scholarly journals A real-time embedded drive-by-wire control module for self-driving cars with ROS2

2021 ◽  
Vol 1 (1) ◽  
pp. 1
Author(s):  
Hang Cui ◽  
Jiaming Zhang ◽  
William R. Norris
Keyword(s):  
Real Time ◽  
Control Module ◽  
Self Driving Cars

scholarly journals Research on Optimized Control Model of Freeway Based on Dynamic Traffic Demand Estimation

2014 ◽  
Vol 6 ◽  
pp. 797293 ◽  
Author(s):  
Zhu Jiang ◽  
Shubin Li
Keyword(s):  
Optimal Control ◽  
Real Time ◽  
Demand Estimation ◽  
Control Model ◽  
Control Module ◽  
Traffic Demand ◽  
The Real ◽  
Traffic Conditions ◽  
Real Time Traffic ◽  
Global Optimal

According to the estimation information of dynamic traffic demands, a novel optimal control model of freeway was established on the basis of the hierarchical concept. There are four control modules in this model. The OD prediction module predicts the total traffic demands in a long time and determines the upper bound of the future queuing length in advance; the global optimal control module predicts the future traffic state and establishes the coordination constraints for each ramp in the network; the traffic demand estimation module estimates the real-time traffic conditions for each ramp; the local adaptive control module regulates ramp metering rate according to the estimated information of the real-time traffic conditions and the results optimized by the global optimal control module. The simulation results show that this control system is of a good dynamic performance. It coordinates the benefits of various ramps and optimizes the overall performance of the freeway network.

scholarly journals Design and Implementation of Edge-Fog-Cloud System through HD Map Generation from LiDAR Data of Autonomous Vehicles

Electronics ◽  
2020 ◽  
Vol 9 (12) ◽  
pp. 2084
Author(s):  
Junwon Lee ◽  
Kieun Lee ◽  
Aelee Yoo ◽  
Changjoo Moon
Keyword(s):  
Real Time ◽  
Autonomous Vehicles ◽  
Fog Computing ◽  
Point Clouds ◽  
Lidar Data ◽  
High Definition ◽  
Localization And Mapping ◽  
Cloud Server ◽  
Map Generation ◽  
Self Driving Cars

Self-driving cars, autonomous vehicles (AVs), and connected cars combine the Internet of Things (IoT) and automobile technologies, thus contributing to the development of society. However, processing the big data generated by AVs is a challenge due to overloading issues. Additionally, near real-time/real-time IoT services play a significant role in vehicle safety. Therefore, the architecture of an IoT system that collects and processes data, and provides services for vehicle driving, is an important consideration. In this study, we propose a fog computing server model that generates a high-definition (HD) map using light detection and ranging (LiDAR) data generated from an AV. The driving vehicle edge node transmits the LiDAR point cloud information to the fog server through a wireless network. The fog server generates an HD map by applying the Normal Distribution Transform-Simultaneous Localization and Mapping(NDT-SLAM) algorithm to the point clouds transmitted from the multiple edge nodes. Subsequently, the coordinate information of the HD map generated in the sensor frame is converted to the coordinate information of the global frame and transmitted to the cloud server. Then, the cloud server creates an HD map by integrating the collected point clouds using coordinate information.

A lightweight vehicle detection and tracking technique for advanced driving assistance systems

2020 ◽  
Vol 39 (3) ◽  
pp. 2693-2710 ◽  
Author(s):  
Wael Farag
Keyword(s):  
Real Time ◽  
Vehicle Detection ◽  
Machine Learning Algorithms ◽  
Tracking Technique ◽  
Detection And Tracking ◽  
Vehicle Detection And Tracking ◽  
Driving Assistance ◽  
Rgb Images ◽  
Assistance Systems ◽  
Self Driving Cars

In this paper, an advanced-and-reliable vehicle detection-and-tracking technique is proposed and implemented. The Real-Time Vehicle Detection-and-Tracking (RT_VDT) technique is well suited for Advanced Driving Assistance Systems (ADAS) applications or Self-Driving Cars (SDC). The RT_VDT is mainly a pipeline of reliable computer vision and machine learning algorithms that augment each other and take in raw RGB images to produce the required boundary boxes of the vehicles that appear in the front driving space of the car. The main contribution of this paper is the careful fusion of the employed algorithms where some of them work in parallel to strengthen each other in order to produce a precise and sophisticated real-time output. In addition, the RT_VDT provides fast enough computation to be embedded in CPUs that are currently employed by ADAS systems. The particulars of the employed algorithms together with their implementation are described in detail. Additionally, these algorithms and their various integration combinations are tested and their performance is evaluated using actual road images, and videos captured by the front-mounted camera of the car as well as on the KITTI benchmark with 87% average precision achieved. The evaluation of the RT_VDT shows that it reliably detects and tracks vehicle boundaries under various conditions.

A Scheme of H.264 HD Encoding/Transcoding System Based on ASIC

2011 ◽  
Vol 58-60 ◽  
pp. 1354-1358 ◽  
Author(s):  
Ming Kui Zheng ◽  
Kai Xiong Su ◽  
Xiu Zhi Yang
Keyword(s):  
Real Time ◽  
Low Cost ◽  
Digital Tv ◽  
High Definition ◽  
Control Module ◽  
Input Interface ◽  
Front End ◽  
Application Specific ◽  
Output Interface ◽  
Ethernet Interface

This paper proposes a scheme of H.264 high-definition encoder/transcoder . The system is based on ASIC. Application-specific high-definition encoding/transcoding chip, software control module, HDMI interface, analog video/audio input interface and ASI input/output interface ,etc. are discussed in detail in this paper. The system also provides the Ethernet interface, which is used for real-time monitoring of coding/transcoding system . The proposed scheme with the property of good real-time and low cost accord with the need of high-definition digital TV front-end system.

Intelligent Safety Control System for Operation of Group Tower Cranes

2013 ◽  
Vol 330 ◽  
pp. 592-597
Author(s):  
Zhen Zhen Zhang ◽  
Hong Liu Xu ◽  
Xiao Guan ◽  
Bin Wang
Keyword(s):  
Control System ◽  
Wireless Communication ◽  
Real Time ◽  
Early Warning ◽  
Intelligent Design ◽  
Failure Diagnosis ◽  
Operational Parameters ◽  
Control Module ◽  
Safety Control ◽  
Data Acquisition Module

An intelligent safety control system for operation of group tower cranes was developed in the context of rising security problems during operation of group tower cranes. The anti-anti-collision principle includes self-anti-collision and multi-tower cranes anti-collision. The system consists of PLC module, Touch screen, signal receiving module, data acquisition module, control module and signal transmitting module. Several techniques such as digital coding, early warning, failure diagnosis, wireless communication, intelligent design and humanization design are applied in the system. Operational parameters of tower canes are detected in real time insure the safety for cross operation of several tower cranes.

scholarly journals Staying at the Edge of Privacy: Edge Computing and Impersonal Extraction

2020 ◽  
Vol 8 (2) ◽  
pp. 270-279 ◽  
Author(s):  
Luke Munn
Keyword(s):  
Real Time ◽  
Personal Data ◽  
Edge Computing ◽  
License Plate ◽  
Process Data ◽  
Detection Model ◽  
Major Shift ◽  
Self Driving Cars ◽  
A Site ◽  
Key Questions

From self-driving cars to smart city sensors, billions of devices will be connected to networks in the next few years. These devices will collect vast amounts of data which needs to be processed in real-time, overwhelming centralized cloud architectures. To address this need, the industry seeks to process data closer to the source, driving a major shift from the cloud to the ‘edge.’ This article critically investigates the privacy implications of edge computing. It outlines the abilities introduced by the edge by drawing on two recently published scenarios, an automated license plate reader and an ethnic facial detection model. Based on these affordances, three key questions arise: what kind of data will be collected, how will this data be processed at the edge, and how will this data be ‘completed’ in the cloud? As a site of intermediation between user and cloud, the edge allows data to be extracted from individuals, acted on in real-time, and then abstracted or sterilized, removing identifying information before being stored in conventional data centers. The article thus argues that edge affordances establish a fundamental new ‘privacy condition’ while sidestepping the safeguards associated with the ‘privacy proper’ of personal data use. Responding effectively to these challenges will mean rethinking person-based approaches to privacy at both regulatory and citizen-led levels.

scholarly journals A PRELIMINARY STUDY ON UPDATING HIGH DEFINITION MAPS: DETECTING AND POSITIONING A TRAFFIC CONE BY USING A STEREO CAMERA

2019 ◽  
Vol XLII-4/W19 ◽  
pp. 271-274
Author(s):  
M. L. R. Lagahit ◽  
Y. H. Tseng
Keyword(s):  
Real Time ◽  
Data Storage ◽  
Autonomous Vehicles ◽  
Detection System ◽  
Time Data ◽  
High Definition ◽  
Stereo Camera ◽  
The Road ◽  
On The Road ◽  
Self Driving Cars

Abstract. The concept of Autonomous Vehicles (AV) or self-driving cars has been increasingly popular these past few years. As such, research and development of AVs have also escalated around the world. One of those researches is about High-Definition (HD) maps. HD Maps are basically very detailed maps that provide all the geometric and semantic information on the road, which helps the AV in positioning itself on the lanes as well as mapping objects and markings on the road. This research will focus on the early stages of updating said HD maps. The methodology mainly consists of (1) running YOLOv3, a real-time object detection system, on a photo taken from a stereo camera to detect the object of interest, in this case a traffic cone, (2) applying the theories of stereo-photogrammetry to determine the 3D coordinates of the traffic cone, and (3) executing all of it at the same time on a Python-based platform. Results have shown centimeter-level accuracy in terms of obtained distance and height of the detected traffic cone from the camera setup. In future works, observed coordinates can be uploaded to a database and then connected to an application for real-time data storage/management and interactive visualization.

scholarly journals Real-Time Object Detection for LiDAR Based on LS-R-YOLOv4 Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Yu-Cheng Fan ◽  
Chitra Meghala Yelamandala ◽  
Ting-Wei Chen ◽  
Chun-Ju Huang
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Real Time ◽  
Point Cloud ◽  
Region Of Interest ◽  
The Self ◽  
Vertical Field ◽  
Pascal Voc ◽  
Self Driving Cars ◽  
Field View

Recently, self-driving cars became a big challenge in the automobile industry. After the DARPA challenge, which introduced the design of a self-driving system that can be classified as SAR Level 3 or higher levels, driven to focus on self-driving cars more. Later on, using these introduced design models, a lot of companies started to design self-driving cars. Various sensors, such as radar, high-resolution cameras, and LiDAR are important in self-driving cars to sense the surroundings. LiDAR acts as an eye of a self-driving vehicle, by offering 64 scanning channels, 26.9° vertical field view, and a high-precision 360° horizontal field view in real-time. The LiDAR sensor can provide 360° environmental depth information with a detection range of up to 120 meters. In addition, the left and right cameras can further assist in obtaining front image information. In this way, the surrounding environment model of the self-driving car can be accurately obtained, which is convenient for the self-driving algorithm to perform route planning. It is very important for self-driving to avoid the collision. LiDAR provides both horizontal and vertical field views and helps in avoiding collision. In an online website, the dataset provides different kinds of data like point cloud data and color images which helps this data to use for object recognition. In this paper, we used two types of publicly available datasets, namely, KITTI and PASCAL VOC. Firstly, the KITTI dataset provides in-depth data knowledge for the LiDAR segmentation (LS) of objects obtained through LiDAR point clouds. The performance of object segmentation through LiDAR cloud points is used to find the region of interest (ROI) on images. And later on, we trained the network with the PASCAL VOC dataset used for object detection by the YOLOv4 neural network. To evaluate, we used the region of interest image as input to YOLOv4. By using all these technologies, we can segment and detect objects. Our algorithm ultimately constructs a LiDAR point cloud at the same time; it also detects the image in real-time.

Sign in / Sign up

Export Citation Format

Share Document