An Effective Mapping for a Mobile Robot using Error Backpropagation based Sensor Fusion

오류 역전파 신경망 기반의 센서융합을 이용한 이동로봇의 효율적인 지도 작성

  • Received : 2010.12.24
  • Accepted : 2010.04.07
  • Published : 2011.09.01

Abstract

This paper proposes a novel method based on error back propagation neural networks to fuse laser sensor data and ultrasonic sensor data for enhancing the accuracy of mapping. For navigation of single robot, the robot has to know its initial position and accurate environment information around it. However, due to the inherent properties of sensors, each sensor has its own advantages and drawbacks. In our system, the robot equipped with seven ultrasonic sensors and a laser sensor navigates to map two different corridor environments. The experimental results show the effectiveness of the heterogeneous sensor fusion using an error backpropagation algorithm for mapping.

Keywords

Acknowledgement

Supported by : 한국과학재단

References

  1. Salinas, R. A. and Abidi, M. A., "Data Fusion: Color Edge Detection and Surface Reconstruction through Regularization," IEEE Transactions on Industrial Electronics, Vol. 43, No. 3, pp. 355-363, 1996. https://doi.org/10.1109/41.499807
  2. Ruo, R. C. and Kay, M. G., "Multisensor Integration and Fusion in Intelligent System," IEEE Transaction on Systems, Man, and Cybernetics, Vol. 19, No. 5, pp. 901-931, 1989. https://doi.org/10.1109/21.44007
  3. Kam, M., Zhu, X. and Kalata, P., "Sensor Fusion for Mobile Robot Navigation," Proceedings of the IEEE, Vol. 85, No. 1, pp. 108-119, 1997. https://doi.org/10.1109/JPROC.1997.554212
  4. Hall, D. L. and Llinas, J., "An Introduction to Multisensor Data Fusion," Proceedings of the IEEE, Vol. 85, No. 1, pp. 6-23, 1997. https://doi.org/10.1109/5.554205
  5. Song, K. T. and Tang, W. H., "Environment Perception for a Mobile Robot Using Double Ultrasonic Sensors and a CCD Camera," IEEE Transactions on Industrial Electronics, Vol. 43, No. 3, pp. 372-379, 1996. https://doi.org/10.1109/41.499809
  6. Wei, S. C., Yagi, Y. and Yachida, M., "Building Local Floor Map by Use of Ultrasonic and Omni-directal Vision Sensor," Proceedings of IEEE International Conference on Robotics and Automation, pp. 2548- 2553, 1998.
  7. Matthies, L. and Elfes, A., "Integration of Sonar and Streo Range Data Using a Grid-Based Representation," Proceedings of IEEE International Conference on Robotics and Automation, pp. 727- 733, 1988.
  8. Wallner, F., Graf, R. and Dillmann, R., "Real-time Map Refinement by Use of Sonar and Active Streovision," Proceedings of IEEE International Conference on Robotics and Autonomous Systems, Vol. 3, pp. 2968-2973, 1995.
  9. Akbarally, H. and Kleeman, L., "3D Robot Sensing from Sonar and vision," Proceedings of IEEE International Conference on Robotics and Automation, pp. 686-691, 1996.
  10. Neira, J., Tardos, J. D., Horn, J. and Schmidt, G., "Fusing Range and Intensity Images for Mobile Robot Localization," IEEE Transactions on Robotics and Automation, Vol. 15, No. 1, pp. 76-84, 1999. https://doi.org/10.1109/70.744604
  11. Dudek, G., Freedman, P. and Rekleitis, I. M., "Just-intime Sensing: Efficiently Combining Sonar and Laser Range Data for Exploring Unknown Worlds," Proceedings of IEEE International Conference on Robotics and Automation, pp. 667-672, 1996.
  12. Lazzizzera, I., Tecchiolli, G., Lee, P., Zorat, A. and Sartori, A., "Fast and Compact Controllers with Digital Neural Networks," IEEE Instrumentation and Measurement Technology Conference, pp. 226-231, 1997.
  13. Kim, K. B., Shin, J. P. and Cha, E. Y., "An Accelerated Error Backpropagation Algorithm by Neuron Structure," Korea Computer Congress, Vol. 19, No. 2, pp. 1061-1064, 1992.
  14. Perugini, N. K. and Engeler, W. E., "Neural Network Learning Time : Effects of Network and Training Set Size," International Joint Conference on Neural Networks, Vol. 2, pp. 395-401, 1989.
  15. Tran, V. H. and Lee, S. G., "Enhanced wavelet-based Methods for Reducing Complexity and Calculation Time in Sonar Measurements," International Journal of Precision Engineering and Manufacturing, Vol. 10, No. 2, pp. 31-37, 2009. https://doi.org/10.1007/s12541-009-0024-1