Proceedings

Object-Based World Modeling in Semi-Static Environments with Dependent Dirichlet Process Mixtures

Download BibTeX Cite

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 3513-3520.

© 2016 International Joint Conferences on Artificial Intelligence

Abstract

To accomplish tasks in human-centric indoor environments, agents need to represent and understand the world in terms of objects and their attributes. We consider how to acquire such a world model via noisy perception and maintain it over time, as objects are added, changed, and removed in the world. Previous work framed this as multiple-target tracking problem, where objects are potentially in motion at all times. Although this approach is general, it is computationally expensive. We argue that such generality is not needed in typical world modeling tasks, where objects only change state occasionally. More efficient approaches are enabled by restricting ourselves to such semi-static environments. We consider a previously-proposed clustering-based world modeling approach that assumed static environments, and extend it to semi-static domains by applying a dependent Dirichlet process (DDP) mixture model. We derive a novel MAP inference algorithm under this model, subject to data association constraints. We demonstrate our approach improves computational performance for world modeling in semi-static environments.

  1. [Ahmed and Xing, 2008] A. Ahmed and E. Xing. Dynamic non-parametric mixture models and the recurrent Chinese restaurant process: with applications to evolutionary clus- tering. In SIAM International Conference on Data Mining, 2008.
  2. [Antoniak, 1974] C.E. Antoniak. Mixtures of Dirichlet pro- cesses with applications to Bayesian nonparametric prob- lems. The Annals of Statistics, 2(6):1152-1174, 1974.
  3. [Bar-Shalom and Fortmann, 1988] Y. Bar-Shalom and T.E. Fortmann. Tracking and Data Association. Academic Press, 1988.
  4. [Besag, 1986] J. Besag. On the statistical analysis of dirty pictures. Journal of the Royal Statistical Society, Series B, 48:259-302, 1986.
  5. [Blei and Jordan, 2006] D.M. Blei and M.I. Jordan. Varia- tional inference for Dirichlet process mixtures. Bayesian Analysis, 1(1):121-143, 2006.
  6. [Cox and Leonard, 1994] I.J. Cox and J.J. Leonard. Model- ing a dynamic environment using a Bayesian multiple hy- pothesis approach. Artificial Intelligence, 66(2):311-344, 1994.
  7. [Dellaert et al., 2003] F. Dellaert, S.M. Seitz, C.E. Thorpe, and S. Thrun. EM, MCMC, and chain flipping for struc- ture from motion with unknown correspondence. Machine Learning, 50(1-2):45-71, 2003.
  8. [Elfring et al., 2013] J. Elfring, S. van den Dries, M.J.G. van de Molengraft, and M. Steinbuch. Semantic world modeling using probabilistic multiple hypothesis anchor- ing. Robotics and Autonomous Systems, 61(2):95-105, 2013.
  9. [Escobar and West, 1995] M.D. Escobar and M. West. Bayesian density estimation and inference using mix- tures. Journal of the American Statistical Association, 90(430):577-588, 1995.
  10. [Huang et al., 2015] R. Huang, F. Zhu, and P.-A. Heng. The dynamic Chinese restaurant process via birth and death processes. In AAAI Conference on Artificial Intelligence, 2015.
  11. [Jain and Neal, 2004] S. Jain and R.M. Neal. A split-merge Markov chain Monte Carlo procedure for the Dirichlet process mixture model. Journal of Computational and Graphical Statistics, 13(1):158-182, 2004.
  12. [Karp, 1972] R.M. Karp. Reducibility among combinato- rial problems. In R.E. Miller, J.W. Thatcher, and J.D. Bohlinger, editors, Complexity of Computer Computa- tions, pages 85-103. Springer US, 1972.
  13. [Kuhn, 1955] H.W. Kuhn. The Hungarian method for the assignment problem. Naval Research Logistics Quarterly, 2(1-2):83-97, 1955.
  14. [Lin et al., 2010] D. Lin, E. Grimson, and J. Fisher. Con- struction of dependent Dirichlet processes based on Pois- son processes. In Advances in Neural Information Pro- cessing Systems, 2010.
  15. [Lin, 2012] D. Lin. Generative Modeling of Dynamic Visual Scenes. PhD thesis, Massachusetts Institute of Technol- ogy, 2012.
  16. [Luo et al., 2015] W. Luo, B. Stenger, X. Zhao, and T.-K. Kim. Automatic topic discovery for multi-object tracking. In AAAI Conference on Artificial Intelligence, 2015.
  17. [MacEachern, 1999] S.N. MacEachern. Dependent nonpara- metric processes. In ASA Section on Bayesian Statistics, 1999.
  18. [MacEachern, 2000] S.N. MacEachern. Dependent Dirichlet processes. Technical report, Ohio State University, 2000.
  19. [Munkres, 1957] J. Munkres. Algorithms for the assignment and transportation problems. Journal of the Society for Industrial and Applied Mathematics, 5(1):32-38, 1957.
  20. [Murty, 1968] K.G. Murty. An algorithm for ranking all the assignments in order of increasing cost. Operations Re- search, 16(3):682-687, 1968.
  21. [Neal, 2000] R.M. Neal. Markov chain sampling methods for Dirichlet process mixture models. Journal of Compu- tational and Graphical Statistics, 9(2):249-265, 2000.
  22. [Neiswanger et al., 2014] W. Neiswanger, F. Wood, and E.P. Xing. The dependent Dirichlet process mixture of objects for detection-free tracking and object modeling. In Inter- national Conference on Artificial Intelligence and Statis- tics, 2014.
  23. [Oh et al., 2009] S. Oh, S. Russell, and S. Sastry. Markov chain Monte Carlo data association for multi-target track- ing. IEEE Transactions on Automatic Control, 54(3):481- 497, 2009.
  24. [Pasula et al., 1999] H. Pasula, S. Russell, M. Ostland, and Y. Ritov. Tracking many objects with many sensors. In International Joint Conference on Artificial Intelligence, 1999. IJCAI
  25. [Rauch et al., 1965] H.E. Rauch, F. Tung, and C.T. Striebel. Maximum likelihood estimates of linear dynamic systems. AIAA Journal, 3(8):1445-1450, 1965.
  26. [Reid, 1979] D.B. Reid. An algorithm for tracking mul- tiple targets. IEEE Transactions on Automatic Control, 24(6):843-854, 1979.
  27. [Teh, 2010] Y.W. Teh. Dirichlet processes. In C. Sammut and G.I. Webb, editors, Encyclopedia of Machine Learn- ing, pages 280-287. Springer US, 2010.
  28. [Wong et al., 2015] L.L.S. Wong, L.P. Kaelbling, and T. Lozano-Pérez. Data association for semantic world modeling from partial views. The International Journal of Robotics Research, 34(7):1064-1082, 2015.
  29. [Wong et al., 2016] L.L.S. Wong, T. Kurutach, L.P. Kael- bling, and T. Lozano-Pérez. Object-based world model- ing in semi-static environments with dependent Dirichlet- process mixtures. arXiv:1512.00573 [cs.AI], 2016.
  30. [Zhu et al., 2005] X. Zhu, Z. Ghahramani, and J. Lafferty. Time-sensitive Dirichlet process mixture models. Techni- cal report, Carnegie Mellon University, 2005.

References were extracted automatically from the PDF and may contain errors.

Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards