Journal of System Simulation ›› 2025, Vol. 37 ›› Issue (5): 1210-1221.doi: 10.16182/j.issn1004731x.joss.23-1593

• Papers • Previous Articles     Next Articles

An Extended Image Features Based Uncalibrated Visual Servoing Method

Zhang Shuzhen1, Cheng Yukun1, Liu Yangbo1, Zha Fusheng2   

  1. 1.School of Electrical and Mechanical Engineering, Lanzhou University of Technology, Lanzhou 730050, China
    2.State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin 150001, China
  • Received:2023-12-28 Revised:2024-03-19 Online:2025-05-20 Published:2025-05-23
  • Contact: Cheng Yukun

Abstract:

Aiming at the traditional uncalibrated visual servo relying on the estimation of image Jacobi matrix and the coupling of the motion of each degree of freedom of the camera, on the basis of image-based uncalibrated visual servo, an extended image features based uncalibrated visual servo method is proposed. By analyzing the relationship between image features and camera frames change in the visual servoing process, the visual servoing process in the image space is decomposed into four basic processes: translation, stretching, rotation and scaling; by analyzing the changing of image features in the visual servoing process, extended image features are used to complement the meaning of traditional image features, image center coordinates, relative length of a straight line, distance between two points, and direction angle are selected to correspond to the motion of each degree of freedom of the camera, and the robot's motion is directly controlled by the error of the image features, which realizes a completely decoupled visual servo that does not depend on the image Jacobian matrix. Comparative simulation experiments on CoppeliaSim platform show that compared with the traditional calibrated visual servoing, the method proposed in this study reduces the image position error, the camera position error, and orientation error by 88%, 94%, and 93% of respectively. The effectiveness of the algorithm is verified using physical experiments.

Key words: robot, uncalibrated visual servoing, extended image feature, feature selection, motion decoupling

CLC Number: