Graduation Design (Dissertation) of Wuhan University of Technology

Research on Driving Navigation Based on Natural Language

College: International Education College

Specialty amp; Class: Automobile GJ1402

Student name: Li Cheng

Tutor: Wei Guo

Statement of Originality

I solemnly declare that the thesis I submit is a piece of writing I completed independently based on my own research under the guidance of my supervisor. Except for the quotations, this paper does not include any writings published or completed by other individuals or groups. I am fully aware that the legal consequences of this statement are borne by me.

Signature of the author:

Date:

Copyright Letter of Authorization to The Dissertation

The author of this dissertation fully understands provisions stipulated by this school on keeping and using dissertations. The author agrees that the school can reserve and send photocopies and electronic versions of this thesis to relevant departments or institutions managing dissertations. This thesis can be read and borrowed. I hereby authorize excellent provincial institutions appraising bachelor dissertations to incorporate all or any part of this dissertation into relevant databases for retrieval, as well as to preserve and compile this dissertation by photocopying, scanning or reprinting it in a reduced format.

This dissertation is: 1. Confidential until(year) and then this authorization letter will apply. 囗

2. Non-confidential. 囗

(Please tick "√" the corresponding box above)

Signature of the author:

Date:

Signature of the tutor:

Date:

Abstract

At present, the application of natural language has gradually become a trend of the times. Whether in aerospace, medical, mechanical manufacturing or automotive, natural language has become the most comfortable and convenient language that users are willing to use. In order to effectively reduce the driver's driving burden, ease fatigue driving, reduce the difficulty of driving operation, freeing the driver from heavy driving tasks, and using natural language for driving navigation can have a good effect. The navigation based on natural language can effectively improve the safety of driving and has high application value. This article relies on a variety of effective methods to collect and establish a natural language corpus for navigation applications. It is compiled on the basis of the sound system of 'Kunda Telecommunications' to achieve the transformation from natural language to command language, and finally on the unity 3d platform. The simulation driving of the trolley under natural language driving navigation is realized.

The main research work of this article includes:

(1) The establishment of a natural language driving instruction corpus. After reading a large amount of related literature, I found three ways to collect natural language driving instructions. Through the use of three kinds of navigation software widely used in the market, a set of relatively standard language description language of natural language was concluded. Throughthe review of articles and related articles on the website, it is natural to find the driving instructions that can be used inside the article. Language description corpus, by learning the research methods in the literature, designing similar experiments for corpus collection

(2) Analysis and conversion of natural language driving instructions. According to the expression and content of natural language driving instructions, the characteristics of natural language are summarized and divided into multiple language units such as space, time and distance. At the same time, the different semantics of words in each sentence are divided into eight categories: verbs, prepositions, and quantifiers. All the words are related to each other and can be flexibly composed of sentences that express different meanings. The sentence is also analyzed, its syntactic patterns are analyzed, and a reasonable split is made. Relying on the system of “Universidad News and Communications”, the system gradually realizes speech recognition that converts natural language into text language and converts text language into semantic understanding of command language.

(3) Relying on the software platform of unity 3d to simulate the driving navigation based on natural language that this article hopes to realize. After obtaining the required city road simulation map and the resource file of the sports car model respectively, it was debugged in the same project file, and the movement of the car in the simulation map was realized. After the initial movement was achieved, the function module of the entire system was installed to initially realize the functions of driving lane changing, traffic light driving, and reversing parking. After the commissioning of the entire system is completed, the completion of the task is first measured, and after finding that the basic requirements can be satisfied, the volunteers are found to analyze the user's operational load. Based on the results of the questionnaire and the data from the NASA-TLX scale, the users were analyzed for differences in load when using navigation systems based on natural language and using command languages directly to accomplish navigation tasks.

Key Words： Natural language, Human-computer interaction, Driving navigation, Unity 3D

Content

I. Introduction 4

1.1 Research Background and Significance 4