{
  "abstract": "Apparatuses, systems, and techniques are disclosed for controlling a robot to execute a task. In at least one embodiment, a current image of the robot in an environment and a text describing the task are obtained. A future image of the robot in the environment is predicted based on the current image and the text. Subsequently, one or more actions are predicted based on the current image, the future image, and the text. The one or more actions can move the robot from a first state corresponding to the current image to a second state corresponding to the future image. The robot executes the sequence of actions to move in the environment.",
  "assignees": [
    "NVIDIA CORP"
  ],
  "authors": [
    "HANDA ANKUR",
    "LIN TSUNG-YI",
    "LIU MING-YU",
    "LI ZHAOSHUO",
    "LU YAO",
    "MA QIANLI",
    "XIANG DONGLAI",
    "ZHAO QINGQING"
  ],
  "canonical_url": "https://opentechnical.org/p/OT-2026-000001926",
  "categories": [
    "robotics-automation/robot-architectures"
  ],
  "extent": {
    "figures": 0,
    "paragraphs": 0,
    "words": 112
  },
  "figures": [],
  "files": [
    {
      "bytes": 9847,
      "media_type": "text/html; charset=utf-8",
      "name": "index.html",
      "sha256": "75f5759678444a87788605edef5a5b9c4eb13b7df080195f283f9e06e5fc4d2b"
    },
    {
      "bytes": 1135,
      "media_type": "text/markdown; charset=utf-8",
      "name": "publication.md",
      "sha256": "e5a3077383a16180eade194aba01dfc2d66851bd55b445da4af75d1fa4fd1d91"
    },
    {
      "bytes": 1208,
      "media_type": "text/plain; charset=utf-8",
      "name": "publication.txt",
      "sha256": "031e35fa27ef05eed5533a716277380486c5c2166ed53fd919f7d82ad8db184e"
    }
  ],
  "integrity": {
    "hash_algorithm": "sha256",
    "keys_url": "https://opentechnical.org/integrity/keys",
    "record_url": "https://opentechnical.org/p/OT-2026-000001926/integrity",
    "signature_algorithm": "Ed25519",
    "signature_file": "manifest.sig",
    "verify_url": "https://opentechnical.org/integrity/verify"
  },
  "keywords": [
    "b25j9/1697",
    "b25j9/1697",
    "b25j9/1697",
    "b25j9/16",
    "b25j9/161",
    "b25j9/161"
  ],
  "language": "en",
  "license": {
    "name": "Creative Commons Attribution 4.0 International",
    "url": "https://creativecommons.org/licenses/by/4.0/"
  },
  "publication_id": "OT-2026-000001926",
  "published_at": "2026-09-15T19:09:33.834647Z",
  "publisher": "Nebula Innovations Limited",
  "record_type": "record",
  "schema": "opentechnical-publication-manifest/1.0",
  "source_date": "2026-03-12",
  "source_id": "US-2026070225-A1",
  "source_name": "the United States Patent and Trademark Office",
  "source_url": "https://patents.google.com/patent/US2026070225A1",
  "supersedes": null,
  "title": "Visual chain-of-thought reasoning for robot vision-language-action models",
  "uuid": "01a0a679-790a-7950-8926-091926ae7c57"
}