A new neural architecture based on ART and AVITE models for anticipatory sensory-motor coordination in robotics
Compartir
Estadísticas
Ver Estadísticas de usoMetadatos
Mostrar el registro completo del ítemGrupo de investigación
Grupo de Electromagnetismo y Materia (GEM); Grupo de Neurotecnología, Control y Robótica. (NEUROCOR)Área de conocimiento
Teoría de la Señal y las ComunicacionesPatrocinadores
This work was supported in part by the SENECA Fundation (Spain) PCMC75/ 00078/FS/02, and the Spanish Science & Technology Ministry (MCYT) under TIC 2003-08164-C03-03 research project.Fecha de publicación
2004-10Editorial
Springer-VerlagCita bibliográfica
PEDREÑO MOLINA, J.L., FLÓREZ GIRÁLDEZ, O., LÓPEZ CORONADO, J. A new neural architecture based on ART and AVITE models for anticipatory sensory-motor coordination in robotics. Lecture Notes in Computer Science, 3315/2004: 524-534, Octubre 2004. ISSN 0302-9743Revisión por pares
SíPalabras clave
RobóticaRedes neuronales
Sistemas robóticos
Sistemas de coordinación sensorio motor
Robotic
Neural Network
Robotic system
Sensory-motor coordinate systems
Resumen
In this paper a novel sensory-motor neural controller applied to robotic
systems for reaching and tracking targets is proposed. It is based on how
the human system projects the sensorial stimulus over the motor joints, sending
motor commands to each articulation and avoiding, in most phases of the movement,
the feedback of the visual information. In this way, the proposed neural
architecture autonomously generates a learning cells structure based on the
adaptive resonance theory, together with a neural mapping of the sensory-motor
coordinate systems in each cell of the arm workspace. It permits a fast openloop
control based on propioceptive information of a robot and a precise
grasping position in each cell by mapping 3D spatial positions over redundant
joints. The proposed architecture has been trained, implemented and tested in a
visuo-motor robotic platform. Robustness, precision and velocity characteristics
have been validated.
Colecciones
- Artículos [1752]
El ítem tiene asociados los siguientes ficheros de licencia:
Redes sociales