TY - GEN
T1 - Learning from demonstration with partially observable task parameters using dynamic movement primitives and Gaussian process regression
AU - Alizadeh, Tohid
AU - Malekzadeh, Milad
AU - Barzegari, Soheila
N1 - Publisher Copyright:
© 2016 IEEE.
Copyright:
Copyright 2017 Elsevier B.V., All rights reserved.
PY - 2016/9/26
Y1 - 2016/9/26
N2 - The problem of learning from demonstration in the case of partially observable external task parameters is addressed in this paper. Such a situation could be present in the daily life scenarios, where information regarding some task parameters are missing or partially available. In the first step, one dynamic movement primitives (DMP) model is learned for each demonstration trajectory. The parameters of the learned DMP model are recorded together with the corresponding external task parameters (query points), to create a database. Then Gaussian process regression (GPR) is used to create a model for the external task parameters and the DMP parameters. During reproduction, DMP parameters are retrieved by providing the new external task parameters and are used to regenerate the trajectory. It is shown how the learning approach could be adapted to deal with the partially observable external task parameters and regenerate the proper trajectory. The proposed methodology is applied to learn a via-point passing experiment with a lightweight robot manipulator (KUKA robot) to illustrate the efficacy of the proposed approach.
AB - The problem of learning from demonstration in the case of partially observable external task parameters is addressed in this paper. Such a situation could be present in the daily life scenarios, where information regarding some task parameters are missing or partially available. In the first step, one dynamic movement primitives (DMP) model is learned for each demonstration trajectory. The parameters of the learned DMP model are recorded together with the corresponding external task parameters (query points), to create a database. Then Gaussian process regression (GPR) is used to create a model for the external task parameters and the DMP parameters. During reproduction, DMP parameters are retrieved by providing the new external task parameters and are used to regenerate the trajectory. It is shown how the learning approach could be adapted to deal with the partially observable external task parameters and regenerate the proper trajectory. The proposed methodology is applied to learn a via-point passing experiment with a lightweight robot manipulator (KUKA robot) to illustrate the efficacy of the proposed approach.
UR - http://www.scopus.com/inward/record.url?scp=84992347130&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84992347130&partnerID=8YFLogxK
U2 - 10.1109/AIM.2016.7576881
DO - 10.1109/AIM.2016.7576881
M3 - Conference contribution
AN - SCOPUS:84992347130
VL - 2016-September
T3 - IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM
SP - 889
EP - 894
BT - 2016 IEEE International Conference on Advanced Intelligent Mechatronics, AIM 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2016 IEEE International Conference on Advanced Intelligent Mechatronics, AIM 2016
Y2 - 12 July 2016 through 15 July 2016
ER -