Refining Process Descriptions from Execution Data in Hybrid Planning Domain Models. / Linday, Alan; Franco Aixela, Santiago; Reya, Rubiya; McCluskey, Lee.

Proceedings of the Thirtieth International Conference on Automated Planning and Scheduling, Nancy, France, October 26-30, 2020. Vol. 30 (2020) AAAI Press, 2020. p. 469-477.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Published

Standard

Refining Process Descriptions from Execution Data in Hybrid Planning Domain Models. / Linday, Alan; Franco Aixela, Santiago; Reya, Rubiya; McCluskey, Lee.

Proceedings of the Thirtieth International Conference on Automated Planning and Scheduling, Nancy, France, October 26-30, 2020. Vol. 30 (2020) AAAI Press, 2020. p. 469-477.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Harvard

Linday, A, Franco Aixela, S, Reya, R & McCluskey, L 2020, Refining Process Descriptions from Execution Data in Hybrid Planning Domain Models. in Proceedings of the Thirtieth International Conference on Automated Planning and Scheduling, Nancy, France, October 26-30, 2020. vol. 30 (2020), AAAI Press, pp. 469-477. <https://www.aaai.org/ojs/index.php/ICAPS/article/view/6742>

APA

Linday, A., Franco Aixela, S., Reya, R., & McCluskey, L. (2020). Refining Process Descriptions from Execution Data in Hybrid Planning Domain Models. In Proceedings of the Thirtieth International Conference on Automated Planning and Scheduling, Nancy, France, October 26-30, 2020 (Vol. 30 (2020), pp. 469-477). AAAI Press. https://www.aaai.org/ojs/index.php/ICAPS/article/view/6742

Vancouver

Linday A, Franco Aixela S, Reya R, McCluskey L. Refining Process Descriptions from Execution Data in Hybrid Planning Domain Models. In Proceedings of the Thirtieth International Conference on Automated Planning and Scheduling, Nancy, France, October 26-30, 2020. Vol. 30 (2020). AAAI Press. 2020. p. 469-477

Author

Linday, Alan ; Franco Aixela, Santiago ; Reya, Rubiya ; McCluskey, Lee. / Refining Process Descriptions from Execution Data in Hybrid Planning Domain Models. Proceedings of the Thirtieth International Conference on Automated Planning and Scheduling, Nancy, France, October 26-30, 2020. Vol. 30 (2020) AAAI Press, 2020. pp. 469-477

BibTeX

@inproceedings{6065290d535a47f48010947d54d5f33e,
title = "Refining Process Descriptions from Execution Data in Hybrid Planning Domain Models",
abstract = "The creation and maintenance of a domain model is a well recognised bottleneck in the use of automated planning; indeed, ensuring a planning engine is fed with an accurate model of an application is essential in order that generated plans are effective. Engineering domain models using a hybrid representation is particularly challenging as it requires accurately describing continuous processes, which can have complex numeric effects. In this work we consider the problem of the refinement of an engineered hybrid domain model, to more accurately capture the effect of the underlying processes. Our approach exploits the information content of the original model, utilising machine learning techniques to identify important situation and temporal features that indicate a variation in the original effect. We use the problem of modelling traffic flows in an Urban Traffic Management setting as a case study and demonstrate in our evaluation that the refined domain models provide more accurate simulation, which can lead to higher quality plans. The contributions of this work are a general approach to the automated refinement of hybrid planning domain models that reduces the knowledge engineering effort in producing a detailed process model. The approach can be used for refining the domain model during the initial stages of development, or for re-configuring the domain model when used in the same problem area but with a different scenario. We test out the approach within a real world case study.",
keywords = "Automated Planning, Hybrid Planning, Domain Model Refinement, Urban Traffic Management",
author = "Alan Linday and {Franco Aixela}, Santiago and Rubiya Reya and Lee McCluskey",
year = "2020",
month = jun,
day = "1",
language = "English",
volume = "30 (2020)",
pages = "469--477",
booktitle = "Proceedings of the Thirtieth International Conference on Automated Planning and Scheduling, Nancy, France, October 26-30, 2020",
publisher = "AAAI Press",

}

RIS

TY - GEN

T1 - Refining Process Descriptions from Execution Data in Hybrid Planning Domain Models

AU - Linday, Alan

AU - Franco Aixela, Santiago

AU - Reya, Rubiya

AU - McCluskey, Lee

PY - 2020/6/1

Y1 - 2020/6/1

N2 - The creation and maintenance of a domain model is a well recognised bottleneck in the use of automated planning; indeed, ensuring a planning engine is fed with an accurate model of an application is essential in order that generated plans are effective. Engineering domain models using a hybrid representation is particularly challenging as it requires accurately describing continuous processes, which can have complex numeric effects. In this work we consider the problem of the refinement of an engineered hybrid domain model, to more accurately capture the effect of the underlying processes. Our approach exploits the information content of the original model, utilising machine learning techniques to identify important situation and temporal features that indicate a variation in the original effect. We use the problem of modelling traffic flows in an Urban Traffic Management setting as a case study and demonstrate in our evaluation that the refined domain models provide more accurate simulation, which can lead to higher quality plans. The contributions of this work are a general approach to the automated refinement of hybrid planning domain models that reduces the knowledge engineering effort in producing a detailed process model. The approach can be used for refining the domain model during the initial stages of development, or for re-configuring the domain model when used in the same problem area but with a different scenario. We test out the approach within a real world case study.

AB - The creation and maintenance of a domain model is a well recognised bottleneck in the use of automated planning; indeed, ensuring a planning engine is fed with an accurate model of an application is essential in order that generated plans are effective. Engineering domain models using a hybrid representation is particularly challenging as it requires accurately describing continuous processes, which can have complex numeric effects. In this work we consider the problem of the refinement of an engineered hybrid domain model, to more accurately capture the effect of the underlying processes. Our approach exploits the information content of the original model, utilising machine learning techniques to identify important situation and temporal features that indicate a variation in the original effect. We use the problem of modelling traffic flows in an Urban Traffic Management setting as a case study and demonstrate in our evaluation that the refined domain models provide more accurate simulation, which can lead to higher quality plans. The contributions of this work are a general approach to the automated refinement of hybrid planning domain models that reduces the knowledge engineering effort in producing a detailed process model. The approach can be used for refining the domain model during the initial stages of development, or for re-configuring the domain model when used in the same problem area but with a different scenario. We test out the approach within a real world case study.

KW - Automated Planning

KW - Hybrid Planning

KW - Domain Model Refinement

KW - Urban Traffic Management

M3 - Conference contribution

VL - 30 (2020)

SP - 469

EP - 477

BT - Proceedings of the Thirtieth International Conference on Automated Planning and Scheduling, Nancy, France, October 26-30, 2020

PB - AAAI Press

ER -