SLAM of View-based Maps using SGD

David Valiente, Arturo Gil Aparicio, Francisco Amorós Espí, Oscar Reinoso

2013

Abstract

This work presents a solution for the problem of Simultaneous Localization and Mapping (SLAM) based on a Stochastic Gradient Descent (SGD) technique and using omnidirectional images. In the field of applications of mobile robotics, SGD has never been tested with visual information obtained from the environment. This paper suggests the introduction of a SGD algorithm into a SLAM scheme which exploits the benefits of omnidirectional images provided by a single camera. Several improvements have been introduced to the vanilla SGD in order to adapt it to the case of omnidirectional observations. This new SGD approach reduces the undesired harmful effects provoked by non-linearities which compromise the convergence of the traditional filter estimates. Particularly, we rely on an efficient map representation, conformed by a reduced set of image views. The first contribution is the adaption of the basic SGD algorithm to work with omnidirectional observations, whose nature is angular, and thus it lacks of scale. Former SGD approaches only process one constraint independently at each iteration step. Instead, we think of a strategy which employes several constraints simultaneously as system inputs, with the purpose of improving the convergence speed when estimating a SLAM solution. In this context, we present different sets of experiments which have been carried out seeking for validation of our new approach based on SGD with omnidirectional observations. In addition, we compare our approach with a basic SGD in order to prove the expected benefits in terms of efficiency.

References

  1. Andrew J. Davison, A. J., Gonzalez Cid, Y., and Kita, N. (2004). Improving data association in vision-based SLAM. In Proc. of IFAC/EURON, Lisboa, Portugal.
  2. Civera, J., Davison, A. J., and Martínez Montiel, J. M. (2008). Inverse depth parametrization for monocular slam. IEEE Trans. on Robotics.
  3. Davison, A. J. and Murray, D. W. (2002). Simultaneous localisation and map-building using active vision. IEEE Trans. on PAMI.
  4. Gil, A., Reinoso, O., Ballesta, M., Juliá, M., and Payá, L. (2010). Estimation of visual maps with a robot network equipped with vision sensors. Sensors.
  5. Grisetti, G., Stachniss, C., and Burgard, W. (2009). Nonlinear constraint network optimization for efficient map learning. IEEE Trans. on Intelligent Transportation Systems.
  6. Grisetti, G., Stachniss, C., Grzonka, S., and Burgard, W. (2007). A tree parameterization for efficiently computing maximum likelihood maps using gradient descent. In Proc. of RSS, Atlanta, USA.
  7. Jae-Hean, K. and Myung Jin, C. (2003). Slam with omnidirectional stereo vision sensor. In Proc. of the IROS, Las Vegas, USA.
  8. Joly, C. and Rives, P. (2010). Bearing-only SAM using a minimal inverse depth parametrization. In Proc. of ICINCO, Funchal, Madeira, Portugal.
  9. Montemerlo, M., Thrun, S., Koller, D., and Wegbreit, B. (2002). Fastslam: a factored solution to the simultaneous localization and mapping problem. In Proc. of the 18th national conference on Artificial Intelligence, Edmonton, Canada.
  10. Neira, J. and Tardó s, J. D. (2001). Data association in stochastic mapping using the joint compatibility test. IEEE Trans. on Robotics and Automation.
  11. Olson, D., Leonard, J., and Teller, S. (2006). Fast iterative optimization of pose graphs with poor initial estimates. In Proc of ICRA, Orlando, USA.
  12. Stachniss, C., Grisetti, G., Haehnel, D., and Burgard, W. (2004). Improved Rao-Blackwellized mapping by adaptive sampling and active loop-closure. In Proc. of the SOAVE, Ilmenau, Germany.
  13. Valiente, D., Gil, A., Fernández, L., and Reinoso, O. (2012). View-based maps using omnidirectional images. In Proc. of ICINCO, Rome, Italy.
Download


Paper Citation


in Harvard Style

Valiente D., Gil Aparicio A., Amorós Espí F. and Reinoso O. (2013). SLAM of View-based Maps using SGD . In Proceedings of the 10th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, ISBN 978-989-8565-71-6, pages 329-336. DOI: 10.5220/0004482603290336


in Bibtex Style

@conference{icinco13,
author={David Valiente and Arturo Gil Aparicio and Francisco Amorós Espí and Oscar Reinoso},
title={SLAM of View-based Maps using SGD},
booktitle={Proceedings of the 10th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},
year={2013},
pages={329-336},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004482603290336},
isbn={978-989-8565-71-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,
TI - SLAM of View-based Maps using SGD
SN - 978-989-8565-71-6
AU - Valiente D.
AU - Gil Aparicio A.
AU - Amorós Espí F.
AU - Reinoso O.
PY - 2013
SP - 329
EP - 336
DO - 10.5220/0004482603290336