PL
 |
EN
Preferencje help
Polish version English version Język
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 14

Liczba wyników na stronie
first rewind previous Strona / 1 next fast forward last
Wyniki wyszukiwania
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 1 next fast forward last
1
Content available Human - machine interface for presentation robot
Krejsa J., Ondrousek V.
Journal of Automation Mobile Robotics and Intelligent Systems
|
2012
|
Vol. 6, No. 2
17-21
EN
The purpose of mobile presentation robot is to interact with the users providing the required information. This paper presents the approach used in the highest software layer of autonomous mobile robot Advee used commercially for presentation purposes. The requirements for the layer are discussed together with available means of the robot. The particular building blocks and overall structure of the module are shown and key features are described in detail together with the behavior definition. Given module serves successfully when exploited to variable environment represented by people with computer literacy of great variation as proved during module verification tests.
2
Chaos in drive system
Houfek L., Kratochvil C, Krejsa J., Navrat Τ.
Modelling and Optimization of Physical Systems
|
2009
|
z. 8
55--58
EN
The paper is focused on analysis of dynamic properties of drive systems. It deseribes the possible ways of stability analysis and possible ways of analysis of bifurcation of steady states and possible oceurrence of chaotic behavior.
3
Scan matching based SLAM - dealing with dynamic obstacles
Krejsa J., Vechet S.
Modelling and Optimization of Physical Systems
|
2008
|
z. 7
59--62
EN
Localization and mapping is essential task in autonomous mobile robotics. There is a number of methods dealing with the task. The method called Potential-Based Scan Matching uses proximity sensor data and does not require the odometry readings for successful localization. The method is resistant towards the noise in proximity sensors. This paper is focused on testing the method in dynamically changing environment. Tests were performed for variable size of obstacles and speed of its motion.
4
Bifurcation diagram for drive system
Houfek L., Kratochvil C., Krejsa J., Navrat T
Modelling and Optimization of Physical Systems
|
2008
|
z. 7
43--46
EN
The paper is focused on analysis of dynamic properties of drive systems. It describes the possible ways of stability analysis and possible ways of analysis of bifurcation of steady states and possible occurrence of chaotic behavior.
5
Bifurcation and chaos in electromechanical drive systems with small motors
Kratochvil C., Houfek L., Houfek M., Krejsa J.
Modelling and Optimization of Physical Systems
|
2008
|
z. 7
55--58
EN
The purpose of this article is to provide an elementary introduction to the subject of chaos in the electromechanical drive systems. In this article, we explore chaotic solutions of maps and continuous time systems. These solutions are also bounded like equilibrium, periodic and quasiperiodic solutions.
6
Chaotic behavior description in technical systems
Houfek L., Kratochvil C., Krejsa J., Houfek M., Navrat Τ.
Modelling and Optimization of Physical Systems
|
2007
|
z. 6
77--80
EN
Chaotic behavior of technical systems is lately under great interest of researchers. The paper describes a possibility to analyze system which exhibits chaotic oscillations. For simplicity the model of Duffing oscillator was selected as analyzed case, as the chaotic oscillations occur in this model. Bifurcation diagram and phase plane analysis are used as analysis tool.
7
Singular cases of parallel and serial mechanism
Houfek L., Brezina L., Krejsa J.
Zeszyty Naukowe Katedry Mechaniki Stosowanej / Politechnika Śląska
|
2006
|
z. 31
59-62
EN
The paper describes the methodology for calculation of singular cases in mechanisms. The singular cases have been defined as those positions in the working space, where the system loses the univocal solution. The solution of two mechanisms - serial and parallel - is presented.
8
Identification of shock absorber nonlinear model characteristics
Krejsa J., Houfek L.
Zeszyty Naukowe Katedry Mechaniki Stosowanej / Politechnika Śląska
|
2006
|
z. 31
99-102
EN
The paper shows the possible way of identification of shock absorber nonlinear model characteristics using genetic algorithm. 2 DOF quarter car model is used with nonlinear characteristics of main spring and damping forces defined as piecewise functions. Using time courses of position, velocity and acceleration of both masses under kinematic excitation the characteristics are found. Simulation results are satisfactory.
9
Bifurcation and chaos in drive systems
Kratochvil C., Houfek L., Houfek M., Krejsa J.
Zeszyty Naukowe Katedry Mechaniki Stosowanej / Politechnika Śląska
|
2006
|
z. 31
89-94
EN
The paper is focused on analysis of dynamic properties of controlled drive systems. It describes the possible ways of stability analysis. Paper is also focused on bifurcation of steady states and possible oceurence of chaotic behavior.
10
Q-learning: from discrete to continuous representation
Věchet S., Krejsa J.
Elektronika : konstrukcje, technologie, zastosowania
|
2004
|
Vol. 45, nr 8-9
12-14
EN
Q-learning algorithm in its standard form is limited by discrete states and actions. In order to improve quality of the control the algorithm must be modified to enable direct use of continuous variables. One possible way, presented in the paper, is to replace the table, by suitable approximator.
PL
Algorytm metody Q-learning w swej standardowej formie jest ograniczony przez dyskretne stany i działania. W celu ulepszenia jakości sterowania algorytm ten trzeba zmodyfikować, aby umożliwić bezpośrednie wykorzystanie zmiennych ciągłych. Jednym z możliwych sposobów jest przedstawione w artykule zastąpienie tablicy odpowiednim aproksymatorem.
11
Modelling of electromechanical drive system failures
Kratochvíl C., Procházka F., Krejsa J.
Elektronika : konstrukcje, technologie, zastosowania
|
2004
|
Vol. 45, nr 8-9
174-178
EN
Analysis of dynamic properties of interactive drive systems is lately the object of interest among researchers from both academic and industry fields. This interest is reflection of mutually contradicting requirements put into the development of current drive systems, mainly the drives itself. On one hand we see the performance and failure-free operation requirements, on the other hand the reduction of energy input, size minimisation and operation automation. The paper introduces some of the problems involved in this field.
PL
Analiza dynamicznych właściwości interakcyjnych układów napędowych stała się ostatnio przedmiotem zainteresowania pracowników naukowo-badawczych zarówno z kręgów akademickich jak i przemysłowych. Zainteresowanie to jest odzwierciedleniem wzajemnie sprzecznych wymagań stawianych przy rozwoju obecnych układów napędowych, głównie samych napędów. Z jednej strony mamy wymagania dotyczące osiągów oraz bezawaryjnego działania, a z drugiej zmniejszenia poboru energii, minimalizacji wielkości oraz automatyzacji działania. Artykuł przedstawia niektóre z problemów związanych z tą dziedziną.
12
Global versus local approximation in inverse problems
Krejsa J., Věchet S., Pulchart J.
Elektronika : konstrukcje, technologie, zastosowania
|
2004
|
Vol. 45, nr 8-9
57-60
EN
The paper compares global end local approximation methods used in inverse problems. Global approximators are represented by feedforward multilayer neural network (FFNN); local approximators are represented by Locally Weighted Regression (LWR) and Receptive Field Weighted Regression (RFWR).
PL
W artykule porównano metody globalnej i lokalnej aproksymacji w zagadnieniach odwrotnych. Aproksymatory globalne reprezentuje wielowarstwowa sieć neuronowa ze sprzężeniem do przodu (FFNN), natomiast aproksymatory lokalne regresja lokalnie ważona (LWR) oraz regresja ważona pola otwartego (RFWR).
13
Použití algoritmu umělé inteligence při modelování dynamickych vlastností pohonovych soustav
Kratochvil C., Krejsa J.
Zeszyty Naukowe Katedry Mechaniki Stosowanej / Politechnika Śląska
|
2001
|
z. 16
81-84
EN
The paper presents application of classical methods of modelling and methods of artificial inteligence for investigations of dynamic properties of drive systems. Comparision of results obtained from classical and heuristic approach shows some characteristic properties of neuronal networks.
14
Recurrent neural networks for non-linear system identification
Krejsa J., Dolezal R.
Zeszyty Naukowe Katedry Mechaniki Stosowanej / Politechnika Śląska
|
1999
|
z. 11
37-40
EN
The contribution shows Elman neural network used for non-linear system identification. A simple example of non-linear dynamic system is used to test the performance of networks with different number of hidden units. Results shows that higher number of hidden neurons surprisingly degrades the performance of the network both in training and generalisation abilities.
PL
W pracy przedstawiono zastosowanie neuronowej sieci Elmana do identyfikacji układu nieliniowego. Na przykładzie prostego nieliniowego układu dynamicznego zbadano osiągi sieci z różną liczbą ukrytych neuronów. Wyniki wskazują, że większe liczb)' ukrytych neuronów zmniejszają zdolności treningowe i uogólniające sieci.
first rewind previous Strona / 1 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.