{
  "abstract": "Techniques are disclosed that enable training a goal-conditioned policy based on multiple data sets, where each of the data sets describes a robot task in a different way. For example, the multiple data sets can include: a goal image data set, where the task is captured in the goal image; a natural language instruction data set, where the task is described in the natural language instruction; a task ID data set, where the task is described by the task ID, etc. In various implementations, each of the multiple data sets has a corresponding encoder, where the encoders are trained to generate a shared latent space representation of the corresponding task description. Additional or alternative techniques are disclosed that enable control of a robot using a goal-conditioned policy network. For example, the robot can be controlled, using the goal-conditioned policy network, based on free-form natural language input describing robot task(s).",
  "assignees": [
    "GOOGLE LLC"
  ],
  "authors": [
    "LYNCH COREY",
    "SERMANET PIERRE"
  ],
  "canonical_url": "https://opentechnical.org/p/OT-2026-000001396",
  "categories": [
    "robotics-automation/robot-architectures"
  ],
  "extent": {
    "figures": 0,
    "paragraphs": 0,
    "words": 149
  },
  "figures": [],
  "files": [
    {
      "bytes": 10190,
      "media_type": "text/html; charset=utf-8",
      "name": "index.html",
      "sha256": "3b2ea8cb7ce637acf37385b42b4ee07b241f4a0ffec2daf971af438a2808c1a4"
    },
    {
      "bytes": 1496,
      "media_type": "text/markdown; charset=utf-8",
      "name": "publication.md",
      "sha256": "6ac878e27e0fd97ad32286a83e0f3d0a8ff1094c173c3146caaf1230cf719988"
    },
    {
      "bytes": 1540,
      "media_type": "text/plain; charset=utf-8",
      "name": "publication.txt",
      "sha256": "77ceb726b1cf108f1a091b3dd0f55337e5fc44b9f12961a5609e46f39954bef2"
    }
  ],
  "integrity": {
    "hash_algorithm": "sha256",
    "keys_url": "https://opentechnical.org/integrity/keys",
    "record_url": "https://opentechnical.org/p/OT-2026-000001396/integrity",
    "signature_algorithm": "Ed25519",
    "signature_file": "manifest.sig",
    "verify_url": "https://opentechnical.org/integrity/verify"
  },
  "keywords": [
    "b25j9/1656",
    "b25j9/1656",
    "b25j9/1664",
    "b25j9/1664",
    "b25j9/16",
    "b25j9/163"
  ],
  "language": "en",
  "license": {
    "name": "Creative Commons Attribution 4.0 International",
    "url": "https://creativecommons.org/licenses/by/4.0/"
  },
  "publication_id": "OT-2026-000001396",
  "published_at": "2026-09-15T19:05:34.938258Z",
  "publisher": "Nebula Innovations Limited",
  "record_type": "record",
  "schema": "opentechnical-publication-manifest/1.0",
  "source_date": "2026-03-26",
  "source_id": "US-2026084306-A1",
  "source_name": "the United States Patent and Trademark Office",
  "source_url": "https://patents.google.com/patent/US2026084306A1",
  "supersedes": null,
  "title": "Training and/or utilizing machine learning model(s) for use in natural language based robotic control",
  "uuid": "01a0a675-d3d9-7bd8-b1fd-24f11e718dee"
}