Březina, Tomáš - Výsledky hledání - Digitální repozitář

host :: přihlásit Digitální repozitář
		Hledej		Nový záznam		Nápověda		O repozitáři

Hlavní stránka > Výsledky hledání: Březina, Tomáš

Hledej:

Tipy pro vyhledávaní :: Rozšířené hledání

Hledej ve sbírkách:

Seřadit podle:	Zobrazit výsledky:	Výstupní formát:

	Using modified Q-learning with LWR for inverted pendulum control Věchet, S. ; Míček, P. ; Březina, Tomáš Paper shows modified version of Q-learning together with locallz weighted learning method used for simple control task. Úplný záznam
	The using some approximating methods by inverse modelling Míček, P. ; Věchet, S. ; Březina, Tomáš Paper compares making of inverse kinematic models using different approximation methods. Úplný záznam
	Control and synchronization drive unit of leg of walking robot Houška, P. ; Březina, Tomáš ; Singule, V. The contribution explores several approaches in control and synchronization of leg drives. It further deals with the selection of suitable trajectory for the movement of leg end point. Kinematics of walking robot leg movement is essentially influenced by used drive units and its control. The speed of leg endpoint relocation and amount of energy consumed in particular movements depends mainly on the drive control. Leg control is proposed in such way that the leg can be considered as independent system. Úplný záznam
	Using Q-learning for four-legged robot walking control Březina, Tomáš ; Houška, P. ; Singule, V. Significant goal in walking robot design is realization of autonomous system which is capable of motion in unknown environment. One of the possibilities how to reach necessary adaptability of control system without modeling of complex and unpredictable cases of system behaviour is the application of machine learning. From various learning paradigms the Q-learning is particularly attractive. Úplný záznam
	The use of leg landing information for walking robot control Houška, P. ; Ehrenberger, Zdeněk ; Březina, Tomáš ; Singule, V. The leg design is described in the contribution. Some possibilities of leg control and requirements related to both sensor system of the leg and complete robot are assigned. The assessment of the force, coming from sensor system, by which the endpoint of the leg acts on the terrain is considerably important. The information about leg landing is necessary for robot control in non-regular terrain. Úplný záznam
	Walking gait of four-legged robot obtained throug Q learning Březina, Tomáš ; Houška, P. ; Singule, V. ; Sedlák, P. The possible method of walking policy obtaining of four-legged robot through Q-learning is discussed in the contribution. Q-learning is implemented using architecture represented by nondeterministic state machine that defines both possible discrete states and admissible transitions between them. Úplný záznam
	The control of active magnetic bearing using two-phase Q-learning Březina, Tomáš ; Krejsa, Jiří The paper compares controllers based on two phase Q-learning with PID controller on active magnetic bearing control task. Úplný záznam
	Active magnetic bearing control through Q-learing Březina, Tomáš ; Krejsa, Jiří ; Kratochvíl, Ctirad Paper is focused on the control of active magnetic bearing using improved version of Q-learning. The improvement subsists in separating Q-learning into two phases - efficient prelearning phase and tutorage phase working with real system. Úplný záznam
	Using Modified Q-learning with LWR for Inverted Pendulum Control Věchet, S. ; Krejsa, Jiří ; Březina, Tomáš Locally Weighted Regression together with Q-learning is demonstrated in control task of a simple model of inverted pendulum. Úplný záznam
	Determination of Q-function optimum grid applied on active magnetic bearing control task Březina, Tomáš ; Krejsa, Jiří AMB control task can be solved using reinforcement learning based method called Q learning. However there are certain issues remaining to solve, mainly the convergence speed. Two-phase Q learning can be used to speed up the learning process. When table is used as Q function approximation the learning speed and precision of found controllers depend highly on the Q function table grid. The paper is denoted to determination of optimum grid with respect to the properties of controllers found by given method. Úplný záznam

Viz též: podobná jména autorů
20	BŘEZINA, Tomáš
2	Březina, T.

Chcete být upozorněni, pokud se objeví nové záznamy odpovídající tomuto dotazu?
Přihlásit se k odběru RSS.

Digitální repozitář :: :: :: ::
Powered by v1.1.2
Spravuje

Tato stránka je dostupná také v následujících jazycích:
Česky English