跳到主要內容

臺灣博碩士論文加值系統

(44.212.99.208) 您好!臺灣時間:2024/04/17 17:12
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:羅翊華
研究生(外文):Yi-Hua Lo
論文名稱:基於LiDAR資料點之室內動態障礙物辨識及動態避障之研究
論文名稱(外文):Indoor Dynamic Obstacle Recognition and Dynamic Obstacle Avoidance with 2D LiDAR
指導教授:陳昭亮
指導教授(外文):Jau-Liang Chen
口試委員:陳紹賢吳天堯
口試日期:2022-08-19
學位類別:碩士
校院名稱:國立中興大學
系所名稱:機械工程學系所
學門:工程學門
學類:機械工程學類
論文種類:學術論文
論文出版年:2022
畢業學年度:110
語文別:中文
論文頁數:89
中文關鍵詞:動態障礙物辨識動態避障LiDAR麥克納姆輪
外文關鍵詞:Dynamic Obstacle RecognitionDynamic Obstacle AvoidanceLiDARMecanum Wheel
相關次數:
  • 被引用被引用:1
  • 點閱點閱:203
  • 評分評分:
  • 下載下載:53
  • 收藏至我的研究室書目清單書目收藏:0
本研究主要探討在室內工廠廠域中動態避障的情況。對於機器人動態避障方法作探討,而機器人動態避障可分為辨識動態障礙物及對其避障兩部分。目前用於辨識動態障礙物的感測器主要有視覺模組及LiDAR,而LiDAR相對於視覺模組而言,有運算量相對低、精度高且不容易受環境光暗影響等優點。本研究使用LiDAR作為感測器,提出一套應用於室內工廠場域中,單一感測器的動態障礙物辨識融合動態避障的系統。
研究方法根據參考文獻中LiDAR動態障礙物辨識演算法並對其多個部分加以改善,及採用維持原本行走路徑的避障方法。根據實驗結果可以得知,在動態障礙物辨識演算法的部分,透過將演算法改善後,偵測的閾值降低,意即對動態障礙物辨識更為靈敏。最後,機器人從動態障礙物辨識到動態避障皆能夠順利完成並且成功抵達目標點,證明於室內工廠廠域中,單一感測器的動態障礙物辨識及動態避障的可行性。
This research mainly discusses the method of dynamic obstacle avoidance for robots mainly used in the indoor factory domain, and the dynamic obstacle avoidance of robots can be divided into two parts: identifying dynamic obstacle and dynamic obstacle avoidance. At present, the sensors used to identify dynamic obstacles mainly include vision modules and LiDAR. Compared with vision modules, LiDAR has the advantages of relatively low computational complexity, high precision, and is not easily affected by ambient light and darkness. This research uses LiDAR as a sensor, and proposes a system that integrates dynamic obstacle recognition and dynamic obstacle avoidance with a single sensor,which applied in an indoor factory field.
The research method is based on the LiDAR dynamic obstacle identification algorithm in the reference and improves several parts of it, and adopts the obstacle avoidance method that maintains the original walking path. According to the experimental results, it can be known that in the part of the dynamic obstacle identification algorithm, after the algorithm is improved, the detection threshold is reduced, which means that it is more sensitive to dynamic obstacle identification. Finally, the robot can successfully complete the process with dynamic obstacle identification and dynamic obstacle avoidance, and successfully reach the target area, which proves the feasibility of dynamic obstacle identification and dynamic obstacle avoidance with a single sensor in an indoor factory.
摘要 i
Abstract ii
目錄 iii
圖目錄 vi
表目錄 ix
第一章、 緒論 1
1.1前言 1
1.2文獻探討 1
1.2.1動態障礙物辨識 1
1.2.2移動機器人動態避障 4
1.3研究目的 6
1.4論文架構 8
第二章、 機器人系統架構 9
2.1實驗平台組成介紹 9
2.2硬體架構 9
2.2.1車體結構 9
2.2.2雷達感測器 10
2.2.3光學編碼器DC馬達 12
2.2.4麥克納姆輪 15
2.2.5樹莓派 16
2.2.6 STM32 17
2.2.7 X-BOX ONE 18
2.3軟體架構 19
第三章、 研究方法 20
3.1控制系統架構 21
3.2動態障礙物辨識系統 21
3.2.1資料點過濾及線段提取 22
3.2.2線段特徵點集中點提取 23
3.2.3找尋動態障礙物 24
3.2.4車體運動推導 25
3.2.5車體移動距離估測 28
3.2.6障礙物座標矯正及確認動態障礙物 33
3.2.7預估動態障礙物速度 34
3.2.8預估動態障礙物涵蓋面積 34
3.3動態避障系統架構 35
3.3.1機器人動態避障角度分割 36
3.3.2 動態障礙物放大及車身安全距離範圍 36
3.4實驗設計 37
3.4.1車體在靜止狀態下辨識動態障礙物 37
3.4.2車體在移動狀態下辨識動態障礙物 38
3.4.3機器人在路口遇到從旁邊接近的動態障礙物 39
3.4.4機器人遇到迎面而來的動態障礙物 40
第四章、 實驗設置與結果分析 42
4.1參數調整 42
4.2實驗場域設置 48
4.2.1車體在靜止狀態下辨識動態障礙物 48
4.2.2車體在動態狀態下辨識動態障礙物 50
4.2.3機器人在路口遇到從旁邊接近的動態障礙物 52
4.2.4機器遇到迎面接近的動態障礙物 54
4.3實驗驗證 58
4.3.1車體在靜止狀態下辨識動態障礙物實驗 58
4.3.2車體在動態狀態下辨識動態障礙物實驗 60
4.3.3機器人在路口遇到從旁邊接近的動態障礙物實驗 65
4.3.4機器遇到迎面接近的動態障礙物實驗 75
第五章、 結論與未來展望 86
5.1結論 86
5.2 未來展望 87
參考文獻 88
[1]Douglas, D. H., & Peucker, T. K. (1973) “Algorithms for the reduction of the number of points required to represent a digitized line or its caricature” Cartographica: the international journal for geographic information and geovisualization, 10(2), 112-122.
[2]Philipps, J. J., Bönninger, I., Weigert, M., & Vásquez, J. (2014, July) “Automatic tracking and counting of moving objects” In 3rd IEEE International Work-Conference on Bioinspired Intelligence (pp. 93-97). IEEE.
[3]Nozari, A., & Hoseini, S. M. (2015, October) “Recognition of Moving Objects in Videos of Moving Camera with Harris Attributes” In 2015 Fourteenth Mexican International Conference on Artificial Intelligence (MICAI) (pp. 42-45). IEEE.
[4]Catapang, A. N., & Ramos, M. (2016, November). Obstacle detection using a 2D LIDAR system for an Autonomous Vehicle. In 2016 6th IEEE International Conference on Control System, Computing and Engineering (ICCSCE) (pp. 441-445). IEEE.Qin, B., Chong, Z. J., Soh, S. H., Bandyopadhyay, T., Ang, M. H., Frazzoli, E., & Rus, D. (2016) “A spatial-temporal approach for moving object recognition with 2d lidar” In Experimental Robotics (pp. 807-820). Springer, Cham.
[5]Qin, B., Chong, Z. J., Soh, S. H., Bandyopadhyay, T., Ang, M. H., Frazzoli, E., & Rus, D. (2016) “A spatial-temporal approach for moving object recognition with 2d lidar” In Experimental Robotics (pp. 807-820). Springer, Cham.
[6]Ahmed, S. A., Topalov, A. V., Shakev, N. G., & Popov, V. L. (2018). “Model-free detection and following of moving objects by an omnidirectional mobile robot using 2d range data” IFAC-PapersOnLine, 51(22), 226-231.
[7]曾偉伯,多感測器移動機器人室內導航系統之研究,碩士學位論文, 國立中興大學機械工程學系, 2018.
[8]Borenstein, J., & Koren, Y. (1991) “The vector field histogram-fast obstacle avoidance for mobile robots” IEEE transactions on robotics and automation, 7(3), 278-288.
[9]Ulrich, I., & Borenstein, J. (2000) “VFH*: Local Obstacle Avoidance with Lookahead Verification” In IEEE int. conf. on Robotics and Automation. San Francisco, USA.
[10]Zhong, X., Peng, X., & Zhou, J. (2011, December) “Dynamic collision avoidance of mobile robot based on velocity obstacles” In Proceedings 2011 International Conference on Transportation, Mechanical, and Electrical Engineering (TMEE) (pp. 2410-2413). IEEE.
[11]林資捷,利用單一感測器掃描法和危險區域偵測法執行自走車的避障,碩士學位論文, 國立成功大學航空太空工程學系, 2013.
[12]Babinec, A., Duchoň, F., Dekan, M., Pásztó, P., & Kelemen, M. (2014) “VFH* TDT (VFH* with Time Dependent Tree): A new laser rangefinder based obstacle avoidance method designed for environment with non-static obstacles” Robotics and autonomous systems, 62(8), 1098-1115.
[13]Liu, Y., Chen, D., & Zhang, S. (2018, April) “Obstacle avoidance method based on the movement trend of dynamic obstacles” In 2018 3rd International Conference on Control and Robotics Engineering (ICCRE) (pp. 45-50). IEEE.
[14]Wang, C., & Mao, J. (2019, October) “Summary of AGV Path Planning” In 2019 3rd International Conference on Electronic Information Technology and Computer Engineering (EITCE) (pp. 332-335). IEEE.
[15]Keyu, L., Yonggen, L., & Yanchi, Z. (2020, November) “Dynamic obstacle avoidance path planning of UAV Based on improved APF” In 2020 5th International Conference on Communication, Image and Signal Processing (CCISP) (pp. 159-163). IEEE.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top