Monte Carlo Tree Search on Directed Acyclic Graphs for Object Pose Verification

  • Dominik BauerEmail author
  • Timothy Patten
  • Markus Vincze
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11754)


Reliable object pose estimation is an integral part of robotic vision systems as it enables robots to manipulate their surroundings. Powerful methods exist that estimate object poses from RGB and RGB-D images, yielding a set of hypotheses per object. However, determining the best hypotheses from the set of possible combinations is a challenging task. We apply MCTS to this problem to find an optimal solution in limited time and propose to share information between equivalent object combinations that emerge during the tree search, so-called transpositions. Thereby, the number of combinations that need to be considered is reduced and the search gathers information on these transpositions in a single statistic. We evaluate the resulting verification method on the YCB-VIDEO dataset and show more reliable detection of the best solution as compared to state of the art. In addition, we report a significant speed-up compared to previous MCTS-based methods for object pose verification.


Hypotheses verification Object pose estimation Monte Carlo Tree Search Analysis-by-synthesis 


  1. 1.
    Aldoma, A., Tombari, F., Di Stefano, L., Vincze, M.: A global hypotheses verification method for 3D object recognition. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7574, pp. 511–524. Springer, Heidelberg (2012). Scholar
  2. 2.
    Aldoma, A., Tombari, F., Di Stefano, L., Vincze, M.: A global hypothesis verification framework for 3D object recognition in clutter. IEEE TPAMI 38(7), 1383–1396 (2016)CrossRefGoogle Scholar
  3. 3.
    Auer, P., Cesa-Bianchi, N., Fischer, P.: Finite-time analysis of the multiarmed bandit problem. Mach. Learn. 47(2–3), 235–256 (2002)CrossRefGoogle Scholar
  4. 4.
    Bauer, D., Patten, T., Vincze, M.: 6D object pose verification via confidence-based Monte Carlo tree search and constrained physics simulation. In: OAGM & ARW Joint Workshop, pp. 153–158 (2019)Google Scholar
  5. 5.
    Brachmann, E., Michel, F., Krull, A., Yang, M.Y., Gumhold, S., et al.: Uncertainty-driven 6D pose estimation of objects and scenes from a single RGB image. In: IEEE CVPR, pp. 3364–3372 (2016)Google Scholar
  6. 6.
    Browne, C.B., et al.: A survey of Monte Carlo tree search methods. T-CIAIG 4(1), 1–43 (2012)Google Scholar
  7. 7.
    Childs, B.E., Brodeur, J.H., Kocsis, L., et al.: Transpositions and move groups in Monte Carlo tree search. In: IEEE CIG, pp. 389–395 (2008)Google Scholar
  8. 8.
    Drost, B., Ulrich, M., Navab, N., Ilic, S.: Model globally, match locally: efficient and robust 3D object recognition. In: IEEE CVPR, pp. 998–1005 (2010)Google Scholar
  9. 9.
    Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. IJCV 88(2), 303–338 (2010)CrossRefGoogle Scholar
  10. 10.
    Gaudel, R., Sebag, M.: Feature selection as a one-player game. In: ICML, pp. 359–366 (2010)Google Scholar
  11. 11.
    He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: IEEE ICCV, pp. 2980–2988 (2017)Google Scholar
  12. 12.
    Hinterstoisser, S., et al.: Model based training, detection and pose estimation of texture-less 3D objects in heavily cluttered scenes. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012. LNCS, vol. 7724, pp. 548–562. Springer, Heidelberg (2013). Scholar
  13. 13.
    Hodaň, T., et al.: BOP: benchmark for 6D object pose estimation. In: ECCV, pp. 19–34 (2018)Google Scholar
  14. 14.
    Hodaň, T., Zabulis, X., Lourakis, M., Obdržálek, Š., Matas, J.: Detection and fine 3D pose estimation of texture-less objects in RGB-D images. In: IEEE/RSJ IROS, pp. 4421–4428 (2015)Google Scholar
  15. 15.
    Kehl, W., Milletari, F., Tombari, F., Ilic, S., Navab, N.: Deep learning of local RGB-D patches for 3D object detection and 6D pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 205–220. Springer, Cham (2016). Scholar
  16. 16.
    Mitash, C., Boularias, A., Bekris, K.E.: Improving 6D pose estimation of objects in clutter via physics-aware Monte Carlo tree search. In: IEEE ICRA, pp. 1–8 (2018)Google Scholar
  17. 17.
    Narayanan, V., Likhachev, M.: Perch: perception via search for multi-object recognition and localization. In: IEEE ICRA, pp. 5052–5059 (2016)Google Scholar
  18. 18.
    Pélissier, A., Nakamura, A., Tabata, K.: Feature selection as Monte-Carlo search in growing single rooted directed acyclic graph by best leaf identification. In: SDM, pp. 450–458 (2019)CrossRefGoogle Scholar
  19. 19.
    Saffidine, A., Cazenave, T., Méhat, J.: UCD: upper confidence bound for rooted directed acyclic graphs. Knowl.-Based Syst. 34, 26–33 (2012)CrossRefGoogle Scholar
  20. 20.
    Tejani, A., Tang, D., Kouskouridas, R., Kim, T.-K.: Latent-class hough forests for 3D object detection and pose estimation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 462–477. Springer, Cham (2014). Scholar
  21. 21.
    Vidal, J., Lin, C.Y., Martí, R.: 6d pose estimation using an improved method based on point pair features. In: ICCAR, pp. 405–409 (2018)Google Scholar
  22. 22.
    Wang, C., et al.: DenseFusion: 6D object pose estimation by iterative dense fusion. In: IEEE CVPR (2019)Google Scholar
  23. 23.
    Wohlhart, P., Lepetit, V.: Learning descriptors for object recognition and 3D pose estimation. In: IEEE CVPR, pp. 3109–3118 (2015)Google Scholar
  24. 24.
    Xiang, Y., Schmidt, T., Narayanan, V., Fox, D.: Posecnn: a convolutional neural network for 6D object pose estimation in cluttered scenes. In: CoRR (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Automation and Control InstituteTU WienViennaAustria

Personalised recommendations