TY - GEN
T1 - Exploiting the task space redundancy in robot programming by demonstration
AU - Alizadeh, Tohid
AU - Karimi, Navab
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/10/5
Y1 - 2018/10/5
N2 - Robot programming by demonstration (PbD) in the unstructured environment is usually a challenging task, which requires to take into account different parameters. One of the main difficulties in an unstructured environment is that the location and orientation of the objects may change dynamically, requiring the learning algorithm to posses acceptable generalization and extrapolation capabilities. There are several category of PbD approaches proposed to tackle such issues, some of which look at the objects in the environment as external parameters (task parameters, or TPs) and assume that the movement or trajectory is modulated by such objects. While, some of those TPs might not be completely observable all the time, introducing additional difficulties on the task learning. On the other hand, in specific situations two or more objects may contain similar information for the task execution. In this paper, an approach based on task-parameterized Gaussian mixture model (TP-GMM) for PbD is proposed that exploits the redundancy in the environment to deal with the partial observability of the task parameters and provide a fault tolerant approach in the sense of availability of the task parameters. The proposed approach is tested using some simulation experiments.
AB - Robot programming by demonstration (PbD) in the unstructured environment is usually a challenging task, which requires to take into account different parameters. One of the main difficulties in an unstructured environment is that the location and orientation of the objects may change dynamically, requiring the learning algorithm to posses acceptable generalization and extrapolation capabilities. There are several category of PbD approaches proposed to tackle such issues, some of which look at the objects in the environment as external parameters (task parameters, or TPs) and assume that the movement or trajectory is modulated by such objects. While, some of those TPs might not be completely observable all the time, introducing additional difficulties on the task learning. On the other hand, in specific situations two or more objects may contain similar information for the task execution. In this paper, an approach based on task-parameterized Gaussian mixture model (TP-GMM) for PbD is proposed that exploits the redundancy in the environment to deal with the partial observability of the task parameters and provide a fault tolerant approach in the sense of availability of the task parameters. The proposed approach is tested using some simulation experiments.
KW - Learning by imitation
KW - Redundancy in the unstructured environment
KW - Robot learning
KW - Robot programming by demonstration
UR - http://www.scopus.com/inward/record.url?scp=85056351531&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85056351531&partnerID=8YFLogxK
U2 - 10.1109/ICMA.2018.8484455
DO - 10.1109/ICMA.2018.8484455
M3 - Conference contribution
AN - SCOPUS:85056351531
T3 - Proceedings of 2018 IEEE International Conference on Mechatronics and Automation, ICMA 2018
SP - 2394
EP - 2399
BT - Proceedings of 2018 IEEE International Conference on Mechatronics and Automation, ICMA 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 15th IEEE International Conference on Mechatronics and Automation, ICMA 2018
Y2 - 5 August 2018 through 8 August 2018
ER -