Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Incremental learning of skills in a task-parameterized Gaussian Mixture Model

Autor
Hoyos, J.; Prieto, F.; Alenyà, G.; Torras, C.
Tipus d'activitat
Article en revista
Revista
Journal of intelligent and robotic systems
Data de publicació
2016
Volum
82
Número
1
Pàgina inicial
81
Pàgina final
99
DOI
https://doi.org/10.1007/s10846-015-0290-3 Obrir en finestra nova
Projecte finançador
RobInstruct: Instructing robots using natural communication skills - TIN2014-58178-R
TextilRob: Robots para el manejo de ropa - 201550E028 - CSIC project
Repositori
http://hdl.handle.net/2117/102402 Obrir en finestra nova
URL
http://link.springer.com/article/10.1007%2Fs10846-015-0290-3 Obrir en finestra nova
Resum
Programming by demonstration techniques facilitate the programming of robots. Some of them allow the generalization of tasks through parameters, although they require new training when trajectories different from the ones used to estimate the model need to be added. One of the ways to re-train a robot is by incremental learning, which supplies additional information of the task and does not require teaching the whole task again. The present study proposes three techniques to add trajectories to ...
Citació
Hoyos, J., Prieto, F., Alenyà, G., Torras, C. Incremental learning of skills in a task-parameterized Gaussian Mixture Model. "Journal of intelligent and robotic systems", 2016, vol. 82, núm. 1, p. 81-99.
Paraules clau
Incremental learning, Programming by demonstration, ROBOTS, Robot learning, cooperative systems, learning (artificial intelligence), uncertainty handling
Grup de recerca
ROBiri - Grup de Robòtica de l'IRI

Participants