Dynamic System Identification of Underwater Vehicles Using Multi-Output Gaussian Processes

Non-parametric system identification with Gaussian Processes for underwater vehicles is explored in this research with the purpose of modelling autonomous underwater vehicle (AUV) dynamics with low amount of data. Multi-output Gaussian processes and its aptitude to model the dynamic system of an underactuated AUV without losing the relationships between tied outputs is used. The simulation of a first-principles model of a Remus 100 AUV is employed to capture data for the training and validation of the multi-output Gaussian processes. The metric and required procedure to carry out multi-output Gaussian processes for AUV with 6 degrees of freedom (DoF) is also shown in this paper. Multi-output Gaussian processes are compared with the popular technique of recurrent neural network show that Multi-output Gaussian processes manage to surpass RNN for non-parametric dynamic system identification in underwater vehicles with highly coupled DoF with the added benefit of providing a measurement of confidence.

[1]  D. Krige.  A statistical approach to some basic mine valuation problems on the Witwatersrand, by D.G. Krige, published in the Journal, December 1951 : introduction by the author , 1951 .

[2]  Wilmer Ariza Ramirez,et al.  Exploration of the Applicability of Probabilistic Inference for Learning Control in Underactuated Autonomous Underwater Vehicles , 2020, Auton. Robots.

[3]  Morton Gertler,et al.  STANDARD EQUATIONS OF MOTION FOR SUBMARINE SIMULATION , 1967 .

[4]  Benedetto Allotta,et al.  Fast Calibration Procedure of the Dynamic Model of an Autonomous Underwater Vehicle from a Reduced Set of Experimental Data , 2017 .

[5]  Dev Ranmuthugala,et al.  Numerical investigation of the hydrodynamic interaction between two underwater bodies in relative motion , 2015 .

[6]  Shantha Gamini Jayasinghe,et al.  Non-parametric dynamic system identification of ships using multi-output Gaussian Processes , 2018 .

[7]  Bidyadhar Subudhi,et al.  Cooperative formation control of autonomous underwater vehicles: An overview , 2016, Int. J. Autom. Comput..

[8]  Wan Kyun Chung,et al.  Accurate and practical thruster modeling for underwater vehicles , 2006 .

[9]  José Luis Gordillo,et al.  Lagrange modeling and navigation based on quaternion for controlling a micro AUV under perturbations , 2020, Robotics Auton. Syst..

[10]  Shiliang Sun,et al.  Variational Dependent Multi-output Gaussian Process Dynamical Systems , 2014, J. Mach. Learn. Res..

[11]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[13]  Mohammad Danesh,et al.  Application of particle filter combined with extended Kalman filter in model identification of an autonomous underwater vehicle based on experimental data , 2019, Applied Ocean Research.

[14]  Marcus R. Frean,et al.  Dependent Gaussian Processes , 2004, NIPS.

[15]  Yuesheng Xu,et al.  Universal Kernels , 2006, J. Mach. Learn. Res..

[16]  A. G. Parkinson,et al.  On the planar motion mechanism used in ship model testing , 1970, Philosophical Transactions of the Royal Society of London. Series A, Mathematical and Physical Sciences.

[17]  Jana Fuhrmann,et al.  Guidance And Control Of Ocean Vehicles , 2016 .

[18]  S. Payandeh,et al.  Robot Navigation Controller: a Non-Parametric Regression Approach , 2010 .

[19]  Thor I. Fossen,et al.  Practical aspects of frequency-domain identification of dynamic models of marine structures from hydrodynamic data , 2011 .

[20]  Debabrata Sen.  A Study on Sensitivity of Maneuverability Performance on the Hydrodynamic Coefficients for Submerged Bodies , 2000 .

[21]  Feng Xu,et al.  Identification modeling of underwater vehicles' nonlinear dynamics based on support vector machines , 2013 .

[22]  Timothy Prestero,et al.  Verification of a six-degree of freedom simulation model for the REMUS autonomous underwater vehicle , 2001 .

[23]  Paulo J. G. Lisboa,et al.  Neural network modelling and control for underwater vehicles , 1996, Artif. Intell. Eng..

[24]  Mark Ebden.  Gaussian Processes for Regression: A Quick Introduction , 2008 .

[25]  Ming Zhang,et al.  A modular autonomous underwater vehicle for environmental sampling: System design and preliminary experimental results , 2014, OCEANS 2014 - TAIPEI.

[26]  Neil D. Lawrence,et al.  Computationally Efficient Convolved Multiple Output Gaussian Processes , 2011, J. Mach. Learn. Res..

[27]  Alexandra Grancharova,et al.  GAUSSIAN PROCESS MODELLING CASE STUDY WITH MULTIPLE OUTPUTS , 2010 .

[28]  S. H. Mousavizadegan,et al.  The effect of appendages on the hydrodynamic characteristics of an underwater vehicle near the free surface , 2017 .

[29]  H. Yoshida,et al.  Evaluation of methods to Estimate Hydrodynamic Force Coefficients of Underwater Vehicle based on CFD , 2013 .

[30]  D. Toal,et al.  Identification of underwater vehicle dynamics with neural networks , 2004, Oceans '04 MTS/IEEE Techno-Ocean '04 (IEEE Cat. No.04CH37600).

[31]  Mohammad Bozorg,et al.  Parameter Estimation of an AUV Using the Maximum Likelihood method and a Kalman Filter with Fading Memory , 2010 .

[32]  Pouria Sarhadi,et al.  Extended and Unscented Kalman filters for parameter estimation of an autonomous underwater vehicle , 2014 .

[33]  Juš Kocijan,et al.  Modelling and Control of Dynamic Systems Using Gaussian Process Models , 2015 .

[34]  Stuart Anstee,et al.  Trim Calculation Methods for a Dynamical Model of the REMUS 100 Autonomous Underwater Vehicle , 2011 .

[35]  Benedetto Allotta,et al.  Identification of the main hydrodynamic parameters of Typhoon AUV from a reduced experimental dataset , 2018 .

[36]  Feng Xu,et al.  Parametric Identification and Sensitivity Analysis for Autonomous Underwater Vehicles in Diving Plane , 2012 .

[37]  Tor Arne Johansen,et al.  Identification of underwater vehicle hydrodynamic coefficients using free decay tests , 2004 .

[38]  Asgeir J. Sørensen,et al.  Neural network augmented identification of underwater vehicle models , 2004 .

[39]  D. Higdon.  Space and Space-Time Modeling using Process Convolutions , 2002 .

[40]  A. Tyagi,et al.  Calculation of transverse hydrodynamic coefficients using computational fluid dynamic approach , 2006 .

[41]  Neil D. Lawrence,et al.  Sparse Convolved Gaussian Processes for Multi-output Regression , 2008, NIPS.

[42]  Bilal Wehbe,et al.  Experimental evaluation of various machine learning regression methods for model identification of autonomous underwater vehicles , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[43]  Huosheng Hu,et al.  Biologically inspired behaviour design for autonomous robotic fish , 2006, Int. J. Autom. Comput..

[44]  Asgeir J. Sørensen,et al.  Neural network augmented identification of underwater vehicle models , 2004 .

[45]  Elías Revestido Herrero,et al.  Measurements of Hydrodynamic Parameters and control of an underwater torpedo-shaped vehicle , 2015 .