成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	方念主 Fang, Nien-Chu
論文名稱：	多機器人協作策略於三對三中型人形機器人足球賽 Multi-Robot Coordination Strategy for 3 vs. 3 Teen-sized Humanoid Robot Soccer Game
指導教授：	李祖聖 Li, Tzuu-Hseng S.
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 電機工程學系 Department of Electrical Engineering
論文出版年：	2017
畢業學年度：	105
語文別：	英文
論文頁數：	95
中文關鍵詞：	人形機器人、多機器人協作、機器人足球賽
外文關鍵詞：	Humanoid Robot, Multi-robot Coordination, Robot Soccer Game
相關次數：	點閱：142 下載：11
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

機器人競賽提供了從事機器人研究者各種測試演算法和系統整合能力與實力的平台。在人形雙足機器人足球賽中，基於「與人類相似」的前提下，具主動偵測能力的感測器均不可使用。機器人須規畫步態，在行進間與踢球時保持平衡，以完成比賽。然而，隨著演算法和整合技術日漸成熟，除了穩定的動作之外，機器人的影像辨識能力、自我定位，以及策略協調合作，將成為新的挑戰。因此，本論文針對RoboCup之三對三中型人形機器人足球賽，提出多機器人協作之策略，主要包含了三個部分: 影像辨識與定位方法、機器人間通訊，以及調度策略。由於比賽場地的邊線、球、球門皆為白色，我們利用場地特徵的輪廓，辨識出特定物件。接著，透過物件在影像中的位置、影像的中心位置，以及攝影機鏡頭在機器人世界座標中的位置，這三點的共線關係，反推出該物件在機器人座標中的位置。在知道機器人絕對位置的狀況下，即可推得該物件的絕對位置。而機器人的位置，是透過機器人身上的慣性測量元件(IMU)所推估而得，機器人的絕對位置會在初進入場地時開始記錄，每次機器人移動後都會利用IMU角度資訊，以及移動距離，更新機器人的位置。每個球員辨識到的資訊，則透過通訊網路統整到主控球員身上，以建立全域地圖，並進行策略調度，根據場上的態勢，決定各球員扮演的角色。各球員則依據命令，移動到目標位置，並執行相對應的動作。本論文依據真實機器人比賽狀況，架設模擬軟體，而模擬比賽的結果顯示所提方法，可讓機器人透過協作策略，取得更多的勝場數。而在人形機器人實驗中，也證實了策略的成果。

Robot competitions are always good platforms for researchers to test and compete their robot systems and algorithms. For the humanoid robot soccer game, any active sensor are prohibited according to the premise of “human-like”. The robot has to plan gaits and maintain balance during moving or kicking a ball to complete the competition. However, with the progress of robot development, multiple-robot coordination and cooperation becomes more and more important. Therefore, this thesis proposes a multi-robot coordination strategy system concerning 3 vs. 3 teen-sized humanoid robot soccer game. Three main technologies are integrated in the system, including object recognition and self-localization, communication, and coordination strategy. Because the line, ball, and goal posts are colored white, we utilize the contour features to recognize them and calculate their positions in robot coordinate. Hence, suppose the robot position in the world coordinate is known, the position of the line, ball, and goal posts in world coordinate can be determined. We figure out the initial position of the robot and update the position by the value of the Inertial Measurement Unit (IMU) and the estimated movement distance. Every robot transmits its location and his own information to the central control player through a communication network to construct a global map used to generate a suitable strategy and to assign roles. A simulation software is constructed in this thesis according to the characteristics of the real robot player and real competitions. After that, experiments show the strategy is effective on humanoid robots. These results illustrate the efficiency of the proposed coordination strategy, where the robot soccer team with the coordination strategy gets more wins.

摘要		I
ABSTRACT		II
ACKNOWLEDGEMENTS	III
CONTENTS		IV
LIST OF FIGURES	VII
LIST OF TABLES	XIII
CHAPTER 1	INTRODUCTION	1
1	Motivation	1
2	Related work	2
2.1	Image processing and localization	2
2.2	Role assignment and objective position decision	3
2.3	Action decision	4
2.4	The effectiveness evaluation of strategy	5
3	3 vs. 3 Humanoid robot soccer scenario	5
3.1	The robocup humanoid league	5
3.2	The implementation of robot soccer players	7
4	Thesis organization	14
CHAPTER 2	LOCALIZATION OF PLAYER, LINE AND OBJECTS	15
1	Introduction	15
2	Object and player recognition	17
2.1	The background filter	18
2.2	Line recognition	20
2.3	Goalpost recognition	23
2.4	Ball recognition	25
2.5	Player recognition	26
3	Target position derivation	30
3.1	Target position derivation method	30
3.2	Object and player position derivation	32
4	Robot Self-localization	34
4.1	Estimation of robot position and orientation	34
4.2	Calibration procedure after robot player falling down	36
4.3	Calibration through the T-shaped feature	37
4.4	Calibration through the goal line feature	43
5	Summary	46
CHAPTER 3	TEAM COORDINATION STRATEGY	47
1	Introduction	47
2	Construction of Global Map	48
2.1	Communication networks	48
2.2	Integration of local information	50
3	Role Assignment	51
4	Objectives Selection	52
5	Avoidance of Obstacles	58
6	Action Selection of Different Roles	60
7	Summary	68
CHAPTER 4	SIMULATIONS	69
1	Introduction	69
2	Simulation Platform Construction	70
3	Simulation Results	73
3.1	The evaluation standard of different strategies	73
3.2	Verification of the proposed strategy	74
3.3	Proposed strategy against proposed strategy but unchanging roles	80
3.4	Proposed strategy against attacking strategy	80
3.5	Proposed strategy against defensing strategy	80
3.6	Proposed strategy against trivial strategy	81
4	Discussion	81
CHAPTER 5	EXPERIMENTS	85
1	Individual action of players	85
2	Cooperation among players	88
CHAPTER 6	CONCLUSIONS AND FUTURE WORKS	90
1	Conclusions	90
2	Future works	91
REFERENCES	92
BIOGRAPHY		95


                                    

[1]. RoboCup[Online]. Available:
https://www.robocuphumanoid.org/
[2]. Y.-T. Ye, “Design and Implementation of Gait Pattern Generation by Improved Linear Inverted Pendulum Model for Teen-sized Humanoid Robot,” M.S. Thesis, Department of Electrical Engineering, National Cheng Kung University, Tainan, Taiwan, R.O.C., 2015.
[3]. Industrial computer, PICO880[Online]. Available:
http://www.axiomtek.com.tw/
[4]. Webcamera, Logitech C920[Online]. Available:
http://www.logitech.com/zh-tw/product/hd-pro-webcam-c920?crid=34
[5]. Inertial measurement unit, x-IMU[Online]. Available:
http://x-io.co.uk/x-imu/
[6]. T.-C. Yu, “Design and Implementation of A Human Thinking Based Cognition Learning Algorithm for Humanoid Robots at A Basketball Competition of the FIRA Hurocup,” M.S. Thesis, Department of Electrical Engineering, National Cheng Kung University, Tainan, Taiwan, R.O.C., 2014.
[7]. A. Gudi, P. D. Kok et al., “Feature Detection and Localization for the Robocup Soccer SPL,” Amsterdam Univ., Amsterdam, Project Rep., Feb. 2013.
[8]. N. Henderson, S. P. Nicklin et al., “The 2008 NUManoids Team Report,” in RoboCup SPL Team Descriptions, Suzhou, China, 2008.
[9]. M. Sridharan and P. Stone, “Real-time Vision on A Mobile Robot Platform,” in Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, Edmonton, Canada, pp. 2148-2153, 2005.
[10]. T. Röfer and M. Jüngel, “Fast and Robust Edge-based Localization in the Sony Four-legged Robot League,” RoboCup 2003: Robot Soccer World Cup VII. Lecture Notes in Computer Science, vol. 3020, pp. 262-273, 2004.
[11]. J. Ashar, D. Claridge et al., “RoboCup Standard Platform League rUNSWift 2010”[Online]. Available: http://www.araa.asn.au/acra/acra2010/papers/pap105s1-file1.pdf
[12]. R. Sheh and B. Hengst, “A Fast Vision Sensor Model: Matching Edges with NightOwl”[Online], 2004, Available:
http://www.cse.unsw.edu.au/~bernhardh/MobileMe/Publications_files/2004-NightOwlACRA04_20041115.pdf
[13]. C.-C. Sun, “Design and Implementation of Obstacle Avoidance and Dribbling Strategy for Humanoid Soccer Robot,” M.S. Thesis, Department of Electrical Engineering, National Cheng Kung University, Tainan, Taiwan, R.O.C., 2010.
[14]. H. Lu, H. Zhang et al, “Vision-based Ball Recognition for Soccer Robots without Color Classification,” in Proceedings of IEEE International Conference on Information and Automation, Zhuhai, Macau, pp. 916-921, 2009.
[15]. M. Teutsch, P. Trantelle, and J. Beyerer, “Adaptive real-time image smoothing using local binary patterns and Gaussian filters,” in Proceedings of IEEE International Conference on Image Processing, Melbourne, Australia, pp. 1120-1124, 2013.
[16]. H. Schulz and S. Behnke, “Utilizing the Structure of Field Lines for Efficient Soccer Robot Localization,” Advanced Robotics, vol. 26, no. 14, pp. 1603-1621, 2012.
[17]. M. Veloso, M. Bowling, and P. Stone, “The CMUnited-98 Champion Small-robot Team,” Advanced Robotics, vol. 13, no. 1, pp. 753-766, 1999.
[18]. T. Weigel, J. Gutmann, M. Dietl, A. Kleiner, and B. Nebel, "CS Freiburg: Coordinating Robots for Successful Soccer Playing,” IEEE Transactions on Robotics and Automation, vol. 18, no. 5, pp. 685-699, 2002.
[19]. C.-M. Chang, “Design and Implementation of Vision and Strategy System for Humanoid Robot Soccer Competition,” M.S. Thesis, Department of Electrical Engineering, National Cheng Kung University, Tainan, Taiwan, R.O.C., 2009.
[20]. J. Bruce and M. Veloso, “Safe Multirobot Navigation within Dynamics Constraints,” Proceedings of the IEEE, vol. 94, no. 7, pp. 1398-1411, 2006.
[21]. K. Hwang, Y. Chen, and C. Lee, “Reinforcement Learning in Strategy Selection for a Coordinated Multirobot System,” IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, vol. 37, no. 6, pp. 1151-1157, 2007.
[22]. D. Gu and H. Hu, “Integration of Coordination Architecture and Behavior Fuzzy Learning in Quadruped Walking Robots,” IEEE Transactions on Systems, Man and Cybernetics, Part C: Applications and Reviews, vol. 37, no. 4, pp. 670-681, 2007.
[23]. B. Browning, J. Bruce, M. Bowling, and M. Veloso, “STP: Skills, Tactics, and Plays for Multi-robot Control in Adversarial Environments,” in Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering, vol. 219, no. 1, pp. 33-52, 2005.
[24]. T. Laue and T. Röfer, “A Behavior Architecture for Autonomous Mobile Robots Based on Potential Fields,” in RoboCup 2004: Robot Soccer World Cup VIII. Lecture Notes in Computer Science, vol. 3276, pp. 122-133, 2005.
[25]. D. Ball and G. Wyeth, “Multi-robot Control in Highly Dynamic, Competitive Environments,” in RoboCup 2003: Robot Soccer World Cup VII. Lecture Notes in Computer Science, vol. 3020, pp. 385-396, 2004.
[26]. T.-K. Wang, “Design and Implementation of Double Passing Strategy for Humanoid Soccer Robot,” M.S. Thesis, Department of Electrical Engineering, National Cheng Kung University, Tainan, Taiwan, R.O.C., 2010.

校內：立即公開
校外：立即公開

簡易檢索 / 詳目顯示

相關論文