Underwater angle-only tracking with propagation delay and time-offset between observers

Khan

Raja

et al. 2021

Entropy

Self Cite

In this study, an intelligent computing paradigm built on a nonlinear autoregressive exogenous (NARX) feedback neural network model with the strength of deep learning is presented for accurate state estimation of an underwater passive target. In underwater scenarios, real-time motion parameters of passive objects are usually extracted with nonlinear filtering techniques. In filtering algorithms, nonlinear passive measurements are associated with linear kinetics of the target, governing by state space methodology. To improve tracking accuracy, effective feature estimation and minimizing position error of dynamic passive objects, the strength of NARX based supervised learning is exploited. Dynamic artificial neural networks, which contain tapped delay lines, are suitable for predicting the future state of the underwater passive object. Neural networks-based intelligence computing is effectively applied for estimating the real-time actual state of a passive moving object, which follows a semi-curved path. Performance analysis of NARX based neural networks is evaluated for six different scenarios of standard deviation of white Gaussian measurement noise by following bearings only tracking phenomena. Root mean square error between estimated and real position of the passive target in rectangular coordinates is computed for evaluating the worth of the proposed NARX feedback neural network scheme. The Monte Carlo simulations are conducted and the results certify the capability of the intelligence computing over conventional nonlinear filtering algorithms such as spherical radial cubature Kalman filter and unscented Kalman filter for given state estimation model.

Section: Simulation Results and Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Design of Nonlinear Autoregressive Exogenous Model Based Intelligence Computing for Efficient State Estimation of Underwater Passive Target

Khan

Raja

et al. 2021

Entropy

Self Cite

“…Although the authors in Ref. [31] also studied the underwater signal propagation delay and the curved sound ray, it is mainly focussed on tracking the constant velocity motion target with double stationary observers, which solves the problem of the time offset between two observers caused by signal propagation delay. Different from Ref.…”

Section: Introductionmentioning

confidence: 99%

Underwater passive manoeuvring target tracking with isogradient sound speed profile

2022

IET Radar Sonar & Navi

Self Cite

Compared with the traditional tracking problem, the underwater 3-D passive manoeuvring target tracking faces the following challenging problems: (1) Since the signal propagation delay is varying and unknown, the relationship between the two adjacent target states is hard to describe; (2) limited by the underwater environment, it is more difficult to establish a target manoeuvring motion model; (3) the propagation speed of the underwater acoustic signal varies with the depth, and the propagation path will be curved instead of straight. Various parameters including signal propagation delay, target pitch angle and receiving frequency measured by the observer cannot be calculated as usual. In this paper, we improved a 3-D constant turn (3D-CT) model to match the underwater target motion. For the problems ( 1) and ( 3), this paper proposes a novel interacting multiple model underwater Gauss-Helmert unscented Kalman filter (IMM-UGHUKF) with isogradient sound velocity profile, which analytically describes the relationship between the state to be estimated and the passive measurement. This method augments the unknown signal emission time into the state with implicit equations, and transits the state by the Gauss-Helmert model. Simulation tests have been carried out, and the results show that IMM-UGHUKF can significantly reduce the estimation error compared with other approaches.

“…This method has two disadvantages, for example, the signal transmission time interval is calculated directly during the iteration process without considering noise while iterative calculation may be excessive due to the linear search method. Another strategy extends the state, and the signal emission time becomes one of the variables [ 36 , 37 , 38 ]. Unlike the traditional Gauss–Markov model (GMM), the Gauss–Hermit model (GHM) in these algorithms can be used to describe strongly complex state equations, which allows the existence of the previous state and the current state at the same time.…”

Section: Introductionmentioning

confidence: 99%

“…However, the application of these methods are relatively limited. In [ 38 ], the method is mainly aimed at eliminating the unknown time offset between two stationary observers under the influence of time propagation delay. The approach in [ 36 ] utilizes a maneuvering single observation station to deal with the bearing-only target tracking.…”

Section: Introductionmentioning

confidence: 99%

Underwater 3D Doppler-Angle Target Tracking with Signal Time Delay

et al. 2020

Sensors

Self Cite

The traditional target tracking is a process of estimating the state of a moving target using measurement information obtained by sensors. However, underwater passive acoustic target tracking will confront further challenges, among which the system incomplete observability and time delay caused by the signal propagation create a great impact on tracking performance. Passive acoustic sensors cannot accurately obtain the target range information. The introduction of Doppler frequency measurement can improve the system observability performance; signal time delay cannot be ignored in underwater environments. It varies with time, which has a continuous negative impact on the tracking accuracy. In this paper, the Gauss–Helmert model is introduced to solve this problem by expanding the unknown signal emission time as an unknown variable to the state. This model allows the existence of the previous state and current state at the same time, while handling the implicit equations. To improve the algorithm accuracy, this paper further takes advantage of the estimated state and covariance for the second stage iteration and propose the Gauss–Helmert iterated Unscented Kalman filter under a three-dimensional environment. The simulation shows that the proposed method in this paper shows superior estimation accuracy and more stable performance compared with other filtering algorithms in underwater environments.