University of Technology, Assina'a Street, Baghdad, Iraq,


Robot Vision is one of the most important applications in Image processing. Visual interaction with the environment is a much better way for the robot to gather information and react more intelligently to the variations of the parameters in that environment. A common example of an application that depends on robot vision is that of Pick-And-Place objects by a robotic arm. This work presents a method for identifying an object in a scene and determines its orientation. The method presented enables the robot to choose the best-suited pair of points on the object at which the two-finger gripper can successfully pick the object. The scene is taken by a camera attached to the arm’s end effector which gives 2D images for analysis. The edge detection operation was used to extract a 2D edge image for all the objects in the scene to reduce the time needed for processing. The methods proposed showed accurate object identification which enabled the robotic to successfully identify and pick an object of interest in the scene


[1] F. Casado, Y. L. lapido, D. P. Losada, and A. Santana-Alonso, “Pose estimation and object tracking using 2D images,” The 27th International Conference on Flexible Automation and Intelligent Manufacturing, FAIM2017, Modena, Italy, 27-30 June 2017.
[2] Y-K. Chen, G-J. Sun, H-Y. Lin, and S-L. Chen, “Random bin picking with multi-view image acquisition and cad-based pose estimation,” IEEE International Conference on Systems, Man, and Cybernetics, 2018.
[3] A. Zeng, S. Song, K.-T. Yu, E. Donlon, F. R. Hogan, and others, “Robotic pick-and-place of novel objects in clutter with multi-affordance grasping and cross-domain image matching,” IEEE International Conference on Robotics and Automation (ICRA), May 21-25, 2018, Brisbane, Australia.
[4] A. Aldoma, F. Tombari, L. Di Stefano, and M. Vincze, “A global hypothesis verification framework for 3D object recognition in clutter,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015.
[5] C. Rennie, R. Shome, K. E. Bekris, and A. F. De Souza, “A dataset for improved RGBD-based object detection and pose estimation for warehouse pick-and-place,” IEEE Robotics and automation letters, Pre-Print Version, 2016.
[6] M. Schwarz, A. Milan, C. Lenz, A. Mu˜noz, and others, “NimbRo picking: versatile part handling for warehouse automation,” IEEE International Conference on Robotics and Automation (ICRA), May 29 - June 3, 2017, Singapore.
[7] K.-T. Song, C.-H. Wu, and S.-Y. Jiang, “CAD-based pose estimation design for random bin picking using a RGB-D camera,” Springer Science+Business Media Dordrecht, 2017.
[8] Y. Xiang, T. Schmidt, V. Narayanan and D. Fox, “Pose CNN: A convolutional neural network for 6D object pose estimation in cluttered scenes,” Siemens and NSF STTR grant 63-5197, Lula Robotics, 2018.
[9] R. O. Duda and P. E. Hart, “Pattern classification and scene analysis,” John Wiley & Sons Inc, 1973.
[10] Le Duc Hanh and Le Minh Duc, “Planar object recognition for bin picking application”. The 5th NAFOSTED Conference on Information and Computer Science (NICS), 2018.
[11] P-C. Wu, H.-Y. Tseng, M.-H. Yang, and S.-Y. Chien, “Direct pose estimation for planar objects,” Computer Vision and Image Understanding, Elsevier, 2018.
[12] K. M. Myint, Z. M. Min Htun, and H. M. Tun, “Position control method for pick and place robot arm for object sorting system,” International Journal of Scientific & Technology Research, Vol. 5, Issue 06, June 2016.