A Method to Estimate 3D Structure for Mobile Robot

This paper describes a method to estimate 3D structure for mobile robot. The vision-based system of the mobile robot includes a monocular CCD camera mounted on it which can find and track the fixed reference points in 3D space while the robot moves freely. In this method a special feature point is always kept at the center of the image as the reference point by visual feedback, and then the rest feature points nearby it could be located to build a local map. In the paper, the method is mainly discussed upon the translational motion and rotational motion of the robot respectively. Experimental results show the validity of this method

[1]  Minoru Asada,et al.  Color-based panoramic representation of outdoor environment for a mobile robot , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[2]  Andrew K. C. Wong,et al.  Robot vision: model synthesis for 3D objects , 1998, Proceedings. 1998 IEEE/RSJ International Conference on Intelligent Robots and Systems. Innovations in Theory, Practice and Applications (Cat. No.98CH36190).

[3]  Dana H. Ballard,et al.  Reference Frames for Animate Vision , 1989, IJCAI.

[4]  Bernardo Wagner,et al.  Using 3D laser range data for SLAM in outdoor environments , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).

[5]  R. J. Blissett.  Retrieving 3D information from video for robot control and surveillance , 1990 .

[6]  Yiannis Aloimonos,et al.  Active vision , 2004, International Journal of Computer Vision.

[7]  Huzefa AKBARALLY,et al.  3D robot sensing from sonar and vision , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[8]  Berthold K. P. Horn,et al.  Passive navigation , 1982, Computer Vision Graphics and Image Processing.