Wyniki wyszukiwania - BazTech

1

Optimal State Estimation via Adaptive Fuzzy Particle Filter

Sąsiadek Jurek, Bitlmal Hamdan Alatresh

Pomiary Automatyka Robotyka

|

2023

|

R. 27, nr 4

5--12

EN

Particle Filters (PF) accomplish nonlinear system estimation and have received high interest from numerous engineering domains over the past decade. The main problem of PF is to degenerate over time due to the loss of particle diversity. One of the essential causes of losing particle diversity is sample impoverishment (most of particle’s weights are insignificant) which affects the result from the particle depletion in the resampling stage and unsuitable prior information of process and measurement noise. To address this problem, a new Adaptive Fuzzy Particle Filter (AFPF) is used to improve the precision and efficiency of the state estimation results. The error in AFPF state is avoided from diverging by using Fuzzy logic. This method is called tuning weighting factor (α) as output membership function of fuzzy logic and input memberships function is the mean and the covariance of residual error. When the motion model is noisier than measurement, the performance of the proposed method (AFPF) is compared with the standard method (PF) at various particles number. The performance of the proposed method can be compared by keeping the noise level acceptable and convergence of the particle will be measured by the standard deviation. The simulation experiment findings are discussed and evaluated.

PL

Adaptacyjny filtr cząstek rozmytych (AFPF) służy do poprawy precyzji i wydajności wyników szacowania stanu. Metoda ta nazywana jest dostrajaniem współczynnika ważenia (α), ponieważ wyjściowa funkcja przynależności logiki rozmytej, a wejściowa funkcja przynależności jest średnią i kowariancją błędu resztowego. Wydajność proponowanej metody jest porównywana przez utrzymanie dopuszczalnego poziomu hałasu, a zbieżność cząstki będzie mierzona przez odchylenie standardowe. Wyniki eksperymentu symulacyjnego są omawiane i oceniane.

2

Human gesture recognition using hidden Markov models and sensor Fusion

Emmanuel Dominguez Ramon, Raquel Diaz Hernandez, Leopoldo Altamirano Robles

Computer Science

|

2022

|

T. 23 (2)

227--245

EN

Considering the continued drive of human needs along with the constant improvement of technology, it is convenient to develop techniques that can enhance communication between computers and humans in the most intuitive ways possible. The possibility of automatically recognizing human gestures using artificial vision (among other kinds of sensors) allows us to explore a whole range of applications to control and interact with environments. Nowadays, most approaches for gesture recognition using sensors agree in the use of vision, myography, and movement devices that are applied to robotic, medical, and industrial applications. In the context of this work, we study the principles of using both vision and body contact sensing applied to the automatic classification of a human gesture set. For this, two different approaches have been evaluated: feed-forward neural networks, and hidden Markov models. These models have been studied and implemented for recognizing up to eight different human hand gestures that are commonly applied in collaborative robotics tasks.

3

Fusion of Depth and Thermal Imaging for People Detection

Gutfeter Weronika, Pacut Andrzej

Journal of Telecommunications and Information Technology

|

2021

|

nr 4

53--60

EN

The methodology presented in this paper covers the topic of automatic detection of humans based on two types of images that do not rely on the visible light spectrum, namely on thermal and depth images. Various scenarios are considered with the use of deep neural networks being extensions of Faster R-CNN models. Apart from detecting people, independently, with the use of depth and thermal images, we proposed two data fusion methods. The first approach is the early fusion method with a 2-channel compound input. As it turned out, its performance surpassed that of all other methods tested. However, this approach requires that the model be trained on a dataset containing both types of spatially and temporally synchronized imaging sources. If such a training environment cannot be setup or if the specified dataset is not sufficiently large, we recommend the late fusion scenario, i.e. the other approach explored in this paper. Late fusion models can be trained with single-source data. We introduce the dual-NMS method for fusing the depth and thermal imaging approaches, as its results are better than those achieved by the common NMS.

4

Inertial Sensors in the Stabilization System of the Balancing Vehicle

Chudzik Stanisław

International Journal of Electronics and Telecommunications

|

2021

|

Vol. 67, No. 2

241--246

EN

The article presents the possibilities of using popular MEMS inertial sensors in the object tilt angle estimation system and in the system for stabilizing the vertical position of the balancing robot. Two research models were built to conduct the experiment. The models use microcontroller development board of the STM32F3 series with the Cortex-M4 core, equipped with a three-axis accelerometer, magnetometer and gyroscope. To determine the accuracy of the angle estimation, comparative tests with a pulse encoder were performed.

5

Motion tracking by the sensor fusion method in the Android environment

Olczak A.

Zeszyty Naukowe. Elektryka / Politechnika Opolska

|

2017

|

z. 75

55--56

EN

This paper describes advantages of the sensor fusion method in motion tracking. The sensor fusion data has been presented in the Android environment.

6

Decision trees and the effects of feature extraction parameters for robust sensor network design

Gerdes M., Galar D., Scholz D.

Eksploatacja i Niezawodność

|

2017

|

Vol. 19, no. 1

31--42

EN

Reliable sensors and information are required for reliable condition monitoring. Complex systems are commonly monitored by many sensors for health assessment and operation purposes. When one of the sensors fails, the current state of the system cannot be calculated in same reliable way or the information about the current state will not be complete. Condition monitoring can still be used with an incomplete state, but the results may not represent the true condition of the system. This is especially true if the failed sensor monitors an important system parameter. There are two possibilities to handle sensor failure. One is to make the monitoring more complex by enabling it to work better with incomplete data; the other is to introduce hard or software redundancy. Sensor reliability is a critical part of a system. Not all sensors can be made redundant because of space, cost or environmental constraints. Sensors delivering significant information about the system state need to be redundant, but an error of less important sensors is acceptable. This paper shows how to calculate the significance of the information that a sensor gives about a system by using signal processing and decision trees. It also shows how signal processing parameters influence the classification rate of a decision tree and, thus, the information. Decision trees are used to calculate and order the features based on the information gain of each feature. During the method validation, they are used for failure classification to show the influence of different features on the classification performance. The paper concludes by analysing the results of experiments showing how the method can classify different errors with a 75% probability and how different feature extraction options influence the information gain.

PL

Niezawodne monitorowanie stanu wymaga niezawodności czujników i pochodzących z nich informacji. Systemy złożone są zazwyczaj monitorowane przez wiele czujników, co pozwala na ocenę stanu technicznego oraz aspektów eksploatacyjnych. Gdy jeden z czujników ulega uszkodzeniu, uniemożliwia to obliczenie bieżącego stanu systemu z dotychczasową niezawodnością lub uzyskanie kompletnych informacji o bieżącym stanie. Stan można co prawda monitorować nawet przy niekompletnych danych, ale wyniki takiego monitorowania mogą nie odpowiadać rzeczywistemu stanowi systemu. Sytuacja taka ma miejsce w szczególności, gdy uszkodzony czujnik jest odpowiedzialny za monitorowanie istotnego parametru systemu. Problem uszkodzenia czujnika można rozwiązywać na dwa sposoby. Pierwszy polega na zwiększeniu złożoności systemu, co umożliwia jego sprawniejsze działanie w sytuacji, gdy dane są niekompletne. Drugim sposobem jest wprowadzenie nadmiarowego sprzętu (hardware'u) lub oprogramowania. Niezawodność czujników stanowi krytyczny aspekt systemu. Oczywiście, ze względu na ograniczenia przestrzenne, ekonomiczne i środowiskowe nie wszystkie czujniki w systemie mogą być nadmiarowe. Redundancja powinna dotyczyć wszystkich czujników, które dostarczają istotnych informacji na temat stanu systemu, natomiast dopuszczalne są błędy mniej ważnych czujników. W niniejszej pracy pokazano jak obliczać istotność informacji o systemie dostarczanych przez poszczególne czujniki z wykorzystaniem metod przetwarzania sygnałów oraz drzew decyzyjnych. Zademonstrowano również w jaki sposób parametry przetwarzania sygnałów wpływają na poprawność klasyfikacji metodą drzewa decyzyjnego, a tym samym na poprawność dostarczanych informacji. Drzew decyzyjnych używa się do obliczania i porządkowania cech w oparciu o przyrost informacji charakteryzujący poszczególne cechy. Podczas weryfikacji zastosowanej metody, drzewa decyzyjne wykorzystano do klasyfikacji uszkodzeń celem przedstawienia wpływu różnych cech na dokładność klasyfikacji. Pracę kończy analiza wyników eksperymentów pokazujących w jaki sposób zastosowana metoda pozwala na klasyfikację różnych błędów z 75-procentowym prawdopodobieństwem oraz jak różne opcje ekstrakcji cech wpływają na przyrost informacji.

7

ITS in the digital society

Kardaś K., Zmidzińska B.

Archives of Transport System Telematics

|

2016

|

Vol. 9, iss. 2

12--21

EN

Uniform for cars, smartphones, Road Side Units and Traffic Management Centers European Cooperative ITS (C-ITS) Architecture model opens the road to integrated design of mobility management systems where pedestrians and cars play an active role in shaping the traffic conditions and dedicated radio frequencies enable them to solve most of the ongoing cases. The new business models involve equally car makers, drivers, passengers, road and railway operators, financial sector (lease, insurance providers, banks), municipalities and governmental road and transport agencies, telecoms, ICT 800 pounds gorillas as well as startups in cooperative design, enhancement, delivery and consumption of mobility services. Will we manage to leverage the global experience, enrich European C-ITS output and avoid being marginalized as pure consumers on new services market?

8

Zastosowanie tanich czujników inercyjnych w układzie regulacji kąta pochylenia pojazdu balansującego

Chudzik S.

Przegląd Elektrotechniczny

|

2015

|

R. 91, nr 6

177-180

PL

W pracy przedstawiono wyniki badań związanych z możliwością wykorzystania niskokosztowych sensorów inercyjnych w układzie stabilizacji pozycji pionowej oraz zadanego kierunku jazdy robota balansującego. Testowany układ sterowania zbudowano w oparciu o płytkę uruchomieniową mikrokontrolera serii STM32F3 z rdzeniem Cortex-M4 wyposażoną w trójosiowy akcelerometr, magnetometr i żyroskop. Do określenia dokładności estymacji kąta nachylenia, przeprowadzono testy porównawcze na stanowisku z enkoderem impulsowym.

EN

The paper presents results of research related to the potential use of low-cost sensors, inertial stabilization system vertical position and specified direction balancing robot. Tested control system was built based on the start up board microcontroller series STM32F3 Cortex-M4 equipped with a triaxial accelerometer, magnetometer and gyroscope. To determine the accuracy of the estimation of the angle of inclination, comparative tests were carried out on a bench with a pulse encoder.

9

WiFi - guided visual loop closure for indoor navigation using mobile devices

Nowicki M.

Journal of Automation Mobile Robotics and Intelligent Systems

|

2014

|

Vol. 8, No. 3

10--18

EN

Mobile, personal devices are getting more capable every year. Equipped with advanced sensors, mobile devices can use them as a viable platform to implement and test more complex algorithms. This paper presents an energy-efficient person localization system allowing to detect already visited places. The presented approach combines two independent information sources: wireless WiFi adapter and camera. The resulting system achieves higher recognition rates than either of the separate approaches used alone. The evaluation of presented system is performed on three datasets recorded in buildings of different structure using a modern Android device.

10

Integracja czujników inercyjnych z konstrukcją robota humanoidalnego cz. I

Kosiński P., Świątek-Brzeziński P., Osypiuk R.

Pomiary Automatyka Kontrola

|

2012

|

R. 58, nr 12

1091-1094

PL

W niniejszym artykule przedstawiono założenia projektowe oraz budowę systemu sterowania ruchem dla robota humanoidalnego Futaba RBT-1. Zaprezentowano wykonany sterownik oparty o mikrokontroler z rdzeniem ARM7, wyposażony w interfejs komunikacji do sterowania serwonapędami cyfrowymi, moduły radiowej wymiany danych oraz zestaw czujników inercyjnych. Ponadto zwrócono uwagę na interesującą metodę wyznaczania wychylenia poruszającego się obiektu względem Ziemi.

EN

This paper presents a part of the control system of the humanoid robot Futaba RBT-1. The hardware consists of a microprocessor based controller equipped with a communication interface for digital servos in robot legs. The main parts of the controller are: an ARM microcontroller, a wireless communication module TLX2401 and a Bluetooth. There was chosen an advanced sensor ADIS16362 iSensorŽ which is a complete inertial system that includes a triaxis gyroscope, a triaxis accelerometer and a programmable digital low-pass filter. The robot control system is shown in Fig. 1. In Section 4 the Inertial Navigation System (INS) is described. It uses the data obtained from the accelerometer and gyroscope to calculate the inclination of the robot body in respect to the gravity direction. It is based on "Efficient Orientation Filter" (developed by Dr. Sebastian Madgwick [1]) which despite being computationally efficient gives very good results. Small computational demands allow it to run on a microcontroller with the ARM7 core in real-time which would be difficult with e.g. Extended Kalman Filter. The main control application (described in the second part of this paper) runs on a PC computer. The robot controller radio-communicates with the PC through ISM 2.4GHz radio modules. Furthermore, the controller has a Bluetooth module which enables it to send measurement data for convinient visualisation in the Matlab/Simulink enviroment.

11

Indoor navigation using particle filter and sensor fusion

Köping L., Mühsam T., Ofenberg C., Czech B., Bernard M., Schmera J., Deinzer F.

Annual of Navigation

|

2012

|

No. 19, part 2

31--40

EN

In this paper we present an indoor localization system based on particle filter and multiple sensor data like acceleration, angular velocity and compass data. With this approach we tackle the problem of documentation on large building yards during the construction phase. Due to the circumstances of such an environment we cannot rely on any data from GPS, Wi-Fi or RFID. Moreover this work should serve us as a first step towards an all-in-one navigation system for mobile devices. Our experimental results show that we can achieve high accuracy in position estimation.

12

Failure mode analysis to define process monitoring systems

McLeay T., Turner M. S.

Journal of Machine Engineering

|

2011

|

Vol. 11, No. 4

118--129

EN

The high costs of using skilled operators in production processes has built a demand for reduced manning, 'lights out machining' manufacture. Process monitoring systems have become a widely researched area in recent years since there is a need for intelligent systems to replace the manual intervention in existing processes. Furthermore, using modern sensors and signal processing techniques, monitoring systems can obtain more informatio about a process and therefore reduce costs further though maximised life of cutting tools, optimised cutting parameters and reduced scrap or re-work. With many application areas available, such as tool condition monitoring, chatter avoidance or feedback control of cutting parameters, it is not always apparent what the key aspects required by an intelligent monitoring system are. In addition, different machining processes have different demands and limitations for monitoring. This paper considers an analytical approach to define the requirements of a monitoring system. A process failure mode effect analysis (FMEA) is carried out to determine the weaknesses of current production processes. From this analysis, the relationships between failures, causes and effects can be used to populate conditional relationships between process faults and sensor signal features in a monitoring system.

13

Multisensor Tracking of Marine Targets : Decentralized Fusion of Kalman and Neural Filters

Stateczny A., Kazimierski W.

International Journal of Electronics and Telecommunications

|

2011

|

Vol. 57, No. 1

65-70

EN

This paper presents an algorithm of multisensor decentralized data fusion for radar tracking of maritime targets. The fusion is performed in the space of Kalman Filter and is done by finding weighted average of single state estimates provided be each of the sensors. The sensors use numerical or neural filters for tracking. The article presents two tracking methods - Kalman Filter and General Regression Neural Network, together with the fusion algorithm. The structural and measurement models of moving target are determined. Two approaches for data fusion are stated - centralized and decentralized - and the latter is thoroughly examined. Further, the discussion on main fusing process problems in complex radar systems is presented. This includes coordinates transformation, track association and measurements synchronization. The results of numerical experiment simulating tracking and fusion process are highlighted. The article is ended with a summary of the issues pointed out during the research.

14

Zastosowanie czujników inercyjnych i metody Monte Carlo do korekcji odczytów GPS w terenie miejskim

Barański R., Polańczyk M., Strumiłło R.

Elektronika : konstrukcje, technologie, zastosowania

|

2010

|

Vol. 51, nr 10

115-118

PL

W artykule omówiono zastosowanie symulacyjnej metody Monte Carlo do poprawy dokładności odczytów GPS (ang. Global Positioning System) w terenie miejskim. Zaprojektowany układ elektroniczny jest elementem systemu do nawigacji pieszej osób niewidomych. W terenie miejskim, na skutek odbić i wielodrogowości sygnałów od satelitów, odczyty GPS są obarczone znacznym błędem dochodzącym do kilkudziesięciu metrów. Jednoczesne odczyty z akcelerometru oraz żyroskopu służą do pomiaru względnego przemieszczenia, a następnie są porównywane z odczytami GPS. Algorytm symulacji wykorzystujący metodę Monte Carlo, służy do wyznaczenia najbardziej prawdopodobnego położenia geograficznego. Zastosowany układ umożliwia nawet kilkukrotne zmniejszenie błędu wyznaczanego położenia geograficznego.

EN

The article presents an application of recursive Monte Carlo method for correcting GPS readouts in an urban environment. The prototype was designed with a view of a pedestrian navigation device for the blind. GPS readouts are at times very inaccurate in an urban environment (reaching several dozens of meters) due to multipath propagation and reflections from buildings, The device houses an accelerometer and gyroscope for estimating the relative motion of the device. This relative displacement is correlated with GPS readouts. An algorithm based on the Monte Carlo simulation is used for assessing the most probable geographical location of the user. From the urban test of the method we conclude that the pro-posed dead reckoning solution improves on GPS receiver readouts by several times.

15

Application of stereovision, digital maps and inertial sensors for estimation of geographical location

Barański P., Polańczyk M., Strumiłło P.

Challenges of Modern Technology

|

2010

|

Vol. 1, no. 1

65--68

EN

The paper presents an approach that integrates stereoscopic images, numerical maps of terrain and inertial sensors’ signals for estimation of geographical location of system user. The proposed solution improves on the GPS system in terms of accuracy and it can be used also inside buildings where GPS readouts are not available. The system was designed with a view of blind pedestrians. The prototype employs the particle fi ltering algorithm to fuse data from diff erent sources.