{
  "abstract": "Scanning Electron Microscopy (SEM) is a foundational technique for characterizing material microstructure, which dictates many fundamental physical and chemical properties. With the rise of Self-Driving Labs (SDLs), samples are now synthesized in large batches, demanding equally high-throughput, autonomous characterization. Existing automated electron microscopy pipelines are task-specific: they detect pre-defined features, optimize known properties, or require prior knowledge of the sample, restricting each pipeline to the material system it was built for. We introduce AutoRASOR, a task-agnostic autonomous SEM pipeline that captures the multi-scale morphology of an unknown sample without domain-specific pre-training, fine-tuning, or human prompting. AutoRASOR embeds micrographs in real time with a vision foundation model (VFM), DINOv3, and selects regions of interest (ROIs) through two complementary policies: Latent Farthest Point Sampling (LFPS) and active learning on morphological ambiguity, which is the conditional variance of unresolved fine-scale features given lower magnification appearance. Active learning on ambiguity consistently captures more diverse and rare morphologies than random ROI selection, while LFPS reliably recovers the specimen's morphological distribution within a limited capture budget, tested both on real SEM micrographs and synthetic phase-field images. By shifting autonomous characterization from pre-defined, task-specific targeting of features to morphological survey, AutoRASOR generates information-rich multi-scale datasets for diverse downstream tasks. Without the need for domain-specific pre-training or prior material assumptions, this framework can be deployed out-of-the-box to characterize novel materials produced by SDLs.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.22411",
  "author_total": 10,
  "authors": [
    {
      "name": "Kevin Zhang"
    },
    {
      "name": "Mohammad Taha"
    },
    {
      "name": "Rafael Espinosa Castañeda"
    },
    {
      "name": "Yutong Liu"
    },
    {
      "name": "Yin Zhu"
    },
    {
      "name": "Lotan Portal"
    },
    {
      "name": "Robert A. Mcleod"
    },
    {
      "name": "Vahid Attari"
    },
    {
      "name": "Jane Y. Howe"
    },
    {
      "name": "Jason Hattrick-Simpers"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/byr6a88a2b9gz.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.22411",
  "fulltext_url": null,
  "id": "byr6a88a2b9gz",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.22411",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cond-mat.mtrl-sci"
    ],
    [
      "arxiv",
      "eess.IV"
    ],
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7214038735",
  "pdf_url": "https://arxiv.org/pdf/2609.22411",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-18",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/byr6a88a2b9gz.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:23:19Z",
      "native_id": "2609.22411",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.22411"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:cond-mat.mtrl-sci",
      "subfield": "condensed-matter"
    }
  ],
  "title": "AutoRASOR: Autonomous Rapid Scanning Electron Microscope Operator",
  "title_text": "AutoRASOR: Autonomous Rapid Scanning Electron Microscope Operator",
  "type": "preprint",
  "updated_at": "2026-10-30T12:23:19Z",
  "url": "https://research.draconitic.com/paper/byr6a88a2b9gz",
  "venue": "arXiv",
  "versions": []
}