Advertisement

Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Dynamic Bayesian network for semantic place classification in mobile robotics

Abstract

In this paper, the problem of semantic place categorization in mobile robotics is addressed by considering a time-based probabilistic approach called dynamic Bayesian mixture model (DBMM), which is an improved variation of the dynamic Bayesian network. More specifically, multi-class semantic classification is performed by a DBMM composed of a mixture of heterogeneous base classifiers, using geometrical features computed from 2D laserscanner data, where the sensor is mounted on-board a moving robot operating indoors. Besides its capability to combine different probabilistic classifiers, the DBMM approach also incorporates time-based (dynamic) inferences in the form of previous class-conditional probabilities and priors. Extensive experiments were carried out on publicly available benchmark datasets, highlighting the influence of the number of time-slices and the effect of additive smoothing on the classification performance of the proposed approach. Reported results, under different scenarios and conditions, show the effectiveness and competitive performance of the DBMM.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Notes

  1. 1.

    Also known, according to Korb and Nicholson (2010), as dynamic belief network, probabilistic temporal network, or dynamic causal probabilistic network.

  2. 2.

    Freib-dataset has laser data indeed, but with low resolution.

  3. 3.

    In this paper the values of \(F_{measure}\) are presented in percentage.

  4. 4.

    http://www.csie.ntu.edu.tw/~cjlin/libsvm/.

References

  1. Chen, S.F., & Goodman, J. (1996). An empirical study of smoothing techniques for language modeling. In Proceedings of the 34th annual meeting on association for computational linguistics, Stroudsburg, PA, ACL ’96 (pp. 310–318).

  2. Costante, G., Ciarfuglia, T., Valigi, P., & Ricci, E. (2013). A transfer learning approach for multi-cue semantic place recognition.it In IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 2122–2129).

  3. Duda, R. O., Hart, P. E., & Stork, D. G. (2001). Pattern classification. New York: Wiley.

  4. Faria, D., Premebida, C., & Nunes, U. (2014). A probabilistic approach for human everyday activities recognition using body motion from RGB-D images. In The 23rd IEEE international symposium on robot and human interactive communication, RO-MAN (pp. 732–737).

  5. Hong, S., Kim, J., Pyo, J., & Yu, S. C. (2015). A robust loop-closure method for visual SLAM in unstructured seafloor environments. Autonomous Robots, 40, 1–15.

  6. Jung, H., Martinez Mozos O., Iwashita, Y., & Kurazume, R. (2014). Indoor place categorization using co-occurrences of LBPs in gray and depth images from RGB-D sensors. In Fifth international conference on emerging security technologies (EST).

  7. Jung, H., Mozos, O. M., Iwashita, Y., & Kurazume, R. (2016). Local n-ary patterns: A local multi-modal descriptor for place categorization. Advanced Robotics, 30(6), 402–415.

  8. Korb, K. B., & Nicholson, A. E. (2010). Bayesian artificial intelligence (2nd ed.). Boca Raton, FL: CRC Press Inc.

  9. Kostavelis, I., & Gasteratos, A. (2015). Semantic mapping for mobile robotics tasks: A survey. Robotics and Autonomous Systems, 66, 86–103.

  10. Luo, J., Pronobis, A., Caputo, B., & Jensfelt, P. (2007). Incremental learning for place recognition in dynamic environments. In IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 721–728). San Diego, CA.

  11. Martinez-Gomez, J., Garcia-Varea, I., Cazorla, M., & Morell, V. (2015). ViDRILO: The visual and depth robot indoor localization with objects information dataset. The International Journal of Robotics Research, 34, 1681.

  12. McManus, C., Upcroft, B., & Newman, P. (2015). Learning place-dependant features for long-term vision-based localisation. Autonomous Robots, 39(3), 363–387.

  13. Mihajlovic, V., & Petkovic., M (2001). Dynamic Bayesian networks: A state of the art. Technical reports series, TR-CTIT-34.

  14. Milford, M. (2013). Vision-based place recognition: how low can you go? The International Journal of Robotics Research, 32(7), 766–789.

  15. Mozos, O. M. (2010). Semantic place labeling with mobile robots. Springer tracts in advanced robotics. Berlin: Springer.

  16. Posner, I., Cummins, M., & Newman, P. (2009). A generative framework for fast urban labeling using spatial andtemporal context. Autonomous Robots, 26(2–3), 153–170.

  17. Premebida, C., Faria, D., Souza, F., & Nunes, U. (2015). Applying probabilistic mixture models to semantic place classification in mobile robotics. In IEEE/RSJ international conference on intelligent robots and systems (IROS).

  18. Pronobis, A., & Jensfelt, P. (2012). Large-scale semantic mapping and reasoning with heterogeneous modalities. In IEEE international conference on robotics and automation (ICRA) (pp. 3515–3522).

  19. Pronobis, A., Caputo, B., Jensfelt, P., & Christensen, H.I. (2006). A discriminative approach to robust visual place recognition. In IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 3829–3836).

  20. Pronobis, A., Mozos, O. M., Caputo, B., & Jensfelt, P. (2010). Multi-modal semantic place classification. The International Journal of Robotics Research (IJRR), 29(2–3), 298–320.

  21. Rogers, J., & Christensen, H. (2012). A conditional random field model for place and object classification. it In IEEE international conference on robotics and automation (ICRA) (pp. 1766–1772).

  22. Shi, L., Kodagoda, S., & Dissanayake, G. (2010). Laser range data based semantic labeling of places. In IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 5941–5946).

  23. Shi, L., Kodagoda, S., & Dissanayake. G. (2012). Application of semi-supervised learning with voronoi graph for place classification. In IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 2991–2996).

  24. Shi, L., Kodagoda, S., & Piccardi, M. (2013). Towards simultaneous place classification and object detection based on conditional random field with multiple cues. In IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 2806–2811).

  25. Ullah, M., Pronobis, A., Caputo, B., Luo, J., Jensfelt, R., & Christensen, H. (2008). Towards robust place recognition for robot localization. In IEEE international conference on robotics and automation (ICRA) (pp. 530–537).

  26. Vasudevan, S., & Siegwart, R. (2008). Bayesian space conceptualization and place classification for semantic maps in mobile robotics. Robotics and Autonomous Systems, 56(6), 522–537.

  27. Werner, F., Sitte, J., & Maire, F. (2012). Topological map induction using neighbourhood information of places. Autonomous Robots, 32(4), 405–418.

  28. Wu, J., Christensen, H., & Rehg, J. (2009). Visual place categorization: Problem, dataset, and algorithm. In IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 4763–4770).

  29. Yuan, L., Chan, K. C., & George Lee, C. S. (2011). Robust semantic place recognition with vocabulary tree and landmark detection. In ASP-AVS-11 Workshop in conjunction with the 2011 IEEE/RSJ International Conference on Intelligence Robots and Systems (ISRO).

Download references

Acknowledgments

This work was partially supported by the Portuguese Foundation for Science and Technology (FCT) and FEDER through COMPETE 2020 under grants RECI/EEI-AUT/0181/2012 (AMSHMI12) and UID/EEA/00048/2013.

Author information

Correspondence to Cristiano Premebida.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Premebida, C., Faria, D.R. & Nunes, U. Dynamic Bayesian network for semantic place classification in mobile robotics. Auton Robot 41, 1161–1172 (2017). https://doi.org/10.1007/s10514-016-9600-2

Download citation

Keywords

  • Semantic place recognition
  • Dynamic Bayesian network
  • Artificial intelligence