Skip to main content
SpringerLink
Log in

Fast Robot Localization Approach Based on Manifold Regularization with Sparse Area Features

  • Published:
Cognitive Computation Aims and scope Submit manuscript

Abstract

Background/Introduction

Robot localization can be considered as a cognition process that takes place during a robot estimating metric coordinates with vision. It provides a natural method for revealing the true autonomy of robots. In this paper, a kernel principal component analysis (PCA)-regularized least-square algorithm for robot localization with uncalibrated monocular visual information is presented. Our system is the first to use a manifold regularization strategy in robot localization, which achieves real-time localization using a harmonic function.

Methods

The core idea is to incorporate labelled and unlabelled observation data in offline training to generate a regression model smoothed by the intrinsic manifold embedded in area feature vectors. The harmonic function is employed to solve the online localization of new observations. Our key contributions include semi-supervised learning techniques for robot localization, the discovery and use of the visual manifold learned by kernel PCA and some solutions for simultaneous parameter selection. This simultaneous localization and mapping (SLAM) system combines dimension reduction methods, manifold regularization techniques and parameter selection to provide a paradigm of SLAM having self-contained theoretical foundations.

Results and Conclusions

In extensive experiments, we evaluate the localization errors from the perspective of reducing implementation and application difficulties in feature selection and magnitude ratio determination of labelled and unlabelled data. Then, a nonlinear optimization algorithm is adopted for simultaneous parameter selection. Our online localization algorithm outperformed the state-of-the-art appearance-based SLAM algorithms at a processing rate of 30 Hz for new data on a standard PC with a camera.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20

Similar content being viewed by others

Notes

  1. The observation matrix is mean centred and the Gaussian RBF kernel function is \(K({\text{obv}}_i,{\text{obv}}_j)=\exp (-\sigma \Vert {\text{obv}}_i-{\text{obv}}_j\Vert ^2)\), where  \(\sigma =200\).

References

  1. Ahn S, Choi J, Doh N, Chung W. A practical approach for EKF-SLAM in an indoor environment: fusing ultrasonic sensors and stereo camera. Auton Robots. 2008;24(3):315–35.

    Article  Google Scholar 

  2. Andreasson H, Duckett T, Lilienthal AJ. A minimalistic approach to appearance-based visual SLAM. IEEE Trans Robot. 2008;24(5):991–1001.

    Article  Google Scholar 

  3. Angeli A, Filliat D, Doncieux S, Meyer JA. Fast and incremental method for loop-closure detection using bags of visual words. IEEE Trans Robot. 2008;24(5):1027–37.

    Article  Google Scholar 

  4. Bailey T, Durrant-Whyte H. Simultaneous localization and mapping (SLAM): part ii. IEEE Robot Autom Mag. 2006;13(3):108–17.

    Article  Google Scholar 

  5. Belkin M, Niyogi P. Laplacian eigenmaps and spectral techniques for embedding and clustering. Adv Neural Inf Process Syst. 2002;14:585–91.

    Google Scholar 

  6. Belkin M, Niyogi P, Sindhwani V. Manifold regularization: a geometric framework for learning from examples. Technical report. 2004.

  7. Belkin M, Niyogi P, Sindhwani V. Manifold regularization: a geometric framework for learning from labeled and unlabeled examples. J Mach Learn Res. 2006;7:2399–434.

    Google Scholar 

  8. Bellotto N, Burn K, Fletcher E, Wermter S. Appearance-based localization for mobile robots using digital zoom and visual compass. Robot Auton Syst. 2008;56(2):143–56.

    Article  Google Scholar 

  9. Bowling M, Ghodsi A, Wilkinson D. Action respecting embedding. In: Proceedings of the 22nd international conference on machine learning. 2005. p. 65–72.

  10. Chung FRK. Spectral graph theory (CBMS regional conference series in mathematics, No. 92). American Mathematical Society. http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20&path=ASIN/0821803158. 1997.

  11. Cummins M, Newman P. Appearance-only SLAM at large scale with FAB-MAP 2.0. Int J Robot Res. 2011;30(9):1100–23.

    Article  Google Scholar 

  12. Dai G, Yeung DY. Kernel selection for semi-supervised kernel machines. In: Proceedings of the 24th international conference on machine learning. Vol. 1273520. Corvalis: ACM; 2007. p. 185–192.

  13. Davison AJ, Reid ID, Molton ND, Stasse OASO. MonoSLAM: real-time single camera SLAM. IEEE Trans Pattern Anal Mach Intell. 2007;29(6):1052–67.

    Article  PubMed  Google Scholar 

  14. Durrant-Whyte H, Bailey T. Simultaneous localization and mapping: part i. IEEE Robot Autom Mag. 2006;13(2):99–110.

    Article  Google Scholar 

  15. Eade E, Drummond T. Edge landmarks in monocular SLAM. Image Vision Comput. 2009;27(5):588–96.

    Article  Google Scholar 

  16. Frese U. A discussion of simultaneous localization and mapping. Auton Robots. 2006;20(1):25–42, 52.

    Article  Google Scholar 

  17. Ham J, Lee DD, Mika S, Schölkopf B. A kernel view of the dimensionality reduction of manifolds. In: Proceedings of the twenty-first international conference on machine learning. ACM; 2004. p 47.

  18. Ham J, Lin Y, Lee DD. Learning nonlinear appearance manifolds for robot localization. In: Proceedings of 2005 IEEE/RSJ international conference on intelligent robots and systems (IROS). 2005. p. 2971–2976.

  19. Hartley RI, Zisserman A. Multiple view geometry in computer vision. 2nd ed. Cambridge: Cambridge University Press; 2004. ISBN: 0521540518.

    Book  Google Scholar 

  20. Hastie T, Tibshirani R, Friedman JH. The elements of statistical learning. Berlin: Springer; 2001.

    Book  Google Scholar 

  21. Ho KL, Newman P. Detecting loop closure with scene sequences. Int J Comput Vis. 2007;74(3):261–86.

    Article  Google Scholar 

  22. Hussain A. Cognitive computation: an introduction. Cogn Comput. 2009;1(1):1–3. doi:10.1007/s12559-009-9013-z.

    Article  Google Scholar 

  23. Hussain A, Niazi M. Toward a formal, visual framework of emergent cognitive development of scholars. Cogn Comput. 2013;6(1):113–24. doi:10.1007/s12559-013-9219-y.

    Article  Google Scholar 

  24. Kim J, Yoon KJ, Kweon IS. Bayesian filtering for keyframe-based visual SLAM. Int J Robot Res. 2015;34(4–5):517–31.

    Article  Google Scholar 

  25. Labrosse F. The visual compass: performance and limitations of an appearance-based method. J Field Robot. 2006;23(10):913–41.

    Article  Google Scholar 

  26. Linåker F, Ishikawa M. Real-time appearance-based Monte Carlo localization. Robot Auton Syst. 2006;54(3):205–20.

    Article  Google Scholar 

  27. Ma Y, Soatto S, Kosecka J, Sastry S. An invitation to 3-D vision: from images to geometric models. Berlin: Springer; 2005.

    Google Scholar 

  28. Mahon I, Williams SB, Pizarro O, Johnson-Roberson M. Efficient view-based SLAM using visual loop closures. IEEE Trans Robot. 2008;24(5):1002–14.

    Article  Google Scholar 

  29. Majdik AL, Verda D, Albers-Schoenberg Y, Scaramuzza D. Air-ground matching: appearance-based GPS-denied urban localization of micro aerial vehicles. J Field Robot. 2015;32(7):1015–39. doi:10.1002/rob.21585.

    Article  Google Scholar 

  30. Mordohai P, Medioni G. Dimensionality estimation, manifold learning and function approximation using tensor voting. J Mach Learn Res. 2010;11:411–50.

    Google Scholar 

  31. Murillo AC, Guerrero JJ, Sagues C. Surf features for efficient robot localization with omnidirectional images. In: IEEE international conference on robotics and automation. 2007. p. 3901–3907

  32. Pan JJ, Yang Q, Pan SJ. Online co-localization in indoor wireless networks by dimension reduction. Proc Natl Conf Artif Intell. 2007;22(2):1102.

    Google Scholar 

  33. Rosset S, Zhu J. Piecewise linear regularized solution paths. Ann Stat. 2007;35(3):1012.

    Article  Google Scholar 

  34. Scaramuzza D, Siegwart R. Appearance-guided monocular omnidirectional visual odometry for outdoor ground vehicles. IEEE Trans Robot. 2008;24(5):1015–26.

    Article  Google Scholar 

  35. Schmidt A, Kraft M. The impact of the image feature detector and descriptor choice on visual SLAM accuracy. In: Choraś RS, editor. Advances in intelligent systems and computing, vol 313. Berlin: Springer; 2015. doi:10.1007/978-3-319-10662-5_25.

    Google Scholar 

  36. Schölkopf B, Smola A, Müller KR. Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput. 1998;10(5):1299–319.

    Article  Google Scholar 

  37. Sindhwani V, Belkin M, Niyogi P. Geometric basis of semi-supervised learning. In: Chapelle O, Schölkopf B, Zien A, editors. Semi-supervised learning. Cambridge: MIT Press; 2006. p. 209–26.

    Google Scholar 

  38. Song D, Tao D. Biologically inspired feature manifold for scene classification. IEEE Trans Image Process. 2010;19(1):174–84. doi:10.1109/TIP.2009.2032939.

    Article  PubMed  Google Scholar 

  39. Song Y, Li Q, Kang Y. Conjugate unscented fastSLAM for autonomous mobile robots in large-scale environments. Cogn Comput. 2014;6(3):496–509. doi:10.1007/s12559-014-9258-z.

    Article  Google Scholar 

  40. Sternberg RJ. Cognitive psychology. Orlando, FL: Harcourt Brace College Publishers Cognitive; 2008. http://psycnet.apa.org/psycinfo/1996-97250-000.

    Google Scholar 

  41. Tsai R. A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses. IEEE J Robot Autom. 1987;3(4):323–44.

    Article  Google Scholar 

  42. Tu Z, Chen X, Yuille A, Zhu S. Image parsing: unifying segmentation, detection, and recognition. Int J Comput Vis. 2005;63(2):113–40.

    Article  Google Scholar 

  43. Vishwanathan SVN, Schraudolph NN, Kondor R, Borgwardt KM. Graph kernels. J Mach Learn Res. 2010;11:1201–42.

    Google Scholar 

  44. Wang G, Yeung D, Lochovsky F. The kernel path in kernelized LASSO. In: ICML 2007, Corvallis, OR, USA. 2007.

  45. Watt R, Morgan M. A theory of the primitive spatial code in human vision. Vis Res. 1985;25(11):1661–74.

    Article  CAS  PubMed  Google Scholar 

  46. Wikipedia. Visual perception—Wikipedia, the free encyclopedia. 2015. https://en.wikipedia.org/wiki/Visual_perception. Accessed 20 Dec 2015.

  47. Wu H, Qin SY. An approach to robot SLAM based on incremental appearance learning with omnidirectional vision. Int J Syst Sci. 2011;42(3):407–27.

    Article  Google Scholar 

  48. Wu Y, Wu H, Yang G, Liu C. Visual data driven approach for metric localization in substation. Chinese J Electron. 2015;24(4):795–801.

    Article  Google Scholar 

  49. Zhang H, Liu Y, Tan J. Loop closing detection in RGB-D SLAM combining appearance and geometric constraints. Sensors. 2015;15(6):14639–60.

    Article  PubMed  PubMed Central  Google Scholar 

  50. Zhang X, Lee W. Hyperparameter learning for graph based semi-supervised learning algorithms. Adv Neural Inf Process Syst. 2007;19:1585.

    Google Scholar 

  51. Zhang Z. A flexible new technique for camera calibration. IEEE Trans Pattern Anal Mach Intell. 2000;22(11):1330–4. doi:10.1109/34.888718.

    Article  Google Scholar 

  52. Zhao J, Du C, Sun H, Liu X, Sun J. Biologically motivated model for outdoor scene classification. Cogn Comput. 2015;7(1):20–33. doi:10.1007/s12559-013-9227-y.

    Article  Google Scholar 

  53. Zheng V, Pan S, Yang Q, Pan J. Transferring multi-device localization models using latent multi-task learning. In: Proceedings of the 23rd AAAI conference on artificial intelligence (AAAI-08), Chicago, Illinois, USA. 2008.

  54. Zhu X, Ghahramani Z, Lafferty J. Semi-supervised learning using gaussian fields and harmonic functions. In: ICML-03, 20th international conference on machine learning. 2003.

Download references

Acknowledgments

This work was supported by the Scientific Research Plan Projects for Higher Schools in Hebei Province (Grant No. QN2015338), the National Natural Science Foundation of China (Grant No. 61105083), the Program for New Century Excellent Talents in University (Grant No. NCET-11-0634), the Program of the Co-Construction with the Beijing Municipality of China (Program No. GJ2013005), the High Tech Research and Development (863) Program of China (Grant No. 2006AA04Z207), the Research Fund for Doctoral Programs of Higher Education of China (Grant No. 20060006018), the International Cooperation Program of Science and Technology of China (Grant No. 2007DFA11530) and the National Natural Science Foundation of China (Grant No. 60875072).

Author information

Authors and Affiliations

  1. School of Control and Computer Engineering, North China Electric Power University, 102206, Beijing, People’s Republic of China

    Hua Wu, Chang-An Liu & Guo-Tian Yang

  2. Department of Disaster Prevention Apparatus, Institute of Disaster Prevention, Langfang, Hebei, People’s Republic of China

    Yan-Xiong Wu

  3. School of Automation Science and Electrical Engineering, Beihang University, Beijing, 100191, People’s Republic of China

    Shi-Yin Qin

Authors
  1. Hua Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yan-Xiong Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chang-An Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Guo-Tian Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Shi-Yin Qin
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hua Wu.

Ethics declarations

Conflict of Interest

Hua Wu, Yan-Xiong Wu, Chang-An Liu, Guo-Tian Yang and Shi-Yin Qin declare that they have no conflict of interest.

Informed Consent

Informed consent was not required as no human or animals were involved.

Human and Animal Rights

This article does not contain any studies with human or animal subjects performed by any of the authors.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wu, H., Wu, YX., Liu, CA. et al. Fast Robot Localization Approach Based on Manifold Regularization with Sparse Area Features. Cogn Comput 8, 856–876 (2016). https://doi.org/10.1007/s12559-016-9427-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12559-016-9427-3

Keywords

Search

Navigation