| Author: | Jia, Kanghao |
| Title: | Internet of things : R&D of a peer-to-peer cooperative mapping and navigation system |
| Advisors: | Ho, Wang-hei Ivan (EIE) |
| Degree: | M.Sc. |
| Year: | 2017 |
| Subject: | Hong Kong Polytechnic University -- Dissertations Internet of things Machine-to-machine communications Automobiles -- Automatic control Intelligent transportation systems |
| Department: | Department of Electronic and Information Engineering |
| Pages: | x, 90 pages : color illustrations |
| Language: | English |
| Abstract: | Recently, Autonomous vehicles have been one of the most popular topics in recent research. The new breed of vehicles with deep integration of information and computing technology is able to drive itself without human control. And intelligent cars could communicate with RSU (Road Side Units) to handle and process real-time dynamic traffic information to navigate automatically. In this research, intelligent navigation system including hidden obstacle detection and efficient information transmission between vehicles and infrastructure is developed based on the Robot Operating System (ROS). 3D point cloud data acquired by on-board sensors currently can actually be transmitted among autonomous vehicles for cooperative navigation. Since 3D point cloud contains massive data which needs a lot of bandwidth to transmit, compression techniques and efficient transmission schemes are required and taken into account in this research. In this thesis, ROS is served as the platform for our mapping and navigation system. The system contains two parts: map transmission and path planning. For map transmission, Octree-based point-cloud compression is adopted to compress 3D point cloud data and optimal index coding is used for efficient transmission. Before encoding the maps, random sample consensus algorithm is utilized for ground detection to match a pair of maps. For path planning, the object detection algorithm is applied to achieve this purpose, but it has roughly 4-5 seconds delay for navigation. Therefore, particle filter is considered to track and predict obstacle's position to solve the delay problem. Finally, in our experiment, two wifibots are able to exchange map information with each other through RSU and avoid hidden obstacle efficiently. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 991022131146703411.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 3.02 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/200/9450