# 臺灣博碩士論文加值系統

(34.226.244.254) 您好！臺灣時間：2021/08/01 01:38

:::

### 詳目顯示

:
 Twitter

• 被引用:1
• 點閱:365
• 評分:
• 下載:17
• 書目收藏:0
 本篇論文將描述一個在未知以及動態環境下之路徑搜尋演算法。提出的方法能夠計算出行走路徑所需花費之時間，並且在獲得地圖資訊變更時修正原來的路徑。現存已有許多演算法能夠解決尋找最短路徑的問題，但這些方法大多數假設所處於的環境是靜態的。事實上不論是實際或虛擬的環境大多不是靜態環境。當遇到地圖資訊變更時重新搜尋路徑是一個應付動態環境最簡單的方法。但使用這種方法在即時的應用中有可能無法及時計算出新的路徑。如果無法及時獲得新的路徑，其結果可能會相當危險。如果一個自動導航車花了太多時間去反應，它有可能撞到行人或者其他車輛。D*能夠不需要全部重新搜尋整張地圖，它能夠保留地圖上未改變的區域來計算改變區域的數值，進而找出新的最佳路徑。D*原本的目的是在未知或部分未知的環境下搜尋路徑並持續地調整。但後來人們發現D*也可以被使用於動態的環境，它能夠在每次有物體移動時有效率地修正路徑。雖然D*能夠勝任動態環境下之路徑規劃，但並不表示它沒有任何問題。我們發現有時候D*會想移動到其他物體正要移動到的地點。這表示有可能會發生碰撞，因此我們才發展出改良型的D*演算法解決上述之問題。
 This thesis presents a method of finding a path between 2 points on a map. The map is considered unknown and containing moving objects. The proposed method calculates the travel time of a path, and modifies it when encountering any information changes.Many algorithms have been developed to solve the shortest path problem. However, most of them assume the environment to be static. In fact, static environments are rare in either real or virtual scenes. Repeated execution of a static path searching algorithm would be a simplest solution to dynamic environments. But it may not meet time requirements in real-time applications. The failure to find a path in time could be fatal. An autonomous vehicle may crash onto people or other vehicles if it takes too much time to react.D* has manage to modify the previous planned path without repeat A* search algorithm. It reuses information from unaffected states on a map to update the costs of changed states. The original purpose of D* algorithm is to find a path and keep updating it in an unknown or partially-known environment. D* can also be used in dynamic environments. D* modifies the path efficiently every time objects move.Although D* can be used in dynamic environments, it’s not completely fine in all situations. Sometimes D* decides to move to a location that an object is moving to. That means future collisions are expected. Hence, we address this problem and develop an improved algorithm of D*.
 ABSTRACT IN CHINESE (i)ABSTRACT IN ENGLISH (ii)ACKNOWLEDGEMENT (iii)TABLE OF CONTENTS (iv)LIST OF TABLES (v)LIST OF FIGURES (vi)Chapter 1 INTRODUCTION (1)1.1 Research Motivation (1)1.2 Survey of Literatures (1)1.3 Thesis Organization (2)Chapter 2 PROPOSED METHOD (3)2.1 Dynamic Programming (3)2.2 A* (10)2.3 D* (16)2.4 The Improved D* (29)Chapter 3 EXPERIMENTAL RESULTS (47)Chapter 4 CONCLUSIONS AND FUTURE WORK (51)REFERENCES (52)APPENDIXA. Optimality of A* (54)
 [1] Yu-Ching Chang, A Study on Outdoor Guidance of Autonomous Land Vehicles by Binocular Computer Vision Based on Artificial Intelligent Policy, Master’s Thesis, National Taipei University of Technology, Taipei, R.O.C., 2003.[2] Che-Chang Ye, Using Relaxed Correlation to Improve Corresponding of 3D Reconstruction for Outdoor Guidance of Autonomous Land Vehicle, Master’s Thesis, National Taipei University of Technology, Taipei, R.O.C., 2006.[3] Yung-Der Chen, A Study on Outdoor Guidance of Autonomous Land Vehicles by Computer Vision Based on Improved A* Search, Master’s Thesis, National Taipei University of Technology, Taipei, R.O.C., 2007.[4] Y. K. Hwang and N. Ahuja, "A Potential Field Approach to Path Planning," IEEE Transactions on Robotics and Automation, vol. 8, no. 1, 1992, pp. 23-32.[5] K.P. Valavanis, T. Hebert, R. Kolluru and N. Tsourveloudis, "Mobile Robot Navigation in 2-D Dynamic Environments Using and Electrostatic Potential Field," IEEE Transactions on System, Man and Cybernetics, vol. 30, no. 2, 2000, pp. 187-196.[6] K. Fujimura and H. Samet, "A Hierarchical Strategy for Path Planning Among Moving Obstacles," IEEE Transactions on Robotics and Automation, vol. 5, no. 1, 1989, pp. 61-69.[7] S. Koenig, M. Likhachev and D. Furcy, "Lifelong Planning A*," Artificial Intelligence Journal, vol. 155, no. 1-2, 2004, pp. 93-146.[8] A. Stentz, "Optimal and Efficient Path Planning for Partially-Known Environments," Proceedings of the IEEE International Conference on Robotics and Automation, May 1994, pp. 3310-3317.[9] S. Koenig and M. Likhachev, "D* Lite," Proceedings of the AAAI Conference of Artificial Intelligence, 2002, pp. 476-483.[10] A. Stentz, " The Focussed D* Algorithm for Real-Time Replanning," Proceedings of the International Joint Conference on Artificial Intelligence, August 1995.
 電子全文
 國圖紙本論文
 推文當script無法執行時可按︰推文 網路書籤當script無法執行時可按︰網路書籤 推薦當script無法執行時可按︰推薦 評分當script無法執行時可按︰評分 引用網址當script無法執行時可按︰引用網址 轉寄當script無法執行時可按︰轉寄

 1 家庭結構、父母管教方式與子女行為表現 2 大學生網路使用行為網路成癮及相關因素之研究 3 組織創新模式建構與實證之研究---以台灣資訊電子業為例 4 青少年生活壓力、家庭氣氛與偏差行為之關係研究 5 國小學童之父親參與、幸福感及學業成就之相關研究 6 父母教養方式、自我韌性與內在性自我控制、少年偏差行為之關係研究 7 休閒農業民宿旅客特性與需求之研究 8 社區居民對生態旅遊衝擊認知與發展態度之研究-以嘉義縣山美村為例 9 國中生家庭結構、學業成就與偏差行為之研究 10 三項元宵節活動吸引力與舉辦地特性之比較研究 11 信用風險之衡量 12 青少年憂鬱傾向、生活壓力、冒險行為對其婚前性行為影響之研究 13 隱私權概念之再思考----關於概念範圍,定義及權利形成方法 14 死亡教育對國中生死亡概念,死亡態度影響之研究

 1 池文海、唐資文、林怡安(2010)，消費者購買涉入、品牌權益、知覺風險與顧客忠誠度之關係。中華管理評論國際學報，13:2，頁1-22b

 1 大鼠紋狀體與運動區之間的腦活動訊號關聯性的研究 2 針刺足三里對健康者餐前與餐後的胃電圖影響 3 攝影機擷取之樂譜自動辨識與演奏系統 4 區塊式立體匹配結合倒傳遞類神經網路應用於雙眼立體視覺自動車導航 5 利用調整光流法進行障礙物偵測基於逆透視轉換運用於行車安全 6 使用延伸型限制性波茲曼機於智慧型物件辨識系統 7 基於Adaboosting人臉追蹤與偵測經由雲端運算技術研究廣告牌之關注程度 8 倒傳遞神經網路與地平面立體視覺作用於自動車導航之障礙物偵測與道路分類 9 使用模糊理論基於格式塔心理學原理對立體視覺匹配之研究 10 基於簡易交通道路分層模型之車載最短路徑之研究 11 人體組織與天線間遠場電磁輻射效應之研究 12 利用區域切割之最短路徑規劃研究 13 權重式最短路徑應用於捷運導航 14 應用進化規劃多目標演算法於配電系統饋線重構之研究 15 奈米潤滑脂應用於氣壓缸之動態磨擦特性量測

 簡易查詢 | 進階查詢 | 熱門排行 | 我的研究室