Chrpa, Lukáš and Thorisson, Kristinn (2015) On Applicability of Automated Planning for Incident Management. In: The international Scheduling and Planning Applications woRKshop (SPARK 2015), 8th June 2015, Jerusalem, Israel.
- Published Version
Download (178kB) | Preview
Incident management aims to save human lives, mitigate the effect of accidents, prevent damages, to mention a few of their benefits. Efficient coordination of rescue team members, allocation of available resources, and appropriate responses to the realtime unfolding of events is critical for managing incidents successfully.
Coordination involves a series of decisions and event monitoring, usually made by human coordinators, for instance task definition, task assignment, risk assessment, etc. Each elementary decision can be described by a named action (e.g. boarding an ambulance, assigning a task). Taken as a whole, the team coordinating an incident
response can be seen as a decision-making system.
In this paper, we discuss how invaluable assistance can be brought to such a system using automated planning.
In consultation with experts we have derived a set of requirements from which we provide a formal specification of the domain. Following the specification, we have developed a prototype domain model and evaluated it empirically. Here we present the results of this evaluation, along with several challenges (e.g uncertainty) that
we have identified
|Item Type:||Conference or Workshop Item (Paper)|
|Subjects:||Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76 Computer software
|Schools:||School of Computing and Engineering > High-Performance Intelligent Computing > Planning, Autonomy and Representation of Knowledge
School of Computing and Engineering > High-Performance Intelligent Computing > Planning, Autonomy and Representation of Knowledge
|Depositing User:||Lukas Chrpa|
|Date Deposited:||14 May 2015 15:35|
|Last Modified:||17 Dec 2016 22:20|
Downloads per month over past year
Repository Staff Only: item control page