Application of UWB modules in indoor navigation system

Kaniewski, Piotr; Kazubek, Jakub; Kraszewski, Tomasz

doi:10.1109/comcas.2017.8244726

Cited by 17 publications

(10 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Kalman Filter algorithm uses a dynamics model describing object's motion and it is the optimal algorithm for its state estimation if the model of the system is linear, and when disturbances of the process and measurements errors are additive and Gaussian. However, in most systems of interest the dynamics and observation equations are non-linear 2,7 . When at least one of the equations describing the system is non-linear, the Kalman Filter cannot be applied.…”

Section: Unscented Kalman Filtermentioning

confidence: 99%

See 1 more Smart Citation

Unscented Kalman filter application in personal navigation

Pasek

Kaniewski

2020

Radioelectronic Systems Conference 2019

Self Cite

View full text Add to dashboard Cite

A choice of positioning algorithm is a key issue when designing a navigation system. The paper presents an Unscented Kalman Filter (UKF) for a personal navigation system using range measurements between ultrawideband radio modules for positioning. The mentioned system is described by a linear dynamics model and a non-linear observation model, and therefore UKF can be successfully applied for its state estimation. The unscented Kalman filter is a suboptimal non-linear filtration algorithm, however, in contrast to algorithms such as EKF or LKF, it uses an unscented transformation (UT) as an alternative to a linearization of non-linear equations with the use of Taylor series expansion. The linearization considers only the first term of a Taylor series and its higher terms are omitted, which degrades estimation accuracy in highly non-linear systems. Lack of necessity of a linearization of the dynamics and observation models leads to a higher navigation system accuracy. It also facilitates an implementation of the algorithm as non-linear transformations of a set of deterministically chosen sigma points replaces calculations of Jacobian matrices. The paper presents a personal navigation system designed by the authors, describes its unscented Kalman filter used for a mobile user position estimation and contains chosen simulation results of the tests of the filter. Based on these data, efficiency of using this kind of filtration in non-linear navigation systems has been assessed.

show abstract

Section: Unscented Kalman Filtermentioning

confidence: 99%

“…Other solutions use some local infrastructure that is deployed around or inside the building. For this purpose, ultrawideband (UWB) modules can be used, whose numerous advantages have made them commonly used in navigation [2][3][4] .…”

Section: Introductionmentioning

confidence: 99%

Unscented Kalman filter application in personal navigation

Pasek

Kaniewski

2020

Radioelectronic Systems Conference 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…geometric, nongeometric, topological. The choice of which image features are to be analyzed is an individual matter, depending on the final result [4,5,10]. For the purposes of this algorithm, however, the most important is the mathematical side of the processing the analyzed image features, resulting in the so-called signatures and skeletons, that is, one-dimensional functions representing the contours of an object.…”

Section: Figure 1 Image Analysis Diagrammentioning

confidence: 99%

The use of machine learning algorithms for image recognition

Matuszewski

Rajkowski

2020

Radioelectronic Systems Conference 2019

View full text Add to dashboard Cite

The article presents a way of using machine learning algorithms to recognize objects in images. To implement this task, an artificial neural network was used, which has a high adaptability and allows work with a very large set of input data. The neural network was described using a program written in the MATLAB simulation environment. The basic problem faced by the designer of objects recognition is to collect a sufficient training set of images to achieve the high probability of correct recognition. The set of learning patterns in the artificial neural networks may contain from several dozen thousands to one million training samples. In this article at the beginning the neural network was pre-trained trained based on the images included in the publicly available CIFAR 100 database, which are characterized by a small size of 32x32 pixels. It contains 70 000 images assigned to 10 basic categories. Then the author's database, consisting from 1000 pedestrians, cars and road signs was used. The article contains a description of applied algorithm, method of supervised learning and correction of weight coefficients, selection of activation function and operation on max pooling filter. The results of proposed solution are presented in the form of screenshots from calculations and in figures depicting results of recognized objects. Attention was also paid to the impact of used database for learning the network on the speed of calculations and recognition efficiency. The proper selection of number and types of layers, number of neurons, activation function and the value of the learning factor is very important in designing the neural network in application to objects recognition contained in the images. The problems occurring in the process of learning the neural networks and suggestions for their further improvement are also presented.

show abstract

“…The observation model 2,6 , on the other hand, is the relationship between the measured distances in the system and the coordinates of the air object location in the state vector:…”

Section: Ekfmentioning

confidence: 99%

“…Also here it is assumed to use radio waves, but the signal structures used will have enough dispersed spectrum that their detection for possible later interference will be much more difficult or even impossible. These conditions are met by ultrawideband modules (UWB) 3,6 working with signals in this technology. It is also planned to examine the proposed solution for the construction of an indoor positioning system where satellite system signals are not available.…”

Section: Introductionmentioning

confidence: 99%