臺灣博碩士論文加值系統

本論文的主要目的是針對Kinect RGB-D感測器開發基於CAD模型之物體姿態辨識及其於機械臂隨機堆疊抓取之應用。本論文運用投票機制(voting scheme)進行待抓物件之6-DOF姿態辨識，使能在一組不同種類雜亂堆疊工件堆裡辨識個別工件及其6-DOF姿態。在資料庫建立方面，本論文結合物件的3D CAD Model及Virtual Camera快速地建立姿態辨識所需的資料庫，然後利用Voxel Grid Filter大幅度減少物件的3D點雲數量以降低姿態辨識所花費的時間。在機械臂抓取物件方面，本論文利用Outlier Filter剔除錯誤的姿態及被遮蔽但正確辨識的姿態，使機械臂總是可以抓取工件堆最上層的工件以提高抓取成功率。透過分析物件與機械臂yaw旋轉角度的相對姿態關係，機械臂可以順利抓取任意姿態的工件。本論文以Kuka 6-DOF機械臂進行實驗，驗證所提出的方法在一連串多物件隨機堆疊抓取實驗當中，所設計的系統抓取隨機姿態工件的成功率為89.7%，且可成功抓取工件直到箱子內沒有工件為止。

In this thesis, we propose a CAD-based 6-DOF pose estimation design for random bin-picking of multiple objects using a Kinect RGB-D sensor. A voting-scheme was adopted for 6-DOF pose estimation as well as recognition of a set of 6-DOF poses of different types of objects in the bin. We combine 3D CAD model of objects with a virtual camera to generate point cloud database for pose estimation. Voxel grid filter is suggested to decrease the number of 3D point cloud of object for reducing time of pose estimation. Furthermore, we use an outlier filter to filter out bad matching poses and occluded ones, so that the robot arm always picks up the upper object in the bin to increase pick up success rate. The yaw rotation angle of object relative to robot arm is calculated, so that robot arm can pick up different types and random poses of objects. A series of experiments of practical random bin-picking of multiple objects reveals that our proposed system can pick up random pose of objects in the bin with a success rate of 89.7%, and the objects in the bin are all picked up until there is no object left.

摘要 i
Abstract ii
誌謝 iii
目錄 iv
圖目錄 vi
表目錄 ix
第一章 緒論 1
1.1 研究動機 1
1.2 相關文獻回顧 2
1.3 問題描述 8
1.4 系統架構 9
1.4.1 CAD-model資料庫系統 10
1.4.2 6-DOF姿態估測系統 11
1.4.3 目標物抓取系統 11
1.5 本論文之主要貢獻 11
1.6 章節說明 12
第二章 6-DOF姿態估測與目標物抓取 13
2.1 CAD-model資料庫系統 13
2.1.1 虛擬攝影機(Virtual Camera) 13
2.1.2 體素過濾器(Voxel Grid Filter) 16
2.1.3 幾何成對特徵(Point to Point Pair Feature) 18
2.1.4 總體模型描述(Global Model Descriptor) – Hash Table 19
2.2 6-DOF 姿態估測系統 20
2.2.1 局部座標(Local Coordinates) 21
2.2.2 投票比對機制(Voting-Scheme Matching) 22
2.2.3 姿態聚集(Pose Clustering) 23
2.2.4 ICP Refinement 24
2.3 目標物抓取系統 24
2.3.1 Outlier Filter 25
2.3.2 決定抓取目標物 26
2.3.3 機械臂抓取姿態 27
2.4 Summary 30
第三章 機械臂系統與影像校正 31
3.1 硬體規格介紹 31
3.1.1 KUKA六軸工業機械臂 31
3.1.2 氣爪 32
3.1.3 Kinect RGB-D感測器 33
3.2 機械臂視覺伺服控制系統架構 34
3.3 座標轉換 35
3.4 Eye-in-Hand手眼協調校正 38
3.5 Summary 39
第四章 實驗結果 41
4.1 模擬結果 41
4.2 機械臂於多物件隨機堆疊抓取之自主加工系統的實驗 44
4.2.1 實驗平台 44
4.2.2 實驗流程 45
4.2.3 姿態估測準確率 50
4.2.4 抓取成功率 51
4.3 基於影像的姿態估測精度 52
第五章 結論與未來展望 56
5.1 結論 56
5.2 未來展望 57
參考文獻 59
附錄A .. 62
A.1 IBVS控制系統設計 62
A.2 HSV自動閥值偵測系統 63
A.3 影像辨識系統 64
A.4 IBVS影像伺服控制系統 64
A.4.1 座標空間轉換關係 65
A.4.2 Fuzzy控制器 66
A.4.3 機械臂控制命令之產生 69
A.5 實驗結果 70

[1]A. Aldoma, N. Blodow, D. Gossow, S. Gedildi, R. B. Rusu, M. Vincze and G. Bradski. “CAD-Model Recognition and 6DOF Pose Estimation Using 3D Cues,” in Proc. of IEEE International Conference on Computer Vision Workshops (ICCV Workshops ), Vienna, Austria, 2011, pp.585-592

[2]M. Ulrich, C. Wiedemann and C. Steger, “CAD-Based Recognition of 3D Objects in Monocular Images,” in Proc. of IEEE International Conference on Robotics and Automation (ICRA), Kobe, Japan, 2009, pp.1191-1198.

[3]W. Wohlkinger, A. Aldoma, R. B. Rusu and M. Vincze, “3DNet: Large-Scale Object Class Recognition from CAD Models,” In Proc. of IEEE International Conference on Robotics and Automation (ICRA), RiverCentre, Saint Paul, Minnesota, USA, May 2012, pp. 5384-5391

[4]P. Neto, J. N. Pires and A. P. Moreira, “CAD-Based Off-Line Robot Programming,” in Proc. of IEEE International Conference on Robotics and Automation (ICRA), Coimbra , Portugal, 2010, pp. 516–521.

[5]F. Chaumette and S. Hutchinson, “Visual Servo Control. I. Basic Approaches,” IEEE Robotics and Automation Magazine, vol. 13, no. 4, 2006, pp. 82-90.

[6]F. Chaumette and S.Hutchinson, “Visual Servo Control. II. Advance Approaches,” IEEE Robotics and Automation Magazine, vol. 14, no. 1, 2007, pp. 109-118.

[7]C. Choi and H. I. Christensen, “Real-Time 3D Model-Based Tracking Using Edge and Keypoint Features for Robotic Manipulation,” in Proc. of IEEE In International Conference on Robotics and Automation (ICRA), Anchorage, Alaska, USA, 2010, pp. 4048-4055.

[8]C. Zang and K. Hashimoto, “A Flexible Visual Inspection System Combining Pose Estimation and Visual Servo Approaches.” in Proc. of IEEE International Conference on Robotics and Automation (ICRA), Minnesota, USA, 2012, pp. 1304-1309.

[9]W. Wohlkinger and M. Vincze. “Shape-Based Depth Image to 3D Model Matching and Classification with Inter-view Similarity,” in Proc. of IEEE/RSJ International Conference on Intelligent Robots and Systems, San Francisco, CA, USA, 2011, pp.4865-4870

[10]W. Wohlkinger and M. Vincze. “Ensemble of Shape Functions for 3D Object Classification, “ in Proc. of IEEE International Conference on Robotics and Biomimetics , Phuket, Thailand, 2011,pp.2987-2992.

[11]R. B. Rusu, G. Bradski, R. Thibaux and J. Hsu, “Fast 3D Recognition and Pose Using the Viewpoint Feature Histogram,” in Proc. of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS),Taipei, Taiwan, 2010, pp. 2155 -2162.

[12]S. Akizuki and M. Hashimoto, “High-Speed and Reliable Object Recognition Using Distinctive 3-D Vector-Pairs in a Range Image.” in Proc. of IEEE International Symposium on Optomechatronic Technologies (ISOT), Chukyo, Japan, 2012.

[13]C. Choi and H. I. Christensen, “3D Pose Estimation of Daily Objects Using an RGB-D Camera,” in Proc. of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vilamoura, Algarve, Portugal, 2012, pp.3342-3349.

[14]A. E. Johnson and M. Hebert, “Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 21, no. 5, 1999, pp 433-449

[15]T. Takeguchi and S. Kaneko, “Depth Aspect Images for Robust Object Recognition,” Proc. SPIE Conference on Optomechatronic Systems IV, vol. 5264, 2003, pp. 54-65

[16]H. Chen and B. Bhanu, “3D Free-form Object Recognition in Range Images Using Local Surface Patches,” in Proc. 17th Int’l Conf. Pattern Recognition, vol. 3, 2004, pp. 136-139.

[17]E. Wahl, G. Hillenbrand and G. Hirzinger. “Surflet-Pair-Relation Histograms: A Statistical 3D-Shape Representation for Rapid Classification,” in Proceedings. Fourth International Conference on 3-D Digital Imaging and Modeling, (3DIM), 2003, pp. 474–481.

[18]T. Rabbani and F. V. D. Heuvel. “Efficient Hough Transform for Automatic Detection of Cylinders in Point Clouds.” in Proceedings of the 11th Annual Conference of the Advanced School for Computing and Imaging (ASCI05), vol. 3, 2005, pp. 60–65.

[19]B. Drost, M. Ulrich, N. Navab and S. Ilic, “Model Globally, Match Locally: Efficient and Robust 3D Object Recognition,” in Proc. of IEEE International Conference on Computer Vision and Pattern Recognition(CVPR), Munich, Germany, 2010, pp.998-1005.

[20]C. Choi, Y. Taguchi, O. Tuzel, M. Liu and S. Ramalingam, "Voting­ Based Pose Estimation for Robotic Assembly Using a 3D Sensor," in Proc. of IEEE International Conference on Robotics and Automation (ICRA),Minnesota, USA, 2012, pp.I724-1731

[21]P.J. Besl and N.D. McKay, “A Method for Registration of 3D Shapes,” IEEE Trans on Pattern Analysis and Machine Intelligence, vol. 14, no. 2, 1992, pp. 239-259.

[22]Ø. Skotheim, M. Lind, P. Ystgaard and S. Fjerdingen, “A Flexible 3D Object Localization System for Industrial Part Handling,” in Proc. of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vilamoura, Algarve, Portugal, 2012, pp.3326-3333

[23]Sin-Yi Jiang, Yen-Chung Chang, Chin-Chia Wu, Cheng-Hei Wu and Kai-Tai Song, “Error Analysis and Experiments of 3D Reconstruction Using a RGB-D Sensor,” in Proc. of International Conference on Automation Science and Engineering (CASE), Taipei, Taiwan, 2014, pp. 1020-1025.

[24]Klaus H. Strobl and Gerd Hirzinger, “Optimal Hand-Eye Calibration” in Proc. of the 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, China, 2006, pp. 4647-4653.

[25]陳煒傑,“A Histogram-Based Multi-Threshold Searching Algorithm for Multiple Color Object Segmentation,”淡江大學電機工程學系機器人工程碩士論文, 2012.

[26]N. Otsu, “A Threshold Selection Method from Gray-Level Histograms,” IEEE Transactions on Systems, Man and Cybernetics, Vol. 9, No. 1, 1979, pp.62-66.