Place Classification using Dempster-Shafer Theory

Barbara Siemiątkowska 1  and Bogdan Harasymowicz-Boggio 1
  • 1 Warsaw University of Technology, Faculty of Mechatronics, Warsaw, Poland

Abstract

The paper presents a novel place labeling method. It is assumed that an indoor mobile robot equipped with a camera or RGB-D sensor ambulates an indoor environment. The places visited by the robot are classified based on objects which have been recognized. Each object (or set of objects) votes for a set of room classes. Data aggregation is performed using Dempster-Shafer theory (DST), which can be regarded as a generalization of the Bayesian theory. The possibility of taking into account the uncertainty of data is the main advantage of the described method. The classic Dempster’s rule of data aggregation has been criticized because it can lead to non-intuitive results. Many alternative methods have been proposed and several were tested during our experiments. Most place classification methods assume a closed world model, i.e. a test sample is assigned to the most probable class even if its corresponding probability is very small. An advantage of our system is the intrinsic capability of giving unknown class as an answer in such situations, which can be used by the robot to take appropriate actions.

If the inline PDF is not rendering correctly, you can download the PDF file here.

  • [2] Althaus P. and Christensen H. I. Behavior coordination in structured environments. Advanced Robotics, 17(7):657–674, 2003.

  • [3] Anguelov D., Biswas R., Koller D., Limketkai B., Sanner S., and Thrun S. Learning hierarchical object maps of non-stationary environments with mobile robots. In Proceedings of the 17th Annual Conference on Uncertainty in AI (UAI), Edmonton, Canada, 2002.

  • [4] Bogler P. L. Shafer-Dempster reasoning with applications to multisensor target identification systems. IEEE Transactions on Systems, Man, and Cybernetics, 17:968–977, 1987.

  • [5] Buschka P. and Saffiotti A. A virtual sensor for room detection. In Intelligent Robots and Systems (IROS), pages 637–642, 2002.

  • [6] Chen Z., Lam O., Jacobson A., and Milford M. Convolutional neural network-based place recognition. CoRR, abs/1411.1509, 2014.

  • [7] Dellaert F., Fox D., Burgard W., and Thrun S. Monte Carlo localization for mobile robots. In IEEE Int. Conf. on Robotics & Automation (ICRA), 1998.

  • [8] Friedman S., Pasula H., and Fox D. Voronoi random fields: Extracting the topological structure of indoor environments via place labeling. In In Proc. of the International Joint Conference on Artificial Intelligence (IJCAI, 2007.

  • [9] Harasymowicz-Boggio B., Chechlinski L., and Siemiatkowska B. Nature-inspired, parallel object recognition. In Szewczyk R., Zieliski C., and Kaliczyska M., editors, Progress in Automation, Robotics and Measuring Techniques. Control and Automation. Advances in Intelligent Systems and Computing vol. 350, pages 53–62. Springer, 2015.

  • [10] Harasymowicz-Boggio B., Chechlinski L., and Siemiatkowska B. Significance of features in object recognition using depth sensors. Optica Applicata, 45(4):559–571, 2015.

  • [11] Himstedt M., Frost J., Hellbach S., Bhme H. J., and Maehle E. Large scale place recognition in 2d lidar scans using geometrical landmark relations. In 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 5030–5035, Sept 2014.

  • [12] Jousselme A.-L., Liu C., Grenier D., and Bosse E. Measuring ambiguity in the evidence theory. Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on, 36(5):890–903, Sept 2006.

  • [13] Jung H., Mozos O. M., Iwashita Y., and Kurazume R. Local n-ary patterns: a local multi-modal descriptor for place categorization. Advanced Robotics, 30(6):402–415, 2016.

  • [14] Koenig S. and Simmons R. G. Xavier: A robot navigation architecture based on partially observable markov decision process models. In Artificial Intelligence Based Mobile Robotics: Case Studies of Successful Robot Systems, pages 91–122. MIT Press, 1998.

  • [15] Milford M., Scheirer W. J., Vig E., Glover A., Baumann O., Mattingley J., and Cox D. D. Condition-invariant, top-down visual place recognition. In The IEEE International Conference on Robotics and Automation (ICRA), June 2014.

  • [16] Mozos O. M., Triebel R., Jensfelt P., Rottman A., and Burgard W. Supervised semantic labeling of places using information extracted from sensor data. Robotics and Autonomous Systems, 5:392–402, 2007.

  • [17] Nistér D. and Stewénius H. Scalable recognition with a vocabulary tree. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), volume 2, pages 2161–2168, June 2006.

  • [18] Oliva A. and Torralba A. Modeling the shape of the scene: A holistic representation of the spatial envelope. Int. J. Comput. Vision, 42(3):145–175, May 2001.

  • [19] Premebida C. and Faria U., Diego R. and Nunes. Dynamic bayesian network for semantic place classification in mobile robotics. Autonomous Robots, 41(5), 2017.

  • [20] Quattoni A. and Torralba A. Recognizing indoor scenes. In IEEE International Conference on Computer Vision and Pattern Recognition, pages 413 – 420, 2009.

  • [21] Renninger L. W. and Malik J. When is scene identification just texture recognition? Vision Research, 44(19):2301–2311, September 2004.

  • [22] Smarandache F. and Dezert J. Information fusion based on new proportional conflict redistribution rules. In Information Fusion, 2005 8th International Conference on, volume 2, pages 8–pp. IEEE, 2005.

  • [23] Teichman A. and Thrun S. Practical object recognition in autonomous driving and beyond. In ARSO, pages 35–38, 2011.

  • [24] Torralba A. Contextual priming for object detection. Int. J. Comput. Vision, 53(2):169–191, July 2003.

  • [25] Ullah M. M., Pronobis A., Caputo B., Luo J., Jensfelt P., and Christensen H. I. Towards robust place recognition for robot localization. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA08), 2008.

  • [26] Vasudevan S. and Siegwart R. Bayesian space conceptualization and place classification for semantic maps in mobile robotics. Robot. Auton. Syst., 56(6):522–537, June 2008.

  • [27] Yang S., Mou W., Wang H., and Ge S. S. Place recognition by combining multiple feature types with a modified vocabulary tree. In 2015 International Conference on Image and Vision Computing New Zealand (IVCNZ), pages 1–6, Nov 2015.

  • [28] Yi C., Suh I. H., Lim G. H., and Choi B. Bayesian robot localization using spatial object contexts. In 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, October 11-15, 2009, St. Louis, MO, USA, pages 3467–3473, 2009.

  • [29] Zadeh L. A. Fuzzy sets. Information and Control, 8:338–353, 1965.

  • [30] Zhou B., Khosla A., Lapedriza À., Oliva A., and Torralba A. Learning deep features for discriminative localization. CoRR, abs/1512.04150, 2015.

  • [31] Zhou B., Lapedriza A., Xiao J., Torralba A., and Oliva A. Learning deep features for scene recognition using places database. In Proceedings of the 27th International Conference on Neural Information Processing Systems, NIPS’14, pages 487–495, Cambridge, MA, USA, 2014. MIT Press.

  • [32] Zhou B., Lapedriza A., Xiao J., Torralba A., and Oliva A. Learning deep features for scene recognition using places database. In NIPS, 2014.

OPEN ACCESS

Journal + Issues

Search