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 trajectory by a 7-DoF manipulator. ; Preprint
Dynamically consistent probabilistic model for robot motion learning
2012-01-01
Miscellaneous
Electronic Resource
English
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Representació del coneixement , Interlibrary loan , learning (artificial intelligence) manipulators robot dynamics PARAULES AUTOR: learning from demonstration , kinesthetic teaching , Gaussian mixture regression (GMR) , hidden Markov models (HMM) , Préstec interbibliotecari , Classificació INSPEC::Automation::Robots::Intelligent robots
DDC: | 629 |
A Consistent Failure Model for Probabilistic Analysis of Shallow Foundations
HENRY – Federal Waterways Engineering and Research Institute (BAW) | 2011
|Learning Probabilistic Structure for Human Motion Detection
British Library Conference Proceedings | 2001
|