{
  "abstract": "Safe collision avoidance for Maritime Autonomous Surface Ships (MASS) remains challenging because autonomous controllers must maintain predictable rule-guided behaviour while adapting to dense and uncertain traffic situations. This research introduces a dual-mode, safety-oriented deep reinforcement learning (DRL) framework that integrates model-based predictability with data-driven adaptability for MASS collision avoidance. Encounter scenarios are quantified in accordance with the International Regulations for Preventing Collisions at Sea (COLREGs), and a multi-objective reward function combines pairwise rule-guided reasoning with dynamic risk awareness. In the routine-navigation mode, Proximal Policy Optimisation (PPO) is employed to generate stable and COLREGs-guided trajectories, whilst the heightened-safety mode applies a tree-based safety filter that prunes unsafe actions and supports autonomous switching under elevated close-quarters risk. Two pruning optimisations–Reachable Envelope Pruning (REP) and the Terminal Safety Criterion (TSC)–jointly reduce node expansions by over 90%, thereby markedly improving computational efficiency. Simulation results demonstrate that the safety layer achieved no observed collisions in two-ship encounters and reduced collision rates by approximately 80–90% in congested multi-ship scenarios compared with the routine-navigation PPO baseline without the heightened-safety mode. Even in six-ship traffic, the agent maintains an average minimum passing distance exceeding 0.5 nautical miles. Latency analysis indicates reduced computational overhead under the tested simulation settings, suggesting the decision-level computational feasibility of the proposed framework.",
  "abstract_shown": true,
  "affiliations": [
    "Navigation College, Dalian Maritime University"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Yifan Du"
    },
    {
      "affs": [
        0
      ],
      "name": "Feixiang Zhu"
    },
    {
      "affs": [
        0
      ],
      "name": "Moxuan Wei"
    },
    {
      "affs": [
        0
      ],
      "name": "Lai Wei"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/fh7a5z1wkhzc2.bib",
  "cited_by": 0,
  "doi": "10.1038/s41598-026-62506-2",
  "fulltext_url": "https://doi.org/10.1038/s41598-026-62506-2",
  "id": "fh7a5z1wkhzc2",
  "issns": [
    "2045-2322"
  ],
  "landing_url": "https://doi.org/10.1038/s41598-026-62506-2",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "lcc",
      "Q"
    ],
    [
      "lcc",
      "R"
    ],
    [
      "openalex",
      "2212|Maritime Navigation and Safety"
    ]
  ],
  "openalex": "W7169652274",
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-07-01",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/fh7a5z1wkhzc2.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T13:45:53Z",
      "native_id": "575e6b81d2974d5e9478539d09142b3e",
      "source": "doaj",
      "url": "https://doi.org/10.1038/s41598-026-62506-2"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "lcc:R",
      "subfield": "general"
    }
  ],
  "title": "Dual-mode deep reinforcement learning for safety-oriented MASS collision avoidance",
  "title_text": "Dual-mode deep reinforcement learning for safety-oriented MASS collision avoidance",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T13:45:53Z",
  "url": "https://research.draconitic.com/paper/fh7a5z1wkhzc2",
  "venue": "Scientific Reports",
  "versions": []
}