A new method of seamless land navigation for GPS/INS integrated system
TL;DR: By re-training NN withWMRA, the system accuracies improved to the level of using normal GPS signal, and NN trained with WMRA improved the approximation to the actual model, further enhancing alignment accuracy.
About: This article is published in Measurement.The article was published on 2012-05-01. It has received 94 citations till now. The article focuses on the topics: GPS/INS & Global Positioning System.
Citations
More filters
Xiyuan Chen1, Chong Shen2, Chong Shen1, Wei-Bin Zhang2, Masayoshi Tomizuka2, Yuan Xu1, Kuanlin Chiu3 •
TL;DR: Comparison results indicate that the proposed model combined with STKF/WNN algorithms can effectively provide high accurate corrections to the standalone INS during GPS outages.
116 citations
Cites methods from "A new method of seamless land navig..."
...[14] also proposed similar model which employed a multi-resolution wavelet and a neural network to mimic the relationship between current INS error and INS output....
[...]
...[14] also introduced a similar model which used wavelet multi-resolution analysis and neural network to assist KF; when GPS outages happen, the trained neural network can be employed as the replacement of GPS to remove high-frequency noise and improve system accuracy....
[...]
TL;DR: A novel hybrid fusion algorithm is proposed to provide a pseudo position information to assist the integrated navigation system during GPS outages and achieves better performance in the prediction of GPS position information than the normal artificial neural network (ANN) trained by Bayesian Regularization.
103 citations
TL;DR: The ensemble learning algorithm (LSBoost or Bagging), similar to the neural network, can build the SINS/GPS position model based on current and some past samples of SINS velocity, attitude and IMU output information.
84 citations
TL;DR: An integrated navigation system that can be used for pedestrian navigation in both outdoor and indoor environments is described and a step detection method is implemented to constrain the growth of the INS error using an Extended Kalman Filter (EKF).
69 citations
Cites background from "A new method of seamless land navig..."
...GPS is spectacularly successfully in generating accurate positioning solutions in most outdoor environments [1, 2]....
[...]
TL;DR: An architecture based on an adaptive neuro-fuzzy inference system is proposed for fusing the GPS/IMU measurements that incorporates the variable delay between the IMU and GPS signals as an additional input to the fusion system.
Abstract: Low-cost navigation systems, deployed for ground vehicles' applications, are designed based on the loosely coupled fusion between the global positioning system (GPS) and the inertial measurement unit (IMU). However, low-cost GPS receivers provide the position and velocity of the vehicle at a lower sampling rate than the IMU-sampled vehicle dynamics. In addition, the GPS measurements might be missed or delayed due to the receiver's inability to lock on the signal or due to obstruction from neighboring vehicles or infrastructures. In this paper, an architecture based on an adaptive neuro-fuzzy inference system is proposed for fusing the GPS/IMU measurements. This integration incorporates the variable delay between the IMU and GPS signals as an additional input to the fusion system. In addition, once the GPS signal becomes available, the measurement is used as a correction reference value to provide an enhancement to the estimation accuracy. The performance of the proposed method is initially demonstrated using a GPS/IMU simulation environment. Subsequently, an experimental test is also conducted to validate the performance of the method.
64 citations
References
More filters
TL;DR: In this article, the problem of least square problems with non-linear normal equations is solved by an extension of the standard method which insures improvement of the initial solution, which can also be considered an extension to Newton's method.
Abstract: The standard method for solving least squares problems which lead to non-linear normal equations depends upon a reduction of the residuals to linear form by first order Taylor approximations taken about an initial or trial solution for the parameters.2 If the usual least squares procedure, performed with these linear approximations, yields new values for the parameters which are not sufficiently close to the initial values, the neglect of second and higher order terms may invalidate the process, and may actually give rise to a larger value of the sum of the squares of the residuals than that corresponding to the initial solution. This failure of the standard method to improve the initial solution has received some notice in statistical applications of least squares3 and has been encountered rather frequently in connection with certain engineering applications involving the approximate representation of one function by another. The purpose of this article is to show how the problem may be solved by an extension of the standard method which insures improvement of the initial solution.4 The process can also be used for solving non-linear simultaneous equations, in which case it may be considered an extension of Newton's method. Let the function to be approximated be h{x, y, z, • • • ), and let the approximating function be H{oc, y, z, • • ■ ; a, j3, y, ■ • ■ ), where a, /3, 7, • ■ ■ are the unknown parameters. Then the residuals at the points, yit zit • • • ), i = 1, 2, ■ • • , n, are
11,253 citations
01 Jan 2007
TL;DR: This chapter discusses the development of the EZW Algorithm as a framework for wavelet-based image processing, and some of the techniques used to develop and designWavelet Families.
Abstract: Notations. Introduction. Chapter 1. A Guided Tour. Chapter 2. Mathematical Framework. Chapter 3. From Wavelet Bases to the Fast Algorithm. Chapter 4. Wavelet Families. Chapter 5. Finding and Designing a Wavelet. Chapter 6. A Short 1D Illustrated Handbook. Chapter 7. Signal Denoising and Compression. Chapter 8. Image Processing with Wavelets. Chapter 9. An Overview of Applications. Appendix: The EZW Algorithm. Bibliography. Index.
441 citations
TL;DR: How localized waveforms are powerful building blocks for signal analysis and rapid prototyping-and how they are now available in software toolkits is described.
Abstract: As every engineering student knows, any signal can be portrayed as an overlay of sinusoidal waveforms of assorted frequencies. But while classical analysis copes superbly with naturally occurring sinusoidal behavior-the kind seen in speech signals-it is ill-suited to representing signals with discontinuities, such as the edges of features in images. Latterly, another powerful concept has swept applied mathematics and engineering research: wavelet analysis. In contrast to a Fourier sinusoid, which oscillates forever, a wavelet is localized in time-it lasts for only a few cycles. Like Fourier analysis, however, wavelet analysis uses an algorithm to decompose a signal into simpler elements. Here, the authors describe how localized waveforms are powerful building blocks for signal analysis and rapid prototyping-and how they are now available in software toolkits.
293 citations
TL;DR: The obtained results demonstrate the effectiveness of different algorithms considered, in controlling the INS error growth, and indicates the potential of MEMS IMUs for use in land vehicle navigation applications.
Abstract: This paper evaluates the performance of a tightly coupled GPS/INS integrated system based on low cost MEMS IMUs in dense urban areas, and investigates two different methods to improve its performance. The first method used is to derive observations from two different constraint equations reflecting the behavior of a typical land vehicle. The first constraint equation is derived assuming that the vehicle does not slip and always remains in contact with the ground. If these assumptions are true the velocity of the vehicle in the plane perpendicular to the forward direction should be zero. The second constraint equation is derived from the fact that the height does not change much in a short time interval in a land vehicular environment. Thus, when a GPS outage occurs (partial/complete), the integrated system combines the INS and constraints-derived virtual measurements to keep the position and velocity errors bounded. This method is suitable for use in real-time applications. The second method is specifically suitable for a post-mission application and involves the use of Rauch-Tung-Striebel (RTS) smoother. The designed system performance is evaluated using two data sets collected in dense urban areas. The obtained results demonstrate the effectiveness of different algorithms considered, in controlling the INS error growth, and indicates the potential of MEMS IMUs for use in land vehicle navigation applications.
233 citations
TL;DR: This paper aims to introduce a multi-sensor system integration approach for fusing data from INS and GPS utilizing artificial neural networks (ANN) utilizing radial basis function (RBF) neural networks, which generally have simpler architecture and faster training procedures than multi-layer perceptron networks.
Abstract: Most of the present navigation systems rely on Kalman filtering to fuse data from global positioning system (GPS) and the inertial navigation system (INS). In general, INS/GPS integration provides reliable navigation solutions by overcoming each of their shortcomings, including signal blockage for GPS and growth of position errors with time for INS. Present Kalman filtering INS/GPS integration techniques have some inadequacies related to the stochastic error models of inertial sensors, immunity to noise, and observability. This paper aims to introduce a multi-sensor system integration approach for fusing data from INS and GPS utilizing artificial neural networks (ANN). A multi-layer perceptron ANN has been recently suggested to fuse data from INS and differential GPS (DGPS). Although being able to improve the positioning accuracy, the complexity associated with both the architecture of multi-layer perceptron networks and its online training algorithms limit the real-time capabilities of this technique. This article, therefore, suggests the use of an alternative ANN architecture. This architecture is based on radial basis function (RBF) neural networks, which generally have simpler architecture and faster training procedures than multi-layer perceptron networks. The INS and GPS data are first processed using wavelet multi-resolution analysis (WRMA) before being applied to the RBF network. The WMRA is used to compare the INS and GPS position outputs at different resolution levels. The RBF-ANN module is then trained to predict the INS position errors and provide accurate positioning of the moving platform. Field-test results have demonstrated that substantial improvement in INS/GPS positioning accuracy could be obtained by applying the combined WRMA and RBF-ANN modules.
139 citations