Scholarlink

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.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

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

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Mahya Mohammadi Kashani,
  • Stefan Heinrich,
  • Andrzej Wąsowski

摘要

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.