TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Learning movement synchronization in multi-component robotic systems

Tutkimustuotosvertaisarvioitu

Standard

Learning movement synchronization in multi-component robotic systems. / Thabet, Mohammad; Montebelli, Alberto; Kyrki, Ville.

2016 IEEE International Conference on Robotics and Automation (ICRA) . IEEE, 2016. s. 249-256.

Tutkimustuotosvertaisarvioitu

Harvard

Thabet, M, Montebelli, A & Kyrki, V 2016, Learning movement synchronization in multi-component robotic systems. julkaisussa 2016 IEEE International Conference on Robotics and Automation (ICRA) . IEEE, Sivut 249-256, IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, 1/01/00. https://doi.org/10.1109/ICRA.2016.7487141

APA

Thabet, M., Montebelli, A., & Kyrki, V. (2016). Learning movement synchronization in multi-component robotic systems. teoksessa 2016 IEEE International Conference on Robotics and Automation (ICRA) (Sivut 249-256). IEEE. https://doi.org/10.1109/ICRA.2016.7487141

Vancouver

Thabet M, Montebelli A, Kyrki V. Learning movement synchronization in multi-component robotic systems. julkaisussa 2016 IEEE International Conference on Robotics and Automation (ICRA) . IEEE. 2016. s. 249-256 https://doi.org/10.1109/ICRA.2016.7487141

Author

Thabet, Mohammad ; Montebelli, Alberto ; Kyrki, Ville. / Learning movement synchronization in multi-component robotic systems. 2016 IEEE International Conference on Robotics and Automation (ICRA) . IEEE, 2016. Sivut 249-256

Bibtex - Lataa

@inproceedings{a28ae4bf1e8b46e3b21f5c37741b5af0,
title = "Learning movement synchronization in multi-component robotic systems",
abstract = "Imitation learning of tasks in multi-component robotic systems requires capturing concurrency and synchronization requirements in addition to task structure. Learning time-critical tasks depends furthermore on the ability to model temporal elements in demonstrations. This paper proposes a modeling framework based on Petri nets capable of modeling these aspects in a programming by demonstration context. In the proposed approach, models of tasks are constructed from segmented demonstrations as task Petri nets, which can be executed as discrete controllers for reproduction. We present algorithms that automatically construct models from demonstrations, showing how elements of time-critical tasks can be mapped into task Petri net elements. The approach is validated by an experiment in which a robot plays a musical passage on a keyboard.",
author = "Mohammad Thabet and Alberto Montebelli and Ville Kyrki",
year = "2016",
month = "6",
day = "8",
doi = "10.1109/ICRA.2016.7487141",
language = "English",
isbn = "9781467380263",
publisher = "IEEE",
pages = "249--256",
booktitle = "2016 IEEE International Conference on Robotics and Automation (ICRA)",

}

RIS (suitable for import to EndNote) - Lataa

TY - GEN

T1 - Learning movement synchronization in multi-component robotic systems

AU - Thabet, Mohammad

AU - Montebelli, Alberto

AU - Kyrki, Ville

PY - 2016/6/8

Y1 - 2016/6/8

N2 - Imitation learning of tasks in multi-component robotic systems requires capturing concurrency and synchronization requirements in addition to task structure. Learning time-critical tasks depends furthermore on the ability to model temporal elements in demonstrations. This paper proposes a modeling framework based on Petri nets capable of modeling these aspects in a programming by demonstration context. In the proposed approach, models of tasks are constructed from segmented demonstrations as task Petri nets, which can be executed as discrete controllers for reproduction. We present algorithms that automatically construct models from demonstrations, showing how elements of time-critical tasks can be mapped into task Petri net elements. The approach is validated by an experiment in which a robot plays a musical passage on a keyboard.

AB - Imitation learning of tasks in multi-component robotic systems requires capturing concurrency and synchronization requirements in addition to task structure. Learning time-critical tasks depends furthermore on the ability to model temporal elements in demonstrations. This paper proposes a modeling framework based on Petri nets capable of modeling these aspects in a programming by demonstration context. In the proposed approach, models of tasks are constructed from segmented demonstrations as task Petri nets, which can be executed as discrete controllers for reproduction. We present algorithms that automatically construct models from demonstrations, showing how elements of time-critical tasks can be mapped into task Petri net elements. The approach is validated by an experiment in which a robot plays a musical passage on a keyboard.

U2 - 10.1109/ICRA.2016.7487141

DO - 10.1109/ICRA.2016.7487141

M3 - Conference contribution

SN - 9781467380263

SP - 249

EP - 256

BT - 2016 IEEE International Conference on Robotics and Automation (ICRA)

PB - IEEE

ER -