碩士 / 國立交通大學 / 資訊科學與工程研究所 / 106 / People today can utilize a navigation device to identify a shortest/fastest route for her/his vehicle or query a navigation service provider about the traffic information at that time in order to plan a route. However, a traffic congestion may still occur because each driver is not aware of the selections of routes of the other drivers. Recently, a navigation algorithm based on near-future traffic evaluation is proposed for automated driving vehicles. That algorithm can effectively reduce the cruising time of a huge set of vehicles. However, the aforementioned algorithm does not consider any kind of uncertain situations, for example, traffic accidents, the change of destination, or a temporary stop. In this thesis, we consider some kinds of uncertain situations which occur in the real world. We present a method to enhance the idea of near-future traffic evaluation. A new flow is proposed to handle each uncertain situation. Experimental results demonstrate that, compared with a dynamically updated navigating system, the proposed algorithm can improve the total cruising time for each test map with a huge set of vehicles.
Identifer | oai:union.ndltd.org:TW/106NCTU5394075 |
Date | January 2018 |
Creators | Huang, Kuan-Lin, 黃冠淋 |
Contributors | Li, Yih-Lang, 李毅郎 |
Source Sets | National Digital Library of Theses and Dissertations in Taiwan |
Language | zh-TW |
Detected Language | English |
Type | 學位論文 ; thesis |
Format | 27 |
Page generated in 0.0145 seconds