PROBABILISTIC MAP BUILDING CONSIDERING SENSOR VISIBILITY

Kazuma Haraguchi, Jun Miura, Nobutaka Shimada, Yoshiaki Shirai

2007

Abstract

This paper describes a method of probabilistic obstacle map building based on Bayesian estimation. Most active or passive obstacle sensors observe only the most frontal objects and any objects behind them are occluded. Since the observation of distant places includes large depth errors, conventional methods which does not consider the sensor occlusion often generate erroneous maps. We introduce a probabilistic observation model which determines the visible objects. We first estimate probabilistic visibility from the current view-point by a Markov chain model based on the knowledge of the average sizes of obstacles and free areas. Then the likelihood of the observations based on the probabilistic visibility are estimated and then the posterior probability of each map grid are updated by Bayesian update rule. Experimental results show that more precise map building can be bult by this method.

References

  1. Grisetti, G., Stachniss, C., and Burgard, W. (2005). Improving Grid-based SLAM with Rao-Blackwellized Particle Filters by Adaptive Proposals and Selective Resampling. In Proc. of the IEEE International Conference on Robotics and Automation (ICRA), pages 2443-2448.
  2. Miura, J., Negishi, Y., and Shirai, Y. (2002). Mobile Robot Map Generation by Integrationg Omnidirectional Stereo and Laser Range Finder. In Proc. of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), pages 250-255.
  3. Montemerlo, M. and Thrun, S. (2002). FastSLAM 2.0: An Improved Particle Filtering Algorithm for Simultaneous Localization and Mapping that Provably Converges.
  4. Moravec, H. P. (1988). Sensor fusion in certainty grids for mobile robots. In AI Magazine, Summer, pages 61-74.
  5. Rachlin, Y., Dolan, J., and Khosla, P. (2005). Efficient mapping through exploitation of spatial dependencies. In Proc. of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), pages 3117-3122.
  6. Suppes, A., Suhling, F., and Hötter, M. (2001). Robust Obstacle Detection from Stereoscopic Image Sequences Using Kalman Filtering. In DAGM-Symposium, pages 385-391.
  7. Thrun, S. (2002a). Learning occupancy grids with forward sensor models. In Autonomous Robots.
  8. Thrun, S. (2002b). Robotic Mapping: A Survey. In Lakemeyer, G. and Nebel, B., editors, Exploring Artificial Intelligence in the New Millenium. Morgan Kaufmann.
  9. Thrun, S., Montemerlo, M., Koller, D., Wegbreit, B., Nieto, J., and Nebot, E. (2004). FastSLAM: An Efficient Solution to the Simultaneous Localization And Mapping Problem with Unknown Data Association. Journal of Machine Learning Research.
Download


Paper Citation


in Harvard Style

Haraguchi K., Miura J., Shimada N. and Shirai Y. (2007). PROBABILISTIC MAP BUILDING CONSIDERING SENSOR VISIBILITY . In Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, ISBN 978-972-8865-83-2, pages 200-206. DOI: 10.5220/0001623502000206


in Bibtex Style

@conference{icinco07,
author={Kazuma Haraguchi and Jun Miura and Nobutaka Shimada and Yoshiaki Shirai},
title={PROBABILISTIC MAP BUILDING CONSIDERING SENSOR VISIBILITY},
booktitle={Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},
year={2007},
pages={200-206},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001623502000206},
isbn={978-972-8865-83-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,
TI - PROBABILISTIC MAP BUILDING CONSIDERING SENSOR VISIBILITY
SN - 978-972-8865-83-2
AU - Haraguchi K.
AU - Miura J.
AU - Shimada N.
AU - Shirai Y.
PY - 2007
SP - 200
EP - 206
DO - 10.5220/0001623502000206