Stefan Heinrich

Stefan Heinrich

Scholar & IT Tinkerer, Associate Professor at the IT University of Copenhagen, Denmark

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

Mahya Kashani, Stefan Heinrich, Andrzej Wąsowski

Conference: Proceedings of the European Robotics Forum 2025 (ERF 2025), pp. 307-313, Stuttgart, DE, May 2025

PDF - DOI

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.