An adaptive selection of motion for online hand-eye calibration

  • Authors:

  • Jing Zhang;Fanhuai Shi;Yuncai Liu

  • Affiliations:

  • Inst. Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, P.R. China;Inst. Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, P.R. China;Inst. Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, P.R. China

  • Venue:
  • AI'05 Proceedings of the 18th Australian Joint conference on Advances in Artificial Intelligence
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

As the robot makes unplanned movement, online hand-eye calibration determines the relative pose between the robot gripper/end-effector and the sensors mounted on it. With noisy measurements, hand-eye calibration is sensitive to small rotations in real applications. Moreover, degenerate cases such as pure translations have no effect in hand-eye calibration. This paper proposes an adaptive motion selection algorithm for online hand-eye calibration, which can adaptively set the thresholds of motion selection according to the characteristics of the unplanned motion sequence. It is achieved by using polynomial-regression to predict the relationship between RMS of calibration error and thresholds. Thus, this procedure leads to an adaptive method of motion selection. It can adapt itself to online hand-eye calibration in various applications. Experiments using simulated data are conducted and present good results. Experiments using real scenes also show that the method is promising.