| Author: | Hu, Sai |
| Title: | A full-stack approach to implement autonomous driving technology for low-speed delivery applications |
| Advisors: | Hsu, Li-ta (ME) |
| Degree: | M.Sc. |
| Year: | 2019 |
| Subject: | Hong Kong Polytechnic University -- Dissertations Automated vehicles Automated vehicles -- Mathematics |
| Department: | Faculty of Engineering |
| Pages: | ix, 94 pages : color illustrations |
| Language: | English |
| Abstract: | As the coming of Fourth Industrial Revolution and rapid development of artificial intelligence, autonomous vehicles will finally change the way people live. In order to achieve automatic functions of a vehicle in urban complicated scenario, different subsystems must have real-time interoperation. These different subsystems consist of perception, localization, path planning, decision making and control. Certainly, these kinds of subsystems should work together on a robust vehicle platform with suitable sensors, good Controller Area Network (CAN bus) and strong computation support. In this paper, we focus on the algorithm and implementation of autonomous driving towards the goal of serve more people using this technology in the future. First, we detect objects in the environment using Light Detection and Ranging (LiDAR) and camera. Then we detect and recognize the traffic light by camera in order to obey the traffic rules in real world. Second, we generate High Definition (HD) map using LiDAR to do map-matching based localization in real time. Then we introduce localization using GPS and LiDAR, finally do sensor fusion to improve localization accuracy in a more robust scenario. Third, we do path planning to get a suitable path from start point to the destination. Finally, we use the data coming from perception, localization and path planning to do path tracking. The controller continuously changes throttle and steering angle to best track the path and make passengers comfortable. Finally, the experiment results will be given to prove the effectiveness of our algorithm and application. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 991022270854703411.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 5.45 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/200/10112