| Author: | Yang, Dingyu |
| Title: | Fog based cooperative autonomous driving |
| Advisors: | Ho, Wang-hei Ivan (EIE) |
| Degree: | M.Sc. |
| Year: | 2020 |
| Subject: | Automated vehicles Vehicular ad hoc networks (Computer networks) Internet of things Cloud computing Hong Kong Polytechnic University -- Dissertations |
| Department: | Department of Electronic and Information Engineering |
| Pages: | viii, 86 pages : color illustrations |
| Language: | English |
| Abstract: | Recently, autonomous vehicles have become the focus of research [1-5]. Self-driving cars are equipped with various sensors to detect the surrounding environment, such as lidar, cameras, etc. In terms of transportation, autonomous driving shows excellent performance in uncertain environments, and route planning can be performed without manual intervention. The navigation system is designed to effectively and safely drive the car from the starting point to the desired destination [5,19]. In particular, autonomous systems can process and analyze the data obtained from sensors for map exploration and navigation [2,4]. Besides, the information exchange between self-driving cars is the key to better perception and detection of collaborative systems, rather than letting each car drive independently [2,5,18,20]. With the development of technology, there will be more and more autonomous vehicles on the road. If all cars use the same cloud server for data processing, a lot of redundant data will be generated, which will seriously affect the real-time and Efficiency requirements. Fog computing provides local users with timely real-time transportation services through close-range data processing, rather than routing data to a remote central data center in the cloud. More importantly, fog computing will revolutionize autonomous driving (AD). This research establishes an automatic driving system based on fog calculation, which simulates multiple vehicles driving in the same area, various vehicles simultaneously explore road information and cooperate in map building, and conduct formation driving, which significantly improves the efficiency of composition. At the same time, the amount of data sent by the processing node to the vehicle is reduced, and the efficiency and real-time performance of autonomous driving are improved. In this article, ROS is used as the platform for our autonomous driving system. The essence of the system is the publication and subscription of topics. Through the establishment of multiple fog computing nodes to process vehicle data and data exchange between close robots. Robots and nodes only need to publish topics to send data, and subscribe to topics to receive data. The network function of ROS can quickly establish the autonomous driving system network required for this research. Finally, in our experiment, multiple vehicles can exchange map information with each other through fog computing nodes, and the entire system can be operated in a low-latency state. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 5172.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 3.09 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/10745