Article: Implement contour following task of objects with unknown geometric models by using combination of two visual servoing techniques Journal: International Journal of Computational Vision and Robotics (IJCVR) 2022 Vol.12 No.5 pp.464 - 486 Abstract: In this paper, two visual servoing techniques are combined to implement the contour following task of objects with unknown geometric models and the contour plane can be anywhere in the workspace. The scaled Euclidean position and orientation of the contour plane are defined based on decomposing the homography matrix. The shortest path visual servoing (SPVS) technique is applied to control the robot end-effector or the camera to the position parallel to the contour plane. Then, the image-based visual servoing (IBVS) technique is applied to conduct the contour following task. The desired feature command points are extracted from the contour using image processing algorithms. Based on the feature command point, four virtual feature points are generated to form the interaction matrix used in IBVS. The effectiveness of the proposed approach is verified based on the simulation result by using a camera attached at the end-effector of the six-DOF PUMA 560 manipulator. Inderscience Publishers - linking academia, business and industry through research

Title: Implement contour following task of objects with unknown geometric models by using combination of two visual servoing techniques

Authors: Le Duc Hanh; Vo Duy Cong

Addresses: Department of Mechatronics, Faculty of Mechanical Engineering, Ho Chi Minh City University of Technology (HCMUT), 268 Ly Thuong Kiet Street, District 10, Ho Chi Minh City, Vietnam; Vietnam National University – Ho Chi Minh City (VNU), Linh Trung Ward, Thu Duc District, Ho Chi Minh City, Vietnam ' Industrial Maintenance Training Center, Ho Chi Minh City University of Technology (HCMUT), 268 Ly Thuong Kiet Street, District 10, Ho Chi Minh City, Vietnam; Vietnam National University – Ho Chi Minh City (VNU), Linh Trung Ward, Thu Duc District, Ho Chi Minh City, Vietnam

Abstract: In this paper, two visual servoing techniques are combined to implement the contour following task of objects with unknown geometric models and the contour plane can be anywhere in the workspace. The scaled Euclidean position and orientation of the contour plane are defined based on decomposing the homography matrix. The shortest path visual servoing (SPVS) technique is applied to control the robot end-effector or the camera to the position parallel to the contour plane. Then, the image-based visual servoing (IBVS) technique is applied to conduct the contour following task. The desired feature command points are extracted from the contour using image processing algorithms. Based on the feature command point, four virtual feature points are generated to form the interaction matrix used in IBVS. The effectiveness of the proposed approach is verified based on the simulation result by using a camera attached at the end-effector of the six-DOF PUMA 560 manipulator.

Keywords: contour following; image-based visual servoing; IBVS; shortest path visual servoing; SPVS; homography matrix.

DOI: 10.1504/IJCVR.2022.125383

International Journal of Computational Vision and Robotics, 2022 Vol.12 No.5, pp.464 - 486

Received: 08 Jun 2021
Accepted: 31 Jul 2021
Published online: 07 Sep 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Implement contour following task of objects with unknown geometric models by using combination of two visual servoing techniques

Keep up-to-date