Dynamic modeling for land mobile navigation using low-cost inertial sensors and least squares support vector machine learning

Frangos, K; Kealy, A; Gikas, V; Hasnur, A

dc.contributor.author	Frangos, K	en
dc.contributor.author	Kealy, A	en
dc.contributor.author	Gikas, V	en
dc.contributor.author	Hasnur, A	en
dc.date.accessioned	2014-03-01T02:52:39Z
dc.date.available	2014-03-01T02:52:39Z
dc.date.issued	2010	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/35974
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-79959985869&partnerID=40&md5=9aea2618dcae64fea452cf9198790491	en
dc.subject.other	Adaptive dynamics	en
dc.subject.other	Apriori knowledge	en
dc.subject.other	Computational overheads	en
dc.subject.other	Dual frequency	en
dc.subject.other	Dynamic modeling	en
dc.subject.other	Filtering method	en
dc.subject.other	Filtering technique	en
dc.subject.other	Gaussian white noise	en
dc.subject.other	GPS receivers	en
dc.subject.other	Inertial sensor	en
dc.subject.other	Land mobile	en
dc.subject.other	Land vehicles	en
dc.subject.other	Learning techniques	en
dc.subject.other	Least squares support vector machines	en
dc.subject.other	Linear dynamics	en
dc.subject.other	Local minimums	en
dc.subject.other	Low costs	en
dc.subject.other	Low-cost sensors	en
dc.subject.other	Melbourne , Australia	en
dc.subject.other	Navigation solution	en
dc.subject.other	Non-Linearity	en
dc.subject.other	Overfitting	en
dc.subject.other	Processing technique	en
dc.subject.other	Random dynamics	en
dc.subject.other	Real-world tests	en
dc.subject.other	Standard Kalman filters	en
dc.subject.other	State prediction	en
dc.subject.other	Structural risk minimization	en
dc.subject.other	SVM theory	en
dc.subject.other	System Dynamics	en
dc.subject.other	Test data	en
dc.subject.other	Training data	en
dc.subject.other	Transition phase	en
dc.subject.other	Algorithms	en
dc.subject.other	Equipment testing	en
dc.subject.other	Global positioning system	en
dc.subject.other	Kalman filters	en
dc.subject.other	Navigation	en
dc.subject.other	Neural networks	en
dc.subject.other	Sensors	en
dc.subject.other	Support vector machines	en
dc.subject.other	System theory	en
dc.subject.other	Time series	en
dc.subject.other	Time series analysis	en
dc.subject.other	Vehicles	en
dc.subject.other	White noise	en
dc.subject.other	Dynamic models	en
dc.title	Dynamic modeling for land mobile navigation using low-cost inertial sensors and least squares support vector machine learning	en
heal.type	conferenceItem	en
heal.publicationDate	2010	en
heal.abstract	Traditional algorithms used to determine a vehicle's navigation state (e.g. Kalman filter) has as one of its prerequisites, a model that describes how the vehicle is expected to move over time. The accuracy of this dynamic model is important, as it allows for optimization of the navigation solution, particularly when dealing with low cost sensors which typically exhibit significant errors and biases. Unfortunately, for land vehicles, apriori knowledge of the true dynamic model is very difficult to achieve by virtue of the random dynamic variations that exist and that there is no general navigation case. This situation is even further complicated in many navigation applications where non-linearity and demanding environments characterize the motion and challenge the assumptions of most filtering methods (e.g. linear dynamics behaviour and Gaussian white noise). To overcome these problems, a new approach has been developed to determine the correct dynamic model for the navigation platform; this approach is based on Support Vector Machines (SVM). SVM is a relatively new learning technique in the field of machine learning and is based on structural risk minimization (SRM) which makes the technique statistically robust. SVM addresses and overcomes the majority of problems faced by typical neural networks such as local minima, over-fitting or over-training, etc. In this research, Least Squares Support Vector Machine (LS-SVM); a sub case of the SVM theory is utilised as a means of maintaining the ratio between overall performance and computational overheads. The approach taken here is to identify the true system dynamics by learning from a time series analysis of a set of training data. A mathematical model which describes the true system dynamics regression is then created from this analysis. This model can then be applied to predicting the behaviour of the navigation platform. In terms of filtering techniques, this is the first step for the formulation of an adaptive dynamic model for state prediction, replacing the standard Kalman filter's transition phase. In this paper, the LS-SVM algorithm used in this research for dynamic modeling is detailed. In addition, practical results that describe the performance of this algorithm will be presented. These results have been generated using a navigation test bed established in Melbourne, Australia. The test data was captured on a land vehicle fitted with one tactical grade IMU, six low cost MEMS IMU sensors and an array of high performance dual frequency GPS receivers. The real-world tests, data captured, analysis, processing techniques and dynamic modeling results will be described and used to demonstrate the performance of the LS-SVM algorithm.	en
heal.journalName	23rd International Technical Meeting of the Satellite Division of the Institute of Navigation 2010, ION GNSS 2010	en
dc.identifier.volume	2	en
dc.identifier.spage	1687	en
dc.identifier.epage	1696	en