Implementation Of Feeding Task Via Learning From Demonstration
Keywords
Activities of daily living tasks (ADLs); Feeding task; Gaussian mixture model (GMM); Human robot interaction (HRI); Learning by imitation; Learning from demonstration (LFD); Meal assistant; Probabilistic motion encoding; Programming by demonstration (PBD)
Abstract
In this paper, a Learning From Demonstration (LFD) approach is used to design an autonomous meal-assistant agent. The feeding task is modeled as a mixture of Gaussian distributions. Using the data collected via kinesthetic teaching, the parameters of Gaussian Mixture Model (GMM) are learned using Gaussian Mixture Regression (GMR) and Expectation Maximization (EM) algorithm. Reproduction of feeding trajectories for different environments is obtained by solving a constrained optimization problem. In this method we show that obstacles can be avoided by robot's end-effector by adding a set of extra constraints to the optimization problem. Finally, the performance of the designed meal assistant is evaluated in two feeding scenario experiments: one considering obstacles in the path between the bowl and the mouth and the other without.
Publication Date
4-2-2018
Publication Title
Proceedings - 2nd IEEE International Conference on Robotic Computing, IRC 2018
Volume
2018-January
Number of Pages
274-277
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/IRC.2018.00058
Copyright Status
Unknown
Socpus ID
85049608147 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85049608147
STARS Citation
Ettehadi, Nabil and Behal, Aman, "Implementation Of Feeding Task Via Learning From Demonstration" (2018). Scopus Export 2015-2019. 9545.
https://stars.library.ucf.edu/scopus2015/9545