Advertisement

Algorithmic solution and simulation results for vision-based autonomous mode of a planetary rover

  • Marina Kolesnik
  • Gerhard Paar
Poster Session II
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1296)

Abstract

A vision based navigation (VBN) system is chosen as a basic tool to support autonomous operations of a planetary rover during space missions. The rover equipped with a stereo vision system and perhaps a laser ranging device shall be able to maintain a high level of autonomy under various illumination conditions and with little a priori information about the underlying scene. Within the LEDA Moon exploration project currently under focus by the European Space Agency, in autonomous mode the rover should perform on-board absolute localization, digital elevation model (DEM) generation, obstacle detection and relative localization, global path planning and execution.

Focus of this paper is to simulate some of the path planning and path execution steps. Using a laboratory terrain mockup and an accurate camera mounting device, stereo image sequences are used for 3D scene reconstruction, risk map generation, local path planning, and position update by landmarks tracking. It is shown that standalone landmark tracking is robust enough to give navigation data for further stereoscopic reconstruction of the surrounding terrain. Iterative tracking and reconstruction leads to a complete description of the rover path and its surrounding with an accuracy high enough to meet the specifications for unmanned space exploration.

Keywords

Digital Elevation Model Interest Point Stereo Match Stereo Pair Stereo Camera 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [Age95]
    European Space Agency. Leda assessment report: Leda-rp-95-02, June 1995.Google Scholar
  2. [BP93]
    Bauer, A. and Paar, G. Stereo Reconstruction From Dense Disparity Maps Using the Locus Method. In Gruen, A. and Kahmen, H., editors, Proc. 2nd Conference on Optical 3-D Measurement Techniques, pages 460–466, Zurich, Switzerland, October 4–7 1993. ETH Zürich, Wichmann Verlag.Google Scholar
  3. [Dij59]
    Dijkstra, E.W. A Note on Two Problems in Connection with Graphs. Numerical Mathematics, 1(5):269–271, October 1959.CrossRefGoogle Scholar
  4. [GT90]
    Grosky, W.I. and Tamburino, L.A. A Unified Approach to the Linear Camera Calibration Problem. IEEE Trans. Patt. Anal. Mach. Intell., 12(7):663–671, July 1990.CrossRefGoogle Scholar
  5. [KK92]
    Kweon, I.S. and Kanade, T. High-Resolution Terrain Map from Multiple Sensor Data. IEEE Trans. Patt. Anal. Mach. Intell., 14(2):278–292, February 1992.CrossRefGoogle Scholar
  6. [Kol95]
    Kolesnik, M. Vision and Navigation of Marsokhod Rover. In Proc. ACCV'95, pages III-772–III-777, Dec. 5–8 1995.Google Scholar
  7. [PLSN93]
    Proy, C., Lamboley, M., Sitenko, I., and Nguen, T.N. Improving Autonomy of Marsokhod 96. In Proc. 44th Congress of the IAF, Graz, Austria, Oct 16–22 1993. IAF. IAF-93-U.6.584.Google Scholar
  8. [PP92]
    Paar,G. and Pölzleitner,W. Robust Disparity Estimation in Terrain Modeling for Spacecraft Navigation. In Proc. 11th ICPR. International Association for Pattern Recognition, 1992.Google Scholar
  9. [PSP95]
    Paar. G., Sidla, O., and Pölzleitner, W. Natural Feature Tracking for Autonomous Navigation. In Proc. 28th International Dedicated Conference on Robotics, Motion and Machine Vision, Stuttgart, Germany, October 1995. ISATA.Google Scholar
  10. [PU93]
    Pölzleitner, W. and Ulm, M. Robust dynamic 3d motion estimation using landmarks. In Optical Tools for Manufacturing and Advanced Automation, Videometrics II, 1993.Google Scholar
  11. [Ros93]
    Ross,B. A Practical Stereo Vision System. In IEEE Computer Society, editor, 1993 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 148–153, New York, June 15–18 1993. IEEE Computer Society Press.Google Scholar
  12. [UP95]
    Ulm, M. and Paar. G. Relative Camera Calibration from Stereo Disparities. In Proc. 3rd Conference on Optical 3-D Measurement Techniques, Vienna, Austria, October 2–4 1995. ISPRS.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Marina Kolesnik
    • 1
  • Gerhard Paar
    • 2
  1. 1.Max-Planck Institute für AeronomieLindauGermany
  2. 2.JOANNEUM RESEARCHGrazAustria

Personalised recommendations