Visually-guided navigation by comparing two-dimensional edge images

We present a method for navigating a robot from an initial position to a specified landmark in its visual field, using a sequence of monocular images. The location of the landmark with respect to the robot is determined using the change in size and position of the landmark in the image as the robot moves. The landmark location is estimated after the first three images are taken, and this estimate is refined after each motion. One of the novel aspects of this method is that it uses no explicit three-dimensional information.<<ETX>>

[1]  Olivier Faugeras,et al.  Building a 3D world model with a mobile robot: 3D line segment representation and integration , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[2]  Giulio Sandini,et al.  Active/Dynamic Stereo for Navigation , 1992, ECCV.

[3]  W. J. Rucklidge.  E?cient Computation of the Minimum Hausdorfi Distance for Visual Recognition , 1994 .

[4]  Matthew J. Barth,et al.  Qualitative route scene description using autonomous landmark detection , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[5]  Daniel P. Huttenlocher,et al.  A multi-resolution technique for comparing images using the Hausdorff distance , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Bruce Randall Donald,et al.  Program mobile robots in Scheme , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[7]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.