Radar Localization with multiple Unmanned Aerial Vehicles using Support Vector Regression

This paper presents a first attempt to solve the geolocation problem using support vector regression (SVR). This paper proposes a method to pinpoint the location of stationary, hostile radar using the time difference of arrival (TDoA) of the same characteristic pulse emitted by the radar at 3 different unmanned aerial vehicles (UAVs) flying in a fixed triangular formation. The performance of the proposed SVR method is compared with a variation of the Taylor series method (TSM) used for solving the same problem and currently deployed by the DSTO, Australia on the Aerosonde Mark III UAVs. The robustness to error of the SVR method is explored and compared with the TSM. Extended applications of the SVR approach to more general localization scenarios in wireless sensor networks are proposed for further work

[1]  Don Torrieri,et al.  Statistical Theory of Passive Location Systems , 1984, IEEE Transactions on Aerospace and Electronic Systems.

[2]  J. Smith,et al.  The spherical interpolation method for closed-form passive source localization using range difference measurements , 1987, ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3]  K. C. Ho,et al.  A simple and efficient estimator for hyperbolic location , 1994, IEEE Trans. Signal Process..

[4]  Kutluyil Dogançay,et al.  Geolocation by time difference of arrival using hyperbolic asymptotes , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5]  Marimuthu Palaniswami,et al.  Incremental training of support vector machines , 2005, IEEE Transactions on Neural Networks.

[6]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[7]  WADE FOY,et al.  Position-Location Solutions by Taylor-Series Estimation , 1976, IEEE Transactions on Aerospace and Electronic Systems.

[8]  J. Abel.  A divide and conquer approach to least-squares estimation , 1990 .

[9]  Chunlei Zhang,et al.  Mobile target tracking with communication delays , 2004, 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601).

[10]  Marimuthu Palaniswami,et al.  Adaptive support vector machines for regression , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[11]  M. Palaniswami.  A Modified ν-SV Method For Simplified Regression , 2006 .