King's College London

Research portal

Personalised Medication Planning using PDDL+

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

Original languageEnglish
Title of host publicationProceedings of the Scheduling and Planning Applications woRKshop (SPARK)
Subtitle of host publicationAt the 28th International Conference on Automated Planning and Scheduling
EditorsSara Bernadini, Simon Parkinson, Kartik Talamadupula
StatePublished - 24 Jun 2018

Documents

King's Authors

Abstract

Prescription medication is typically prescribed with a standardised set of instructions, to be followed regularly, with the aim being to manage symptoms while remaining within safe dosage limits. The caveat of such standardisation is that it is not tailored to the needs of the patient, in terms of their activities. In this paper, we take the first steps towards modelling medication pharmacokinetics as a PDDL+ hybrid planning problem. As pharmacokinetics are inherently non-linear, we present a planner-independent linearise--validate cycle, where tasks can be solved by iterative refinement of a linear approximation of the domain, by validation against the full non-linear semantics.

Download statistics

No data available

View graph of relations

© 2018 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454