標題: 模擬賽車遊戲中駕駛風格模仿之技術
Techniques of Driving Style Imitation in Simulated Car Racing Games
作者: 廖耿德
Liao, Keng-Te
王才沛
Wang, Tsai-Pei
多媒體工程研究所
關鍵字: 賽車遊戲;行為模仿;模糊邏輯;多目標演化演算法;TORCS;imitation;fuzzy logic;multi-objective evolutionary algorithm
公開日期: 2013
摘要: 本文的研究目的,是在TORCS平台上對於人類和非人類玩家進行駕駛風格上的分析及模仿。本文將目前已被提出的控制器架構分為高階和低階控制器,並且透過整合這二類型的控制器達到了更好的模仿效果。 對於模仿效果的評估,本文提出了計算風格相似度的方法。這個方法也有助於讓訓練後的控制器適應未接觸過的賽道。本文中透過使用多目標最佳化演算法,讓控制器在非訓練用的賽道中也能作到自我調整,將駕駛風格及速度表現更加提升。根據實驗,當以一個速度表現接近最佳情況的NPC為模仿對象時,即使是在非常困難且未接觸的賽道中也可以表現出相似的軌跡,而且只慢了4%~14%。 對於人類玩家是否具有獨特的自我駕駛風格,本文中也進行了討論及實驗。透過提出的駕駛風格相似度判斷器,可以分析出玩家們風格的差異,並且作到透過駕駛資料來辨識出玩家。此外,在過去的研究中,如果模仿的對象是人類玩家,那麼訓練出的控制器容易頻繁的發生車禍而有著很低的速度表現。對於這個問題,本文中提出了在具有穩健的駕駛風格的前提下,訓練出的控制器仍然可以表現出模仿對象的駕駛特徵並且幾乎不發生車禍的模仿方法。
This thesis is about the analysis and imitation of human and non-human players’ driving styles in the TORCS platform. We classify existing controller architectures as low-level controllers or high-level controllers, and we achieve better results of imitation by integrating these types of controllers. For evaluating the imitation results, we propose a method to estimate the similarity of driving styles. It is also useful for a trained controller to adapt to a new track. We use multi-objective optimization algorithm as a method for controllers’ self-adaptation. According to our experiments, if a NPC with almost optimal speed performance is selected as the imitation target, the trained controller is able to produce similar trajectories and is only slower by 4%~14% than the imitation target in very difficult and unfamiliar tracks. In this thesis, we also discuss whether different human players have unique driving styles. By using our proposed method for estimating driving style similarities, it is possible to observe the differences of driving styles and we can even recognize a player by analyzing the driving data. Besides, according to some proposed researches, if human players are selected as the imitation targets, the trained controllers usually crash on the tracks frequently. Therefore, the speed performance is quite low. For dealing with this issue, we propose a method to train a controller with robust driving style. Such a trained controller is able to show some driving behaviors of the target human player and seldom crashes.
URI: http://140.113.39.130/cdrfb3/record/nctu/#GT070056606
http://hdl.handle.net/11536/73039
顯示於類別:畢業論文


文件中的檔案:

  1. 660601.pdf

若為 zip 檔案,請下載檔案解壓縮後,用瀏覽器開啟資料夾中的 index.html 瀏覽全文。