{
  "abstract": "Systems utilizing a vision-language model configured with a training dataset that includes images labeled with spatial question-and-answer pairs, the question-and-answer pairs encoding object-to-object relationships and object-to-space relationships depicted in the images, and at least one data processor configured to operate the vision-language model to carry out a robotic task.",
  "assignees": [
    "NVIDIA CORP"
  ],
  "authors": [
    "BIRCHFIELD STANLEY THOMAS",
    "BLUKIS VALTS",
    "SONG CHAN HEE",
    "TREMBLAY JONATHAN",
    "TYREE STEPHEN"
  ],
  "canonical_url": "https://opentechnical.org/p/OT-2026-000002169",
  "categories": [
    "robotics-automation/robot-architectures"
  ],
  "extent": {
    "figures": 0,
    "paragraphs": 0,
    "words": 49
  },
  "figures": [],
  "files": [
    {
      "bytes": 9580,
      "media_type": "text/html; charset=utf-8",
      "name": "index.html",
      "sha256": "3f85658a593c9d2d7634f4ddb810b0177e7bbe2369275cfd5480608a91f88751"
    },
    {
      "bytes": 877,
      "media_type": "text/markdown; charset=utf-8",
      "name": "publication.md",
      "sha256": "170cd5ec60195030b50ff63405f34438e37094a6aefba755999fe697cf48420b"
    },
    {
      "bytes": 949,
      "media_type": "text/plain; charset=utf-8",
      "name": "publication.txt",
      "sha256": "eaeb42d100d6559d42147ff3326c9aa35d231cbb9219134fa3bae9778b5da415"
    }
  ],
  "integrity": {
    "hash_algorithm": "sha256",
    "keys_url": "https://opentechnical.org/integrity/keys",
    "record_url": "https://opentechnical.org/p/OT-2026-000002169/integrity",
    "signature_algorithm": "Ed25519",
    "signature_file": "manifest.sig",
    "verify_url": "https://opentechnical.org/integrity/verify"
  },
  "keywords": [
    "b25j9/163",
    "b25j9/163",
    "b25j9/1697",
    "b25j9/16",
    "b25j9/163",
    "b25j9/1697"
  ],
  "language": "en",
  "license": {
    "name": "Creative Commons Attribution 4.0 International",
    "url": "https://creativecommons.org/licenses/by/4.0/"
  },
  "publication_id": "OT-2026-000002169",
  "published_at": "2026-09-15T19:11:13.887898Z",
  "publisher": "Nebula Innovations Limited",
  "record_type": "record",
  "schema": "opentechnical-publication-manifest/1.0",
  "source_date": "2026-03-05",
  "source_id": "US-2026061605-A1",
  "source_name": "the United States Patent and Trademark Office",
  "source_url": "https://patents.google.com/patent/US2026061605A1",
  "supersedes": null,
  "title": "Configuring a visual language model with spatial understanding for robotics",
  "uuid": "01a0a67a-ffdf-7c6e-bbd1-1b21b45c1f9c"
}