Detail publikace

Artificial Neural Network Application To Walk Of A Four Legged Robot

BEZDÍČEK, M. GREPL, R. ŠVEHLÁK, M. CHMELÍČEK, J.

Český název

Artificial Neural Network Application To Walk Of A Four Legged Robot

Anglický název

Artificial Neural Network Application To Walk Of A Four Legged Robot

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

cs

Originální abstrakt

This paper presents simple method to extrapolate walk of a four legged robot. Movement of the robot is actuated by twelve servo-drives. This technique of walking is based on a few stable positions of robot body. To reach smooth movement, is sequence of positions extrapolated by artificial neural network. ANN is trained directly on values of servo angles. The servo angles are corresponding to the stable positions. Created neural network is able to extrapolate any posture for continuously changing input parameter. The input parameter is information about required position of the movement. Outputs of network are values of servo angles. Speed of the movement is dependent on the input parameter alternation rate. Introduced technique of walking is useful for plain surface moving.

Český abstrakt

This paper presents simple method to extrapolate walk of a four legged robot. Movement of the robot is actuated by twelve servo-drives. This technique of walking is based on a few stable positions of robot body. To reach smooth movement, is sequence of positions extrapolated by artificial neural network. ANN is trained directly on values of servo angles. The servo angles are corresponding to the stable positions. Created neural network is able to extrapolate any posture for continuously changing input parameter. The input parameter is information about required position of the movement. Outputs of network are values of servo angles. Speed of the movement is dependent on the input parameter alternation rate. Introduced technique of walking is useful for plain surface moving.

Anglický abstrakt

This paper presents simple method to extrapolate walk of a four legged robot. Movement of the robot is actuated by twelve servo-drives. This technique of walking is based on a few stable positions of robot body. To reach smooth movement, is sequence of positions extrapolated by artificial neural network. ANN is trained directly on values of servo angles. The servo angles are corresponding to the stable positions. Created neural network is able to extrapolate any posture for continuously changing input parameter. The input parameter is information about required position of the movement. Outputs of network are values of servo angles. Speed of the movement is dependent on the input parameter alternation rate. Introduced technique of walking is useful for plain surface moving.

Klíčová slova anglicky

artificial neural network, walking robot, gait

Rok RIV

2004

Vydáno

01.01.2004

Místo

Svratka

ISBN

80-85918-88-9

Kniha

Engineering mechanics 2004

Počet stran

2

BIBTEX


@inproceedings{BUT12234,
  author="Milan {Bezdíček} and Robert {Grepl} and Michal {Švehlák} and Jaroslav {Chmelíček},
  title="Artificial Neural Network Application To Walk Of A Four Legged Robot",
  booktitle="Engineering mechanics 2004",
  year="2004",
  month="January",
  address="Svratka",
  isbn="80-85918-88-9"
}