Modeling and Analysis of a Humanoid Robot Active Stereo Vision Platform


Article Preview

Humanoid robot is not only expected to walk stably, but also is required to perform manipulation tasks autonomously in our work and living environment. This paper discusses the visual perception and the object manipulation based on visual servoing of a humanoid robot, an active robot vision model is built, and then the 3D location principle, the calibration method and precision of this model are analyzed. This active robot vision system with two DOF enlarges its visual field and the stereo is the most simple camera configuration for 3D position information.



Edited by:

Qi Luo




Q. J. Du et al., "Modeling and Analysis of a Humanoid Robot Active Stereo Vision Platform", Applied Mechanics and Materials, Vols. 55-57, pp. 868-871, 2011

Online since:

May 2011




[1] J.L. Mundy, A. Zisserman. Projective Geometry for Machine Vision. In Geometric Invariance in Computer Vision. Artificial Intelligence Series, MIT Press, (1992).

[2] L.S. Shapiro, A. Zisserman, M. Brady. 3D Motion Recovery via Affine Epipolar Geometry. International Journal of Computer Vision, 1995, 16(2): 147–182.


[3] Jong-Hann Jean, Tien-Pao Wu. Robust Visual Servo Control of a Mobile Robot for Object Tracking in Shape Parameter Space, IEEE Conf. Decision Control, vol4, pp.4016-4021, (2004).


[4] Yunting Pang, Qiang Huang, et al. Fast Object Location and Tracing Using Two CCD Cameras and Laser Range Finder, Proc. IEEE Conf. Information Acquisition, pp.368-372, (2005).


[5] Rajpar, Altaf Hussain, Huang Qiang, Pang Yunting, et al. Location and tracking of robot end-effector based on stereo vision, ROBIO, 2006, pp.1140-1145.


[6] Pang Yunting, Huang Qiang, Jia Dongyong, et al. Object manipulation of a humanoid robot based on visual servoing, IEEE Conference on Intelligent Robots and Systems, pp.1124-1129, (2007).


[7] D. Kragic and H.I. Christensen, Cue integration for visual servoing, IEEE Trans. Robotics and Automation, 17(1): 18–26, (2001).


Fetching data from Crossref.
This may take some time to load.