Obstacle Avoidance and Trajectory Planning for an Indoor Mobile Robot Using Stereo Vision and Delaunay Triangulation
This article describes the work at INRIA on obstacle avoidance and trajectory planning for a mobile robot using stereo vision. Our mobile robot is equipped with a trinocular vision system that is being put into hardware and will be capable of delivering 3-D maps of the environment at rates between 1 and 5 Hz. The 3-D maps contain line segments extracted from the images and reconstructed in three dimensions. They are used for a variety of tasks, including obstacle avoidance and trajectory planning.
For those two tasks, we project on the ground floor the 3-D line segments to obtain a two-dimensional map, simplify the map according to some simple geometric criteria, and use the remaining 2-D segments to construct a tessellation, more precisely a triangulation, of the ground floor. This tessellation has several advantages.
It is adapted to the structure of the environment since all stereo segments are edges of triangles in the tessellation.
It can be efficiently computed (the algorithm we use has a complexity o(n) if n is the number of segments used).
It is dynamic in the sense that segments can be efficiently added or subtracted from an existing triangulation.
We use this triangulation as a support for further processing. We first determine free space simply by marking those triangles that are empty, again a very simple process, and then use the graph formed by those triangles to generate collision-free trajectories. When new sensory data are acquired, the ground floor map is easily updated using the nice computational properties of the Delaunay triangulation, and the process is iterated.
We show an example in which our robot navigates freely in a real indoor environment using this system.
KeywordsLine Segment Mobile Robot Voronoi Diagram Obstacle Avoidance Delaunay Triangulation
Unable to display preview. Download preview PDF.
- Ayache, Nicholas, and Faugeras, Olivier D. (1989). “Maintaining Representations of the Environment of a Mobile Robot.” IEEE Transactions on Robotics and Automation, December. Also INRIA Report 789.Google Scholar
- Ayache, N., and Lustman, F. (1987). “Fast and Reliable Passive Trinocular Stereovision. In Proceedings ICCV’87, London, 422–427, IEEE, June.Google Scholar
- Faugeras, Olivier D., Lebras-Mehlman, Elizabeth, and Boissonnat, Jean-Daniel. (1990). Representing Stereo data with the Delaunay Triangulation. Artificial Intelligence Journal 44(1–2), July (also INRIA Tech. Report 788).Google Scholar
- Preparata, F., and M. Shamos, (1985). Computational Geometry. Springer-Verlag, Berlin and New-York.Google Scholar
- Zhang, Zhengyou, and Faugeras, Olivier D. (1990). “Motion Analysis of Two Stereo Views and Its Applications. In Proceedings of the ISPRS Symposium on Close-Range Photogrammetry Meets Machine Vision, September.Google Scholar
- Zhang, Zhengyou, and Faugeras, Olivier D. (1990). “Tracking and Motion Estimation in a Sequence of Stereo Frames.” In Proceedings of the 9th European Conference on Artificial Intelligence, ECAI, August 1990.Google Scholar
- Zhang, Zhengyou (1990).”Analysis from a Sequence of Stereo Frames and Its Applications.” PhD Thesis, University of Paris-Sud, Orsay, Paris, France, (in English).Google Scholar