Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Dynamically consistent probabilistic model for robot motion learning

Autor
Pardo, D.E.; Rozo, L.; Alenyà, G.; Torras, C.
Tipus d'activitat
Presentació treball a congrés
Nom de l'edició
IROS'2012 Workshop on Learning and Interaction in Haptic Robots
Any de l'edició
2012
Data de presentació
2012
Llibre d'actes
Proceedings of the IROS'2012 Workshop on Learning and Interaction in Haptic Robots
Pàgina inicial
1
Pàgina final
2
Repositori
http://hdl.handle.net/2117/17450 Obrir en finestra nova
URL
http://www.iit.it/images/stories/advanced-robotics/Workshops/Iros_2012/Pardo-IROS2012WS.pdf Obrir en finestra nova
Resum
This work presents a probabilistic model for learning robot tasks from human demonstrations using kinesthetic teaching. The difference with respect to previous works is that a complete state of the robot is used to obtain a consistent representation of the dynamics of the task. The learning framework is based on hidden Markov models and Gaussian mixture regression, used for coding and reproducing the skills. Benefits of the proposed approach are shown in the execution of a simple self-crossing t...
Citació
Pardo, D.E. [et al.]. Dynamically consistent probabilistic model for robot motion learning. A: Workshop on Learning and Interaction in Haptic Robots. "Proceedings of the IROS'2012 Workshop on Learning and Interaction in Haptic Robots". Algarve: 2012, p. 1-2.
Paraules clau
Gaussian mixture regression (GMR), hidden Markov models (HMM), kinesthetic teaching, learning (artificial intelligence) manipulators robot dynamics PARAULES AUTOR: learning from demonstration
Grup de recerca
GREC - Grup de Recerca en Enginyeria del Coneixement
ROBiri - Grup de Robòtica de l'IRI

Participants