Autonomous Robots

, Volume 24, Issue 1, pp 69–86 | Cite as

Learning traversability models for autonomous mobile vehicles

  • Michael Shneier
  • Tommy Chang
  • Tsai Hong
  • Will Shackleford
  • Roger Bostelman
  • James S. Albus
Article

Abstract

Autonomous mobile robots need to adapt their behavior to the terrain over which they drive, and to predict the traversability of the terrain so that they can effectively plan their paths. Such robots usually make use of a set of sensors to investigate the terrain around them and build up an internal representation that enables them to navigate. This paper addresses the question of how to use sensor data to learn properties of the environment and use this knowledge to predict which regions of the environment are traversable. The approach makes use of sensed information from range sensors (stereo or ladar), color cameras, and the vehicle’s navigation sensors. Models of terrain regions are learned from subsets of pixels that are selected by projection into a local occupancy grid. The models include color and texture as well as traversability information obtained from an analysis of the range data associated with the pixels. The models are learned without supervision, deriving their properties from the geometry and the appearance of the scene.

The models are used to classify color images and assign traversability costs to regions. The classification does not use the range or position information, but only color images. Traversability determined during the model-building phase is stored in the models. This enables classification of regions beyond the range of stereo or ladar using the information in the color images. The paper describes how the models are constructed and maintained, how they are used to classify image regions, and how the system adapts to changing environments. Examples are shown from the implementation of this algorithm in the DARPA Learning Applied to Ground Robots (LAGR) program, and an evaluation of the algorithm against human-provided ground truth is presented.

Keywords

Learning Traversability Classification Color models Texture Range Mobile robotics 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Albus, J. S., & Meystel, A. (2001). Engineering of mind: an introduction to the science of intelligent systems. Somerset: Wiley. Google Scholar
  2. Albus, J. S., Huang, H.-M., Messina, E., Murphy, K., Juberts, M., Lacaze, A., Balakirsky, S., Shneier, M. O., Hong, T., Scott, H., Horst, J., Proctor, F., Shackleford, W., Szabo, S., & Finkelstein, R. (2002). 4D/RCS Version 2.0: A reference model architecture for unmanned vehicle systems (NISTIR 6912). Gaithersburg, MD: National Institute of Standards and Technology. Google Scholar
  3. Albus, J., Bostelman, R., Chang, T., Hong, T., Shackleford, W., & Shneier, M. (2006). Learning in a hierarchical control system: 4D/RCS in the DARPA LAGR program. Journal of Field Robotics, 23(11/12), 975–1003. CrossRefGoogle Scholar
  4. Chakravarty, S. (1999). Sample size determination for multinomial population. In National association for welfare research and statistics 39th annual workshop, Cleveland, Ohio. http://www.nawrs.org/ClevelandPDF/papers/Page_2x.html.
  5. Chang, T., Hong, T., Legowik, S., & Abrams, M. (1999). Concealment and obstacle detection for autonomous driving. In Proceedings of the robotics & applications conference (pp. 147–152). Santa Barbara, CA. Google Scholar
  6. DeSouza, G. N., & Kak, A. C. (2002). Vision for mobile robot navigation: a survey. IEEE Transaction on Pattern Analysis and Machine Intelligence, 24(2), 237–267. CrossRefGoogle Scholar
  7. Hadsell, R., Sermanet, P., Ben, J., Han, J., Chopra, S., Ranzato, M., Sulsky, Y., Flepp, B., Muller, U., & LeCun, Y. (2006). On-line learning of long-range obstacle detection for off-road robots. In The learning workshop, Snowbird, UT. Google Scholar
  8. Howard, A., Tunstel, E., Edwards, D., & Carlson, A. (2001). Enhancing fuzzy robot navigation systems by mimicking human visual perception of natural terrain traversability. In Joint 9th IFSA world congress and 20th NAFIPS international conference (pp. 7–12). Google Scholar
  9. Jackel, L. D., Krotkov, E., Perschbacher, M., Pippine, J., & Sullivan, C. (2006). The DARPA LAGR program: goals, challenges, methodology and phase I results. Journal of Field Robotics, 23(11/12), 945–973. CrossRefGoogle Scholar
  10. Kwong, W. A., & Passino, K. M. (1996). Dynamically focused fuzzy learning control, Part B. IEEE Transactions on Systems, Man and Cybernetics, 26(1), 53–74. CrossRefGoogle Scholar
  11. Ojala, T., Pietikainen, M., & Harwood, D. (1996). A comparative study of texture measures with classification based on feature distributions. Pattern Recognition, 29, 51–59. CrossRefGoogle Scholar
  12. Pietikainen, M., Nieminen, S., Marszalec, E., & Ojala, T. (1996). Accurate color discrimination with classification based on feature distributions. In 13th international conference on pattern recognition (ICPR’96) (Vol. 3, pp. 833–838). Google Scholar
  13. Puzicha, J., Hofmann, T., & Buhmann, J.M. (1997). Non-parametric similarity measures for unsupervised texture segmentation and image retrieval. In IEEE computer society conference on computer vision and pattern recognition (CVPR’97) (pp. 267–272). San Juan, Puerto Rico. Google Scholar
  14. Shirkhodaie, A., Amrani, R., Chawla, N., & Vicks, T. (2004). Traversable terrain modeling and performance measurement of mobile robots. In Performance metrics for intelligent systems, PerMIS’04, Gaithersburg, MD. Google Scholar
  15. Shneier, M., Shackleford, W., Hong, T., & Chang, T. (2006). Performance evaluation of a terrain traversability learning algorithm in the DARPA LAGR program. In Performance metrics for intelligent systems, PerMIS 2006. Google Scholar
  16. Swain, M. J., & Ballard, D. H. (1991). Color indexing. International Journal of Computer Vision, 7(1), 11–32. CrossRefGoogle Scholar
  17. Talukder, A., Manduchi, R., Castano, R., Matthies, L., Castano, A., & Hogg, R. (2002). Autonomous terrain characterisation and modelling for dynamic control of unmanned vehicles. In IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 708–713). Google Scholar
  18. Tan, C., Hong, T., Shneier, M., & Chang, T. (2006). Color model-based real-time learning for road following. In IEEE intelligent transportation systems conference (ITSC’06) (pp. 939–944). Toronto, Canada. Google Scholar
  19. Ulrich, I., & Nourbakhsh, I. (2000a). Appearance-based obstacle detection with monocular color vision. In Proceedings of the AAAI national conference on artificial intelligence. Austin, TX. Google Scholar
  20. Ulrich, I., & Nourbakhsh, I. (2000b). Appearance-based place recognition for topological localization. In IEEE international conference on robotics and automation (pp. 1023–1029). San Francisco, CA. Google Scholar
  21. Wellington, C., & Stentz, A. (2003). Learning predictions of the load-bearing surface for autonomous rough-terrain navigation in vegetation. In International conference on field and service robotics (pp. 49–54). Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  • Michael Shneier
    • 1
  • Tommy Chang
    • 1
  • Tsai Hong
    • 1
  • Will Shackleford
    • 1
  • Roger Bostelman
    • 1
  • James S. Albus
    • 1
  1. 1.National Institute of Standards and TechnologyGaithersburgUSA

Personalised recommendations