Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74954
Title: | 基於深層強化學習之增強式跟車模型 Enhanced Car-Following Model with Deep Reinforcement Learning |
Authors: | Yi-Tung Yen 顏逸東 |
Advisor: | 施吉昇 |
Keyword: | 自駕車,機器學習,深層強化學習,跟車模型,主動式定速巡航, Autonomous Vehicle,Self-driving Vehicle,Adaptive Cruise Control,Car-Following Model,Machine Learning,Deep Reinforcement Learning, |
Publication Year : | 2019 |
Degree: | 碩士 |
Abstract: | 隨著人工智慧以及科技的快速發展,也帶動了自駕車領域的興起,而一個良好的跟車模型在自駕車當中扮演著不可或缺的角色。一個良好的跟車模型,能使自駕車以安全、舒適且有效率的方式駕駛,不僅提高車輛行駛的安全性及乘客的舒適性,更能進一步的提升整體道路的使用率。
本研究致力於建構一個更加良好的跟車模型,根據現行文獻、法規,將安全、舒適以及效率精確地量化成報酬函數,並透過強化學習使電腦不斷地與環境互動,藉由環境的反饋學習以達到報酬最大化。 結果顯示我們的模型不僅能夠減少人類駕駛中低效率以及不安全的時間車距,也減小了過大的急煞。更進一步地,我們的模型在效率評估方面勝過了79%的人類駕駛,達到了相當於98%的最佳解。除此之外,與SUMO中的主動式定速巡航模型相比,在同樣的發車數目之下,我們能夠在同樣實驗時間區間內提升抵達車輛的數目以及平均車速,進而達到整體道路使用率的改善。 With the rapid evolution of artificial intelligence and technology, autonomous vehicle is regarded as the future of transportation. One of the important functions that autonomous vehicle should be equipped is a well-designed car-following model. With a well-designed car-following model, autonomous vehicle can drive in a safe, comfortable and efficient manner. This will increase driving safety, passenger comfort and improve road efficiency. This thesis designs and implements an enhanced car-following model. According to the laws, regulations and standards, we modeled the safety, comfort and efficiency into quantified reward functions. Using reinforcement learning, the network agent learns the best policy to achieve the maximum reward by repeated the learning process. The evaluation results show that our model not only reduces the number of inefficient and dangerous headways but also eliminates the jerk to achieve more efficient and comfortable driving than human drivers. The model outperformed 79% human drivers in public dataset. The achieved efficiency is 98% of the optimal bound. Furthermore, compared to the SUMO’s ACC model, given the same number of departed vehicles, our model enables more arrived vehicles and higher average speed to improve the overall road capacity. |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74954 |
DOI: | 10.6342/NTU201904015 |
Fulltext Rights: | 有償授權 |
Appears in Collections: | 資訊工程學系 |
Files in This Item:
File | Size | Format | |
---|---|---|---|
ntu-108-1.pdf Restricted Access | 2.1 MB | Adobe PDF |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.