to fuse data from all sensors in two phases. In the preliminary stage, the SLAM-based vehicle coordinates are fused with the GPS-based positioning. The output of this stage is then fused with the objects-based localization. This approach was successfully tested on FEV’s Smart Vehicle Demonstrator at FEV’s HQ representing a complicated test environment with dynamic and static objects. The test results show that multi-sensor fusion improves the vehicle’s localization compared to GPS or LiDAR alone.
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Heartbeat Detection Technology for Monitoring Driver's Physical Condition

Aisin Seiki Co., Ltd.-Kento Tsuchiya, Kenta Mochizuki
Keio University-Tomoaki Ohtsuki, Kohei Yamamoto
  • Technical Paper
  • 2020-01-1212
To be published on 2020-04-14 by SAE International in United States
In recent years, the number of reported traffic accidents due to sudden deterioration in driver’s physical condition has been increasing, and it is expected to develop a system that prevents accidents even if physical condition suddenly changes while driving, or reduces damage through vehicle body control.For this purpose it is necessary to detect sudden changes of the driver’s physical condition, and research is being conducted widely. Among them, it is reported that some of such changes may appear in the heartbeat interval. In other words, by acquiring the driver's heartbeat interval in real time, it may be possible to detect the sudden changes, and reduce traffic accident. Even if a traffic accident has occurred, the damage can be reduced by emergency evacuation immediately after detecting sudden changes. Therefore, we focused on the technology to detect the heartbeat interval wiht 24GHz microwave doppler radar, which can acquire heartbeat non-contactly while maintaining the interior design and passenger’s privacy. Doppler radar with microwave is sensitive enough to detect heartbeat, but vibration noise is also superimposed on the sensor…
   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.

3-D HORN

John Deere Technology Center-Shubham Jaiswal, Shrutika Upase
  • Technical Paper
  • 2020-01-1375
To be published on 2020-04-14 by SAE International in United States
3-D HORN is a vehicle to vehicle communication based technology which helps in reducing the noise pollution, which occurs, due to honking of automobile horns by letting only the drivers of the automobile to hear the horns and not the whole environment around him. To achieve this, a number of relatively small horn speakers are placed inside the car. These speakers are controlled by drivers of other cars. In this way honking will be heard only by the drivers. The most unique feature of this technology is the 3-D effect caused by the speakers which will let the driver know the location of the outside car which is honking. The 3-D effect is achieved by varying the intensity and proper allotment of sound to the positioned speakers in such a way that it will give the feel of the location of the outside car to the driver. Human detection is another important feature this technology provides. It will recognize whether the horn is honked for an automobile or for a human. In case of human…
   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…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

IMM-KF Algorithm for Multitarget Tracking of on-Road Vehicle

Tongji University-Puhang Xu, Lu Xiong, Dequan Zeng, Zhenwen Deng, Zhuoren Li
  • Technical Paper
  • 2020-01-0117
To be published on 2020-04-14 by SAE International in United States
Tracking vehicle motion trajectories is essential for autonomous vehicles and advanced driver-assistance systems to understand traffic environment and evaluate collision risk. In order to reduce the position deviation and fluctuation of tracking on-road vehicle by millimeter-wave radar (MMWR), an adaptive interactive multi-model Kalman filter (IMM-KF) tracking algorithm including data association and track management is proposed. In general, it is difficult to model the target vehicle accurately due to lack of vehicle kinematics parameters, like wheel base, uncertainty of driving behavior and limitation of sensor’s field of view. To handle the uncertainty problem, an interacting multiple model (IMM) approach using Kalman filters is employed to estimate multitarget’s states. Then the compensation of radar ego motion is achieved, since the original measurement is under the radar coordinate system. In addition, an adaptive Kalman filter is engaged to handle the uncertainty of radar measurement noise and process noise. Taking into account the real-time performance of the algorithm and the distinguishability of vehicles involved in traffic, the nearest neighbor data association (NNDA) is used to associate observation with trajectory,…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Research on Tracking Algorithm for Forward Target Vehicle Using Millimeter-Wave Radar

Jinlin University-Shiping Song, Jian Wu, Yu Yang, Rui He, Xuesong Chen, Xin Li
  • Technical Paper
  • 2020-01-0702
To be published on 2020-04-14 by SAE International in United States
In order to solve the problem that the millimeter-wave radar can’t be directly used for target tracking due to measurement can’t reflect the historical state information of the target, the target measurement information outside the millimeter- wave radar detection range is eliminated by the data plausibility judgment method based on the millimeter-wave radar detection parameters. In order to eliminate clutter interference, target clustering by the Manhattan distance achieve multiple target measurements into one target measurement value. The data association by Nearest Neighbor to determine the measurement information received by the sensor and the real target correspondence. The relative radial distance, relative radial velocity and azimuth angle of the target vehicle detected by the millimeter-wave radar are based on the millimeter-wave radar coordinate system, because the millimeter-wave radar is installed in the front of the vehicle and fixed on the vehicle body. As the vehicle detected by the millimeter-wave radar in the course of driving generally has no vertical direction or vertical velocity is small, and the mobility of moving state is small, the constant acceleration…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Using Polygot Persistence with NoSQL databases for Streaming Multimedia, Sensor, and Messaging Services in Autonomous Vehicles.

Wayne State University-Kyle W. Brown
  • Technical Paper
  • 2020-01-0942
To be published on 2020-04-14 by SAE International in United States
The explosion of data has created challenges for both cloud-based systems and autonomous vehicles in data collection and management. The same challenges are now being realized in developing autonomous databases for the implementation of on-demand services in autonomous vehicles. With just one autonomous vehicle expecting to generate over 30 Terabytes of data a day, modern databases provide opportunities to horizontally scale autonomous data seamlessly. An autonomous vehicle database will be required to handle several data types, radar, lidar, ultra-sonic, GPS, odometry, inertial measurement units, sensor data, while providing streaming services. Multimedia, social media, GPS data, audio, and messaging services will be instrumental to incorporating Platform as a Services (PaaS) into autonomous vehicles. Modern databases such as NoSQL provide solutions designed to accommodate a wide variety of data models, including key-value, document, columnar and graph databases. NoSQL can store and utilize structured, semi-structured, and unstructured data necessary for multimedia storage. NoSQL databases such as graph databases supports big data necessary for the demands of modern software development of streaming services for applications with integration and scalability…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.
new

Modification of Density-Based Clustering and Threshold Adjustment Detection-Tracking Integration Algorithm for 77 GHz Automotive Radar

Harbin Institute of Technology, China-Zhang Houyuan, Jiang Yicheng
Zhejiang Tmall Technology Co., Ltd-Miao Zhenwei, Ye Gang, Wang Bing
  • Technical Paper
  • 2020-01-5027
Published 2020-02-24 by SAE International in United States
In this paper, a modification of Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm is proposed based on real-world high resolution point clusters, which is obtained by 77-GHz frequency modulated automotive radar through CFAR technology. The modification of DBSCAN includes introducing normalized DBSCAN pre-processing method and a scale factor for dimension stretching/compression, which makes the target have similar measurement in three different dimensions of two-dimensional Cartesian coordinate system and velocity dimension, a The scale factor can adjust the sensitivity of DBSCAN algorithm to velocity dimension to deal with velocity expansion problem. Based on the clustering results, this paper proposes CFAR-JPDA algorithm, which integrates detection and tracking, and proposes a new extended Kalman filter state equation and measurement equation for road moving targets. In terms of data association, the modified JPDA algorithm is proposed, and the shape information of the target is used to confirm the measurement twice, which improves the accuracy of the target association.
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.
new

A Data-Driven Radar Object Detection and Clustering Method Aided by Camera

Dongfeng Motor Corporation Technial Center, China-Zhang Darui, Yang Hang, Wang Daihan, Bian Ning, Zhou Jianguang
Laval University-Liu Ruoyu
  • Technical Paper
  • 2020-01-5035
Published 2020-02-24 by SAE International in United States
The majority of road accidents are caused by human oversight. Advanced Driving Assistance System (ADAS) has the potential to reduce human error and improve road safety. With the rising demand for safety and comfortable driving experience, ADAS functions have become an important feature when car manufacturers developing new models. ADAS requires high accuracy and robustness in the perception system. Camera and radar are often combined to create a fusion result because the sensors have their own advantages and drawbacks. Cameras are susceptible to bad weather and poor lighting condition and radar has low resolution and can be affected by metal debris on the road.Clustering radar targets into objects and determine whether radar targets are valid objects are challenging tasks. In the literature, rule-based and thresholding methods have been proposed to filter out stationary objects and objects with low reflection power. However, static vehicles could be missed and thus result in low detection accuracy. To overcome these drawbacks, a data-driven method has been proposed, which uses a variety of features and thus is more suitable for…
This content contains downloadable datasets
Annotation ability available