深度攝影機可以快速取得拍攝範圍內，面對鏡頭之物件表面3D點雲輪廓。由於對後續應用之方向不同，使將點雲解析的方式有所差異。對於現場運作的工業機器手臂而言，將工件取與放之前，必須能即時認知爪夾可以靠近並抓取之部位及其3D輪廓，或是物件預備放置處的3D輪廓概況。然而機器手臂的抓取方式受限於爪夾造型，因而在抓取前只需辨認有限數量之夾持特徵是否存在，以及其位置與方向為何即可。一般而言，工作物件之外觀可視為由數個夾持特徵依據固定之拓樸關係所組成之集合，若能辨識到越多特徵則對物件的類別及方位將更為清晰，亦表示可達到如同人員般的智慧識別能力。本研究將探討深度攝影影像之點雲解析方法，藉由分析辨識凌亂擺放工件之3D點雲是否存在特定夾持特徵來求得夾持之方位，並可進一步推算出抓取搬移後的放置方位，以達到替代人員使用視覺做辨識之能力。

Depth camera can be used to capture 3D terrain in front of it in the form of point clouds. Many applications can then be developed by specific deciphering methods. One of the applications is to realize the existence of any 3D grasp features on a work part for an industrial robot, and then plan for grasping operations in realtime automatically. Since the way of grasping has everything to do with the shape/design of a gripper, the topology of a grasp feature is therefore limited. Moreover, if a part is graspable, then it must have at least one grasp feature on its outer surface, or a part topology must include the topology of the grasp features. Since point clouds represent 3D terrain, any grasp feature on the point clouds will reveal the position and orientation for its grasping. In this research, a methodology of topology mapping from 3D point clouds is developed to discover the existence of grasp features from several disorderly placed work parts. A grasp operation can then be created using inverse kinematics based on the feature position and orientation. It is believed that the research setup may adequately replace human vision on part handling tasks.

摘要...i
Abstract...ii
誌謝...iii
目錄...iv
表目錄...vi
圖目錄...vii
第一章...緒論 1
1.1研究背景...1
1.2研究動機...1
1.3研究目的...2
1.4研究限制...2
1.5章節說明...2
第二章 文獻探討...3
2.1深度攝影機(Depth camera)...3
2.1.1 Intel RealSense...4
2.1.2 點雲(PointCloud)...4
2.2 3D特徵辨識...5
2.3 機器人夾持...6
2.4智慧製造...7
2.5文獻總結...8
第三章 研究方法...10
3.1研究概述...10
3.2實驗環境架設...12
3.3工件點雲取得...13
3.4 PointNet...16
3.5特徵抓取定位...17
第四章 實作部分...20
4.1環境...20
4.2點雲資料...22
4.2.1工件點雲...23
4.2.2場景點雲...25
4.3 PointNet...31
4.4實驗結果...33
4.4.1辨識實驗結果...33
4.4.2距離實驗結果...34
4.4.3光源實驗...36
4.5實驗結論...39
第五章 結論...40
5.1研究成果...40
5.2未來研究...40
參考文獻...41
Extended Abstract...44

Ala, R., Kim, D. H., Shin, S. Y., Kim, C.& Park, S.-K., 2015, A 3D-grasp synthesis algorithm to grasp unknown objects based on graspable boundary and convex segments, Information Sciences, Vol. 295, pp. 91-106.
Aleotti, J. & Caselli, S., 2012, A 3D shape segmentation approach for robot grasping by parts, Robotics and Autonomous Systems, Vol. 60, No. 3, pp. 358-366.
Biederman, I. J. P. r., 1987, Recognition-by-components: a theory of human image understanding, Psychological review, Vol. 94, No. 2, pp. 115-147 .
Chen, L., Huang, P. & Meng, Z., 2019, Convolutional multi-grasp detection using grasp path for RGBD images, Robotics and Autonomous Systems, Vol. 113, pp. 94-103.
Condotta, I. C. F. S., Brown-Brandl, T. M., Pitla, S. K., Stinn, J. P.& Silva-Miranda, K. O., 2020, Evaluation of low-cost depth cameras for agricultural applications, Computers and Electronics in Agriculture, Vol. 173, pp. 1-15
Deng, T., Cai, J., Cham, T.-J. & Zheng, J., 2017, Multiple consumer-grade depth camera registration using everyday objects, Image and Vision Computing, Vol. 62, pp. 1-7.
Di Angelo, L., Di Stefano, P. & Morabito, A. E., 2019, Fillets, rounds, grooves and sharp edges segmentation from 3D scanned surfaces, Computer-Aided Design, Vol. 110, pp. 78-91.
Fotsing, C., Menadjou, N. & Bobda, C., 2021, Iterative closest point for accurate plane detection in unorganized point clouds, Automation in Construction, Vol. 125, pp.103610.
Guo, N., Zhang, B., Zhou, J., Zhan, K. & Lai, S., 2020, Pose estimation and adaptable grasp configuration with point cloud registration and geometry understanding for fruit grasp planning, Computers and Electronics in Agriculture, Vol. 179, pp. 105818.
Horváth, G. & Erdős, G., 2020, Object localization utilizing 3D point cloud clustering approach, Procedia CIRP, Vol. 93, pp. 508-513.
Jerbić, B., Šuligoj, F., Švaco, M. & Šekoranja, B., 2015, Robot Assisted 3D Point Cloud Object Registration, Procedia Engineering, Vol. 100, pp. 847-852.
Toquica, J. S., oliveira, patrícia S.,Souza, W. S. r., Motta, josé maurício S.t., & Borges, D. L., 2021, An analytical and a Deep Learning model for solving the inverse kinematic problem of an industrial parallel robot, Computers & Industrial Engineering, Vol. 151, pp. 106682.
Li, D., Liu, N., Guo, Y., Wang, X. & Xu, J., 2019, 3D object recognition and pose estimation for random bin-picking using Partition Viewpoint Feature Histograms, Pattern Recognition Letters, Vol. 128, pp. 148-154.
Mavrakis, N. & Stolkin, R., 2020, Estimation and exploitation of objects , inertial parameters in robotic grasping and manipulation: A survey, Robotics and Autonomous Systems, Vol. 124, pp. 103374.
LiBretto, M., Qiu, Y., Kim, E., Pluckter, K., Yuk, N. & Ueda, J., 2020, Singularity-free solutions for inverse kinematics of degenerate mobile robots, Mechanism and Machine Theory, Vol. 153, pp. 103988.
Lu, J., Du, F., Li, Y., Lei, Y., Zhang, T. & Zhang, G., 2021, A novel inverse kinematics algorithm using the Kepler oval for continuum robots, Applied Mathematical Modelling, Vol. 93, pp. 206-225.
Qi, C. R., Su, H., Mo, K. & Guibas, L. J., 2017, Pointnet: Deep learning on point sets for 3d classification and segmentation, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 652-660.
Ramisa, A., Alenyà, G., Moreno-Noguer, F. & Torras, C., 2016, A 3D descriptor to detect task-oriented grasping points in clothing, Pattern Recognition, Vol. 60, pp. 936-948.
Tao, W., Leu, M. C., & Yin, Z., 2020, Multi-modal recognition of worker activity for human-centered intelligent manufacturing, Engineering Applications of Artificial Intelligence, Vol. 95, pp. 103868.
Lei, T., Rong, Y., Wang, H., Huang, Y. & Li, M., 2020, A review of vision-aided robotic welding, Computers in Industry, Vol. 123, pp. 103326.
Wu, G., Li, B., Zhu, Q., Huang, M. & Guo, Y., 2020, Using color and 3D geometry features to segment fruit point cloud and improve fruit recognition accuracy, Computers and Electronics in Agriculture, Vol. 174, pp. 105475.
Wang, W., Tian, W., Liao, W. & Li, B., 2021, Pose accuracy compensation of mobile industry robot with binocular vision measurement and deep belief network, Optik, Vol. 238, pp. 166716.
Yang, J., Zhang, Q., Xian, K., Xiao, Y. & Cao, Z., 2017, Rotational contour signatures for both real-valued and binary feature representations of 3D local shape, Computer Vision and Image Understanding, Vol. 160, pp. 133-147.
Zhong, R. Y., Xu, X., Klotz, E. & Newman, S. T., 2017, Intelligent Manufacturing in the Context of Industry 4.0: A Review. Engineering, Vol. 3, No. 5 , pp. 616-630.