Exploring knowledge engineering strategies in designing and modelling a road traffic accident management domain

Mohammad M. Shah, Lukáš Chrpa, Diane Kitchin, Thomas L. McCluskey, Mauro Vallati

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

7 Citations (Scopus)

Abstract

Formulating knowledge for use in AI Planning engines is currently something of an ad-hoc process, where the skills of knowledge engineers and the tools they use may significantly influence the quality of the resulting planning application. There is little in the way of guidelines or standard procedures, however, for knowledge engineers to use when formulating knowledge into planning domain languages such as PDDL. This paper seeks to investigate this process using as a case study a road traffic accident management domain. Managing road accidents requires systematic, sound planning and coordination of resources to improve outcomes for accident victims. We have derived a set of requirements in consultation with stakeholders for the resource coordination part of managing accidents. We evaluate two separate knowledge engineering strategies for encoding the resulting planning domain from the set of requirements: (a) the traditional method of PDDL experts and text editor, and (b) a leading planning GUI with built in UML modelling tools. These strategies are evaluated using process and product metrics, where the domain model (the product) was tested extensively with a range of planning engines. The results give insights into the strengths and weaknesses of the approaches, highlight lessons learned regarding knowledge encoding, and point to important lines of research for knowledge engineering for planning.

LanguageEnglish
Title of host publicationIJCAI 2013 - Proceedings of the 23rd International Joint Conference on Artificial Intelligence
Pages2373-2379
Number of pages7
Publication statusPublished - 2013
Event23rd International Joint Conference on Artificial Intelligence - Beijing, China
Duration: 3 Aug 20139 Aug 2013
Conference number: 23

Conference

Conference23rd International Joint Conference on Artificial Intelligence
Abbreviated titleIJCAI 2013
CountryChina
CityBeijing
Period3/08/139/08/13

Fingerprint

Knowledge engineering
Highway accidents
Planning
Accidents
File editors
Engines
Engineers
Graphical user interfaces
Acoustic waves

Cite this

Shah, M. M., Chrpa, L., Kitchin, D., McCluskey, T. L., & Vallati, M. (2013). Exploring knowledge engineering strategies in designing and modelling a road traffic accident management domain. In IJCAI 2013 - Proceedings of the 23rd International Joint Conference on Artificial Intelligence (pp. 2373-2379)
Shah, Mohammad M. ; Chrpa, Lukáš ; Kitchin, Diane ; McCluskey, Thomas L. ; Vallati, Mauro. / Exploring knowledge engineering strategies in designing and modelling a road traffic accident management domain. IJCAI 2013 - Proceedings of the 23rd International Joint Conference on Artificial Intelligence. 2013. pp. 2373-2379
@inproceedings{132ba3fa5092455bbe3624eb294f0c0e,
title = "Exploring knowledge engineering strategies in designing and modelling a road traffic accident management domain",
abstract = "Formulating knowledge for use in AI Planning engines is currently something of an ad-hoc process, where the skills of knowledge engineers and the tools they use may significantly influence the quality of the resulting planning application. There is little in the way of guidelines or standard procedures, however, for knowledge engineers to use when formulating knowledge into planning domain languages such as PDDL. This paper seeks to investigate this process using as a case study a road traffic accident management domain. Managing road accidents requires systematic, sound planning and coordination of resources to improve outcomes for accident victims. We have derived a set of requirements in consultation with stakeholders for the resource coordination part of managing accidents. We evaluate two separate knowledge engineering strategies for encoding the resulting planning domain from the set of requirements: (a) the traditional method of PDDL experts and text editor, and (b) a leading planning GUI with built in UML modelling tools. These strategies are evaluated using process and product metrics, where the domain model (the product) was tested extensively with a range of planning engines. The results give insights into the strengths and weaknesses of the approaches, highlight lessons learned regarding knowledge encoding, and point to important lines of research for knowledge engineering for planning.",
author = "Shah, {Mohammad M.} and Luk{\'a}š Chrpa and Diane Kitchin and McCluskey, {Thomas L.} and Mauro Vallati",
year = "2013",
language = "English",
isbn = "9781577356332",
pages = "2373--2379",
booktitle = "IJCAI 2013 - Proceedings of the 23rd International Joint Conference on Artificial Intelligence",

}

Shah, MM, Chrpa, L, Kitchin, D, McCluskey, TL & Vallati, M 2013, Exploring knowledge engineering strategies in designing and modelling a road traffic accident management domain. in IJCAI 2013 - Proceedings of the 23rd International Joint Conference on Artificial Intelligence. pp. 2373-2379, 23rd International Joint Conference on Artificial Intelligence, Beijing, China, 3/08/13.

Exploring knowledge engineering strategies in designing and modelling a road traffic accident management domain. / Shah, Mohammad M.; Chrpa, Lukáš; Kitchin, Diane; McCluskey, Thomas L.; Vallati, Mauro.

IJCAI 2013 - Proceedings of the 23rd International Joint Conference on Artificial Intelligence. 2013. p. 2373-2379.

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

TY - GEN

T1 - Exploring knowledge engineering strategies in designing and modelling a road traffic accident management domain

AU - Shah, Mohammad M.

AU - Chrpa, Lukáš

AU - Kitchin, Diane

AU - McCluskey, Thomas L.

AU - Vallati, Mauro

PY - 2013

Y1 - 2013

N2 - Formulating knowledge for use in AI Planning engines is currently something of an ad-hoc process, where the skills of knowledge engineers and the tools they use may significantly influence the quality of the resulting planning application. There is little in the way of guidelines or standard procedures, however, for knowledge engineers to use when formulating knowledge into planning domain languages such as PDDL. This paper seeks to investigate this process using as a case study a road traffic accident management domain. Managing road accidents requires systematic, sound planning and coordination of resources to improve outcomes for accident victims. We have derived a set of requirements in consultation with stakeholders for the resource coordination part of managing accidents. We evaluate two separate knowledge engineering strategies for encoding the resulting planning domain from the set of requirements: (a) the traditional method of PDDL experts and text editor, and (b) a leading planning GUI with built in UML modelling tools. These strategies are evaluated using process and product metrics, where the domain model (the product) was tested extensively with a range of planning engines. The results give insights into the strengths and weaknesses of the approaches, highlight lessons learned regarding knowledge encoding, and point to important lines of research for knowledge engineering for planning.

AB - Formulating knowledge for use in AI Planning engines is currently something of an ad-hoc process, where the skills of knowledge engineers and the tools they use may significantly influence the quality of the resulting planning application. There is little in the way of guidelines or standard procedures, however, for knowledge engineers to use when formulating knowledge into planning domain languages such as PDDL. This paper seeks to investigate this process using as a case study a road traffic accident management domain. Managing road accidents requires systematic, sound planning and coordination of resources to improve outcomes for accident victims. We have derived a set of requirements in consultation with stakeholders for the resource coordination part of managing accidents. We evaluate two separate knowledge engineering strategies for encoding the resulting planning domain from the set of requirements: (a) the traditional method of PDDL experts and text editor, and (b) a leading planning GUI with built in UML modelling tools. These strategies are evaluated using process and product metrics, where the domain model (the product) was tested extensively with a range of planning engines. The results give insights into the strengths and weaknesses of the approaches, highlight lessons learned regarding knowledge encoding, and point to important lines of research for knowledge engineering for planning.

UR - http://www.scopus.com/inward/record.url?scp=84896062087&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781577356332

SP - 2373

EP - 2379

BT - IJCAI 2013 - Proceedings of the 23rd International Joint Conference on Artificial Intelligence

ER -

Shah MM, Chrpa L, Kitchin D, McCluskey TL, Vallati M. Exploring knowledge engineering strategies in designing and modelling a road traffic accident management domain. In IJCAI 2013 - Proceedings of the 23rd International Joint Conference on Artificial Intelligence. 2013. p. 2373-2379