Mobile Robot Localization via Machine Learning

  • Alexander Kuleshov
  • Alexander Bernstein
  • Evgeny Burnaev
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10358)


We consider an appearance-based robot self-localization problem in the machine learning framework. Using recent manifold learning techniques, we propose a new geometrically motivated solution. The solution includes estimation of the robot localization mapping from the appearance manifold to the robot localization space, as well as estimation of the inverse mapping for image modeling. The latter allows solving the robot localization problem as a Kalman filtering problem.


Machine learning Robotics Mobile robot self-localization Appearance-based learning Manifold learning Regression on manifolds 



The research was supported solely by the Russian Science Foundation grant (project 14-50-00150).


  1. 1.
    Talluri, R., Aggarwal, J.K.: Position estimation techniques for an autonomous mobile robot – A review. In: Chen, C.H., Pau, L.F., Wang, P.S.P. (eds.) Handbook of Pattern Recognition and Computer Vision, chap. 4.4, pp. 769–801. World Scientific, Singapore (1993)Google Scholar
  2. 2.
    Borenstein, J.H., Everett, R., Feng, L., Wehe, D.: Mobile robot positioning: sensors and techniques. J. Robot. Syst. 14, 231–249 (1997)CrossRefGoogle Scholar
  3. 3.
    Candy, J.V.: Model-Based Signal Processing. John Wiley & Sons, Inc., New York (2006)Google Scholar
  4. 4.
    Olson, C.F.: Probabilistic self-localization for mobile robots. IEEE Trans. Robot. Autom. 16(1), 55–66 (2000)CrossRefGoogle Scholar
  5. 5.
    DeSouza, G.N., Kak, A.C.: Vision for mobile robot navigation: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 24(2), 237–267 (2002)CrossRefGoogle Scholar
  6. 6.
    Bonin-Font, F., Ortiz, A., Oliver, G.: Visual navigation for mobile robots: a survey. J. Intell. Rob. Syst. 53(3), 263–296 (2008)CrossRefGoogle Scholar
  7. 7.
    Kröse, B.J.A., Vlassis, N., Bunschoten, R.: Omnidirectional vision for appearance-based robot localization. In: Hager, G.D., Christensen, H.I., Bunke, H., Klein, R. (eds.) Sensor Based Intelligent Robots. LNCS, vol. 2238, pp. 39–50. Springer, Heidelberg (2002). doi: 10.1007/3-540-45993-6_3 CrossRefGoogle Scholar
  8. 8.
    Krose, B.J.A., Vlassis, N., Bunschoten, R., Motomura, Y.: A probabilistic model for appearance-based robot localization. Image Vis. Comput. 19, 381–391 (2001)CrossRefGoogle Scholar
  9. 9.
    Saito, M., Kitaguchi, K.: Appearance based robot localization using regression models. In: Proceedings of 4th IFAC-Symposium on Mechatronic Systems, vol. 2, pp. 584–589 (2006)Google Scholar
  10. 10.
    Hamm, J., Lin, Y., Lee, D.D.: Learning nonlinear appearance manifolds for robot localization. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2005), pp. 1239–1244 (2005)Google Scholar
  11. 11.
    Crowley, J.L., Pourraz, F.: Continuity properties of the appearance manifold for mobile robot position estimation. Image Vis. Comput. 19(11), 741–752 (2001)CrossRefGoogle Scholar
  12. 12.
    Pauli, J.: Learning-Based Robot Vision. LNCS, vol. 2048, 292 p. Springer, Heidelberg (2001)Google Scholar
  13. 13.
    Oore, S., Hinton, G.E., Dudek, G.: A mobile robot that learns its place. Neural Comput. 9, 683–699 (1997)CrossRefGoogle Scholar
  14. 14.
    Thrun, S.: Bayesian landmark learning for mobile robot localization. Mach. Learn. 33(1), 41–76 (1998)CrossRefMATHGoogle Scholar
  15. 15.
    Krose, B.J.A., Bunschoten, R.: Probabilistic localization by appearance models and active vision. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA 1999), Detroit, Michigan, pp. 2255–2260 (1999)Google Scholar
  16. 16.
    Vlassis, N., Krose, B.J.A.: Robot environment modeling via principal component regression. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 1999), pp. 677–682 (1999)Google Scholar
  17. 17.
    Se, S., Lowe, D., Little, J.: Local and global localization for mobile robots using visual landmarks. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2001), pp. 414–420 (2001)Google Scholar
  18. 18.
    Hayet, J., Lerasle, F., Devy, M.: Visual landmarks detection and recognition for mobile robot navigation. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2003), vol. 2, pp. 313–318 (2003)Google Scholar
  19. 19.
    Bunschoten, R., Krose, B.J.A.: 3-D scene reconstruction from cylindrical panoramic images. In Proceedings of the 9th International Symposium on Intelligent Robotic Systems (SIRS-2001), pp. 199–205 (2001)Google Scholar
  20. 20.
    Gluckman, J., Nayar, S.K.: Ego-motion and omnidirectional cameras. In: Proceedings of the Sixth International Conference on Computer Vision (ICCV 1998), pp. 999–1005 (1998)Google Scholar
  21. 21.
    Colin de Verdiere, V., Crowley, J.L.: Local appearance space for recognition of navigation landmarks. J. Robot. Auton. Syst. 32(1–2), 61–89 (2000)CrossRefGoogle Scholar
  22. 22.
    Dudek, G., Jugessur, D.: Robust place recognition using local appearance based methods. In: Proceedings of the International Conference on Robotics and Automation (ICRA 2000), pp. 1030–1035 (2000)Google Scholar
  23. 23.
    Betke, M., Gurvits, L.: Mobile robot localization using landmarks. IEEE Trans. Robot. Autom. 13, 251–263 (1997)CrossRefGoogle Scholar
  24. 24.
    Sugihara, K.: Some location problems for robot navigation using a single camera. Comput. Vis. Graph. Image Process. 42, 112–129 (1988)CrossRefGoogle Scholar
  25. 25.
    Sim, R., Dudek, G.: Robot positioning using learned landmarks. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 1998), vol. 2, pp. 1060–1065 (1998)Google Scholar
  26. 26.
    Friedman, A.: Robot localization using landmarks. In: Mathematics in Industrial Problems. The IMA Volumes in Mathematics and its Applications, vol. 67(7), pp. 86–94. Springer, New York (1995)Google Scholar
  27. 27.
    Jogan, M., Leonardis, A.: Robust localization using panoramic view-based recognition. In: Proceedings of the 15th International Conference on Pattern Recognition (ICPR 2000), pp. 136–139. IEEE Computer Society (2000)Google Scholar
  28. 28.
    Vlassis, N., Motomura, Y., Krse, B.J.A.: Supervised dimension reduction of intrinsically low-dimensional data. Neural Comput. 14(1), 191–215 (2002)Google Scholar
  29. 29.
    Se, S., Lowe, D., Little, J.: Vision-based global localization and mapping for mobile robots. IEEE Trans. Rob. 21(3), 364–375 (2005)CrossRefGoogle Scholar
  30. 30.
    Cobzas, D., Zhang, H.: Cylindrical panoramic image-based model for robot localization. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Maui, HI, pp. 1924–1930 (2001)Google Scholar
  31. 31.
    Crowley, J.L., Wallner, F., Schiele, B.: Position estimation using principal components of range data. In: Proceedings of the 1998 IEEE International Conference on Robotics and Automation, vol. 4, pp. 3121–3128 (1998)Google Scholar
  32. 32.
    Jollie, T.: Principal Component Analysis. Springer, New-York (2002)Google Scholar
  33. 33.
    Peres-Neto, P.R., Jackson, D.A., Somers, K.M.: How many principal components? stopping rules for determining the number of non-trivial axes revisited. Comput. Stat. Data Anal. 49(4), 974–997 (2005)MathSciNetCrossRefMATHGoogle Scholar
  34. 34.
    Härdle, W.K., Simar, L.: Canonical correlation analysis. In: Applied Multivariate Statistical Analysis, pp. 443–454. Springer, Heidelberg (2015). doi: 10.1007/978-3-662-45171-7_16 Google Scholar
  35. 35.
    Melzer, T., Reiter, M., Bischof, H.: Appearance models based on kernel canonical correlation analysis. Pattern Recogn. 36(9), 1961–1973 (2003)CrossRefMATHGoogle Scholar
  36. 36.
    Skocaj, D., Leonardis, A.: Appearance-based localization using CCA. In: Proceedings of the of the 9th Computer Vision Winter Workshop (CVWW 2004), pp. 205–214 (2004)Google Scholar
  37. 37.
    Se, S., Lowe, D., Little, J.: Mobile robot localization and mapping with uncertainty using scale-invariant visual landmarks. Int. J. Robot. Res. 21(8), 735–758 (2002)CrossRefGoogle Scholar
  38. 38.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)CrossRefGoogle Scholar
  39. 39.
    Vlassis, N., Motomura, Y., Krose, B.J.A.: Supervised linear feature extraction for mobile robot localization. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA 2000), vol. 4, pp. 2979–2984 (2000)Google Scholar
  40. 40.
    Saul, L.K., Roweis, S.T.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000)CrossRefGoogle Scholar
  41. 41.
    Wang, K., Wang, W., Zhuang, Y.: Appearance-based map learning for mobile robot by using generalized regression neural network. In: Liu, D., Fei, S., Hou, Z.-G., Zhang, H., Sun, C. (eds.) ISNN 2007. LNCS, vol. 4491, pp. 834–842. Springer, Heidelberg (2007). doi: 10.1007/978-3-540-72383-7_97 CrossRefGoogle Scholar
  42. 42.
    Scholkopf, B., Smola, A., Muller, K.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput. 10(5), 1299–1319 (1998)CrossRefGoogle Scholar
  43. 43.
    Wu, H., Wu, Y.-X., Liu, C.-A., Yang, G.-T., Qin, S.-Y.: Fast robot localization approach based on manifold regularization with sparse area features. Cognitive Comput. 8(5), 856–876 (2016)CrossRefGoogle Scholar
  44. 44.
    Do, H.N., Jadaliha, M., Choi, J., Lim, C.Y.: Feature selection for position estimation using an omnidirectional camera. Image Vis. Comput. 39, 1–9 (2015)CrossRefGoogle Scholar
  45. 45.
    Do, H.N., Choi, J., Lim, C.Y., Maiti, T.: Appearance-based localization using Group LASSO regression with an indoor experiment. In: Proceedings of the 2015 IEEE International Conference on Advanced Intelligent Mechatronics (AIM 2015), pp. 984–989 (2015)Google Scholar
  46. 46.
    Do, H.N., Choi, J.: Appearance-based outdoor localization using group lasso regression. In: Proceedings of the ASME Dynamic Systems and Control Conference (DSCC 2015), vol. 3, 8 p. (2015)Google Scholar
  47. 47.
    Tibshirani, R.: Regression shrinkage and selection via the lasso: a retrospective. J. Roy. Stat. Soc.: Ser. B (Methodol.) 73(3), 273–282 (2011)MathSciNetCrossRefGoogle Scholar
  48. 48.
    Ribeiro, M.I.: Kalman and extended Kalman filters: Concept, derivation and properties. Institute for Systems and Robotics, Technical report, 44 p. (2004)Google Scholar
  49. 49.
    Herbert, B., Andreas, E., Tuytelaars, T., Gool, L.V.: Speeded-Up Robust Features (SURF). Comput. Vis. Image Underst. 110(3), 346–359 (2008)CrossRefGoogle Scholar
  50. 50.
    Obozinski, G., Wainwright, M.J., Jordan, M.I., et al.: Support union recovery in high-dimensional multivariate regression. Annal. Stat. 39(1), 1–47 (2011)MathSciNetCrossRefMATHGoogle Scholar
  51. 51.
    Ma, Y., Fu, Y. (eds.): Manifold Learning Theory and Applications. CRC Press, London (2011)Google Scholar
  52. 52.
    Kuleshov, A.P., Bernstein, A.V.: Manifold learning in data mining tasks. In: Perner, P. (ed.) MLDM 2014. LNCS, vol. 8556, pp. 119–133. Springer, Heidelberg (2014)Google Scholar
  53. 53.
    Kuleshov, A.P., Bernstein, A.V.: Statistical learning on manifold-valued data. In: Perner, P. (ed.) MLDM 2016. LNCS, vol. 9729, pp. 311–325. Springer International Publishing, Switzerland (2016)Google Scholar
  54. 54.
    Stone, C.J.: Optimal rates of convergence for nonparametric estimators. Ann. Stat. 8, 1348–1360 (1980)MathSciNetCrossRefMATHGoogle Scholar
  55. 55.
    Stone, C.J.: Optimal global rates of convergence for nonparametric regression. Ann. Stat. 10, 1040–1053 (1982)MathSciNetCrossRefMATHGoogle Scholar
  56. 56.
    Lee, J.M.: Manifolds and Differential Geometry. Graduate Studies in Mathematics, vol. 107. American Mathematical Society, Providence (2009)Google Scholar
  57. 57.
    Lee, J.M.: Introduction to Smooth Manifolds. Springer, New York (2003)CrossRefGoogle Scholar
  58. 58.
    Bernstein, A.V., Kuleshov, A.P.: Tangent bundle manifold learning via Grass-mann & Stiefel eigenmaps. In: arxiv:1212.6031v1 [cs.LG], pp. 1–25 (2012), December 2012
  59. 59.
    Bernstein, A.V., Kuleshov, A.P.: Manifold Learning: generalizing ability and tangent proximity. Int. J. Softw. Inf. 7(3), 359–390 (2013)Google Scholar
  60. 60.
    Kuleshov, A., Bernstein, A.: Incremental construction of low-dimensional data representations. In: Schwenker, F., Abbas, H.M., El Gayar, N., Trentin, E. (eds.) ANNPR 2016. LNCS, vol. 9896, pp. 55–67. Springer, Cham (2016). doi: 10.1007/978-3-319-46182-3_5 CrossRefGoogle Scholar
  61. 61.
    Golub, G.H., Van Loan, C.F.: Matrix Computation, 3rd edn. Johns Hopkins University Press, Baltimore (1996)MATHGoogle Scholar
  62. 62.
    Kuleshov, A.P., Bernstein, A.V.: Regression on high-dimensional inputs. In: Workshops Proceedings volume of the IEEE International Conference on Data Mining (ICDM 2016), pp. 732–739. IEEE Computer Society, USA (2016)Google Scholar
  63. 63.
    Burnaev, E., Belyaev, M., Kapushev, E.: Computationally efficient algorithm for Gaussian Processes based regression in case of structured samples. Comput. Math. Math. Phys. 56(4), 499–513 (2016)MathSciNetCrossRefMATHGoogle Scholar
  64. 64.
    Burnaev, E., Panov, M., Zaytsev, A.: Regression on the basis of nonstationary Gaussian processes with Bayesian regularization. J. Commun. Technol. Electron. 61(6), 661–671 (2016)CrossRefGoogle Scholar
  65. 65.
    Burnaev, E., Zaytsev, A.: Surrogate modeling of mutlifidelity data for large samples. J. Commun. Technol. Electron. 60(12), 1348–1355 (2016)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Alexander Kuleshov
    • 1
  • Alexander Bernstein
    • 1
    • 2
  • Evgeny Burnaev
    • 1
    • 2
  1. 1.Skolkovo Institute of Science and TechnologyMoscowRussia
  2. 2.Kharkevich Institute for Information Transmission Problems RASMoscowRussia

Personalised recommendations