Skip to main content
SpringerLink
Log in

Enhanced SLAM for a mobile robot using extended Kalman Filter and neural networks

  • Published:
International Journal of Precision Engineering and Manufacturing Aims and scope Submit manuscript

Abstract

This paper presents a Hybrid filter based Simultaneous Localization and Mapping (SLAM) scheme for a mobile robot to compensate for the Extended Kalman Filter (EKF) based SLAM errors inherently caused by its linearization process. The proposed Hybrid filter consists of a Radial Basis Function (RBF) and EKF which is a milestone for SLAM applications. A mobile robot autonomously explores the environment by interpreting the scene, building an appropriate map, and localizing itself relative to this map. A probabilistic approach has dominated the solution to the SLAM problem, which is a fundamental requirement for mobile robot navigation. The proposed approach, based on a Hybrid filter, has some advantages in handling a robotic system with nonlinear dynamics because of the learning property of the neural networks. The simulation and experimental results show the effectiveness of the proposed algorithm comparing with an EKF based SLAM and Multi Layer Perceptron (MLP) method.

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

Similar content being viewed by others

Abbreviations

d :

center of the basis function

g :

the Taylor expansion of function at the motion model

h :

nonlinear measurement function

k :

time step of a mobile robot navigation

m :

vector of a landmark’s pose

n :

number of input nodes

s :

identity of a landmark

u :

input vector

vl :

velocity of robot’s left wheel

vr :

velocity of robot’s right wheel

v k :

average velocity of robot’s wheels

Δv k :

velocity difference between robot’s wheels

w :

weight of the multi layer perceptron

x :

horizontal component of the robot pose

y :

vertical component of the robot pose

z :

measurement vector

ẑ:

estimated measurement vector

α :

number of the first hidden layer’s nodes

β :

number of the second hidden layer’s nodes

γ :

number of output layer’s nodes

δt :

sampling period

θ :

heading angle of the robot

τ :

width of the basis function on the radial basis function algorithm

μ :

mean

\( \bar \mu \) :

prior mean

\( \bar \mu \) :

mean which results from neural network process

Σ :

covariance

\( \bar \Sigma \) :

prior covariance

Π :

vector of estimated measurement of a landmark

G :

Jacobian of g

H :

Jacobian of h

K :

Kalman gain

L :

width between robot’s wheels

M :

covariance matrix of the noise in control space

N :

the number of hidden layer’s nodes on the radial basis function algorithm

Q :

covariance of the additional measurement noise

V :

Jacobian of g

X :

vector of the motion model

Y :

vector of the motion model involving map information

References

  1. Kim, J. M., Kim, Y. T. and Kim, S. S., “An accurate localization for mobile robot using extended Kalman filter and sensor fusion,” IEEE International Joint Conference on Neural Networks, pp. 2928–2933, 2008.

  2. Lee, S. J., Lim, J. H. and Cho, D. W., “Effective Recognition of Environment Using Sonar Ring Data for Localization of a Mobile Robot,” Proceedings of the Korean Society of Precision Engineering Spring Conference, pp. 1–2, 2008.

  3. Kim, G. S., “Perception of small-obstacle using ultrasonic sensors for a mobile robot,” Proceedings of the Korean Society of Precision Engineering Autumn Conference, pp. 21–24, 2004.

  4. Panzieri, S., Pascucci, F. and Setola, R., “Multirobot localisation using interlaced extended Kalman filter,” IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 2816–2821, 2006.

  5. Caron, F., Davy, M., Duflos, E. and Vanheeghe, P., “Particle Filtering for Multisensor Data Fusion With Switching Observation Models: Application to Land Vehicle Positioning,” IEEE Transactions on Signal Processing, Vol. 55,Issue 6, pp. 2703–2719, 2007.

    Article  MathSciNet  Google Scholar 

  6. Lee, S. J., Lim, J. H. and Cho, D. W., “EKF Localization and mapping by using consistent sonar feature with given minimum features,” SICE-ICASE International Joint Conference, pp. 2606–2611, 2006.

  7. Houshangi, N. and Azizi, F., “Accurate mobile robot position determination using unscented Kalman filter,” 2005 Canadian Conference on Electrical and Computer Engineering, pp. 846–851, 2005.

  8. Zhu, J., Zheng, N., Yuan, Z., Zhang, Q. and Zhang, X., “Unscented SLAM with conditional iterations,” 2009 IEEE Intelligent Vehicles Symposium, pp. 134–139, 2009.

  9. Harb, M., Abielmona, R., Naji, K. and Petriul, E., “Neural networks for environmental recognition and navigation of a mobile robot,” IEEE International Instrumentation and Measurement Technology Conference, pp. 1123–1128, 2008.

  10. Zu, L., Wang, H. K. and Yue, F., “Artificial neural networks for mobile robot acquiring heading angle,” Proceedings of the Third International Conference on Machine Laming and Cybemetics, pp. 26–29, 2004.

  11. Bugeja, M. K. and Fabri, S. G., “Multilayer Perceptron Adaptive Dynamic Control for Trajectory Tracking of Mobile Robots,” IEEE Industrial Electronics Annual Conference, pp. 3798–3803, 2006.

  12. Vafaeesefat, A, “Optimum Creep Feed Grinding Process Conditions for Rene 80 Supper Alloy Using Neural network,” Int. J. Precis. Eng. Manuf., Vol. 10, No. 3, pp. 5–11, 2009.

    Article  Google Scholar 

  13. Cho, S. H., “Trajectory Tracking Control of a Pneumatic X-Y Table using Neural Network Based PID Control,” Int. J. Precis. Eng. Manuf., Vol. 10, No. 5, pp. 37–44, 2009.

    Article  Google Scholar 

  14. Choi, M. Y., Sakthivel, R. and Chung, W. K., “Neural networkaided extended Kalman filter for SLAM problem,” IEEE International Conference on Robotics and Automation, pp. 1686–1690, 2007.

  15. Stubberud, S. C., Lobbia, R. N. and Owen, M., “An Adaptive Extended Kalman Filter Using Artificial Neural Networks,” Proceedings of the 34th Conference on Decision & Control, pp. 1852–1856, 1995.

  16. Hu, Y. H. and Hwang, J. N., “Handbook of Neural Network Signal Processing,” CRC Press, pp. 3.1–3.23, 2001.

  17. Jang, P. S., “Neural network based position tracking control of mobile robot,” M.S thesis, Department of Mechatronics, Chungnam National University, pp. 13–37, 2003.

  18. Oh, C. M., “Control of mobile robots using RBF network,” M.S thesis, Department of Electrical Engineering and Computer Science, Korea Advanced Institute of Science and Technology, pp. 4–19, 2003.

  19. Mehra, P. and Wah, B. W., “Artificial neural networks: Concepts and theory,” IEEE Computer Society Press, pp. 13–31, 1992.

  20. Iiguni, Y., Sakai, H. and Tokumaru, H., “A Real-Time Learning Algorithm for a Multilayered Neural Network Based on the Extended Kalman Filter,” IEEE Transactions on Signal Processing, Vol. 40, No. 4, pp. 959–966, 1992.

    Article  Google Scholar 

  21. Thrun, S., Burgard, W. and Fox, D., “Probabilistic Robotics,” The MIT Press, pp. 309–334, 2005.

  22. Bailey, T., Nieto, J., Guivant, J., Stevens, M. and Nebot, E., “Consistency of the EKF-SLAM Algorithm,” IEEE International Conference on Intelligent Robotics and Systems, pp. 3562–3568, 2006.

  23. Bailey, T., http://www-personal.acfr.usyd.edu.au/tbailey.

Download references

Author information

Authors and Affiliations

  1. Electrical Engineering, Yeungnam University, 214-1, Dae-dong, Gyongsan, Gyongbuk, South Korea, 712-749

    Kyung-Sik Choi & Suk-Gyu Lee

Authors
  1. Kyung-Sik Choi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Suk-Gyu Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Suk-Gyu Lee.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Choi, KS., Lee, SG. Enhanced SLAM for a mobile robot using extended Kalman Filter and neural networks. Int. J. Precis. Eng. Manuf. 11, 255–264 (2010). https://doi.org/10.1007/s12541-010-0029-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12541-010-0029-9

Keywords

Search

Navigation