Semi-supervised Learning for the Positioning of a Smartphone-based Robot

스마트폰 로봇의 위치 인식을 위한 준 지도식 학습 기법

  • Yoo, Jaehyun (School of Mechanical and Aerospace Engineering, Seoul National University) ;
  • Kim, H. Jin (School of Mechanical and Aerospace Engineering, Seoul National University)
  • 유재현 (서울대학교 기계항공공학부 항공우주신기술연구소) ;
  • 김현진 (서울대학교 기계항공공학부 항공우주신기술연구소)
  • Received : 2014.11.17
  • Accepted : 2015.03.31
  • Published : 2015.06.01


Supervised machine learning has become popular in discovering context descriptions from sensor data. However, collecting a large amount of labeled training data in order to guarantee good performance requires a great deal of expense and time. For this reason, semi-supervised learning has recently been developed due to its superior performance despite using only a small number of labeled data. In the existing semi-supervised learning algorithms, unlabeled data are used to build a graph Laplacian in order to represent an intrinsic data geometry. In this paper, we represent the unlabeled data as the spatial-temporal dataset by considering smoothly moving objects over time and space. The developed algorithm is evaluated for position estimation of a smartphone-based robot. In comparison with other state-of-art semi-supervised learning, our algorithm performs more accurate location estimates.


Supported by : 한국연구재단


  1. A. R. Jimenez, F. Seco, J. C. Prieto, and J. Guevara, "Indoor pedestrian navigation using an INS/EKF framework for yaw drift reduction and a foot-mounted IMU," Positioning Navigation and Communication, 2010 7th Workshop on. IEEE, pp. 135-143, 2010.
  2. J. Collin, O. Mezentsev, and G. Lachapelle, "Indoor positioning system using accelerometry and high accuracy heading sensors," Proc. of ION GPS/GNSS 2003 Conference, 2003.
  3. S.-B. Kim, D.-H. Lee, and J.-M. Lee, "Indoor localization scheme of a mobile robot applying RFID technology," Journal of Institute of Control, Robotics and Systems (in Korean), vol. 11, no. 12, pp. 996-1001, 2005.
  4. D.-G. Seo, S.-H. Cho, and J.-M. Lee, "Localization algorithm for a mobile robot using iGS," Journal of Institute of Control, Robotics and Systems (in Korean), vol. 14, no. 3, pp. 242-247, 2008.
  5. L. M. Ni, D. Zhang, and M. R. Souryal, "RFID-based localization and tracking technologies," Wireless Communications, IEEE, vol. 18, no. 2, pp. 45-51, 2011.
  6. G. Retscher, Gunther, "Location determination in indoor environments for pedestrian navigation," Position, Location, And Navigation Symposium, IEEE/ION, 2006.
  7. N. Ravi, P. Shankar, A. Frankel, A. Elgammal, and L. lftode, "Indoor localization using camera phones," Mobile Computing Systems and Applications, 2006.
  8. H. Hile and G. Borriello, "Positioning and orientation in indoor environments using camera phones," IEEE Computer Graphics and Applications, vol. 28, no. 4, pp. 32-39, 2008.
  9. Y. J. Kim and D. H. Kim, "Smart phone based image processing methods for motion detection of a moving object via a network camera," Journal of Institute of Control, Robotics and Systems (in Korean), vol. 19, no.1 pp. 65-71, 2013.
  10. A. S. Paul and E. A. Wan, "RSSI-based indoor localization and tracking using sigma-point kalman smoothers," Selected Topics in Signal Processing, IEEE Journal of, vol. 3, no. 5, pp. 860-873, 2009.
  11. H. S. Ahn and W. Yu, Hyo-Sung, "Environmental-adaptive RSSI-based indoor localization," Automation Science and Engineering, IEEE Transactions on, vol. 6 no. 4, pp. 626-633, 2009.
  12. D. A. Tran and T. Zhang, "Fingerprint-based location tracking with hodrick-prescott filtering," Wireless and Mobile Networking Conference, IEEE, pp. 1-8, 2014.
  13. S. Y. Cho and J. G. Park, "Radio propagation model and spatial correlation method-based efficient database construction for positioning fingerprints," Journal of Institute of Control, Robotics and Systems (in Korean), vol. 20, no. 7, pp. 774-781, 2014.
  14. M. Belkin and P. Niyogi, "Semi-supervised learning on riemannian manifolds," Machine Learning, vol. 56, no. 1-3, pp. 209-239, 2004.
  15. Scholkopf, Bernhard, R. Herbrich, and A. J. Smola, "A generalized representer theorem," Computational Learning Theory, Springer Berlin Heidelberg, 2001.
  16. M. M. Adankon, M. Cheriet, and A. Biem, "Semisupervised least squares support vector machine," Neural Networks, IEEE Transactions on, vol. 20, no. 12, pp. 1858-1870, 2009.
  17. M. O. Ravn and H. Uhlig, "On adjusting the hodrick-prescott filter for the frequency of observations," Review of Economics and Statistics, vol. 84, no. 2, pp. 371-376, 2002.