Robust task execution through experience-based guidance for cognitive robots

Sanem Sariel; Petek Yildiz; Sertac Karapinar; Dogan Altan; Melis Kapotoglu

doi:10.1109/ICAR.2015.7251527

Robust task execution through experience-based guidance for cognitive robots

Sanem Sariel, Petek Yildiz, Sertac Karapinar, Dogan Altan, Melis Kapotoglu

Department of Artificial Intelligence and Data Engineering

Istanbul Technical University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

6 Citations (Scopus)

Abstract

Robustness in task execution requires tight integration of continual planning, monitoring, reasoning and learning processes. In this paper, we investigate how robustness can be ensured by learning from experience. Our approach is based on a learning guided planning process for a robot that gains its experience from action execution failures through lifelong experiential learning. Inductive Logic Programming (ILP) is used as the learning method to frame hypotheses for failure situations. It provides first-order logic representation of the robot's experience. The robot uses this experience to construct heuristics to guide its future decisions. The performance of the learning guided planning process is analyzed on our Pioneer 3-AT robot. The results reveal that the hypotheses framed for failure cases are sound and ensure safety and robustness in future tasks of the robot.

Original language	English
Title of host publication	Proceedings of the 17th International Conference on Advanced Robotics, ICAR 2015
Editors	Uluc Saranli, Sinan Kalkan
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	663-668
Number of pages	6
ISBN (Electronic)	9781467375092
DOIs	https://doi.org/10.1109/ICAR.2015.7251527
Publication status	Published - 13 Oct 2015
Event	17th International Conference on Advanced Robotics, ICAR 2015 - Istanbul, Turkey Duration: 27 Jul 2015 → 31 Jul 2015

Publication series

Name	Proceedings of the 17th International Conference on Advanced Robotics, ICAR 2015

Conference

Conference	17th International Conference on Advanced Robotics, ICAR 2015
Country/Territory	Turkey
City	Istanbul
Period	27/07/15 → 31/07/15

Bibliographical note

Publisher Copyright:
© 2015 IEEE.

Access to Document

10.1109/ICAR.2015.7251527

Cite this

Sariel, S., Yildiz, P., Karapinar, S., Altan, D., & Kapotoglu, M. (2015). Robust task execution through experience-based guidance for cognitive robots. In U. Saranli, & S. Kalkan (Eds.), Proceedings of the 17th International Conference on Advanced Robotics, ICAR 2015 (pp. 663-668). Article 7251527 (Proceedings of the 17th International Conference on Advanced Robotics, ICAR 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICAR.2015.7251527

Sariel, Sanem ; Yildiz, Petek ; Karapinar, Sertac et al. / Robust task execution through experience-based guidance for cognitive robots. Proceedings of the 17th International Conference on Advanced Robotics, ICAR 2015. editor / Uluc Saranli ; Sinan Kalkan. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 663-668 (Proceedings of the 17th International Conference on Advanced Robotics, ICAR 2015).

@inproceedings{ae6249432a384f89b96c280ce1758b28,

title = "Robust task execution through experience-based guidance for cognitive robots",

abstract = "Robustness in task execution requires tight integration of continual planning, monitoring, reasoning and learning processes. In this paper, we investigate how robustness can be ensured by learning from experience. Our approach is based on a learning guided planning process for a robot that gains its experience from action execution failures through lifelong experiential learning. Inductive Logic Programming (ILP) is used as the learning method to frame hypotheses for failure situations. It provides first-order logic representation of the robot's experience. The robot uses this experience to construct heuristics to guide its future decisions. The performance of the learning guided planning process is analyzed on our Pioneer 3-AT robot. The results reveal that the hypotheses framed for failure cases are sound and ensure safety and robustness in future tasks of the robot.",

author = "Sanem Sariel and Petek Yildiz and Sertac Karapinar and Dogan Altan and Melis Kapotoglu",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 17th International Conference on Advanced Robotics, ICAR 2015 ; Conference date: 27-07-2015 Through 31-07-2015",

year = "2015",

month = oct,

day = "13",

doi = "10.1109/ICAR.2015.7251527",

language = "English",

series = "Proceedings of the 17th International Conference on Advanced Robotics, ICAR 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "663--668",

editor = "Uluc Saranli and Sinan Kalkan",

booktitle = "Proceedings of the 17th International Conference on Advanced Robotics, ICAR 2015",

address = "United States",

}

Sariel, S, Yildiz, P, Karapinar, S, Altan, D & Kapotoglu, M 2015, Robust task execution through experience-based guidance for cognitive robots. in U Saranli & S Kalkan (eds), Proceedings of the 17th International Conference on Advanced Robotics, ICAR 2015., 7251527, Proceedings of the 17th International Conference on Advanced Robotics, ICAR 2015, Institute of Electrical and Electronics Engineers Inc., pp. 663-668, 17th International Conference on Advanced Robotics, ICAR 2015, Istanbul, Turkey, 27/07/15. https://doi.org/10.1109/ICAR.2015.7251527

Robust task execution through experience-based guidance for cognitive robots. / Sariel, Sanem; Yildiz, Petek; Karapinar, Sertac et al.
Proceedings of the 17th International Conference on Advanced Robotics, ICAR 2015. ed. / Uluc Saranli; Sinan Kalkan. Institute of Electrical and Electronics Engineers Inc., 2015. p. 663-668 7251527 (Proceedings of the 17th International Conference on Advanced Robotics, ICAR 2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Robust task execution through experience-based guidance for cognitive robots

AU - Sariel, Sanem

AU - Yildiz, Petek

AU - Karapinar, Sertac

AU - Altan, Dogan

AU - Kapotoglu, Melis

PY - 2015/10/13

Y1 - 2015/10/13

N2 - Robustness in task execution requires tight integration of continual planning, monitoring, reasoning and learning processes. In this paper, we investigate how robustness can be ensured by learning from experience. Our approach is based on a learning guided planning process for a robot that gains its experience from action execution failures through lifelong experiential learning. Inductive Logic Programming (ILP) is used as the learning method to frame hypotheses for failure situations. It provides first-order logic representation of the robot's experience. The robot uses this experience to construct heuristics to guide its future decisions. The performance of the learning guided planning process is analyzed on our Pioneer 3-AT robot. The results reveal that the hypotheses framed for failure cases are sound and ensure safety and robustness in future tasks of the robot.

AB - Robustness in task execution requires tight integration of continual planning, monitoring, reasoning and learning processes. In this paper, we investigate how robustness can be ensured by learning from experience. Our approach is based on a learning guided planning process for a robot that gains its experience from action execution failures through lifelong experiential learning. Inductive Logic Programming (ILP) is used as the learning method to frame hypotheses for failure situations. It provides first-order logic representation of the robot's experience. The robot uses this experience to construct heuristics to guide its future decisions. The performance of the learning guided planning process is analyzed on our Pioneer 3-AT robot. The results reveal that the hypotheses framed for failure cases are sound and ensure safety and robustness in future tasks of the robot.

UR - http://www.scopus.com/inward/record.url?scp=84957689333&partnerID=8YFLogxK

U2 - 10.1109/ICAR.2015.7251527

DO - 10.1109/ICAR.2015.7251527

M3 - Conference contribution

AN - SCOPUS:84957689333

T3 - Proceedings of the 17th International Conference on Advanced Robotics, ICAR 2015

SP - 663

EP - 668

BT - Proceedings of the 17th International Conference on Advanced Robotics, ICAR 2015

A2 - Saranli, Uluc

A2 - Kalkan, Sinan

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 17th International Conference on Advanced Robotics, ICAR 2015

Y2 - 27 July 2015 through 31 July 2015

ER -

Sariel S, Yildiz P, Karapinar S, Altan D, Kapotoglu M. Robust task execution through experience-based guidance for cognitive robots. In Saranli U, Kalkan S, editors, Proceedings of the 17th International Conference on Advanced Robotics, ICAR 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 663-668. 7251527. (Proceedings of the 17th International Conference on Advanced Robotics, ICAR 2015). doi: 10.1109/ICAR.2015.7251527

Robust task execution through experience-based guidance for cognitive robots

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this