Hand-Eye Coordination of a Robotic Arm Using a Stereo Camera
Abstract
This work presents the results obtained after implementing a computer vision algorithm developed in Python to estimate the position of an object through visual information from a stereo camera. The object’s position estimation is utilized by the controller of a robotic arm to position it for grasping the object. However, the robotic arm does not always reach the expected point accurately. Consequently, this process was complemented with a position correction algorithm based on the Gradient Descent optimization algorithm and the hand-eye coordination process performed by humans.The position values are sent via wifi using the TCP/IP protocol through sockets to the robotic arm controller. Experimental results demonstrate that, with higher camera image resolution, the object’s position estimation improves. Overall, with the implemented correction algorithm, the distance between the robot’s final position and the object’s position does not exceed 10 mm.
Downloads
References
F. von Drigalski, K. Hayashi, Y. Huang, R. Yonetani, M. Amaya, K. Tanaka, et al., "Precise Multi-Modal In-Hand Pose Estimation using Low-Precision Sensors for Robotic Assembly", 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021, pp. 968-974. https://doi.org/10.1109/ICRA48506.2021.9561222
C. Li y Q. Bi, "Vision-driven High Precision Positioning Method for Bracket Assembly with Industrial Robot", 2022 5th World Conference on Mechanical Engineering and Intelligent Manufacturing (WCMEIM), 2022, pp. 825-830. https://doi.org/10.1109/WCMEIM56910.2022.10021493
D. A. Forsyth y J. Ponce, Computer vision: a modern approach, 2a ed., New Jersey: Pearson, 2012.
R. Hartley y A. Zisserman, Multiple View Geometry in computer vision. New York: Cambridge University Press, 2003.https://doi.org/10.1017/CBO9780511811685
Z. Zhang, "A flexible new technique for camera calibration", IEEE Trans Pattern Anal Mach Intell., vol. 22, no. 11, pp. 1330-1334, 2000, http://doi.org/10.1109/34.888718.
J. Heikkila y O. Silven, "A four-step camera calibration procedure with implicit image correction", Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Comput. Soc, pp. 1106-1112.https://doi.org/10.1109/CVPR.1997.609468
H.-C. Kang, H.-N. Han, H.-C. Bae, M.-G. Kim, J.-Y. Son, y Y.-K. Kim, "HSV Color-Space-Based Automated Object Localization for Robot Grasping without Prior Knowledge", Applied Sciences, vol. 11, no. 16, p. 7593, 2021, http://doi.org/10.3390/app11167593.
D. Giuliani, "Metaheuristic Algorithms Applied to Color Image Segmentation on HSV Space", J Imaging, vol. 8, no. 1, p. 6, 2022, https://doi.org/10.3390/jimaging8010006
H. Zhang, G. Guan, H. Zhao, X. Liu, L. Xue, y C. Xiong, "Design of image transmission system based on TCP/IP protocol", en 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology (ICCASIT), IEEE, 2022, pp. 617-622. https://doi.org/10.1109/ICCASIT55263.2022.9987111
IBM Corporation, "Sockets", IBM Corporation. Consultado: el 26 de julio de 2023. [En línea]. Disponible en: https://www.ibm.com/docs/es/aix/7.3?topic=concepts-sockets
T. Sun, K. Tang, y D. Li, "Gradient Descent Learning With Floats", IEEE Trans Cybern, vol. 52, no. 3, pp. 1763-1771, 2022, http://doi.org/10.1109/TCYB.2020.2997399.
J. Fliege, A. I. F. Vaz, y L. N. Vicente, "Complexity of gradient descent for multiobjective optimization", Optim Methods Softw, vol. 34, no. 5, pp. 949-959, 2019, http://doi.org/10.1080/10556788.2018.1510928.
Copyright (c) 2023 Ciencia e Ingenieria Neogranadina
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.