PROBABILISTIC APPEARANCE-BASED NAVIGATION OF A MOBILE ROBOT - Controlling a Robot in Route Following

Luis Payá, Oscar Reinoso, Arturo Gil, M. Asuncion Vicente, Jose L. Aznar

Abstract

In this work, a solution to the problem of multi-robot following routes is proposed using an appearance-based method. In this approach, several images are stored along the route to follow, using an uncalibrated forward-looking camera. To extract the most relevant information, an incremental PCA process has been implemented. This incremental process allows adding new locations to the PCA database without necessity of creating it from the scratch. Then, the follower robots can follow the route while a leader one is still recording it. These follower robots, using this database, make first an auto-location process to know their current position and then a control phase to compute the necessary steering speed to tend to the route and follow it till the end. Both speeds are obtained also through the visual information in an appearance-based approach. The problem of ‘visual aliasing’, typical in office environments, is avoided with a probabilistic approach that, using a Markov-process model, makes the localization more robust. The experimental results have shown how this is a simple but robust and powerful approach for routes in an office environment.

References

  1. Artac, M., Jogan, M., Leonardis, A., 2002. Mobile Robot Localization Using an Incremental Eigenspace Model. In Proc. IEEE Int. Conf. on robotics and Automation, pp. 1205-1030.
  2. Balch, T., Arkin, R., 1998. Behavior-based formation control for multi-robot teams. IEEE Transactions on Robotics and Automation, 14(6), pp. 926-938.
  3. Burschka, D., Hager, G., 2001. Vision-Based Control of Mobile Robots. In Proc. IEEE Int. Conf. on Robotics and Automation, pp. 1707-1713.
  4. Fenwick, J., Newman, P., Leonard, J., 2002. Cooperative Concurrent Mapping and Localization. In Proc. IEEE Int. Conf. on Robotics and Automation, pp. 1810-1817.
  5. Ho, K., Newman, P., 2005. Multiple Map Intersection Detection using Visual Appearance. In Proc. 3rd Int. Conf. on Computational Intelligence, Robotics and Autonomous Systems.
  6. Kirby, M., 2001. Geometric data analysis, Wiley Interscience.
  7. Kröse, B., Bunschoten, R., Hagen, S., Terwijn, B., Vlassis, N., 2004. Household robots: Look and learn. In IEEE Robotics & Automation magazine, 11(4), pp. 45-52.
  8. Maeda, S., Kuno, Y., Shirai, Y., 1997. Active navigation vision based on eigenspace analysis. In Proc. IEEE Int. Conf. on Intelligent Robots and Systems, Vol. 2, pp. 1018-1023.
  9. Matsumoto, Y., Ikeda, K., Inaba, M., Inoue, H., 1999. Visual Navigation Using Omnidirectional View Sequence. In Proc. IEEE Int. Conf. on Intelligent Robots and Systems, pp. 317-322.
  10. Payá, L., Reinoso, O., Gil, A., Pedrero, J., Ballesta, M., 2007. Appearance-Based Multi-Robot Following Routes Using Incremental PCA. In Int. Conf. on Knowledge-Based and Intelligent Information and Engineering Systems, pp. 1170-1178.
  11. Thrun, S., 2002. Robotic Mapping: A Survey. Exploring Artificial Intelligence in the New Milenium, Morgan Kaufmann.
  12. Turk, M., Pentland, A., 1991. Eigenfaces for recognition. In Journal on Cognitive Neuroscience, 3(1), pp. 71-86.
  13. Zhou, C., Wei, T., Tan, T., 2003. Mobile robot selflocalization based on global visual appearance features. In Proc. of the 2003 IEEE Int. Conf. on Robotics & Automation, pp. 1271-1276.
Download


Paper Citation


in Harvard Style

Payá L., Reinoso O., Gil A., Asuncion Vicente M. and L. Aznar J. (2008). PROBABILISTIC APPEARANCE-BASED NAVIGATION OF A MOBILE ROBOT - Controlling a Robot in Route Following . In Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008) ISBN 978-989-8111-21-0, pages 391-398. DOI: 10.5220/0001085303910398


in Bibtex Style

@conference{visapp08,
author={Luis Payá and Oscar Reinoso and Arturo Gil and M. Asuncion Vicente and Jose L. Aznar},
title={PROBABILISTIC APPEARANCE-BASED NAVIGATION OF A MOBILE ROBOT - Controlling a Robot in Route Following},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)},
year={2008},
pages={391-398},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001085303910398},
isbn={978-989-8111-21-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)
TI - PROBABILISTIC APPEARANCE-BASED NAVIGATION OF A MOBILE ROBOT - Controlling a Robot in Route Following
SN - 978-989-8111-21-0
AU - Payá L.
AU - Reinoso O.
AU - Gil A.
AU - Asuncion Vicente M.
AU - L. Aznar J.
PY - 2008
SP - 391
EP - 398
DO - 10.5220/0001085303910398