Intelligent system modelling of a three-dimensional ultrasonic positioning system using neural networks and genetic algorithms

Abstract

This paper presents a neural network model for a three-dimensional ultrasonic position estimation system that uses the difference in the time of arrivals of waves from a transmitter to various receivers. Even though a linearized analytical model for the three-dimensional system exists and is currently being used to estimate the position of the transmitter, its accuracy is highly dependent on complex and time consuming signal conditioning. A neural network approach is developed to train the system based on unconditioned training sets obtained directly from the receivers. It is proposed to use the final trained system to estimate the three-dimensional position in real time using these raw signals, thereby simplifying the hardware and the computational software as well as increasing the update rate. The weights of the neural network are obtained from a traditional back-progation method and by using genetic algorithms. Results for one-, two- and three-dimensional systems are presented as proof of concept. The performance of the neural network model using the raw signals is shown to be comparable to the analytical model using conditioned signals. Further, it is shown that the neural network model is extremely robust in terms of providing accurate position estimates, even after loss of information from multiple receivers. This work has significant applications in robotics, autonomous systems, virtual reality and image-guided surgery.

Keywords

three-dimensional positioning triangulation ultrasonics neural networks genetic algorithms robotics intelligent systems

Get full access to this article

View all access options for this article.

References

Milliken

R. J.

Zoller

C. J.

Principle of operation of NAVSTAR and system characteristics. Navigation, Summer 1978, 25 (2), 95–106.

Rathbone

R. R.A.

Kindlmann

P. J.

Beacon-referenced dead reckoning: A versatile guidance system

Robotics Engng, 1988, 8 (12), 11–16.

Miller

G. L.

Wagner

E. R.

An optical Rangefinder for autonomous robot cart navigation. In Mobile Robots II, 1988, Vol. 852 (Society of Photo-Optical Instrumentation Engineers, Bellingham, Washington).

Hongo

Arakawa

Sugimoto

Tange

Yamamoto

In Proceedings of the IEEE/SICE International Conference on Industrial, Electronic and Control Instumentation

(ICON ‘85), San Francisco, California, 18–22 November 1985, p. 535.

Aggarwal

J. K.

Nandhakumar

On the computation of motion from sequence of images-a review. Proc. IEEE, August 1988, 76 (8), 917–935.

Biber

Elkin

Shenk

Stempeck

The Polaroid ultrasonic ranging system. In 67th Convention of the Audio Engineering Society, New York, 31 October-3 November 1980, Technical paper 1696(A-8).

Wehn

H. W.

Belanger

P. R.

Ultrasound-based robot position estimation. IEEE Trans. Robotics and Automn, October 1997, 13 (5), 682–692.

Figueroa

Mahajan

A robust method to determine the coordinates of a wave source for 3-D position sensing. Trans. ASME, J. Dynamic Systems, Measmts, and Control, September 1994, 116, 505–511.

Mahajan

Figueroa

An automatic self installation and calibration method for a 3D position sensing system using ultrasonics. Robotics and Autonomous Systems, 1999, 28 (4), 281–294.

10.

Mahajan

Walworth

3D position sensing using the difference in time-of-flights to various receivers from a single transmitter of wave energy. IEEE Trans. Robotics and Automn, February 2001, 17 (1), 91–94.

11.

Ljung

System Identification-Theory for the User, 1987 (Prentice-Hall, Englewood Cliffs, New Jersey).

12.

Juang

J.-N.

Applied System Identification, 1994 (PRT Prentice-Hall, Englewood Cliffs, New Jersey).

13.

Gustavsson

Ljung

Soderstrom

Survey paper identification of processes in closed-loop-identifiability and accuracy aspects. Automatica, 1977, 13, 59–75.

14.

Chen

C. W.

Juang

J.-N.

Huang

J.-K.

Adaptive linear identification and state estimation. In Control and Dynamic Systems: Advances in Theory and Applications, Vol. 57, Multidisciplinary Engineering Systems: Design and Optimization Techniques and Their Application (Ed. Leondes

C. T.

), 1993, pp. 331–368 (Academic Press, New York).

15.

Huang

J.-K.

Hsiao

M.-H.

Cox

D. E.

Indirect identification of linear stochastic systems with known feedback dynamics. J. Guidance, Control, and Dynamics, 1996, 19 (4), 836–841.

16.

Huang

J.-K.

Lee

H. C.

Schoen

M. P.

Hsiao

M.-H.

State-space system identification from closed-loop frequency response data. J. Guidance, Control, and Dynamics, 1996, 19 (6), 1378–1380.

17.

Rooij

A. J. F.

Jain

L. C.

Johnson

R. P.

Neural network training using genetic algorithms. Series in Machine Perception Artificial Intelligence, 1996, Vol. 26 (World Scientific, New Jersey).

18.

Unnikrishnan

Ray

P. K.

Mahajan

Chu

Accuracy considerations in a 3D ultrasonic positioning system that uses the difference in time-of-flights. Trans. ASME, Dynamic Systems, Measmts, and Control, December 2002, 124 (4), 688–693.

19.

Deigman

P. B.

Jr. Meckl

P. H.

Franchek

Abraham

Jaliwala

Using mutual information to preprocess input data for a virtual sensor. In Proceedings of the American Control Conference, Chicago, Illinois, June 2000.

20.

Figueroa

J. F.

Lamancusa

A method for accurate detection of time-of-arrival analysis and design of an ultrasonic ranging system. J. Acoust. Soc. Am., January 1992, 91 (1), 486–494.