In underwater acoustic localization via matched-field-processing, given a propagation model and a suitable environmental parameterization, one searches for the location (of the transmitter or receiver) whose replica field is closest to the observed one. The high computational complexity of such non-gradient-based optimization methods renders them infeasible for many real-time scenarios, especially when an accurate solution is desired, due to resolution of the search grid required, or as the search dimensionality increases (e.g., when it is necessary to optimize over uncertain environmental parameters such as sound speed or bathymetry). In this work, we propose a ray-based, differentiable model for acoustic propagation for the purpose of a gradient-based optimization for localization. For localization applications in which accurate times of arrivals might not be available, the proposed method can be adapted to work without requiring this information. In such a scenario, it seeks the location (and possibly environmental parameters) that minimize the squared-error between the observed signal and its estimate via the differentiable model. We leverage the PyTorch optimization and auto-differentiation tools for the implementation and demonstrate successful localization on synthetic data inspired from a real-world scenario in a dense multipath environment.
Skip Nav Destination
,
,
,
Article navigation
8 May 2022
184th Meeting of the Acoustical Society of America
8–12 May 2023
Chicago, Illinois
Computational Acoustics: Paper 2pSP11
Article Contents
September 18 2023
A gradient-based optimization approach for underwater acoustic source localization Free
Dariush Kari;
Dariush Kari
1
Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign
, Urbana, IL, 61801, USA
; [email protected]; [email protected]
Search for other works by this author on:
Andrew C. Singer
;
Andrew C. Singer
1
Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign
, Urbana, IL, 61801, USA
; [email protected]; [email protected]
Search for other works by this author on:
Hari Vishnu
;
Hari Vishnu
2
Acoustic Research Laboratory, National University of Singapore
, Singapore, SINGAPORE
; [email protected]
Search for other works by this author on:
Amir Weiss
Amir Weiss
Search for other works by this author on:
Dariush Kari
1
Andrew C. Singer
1
Hari Vishnu
2
Amir Weiss
3
1
Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign
, Urbana, IL, 61801, USA
; [email protected]; [email protected]
2
Acoustic Research Laboratory, National University of Singapore
, Singapore, SINGAPORE
; [email protected]Proc. Mtgs. Acoust. 51, 022002 (2023)
Article history
Received:
June 08 2023
Accepted:
June 27 2023
Connected Content
This is a companion to:
Underwater acoustic localization via gradient-based optimization
Citation
Dariush Kari, Andrew C. Singer, Hari Vishnu, Amir Weiss; A gradient-based optimization approach for underwater acoustic source localization. Proc. Mtgs. Acoust. 8 May 2023; 51 (1): 022002. https://doi.org/10.1121/2.0001753
Download citation file:
Citing articles via
Pickleball noise: The physiological and psychological effects on nearby residents
Kathleen M. Romito, Daniel Fink
Evaluating a scale model reverberation room for Sound Absorption Coefficient measurements: A cost-effective alternative
Jacques Martell-Villalpando, Alejandro Martínez-Borquez, et al.
Related Content
Underwater acoustic localization via gradient-based optimization
J. Acoust. Soc. Am. (March 2023)
Development tools for deep learning models of acoustical signal processing
J. Acoust. Soc. Am. (April 2022)
Using computational models to study accent adaptation: A tutorial
J. Acoust. Soc. Am. (March 2024)
Revisiting rapid accent adaptation with computational modeling
J. Acoust. Soc. Am. (March 2024)
A physics-informed neural network for sound propagation in the atmospheric boundary layer
Proc. Mtgs. Acoust. (March 2021)