Diagnosis makes the difference for a successful execution of high-level robot control programs

Clemens Mühlbacher, Gerald Steinbauer

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Abstract

Faults in action execution and perception that occur at runtime negatively affects the probability that an agent is able to finish a task successfully. There are several techniques such as hand-coded error recovery or diagnosis and repair approaches to deal with this problem. In this paper we present an experimental comparison of the fault tolerance of the popular (CRAM) framework using hand-coded error recovery and an approach using model-based diagnosis. The approaches were evaluated using a simulated robot delivery domain. Experimental results confirm that a control approach using diagnosis is able to significantly increase the success-rate and outperforms hand-coded error strategies.

Original languageEnglish
Title of host publicationIntelligent Autonomous Systems - Proceedings of the 13th International Conference IAS, 2014
PublisherSpringer Verlag
Pages1119-1132
Number of pages14
Volume302
ISBN (Print)9783319083377
DOIs
Publication statusPublished - 2016
Event13th International Conference on Intelligent Autonomous Systems, IAS 2014 - Padova, Italy
Duration: 15 Jul 201418 Jul 2014

Publication series

NameAdvances in Intelligent Systems and Computing
Volume302
ISSN (Print)21945357

Conference

Conference13th International Conference on Intelligent Autonomous Systems, IAS 2014
CountryItaly
CityPadova
Period15/07/1418/07/14

Fingerprint

Robots
Fault tolerance
Repair

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

Cite this

Mühlbacher, C., & Steinbauer, G. (2016). Diagnosis makes the difference for a successful execution of high-level robot control programs. In Intelligent Autonomous Systems - Proceedings of the 13th International Conference IAS, 2014 (Vol. 302, pp. 1119-1132). (Advances in Intelligent Systems and Computing; Vol. 302). Springer Verlag. https://doi.org/10.1007/978-3-319-08338-4_81

Diagnosis makes the difference for a successful execution of high-level robot control programs. / Mühlbacher, Clemens; Steinbauer, Gerald.

Intelligent Autonomous Systems - Proceedings of the 13th International Conference IAS, 2014. Vol. 302 Springer Verlag, 2016. p. 1119-1132 (Advances in Intelligent Systems and Computing; Vol. 302).

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Mühlbacher, C & Steinbauer, G 2016, Diagnosis makes the difference for a successful execution of high-level robot control programs. in Intelligent Autonomous Systems - Proceedings of the 13th International Conference IAS, 2014. vol. 302, Advances in Intelligent Systems and Computing, vol. 302, Springer Verlag, pp. 1119-1132, 13th International Conference on Intelligent Autonomous Systems, IAS 2014, Padova, Italy, 15/07/14. https://doi.org/10.1007/978-3-319-08338-4_81
Mühlbacher C, Steinbauer G. Diagnosis makes the difference for a successful execution of high-level robot control programs. In Intelligent Autonomous Systems - Proceedings of the 13th International Conference IAS, 2014. Vol. 302. Springer Verlag. 2016. p. 1119-1132. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-319-08338-4_81
Mühlbacher, Clemens ; Steinbauer, Gerald. / Diagnosis makes the difference for a successful execution of high-level robot control programs. Intelligent Autonomous Systems - Proceedings of the 13th International Conference IAS, 2014. Vol. 302 Springer Verlag, 2016. pp. 1119-1132 (Advances in Intelligent Systems and Computing).
@inproceedings{3b0b3d60fe70456d8e8d16e0f6c6b99b,
title = "Diagnosis makes the difference for a successful execution of high-level robot control programs",
abstract = "Faults in action execution and perception that occur at runtime negatively affects the probability that an agent is able to finish a task successfully. There are several techniques such as hand-coded error recovery or diagnosis and repair approaches to deal with this problem. In this paper we present an experimental comparison of the fault tolerance of the popular (CRAM) framework using hand-coded error recovery and an approach using model-based diagnosis. The approaches were evaluated using a simulated robot delivery domain. Experimental results confirm that a control approach using diagnosis is able to significantly increase the success-rate and outperforms hand-coded error strategies.",
author = "Clemens M{\"u}hlbacher and Gerald Steinbauer",
year = "2016",
doi = "10.1007/978-3-319-08338-4_81",
language = "English",
isbn = "9783319083377",
volume = "302",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer Verlag",
pages = "1119--1132",
booktitle = "Intelligent Autonomous Systems - Proceedings of the 13th International Conference IAS, 2014",
address = "Germany",

}

TY - GEN

T1 - Diagnosis makes the difference for a successful execution of high-level robot control programs

AU - Mühlbacher, Clemens

AU - Steinbauer, Gerald

PY - 2016

Y1 - 2016

N2 - Faults in action execution and perception that occur at runtime negatively affects the probability that an agent is able to finish a task successfully. There are several techniques such as hand-coded error recovery or diagnosis and repair approaches to deal with this problem. In this paper we present an experimental comparison of the fault tolerance of the popular (CRAM) framework using hand-coded error recovery and an approach using model-based diagnosis. The approaches were evaluated using a simulated robot delivery domain. Experimental results confirm that a control approach using diagnosis is able to significantly increase the success-rate and outperforms hand-coded error strategies.

AB - Faults in action execution and perception that occur at runtime negatively affects the probability that an agent is able to finish a task successfully. There are several techniques such as hand-coded error recovery or diagnosis and repair approaches to deal with this problem. In this paper we present an experimental comparison of the fault tolerance of the popular (CRAM) framework using hand-coded error recovery and an approach using model-based diagnosis. The approaches were evaluated using a simulated robot delivery domain. Experimental results confirm that a control approach using diagnosis is able to significantly increase the success-rate and outperforms hand-coded error strategies.

UR - http://www.scopus.com/inward/record.url?scp=84945902657&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-08338-4_81

DO - 10.1007/978-3-319-08338-4_81

M3 - Conference contribution

SN - 9783319083377

VL - 302

T3 - Advances in Intelligent Systems and Computing

SP - 1119

EP - 1132

BT - Intelligent Autonomous Systems - Proceedings of the 13th International Conference IAS, 2014

PB - Springer Verlag

ER -