Bridging GPS outages of tightly coupled GPS/SINS based on the Adaptive Track Fusion using RBF neural network

Pang, Chen-peng; Zao-zhen, Liu

doi:10.1109/isie.2009.5222600

Cited by 9 publications

(8 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During DVL malfunctions, the SINS/DVL/MCP/PS integrated navigation system is processed by four different solutions: (1) insulate the faulted DVL measurements without predictor (i.e., the local filter 1 introduced in Section 2.1 only executes the time update process); (2) use only PLSR predictor; (3) use radial basis function (RBF) neural network predictor [34]; (4) use PLSR-SVR hybrid predictor. It is worth noting that the DVL malfunctions listed in the introduction are all short-term, lasting for a few seconds or minutes.…”

Section: Simulations and Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Hybrid Approach to Deal with DVL Malfunctions for Underwater Integrated Navigation Systems

Zhu

Cheng

et al. 2017

Applied Sciences

View full text Add to dashboard Cite

Abstract:As a common device for underwater integrated navigation systems, Doppler velocity log (DVL) has the risk of malfunction. To improve the reliability of navigation systems, a hybrid approach is presented to forecast the measurements of the DVL while it malfunctions. The approach employs partial least squares regression (PLSR) coupled with support vector regression (SVR) to build a hybrid predictor. As the current and past calculating velocities of strapdown inertial navigation system (SINS) are taken as the predictor's inputs, PLSR is applied to cope with the situation where there exists intense relativity among independent variables. Since PLSR is a linear regression, SVR is used to predict the residual components of the PLSR prediction to improve the accuracy. When the DVL works well, the hybrid predictor is trained online as a backup, whereas during malfunctions, the predictor offers the estimation of the DVL measurements for information fusion. The performance of the proposed approach is verified with simulations based on SINS/DVL/MCP/pressure sensor (PS) integrated navigation system. The comparison results indicate that the PLSR-SVR hybrid predictor can correctly provide the estimated DVL measurements and effectively extend the tolerance time on DVL malfunctions, thereby improving the navigation accuracy and reliability.

show abstract

Section: Simulations and Resultsmentioning

confidence: 99%

“…neural network predictor [34] Figure 8a shows that, the east and north velocity errors of the system with the first solution increase significantly during the malfunction period, which is due to the lack of external velocity information. By comparison, the systems with the other three predictors work better.…”

Section: Simulations and Resultsmentioning

confidence: 99%

A Novel Hybrid Approach to Deal with DVL Malfunctions for Underwater Integrated Navigation Systems

Zhu

Cheng

et al. 2017

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…With the intention of effectively predicting the vehicle position in free, partial, and full GPS outages based on the Compute the random Gaussian matrix according to (3); (5) ← (6) end for (7) Explore the measurement matrix based on RIP such that the optimization problem is resolved via [29]; (8) GeneratêI NS ,̂G PS ,̂G PS and̂I NS using MLE (see (11), (13) and (14)); (9) Calculate the likelihoods gps (̂| ) and INS (̂| ) according to (10) and (12); (10) Generate and evaluate the GPS weight GPS according to (8); (11) if GPS = 1, (Free GPS outage) then (12) Predict vehicle position such that (̂| ) = (̂G PS | ) based on (9) and (10); (13) end if (14) if GPS = 0 (Full GPS outage), then (15) Predict vehicle position such that (̂| ) = (̂I NS | ) based on (9) and (12); (16) Otherwise (0 < GPS < 1, Partial GPS outage) (17) Compute (̂G PS∧INS ) = ∑ =1 ( |̂) according to (27); (18) Predict the vehicle position such that ‖̂G PS∧INS ‖ 1 ≥ (19) end if (20) end for (21) Return the predicted measurement of the vehicle position̂(̆). proposed method, the test vehicle was driven along different roads in Hunan University area with different velocities for about 25 minutes.…”

Section: Experiments and Evaluation Resultsmentioning

confidence: 99%

“…Although this method is flexible and simple to implement, it is more computer-intensive demanding [14]. To forecast the measurement update of KF method, the authors in [7,15] have introduced the prediction method based on radial basis function (RBF) neural network coupled with time series analysis. In [7], for instance, when GPS outages occur, the outputs of RBF neural network are used straightly to correct the INS results.…”

Section: Mathematical Problems In Engineeringmentioning

confidence: 99%

“…In [7], for instance, when GPS outages occur, the outputs of RBF neural network are used straightly to correct the INS results. In [15], RBF neural network is used to predict measurement of GPS/SINS KF in order to guarantee the regular operation of the filter in the system during the GPS outages. Furthermore, with the intention of improving the positioning accuracy during outages [12], the trained SVM model is used to correct the INS error and the DS contributes when the GPS signals are available.…”

Section: Mathematical Problems In Engineeringmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Probabilistic Approach for Vehicle Position Prediction in Free, Partial, and Full GPS Outages

Havyarimana

Wang

Xiao

2015

Mathematical Problems in Engineering

View full text Add to dashboard Cite

In this paper, a novel framework is developed with the intention of continuously predicting vehicle position even in the challenging environments such as partial and full GPS outages. To achieve this, the Bayesian-Sparse Random Gaussian Prediction (B-SRGP) approach is proposed where the sparse random Gaussian matrix which obeys the restricted isometry property with high probability is adopted to handle the measurement model. During the full GPS outages, the proposed method fuses all available INS measurements to improve the vehicle position prediction whereas in free outages only the GPS data are processed. Besides, the Bayesian inference is used to specifically deal with the vehicle position prediction in partial GPS outages where data from both GPS and INS are taken as inputs. In all cases, measurement noises are assumed to be non-Gaussian distributed and follow the generalized error distribution. The performance of B-SRGP is evaluated with respect to real-world data collected using Smartphonebased vehicular sensing model. The proposed method is tested when measurement noises are both Gaussian and non-Gaussian distributed and also compared with the existing prediction methods. Experimental results confirm that B-SRGP presents higher accuracy prediction and lower mean-squared prediction error for vehicle position when measurement noises are non-Gaussian distributed.

show abstract

Bridging GPS Outages for Fixed-wing Unmanned Aerial Vehicles

Zhao

Fang

2014

J. Navigation

View full text Add to dashboard Cite

This paper reports on a new navigation algorithm for fixed-wing Unmanned Aerial Vehicles (UAVs) to bridge Global Position System (GPS) outages, based on a common navigation system configuration. The ground velocity is obtained from wind-compensated airspeed, and a centripetal force model is introduced to estimate the motion acceleration. Compensated by this acceleration, the gravity vector can be extracted from the accelerometer measurement. Finally, fusing the information of the ground velocity, magnetic heading, barometric height, and gravity vector, the Integrated Navigation System (INS) is reconstructed, and an Extended Kalman Filter (EKF) is used to estimate INS errors. Hardware-in-loop simulation results show that compared with INS-only solutions, the proposed method effectively resists long-term drift of INS errors and significantly improves the accuracy for dynamic navigation during GPS outages. K E Y WO R D S1. Fixed-wing UAV.2. GPS outages. 3. Navigation reconstruction. 4. Kalman filtering.

show abstract

Bridging GPS outages of tightly coupled GPS/SINS based on the Adaptive Track Fusion using RBF neural network

Cited by 9 publications

References 1 publication

A Novel Hybrid Approach to Deal with DVL Malfunctions for Underwater Integrated Navigation Systems

A Novel Hybrid Approach to Deal with DVL Malfunctions for Underwater Integrated Navigation Systems

A Novel Probabilistic Approach for Vehicle Position Prediction in Free, Partial, and Full GPS Outages

Bridging GPS Outages for Fixed-wing Unmanned Aerial Vehicles

Contact Info

Product

Resources

About