MarineLLM-PDDL: Generation of Planning Domains for Marine Vessels Using Past Incident Response Plans

Mahya Mohammadi Kashani, Stefan Heinrich, Andrzej Wasowski

Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review

Abstract

Testing the hardware and software of marine vessels in field trials is a necessity to avoid technical and environmental catastrophes. Conducting tests with large vessels is costly. Multiple realistic domain descriptions based on past missions could increase the value of simulation tests, reducing the need for expensive field tests. In this paper, we generate scenarios from unstructured Incident Response Plan (IRP) documents using Large Language Models (LLMs), converting them to standard structured planning programs. The two synthesized marine test-domain datasets contain approximately 90% parsable, 75% solvable, and 57% correct planning programs.
OriginalsprogEngelsk
Titel Springer Proceedings in Advanced Robotics
Antal sider7
Vol/bind36
UdgivelsesstedSpringer Cham
ForlagSpringer
Publikationsdato2025
Sider307-313
ISBN (Trykt)978-3-031-89470-1
ISBN (Elektronisk)978-3-031-89471-8
DOI
StatusUdgivet - 2025
NavnEuropean Robotics Forum

Fingeraftryk

Dyk ned i forskningsemnerne om 'MarineLLM-PDDL: Generation of Planning Domains for Marine Vessels Using Past Incident Response Plans'. Sammen danner de et unikt fingeraftryk.

Citationsformater