{
  "abstract": "Foundation models such as VLMs and LLMs are increasingly being used to address open-world tasks in robotics. While these models excel at task execution, they often face challenges in detecting and reasoning over failures, which are skills that are crucial for navigating dynamic and complex environments. The present disclosure provides a VLM that detects and reasons about failures in robotic manipulation using natural language, where the natural language feedback can then be used for improving downstream task performance through error correction.",
  "assignees": [
    "NVIDIA CORP"
  ],
  "authors": [
    "Duan Jiafei",
    "FOX DIETER",
    "GUO YIJIE",
    "MANDLEKAR AJAY"
  ],
  "canonical_url": "https://opentechnical.org/p/OT-2026-000001173",
  "categories": [
    "robotics-automation/robot-architectures"
  ],
  "extent": {
    "figures": 0,
    "paragraphs": 0,
    "words": 81
  },
  "figures": [],
  "files": [
    {
      "bytes": 9759,
      "media_type": "text/html; charset=utf-8",
      "name": "index.html",
      "sha256": "11c26c23f825460d1593c115c942e1ffd64d3e3bea164b926c056d4b6702af96"
    },
    {
      "bytes": 1022,
      "media_type": "text/markdown; charset=utf-8",
      "name": "publication.md",
      "sha256": "8105daa17986b45241083178b74d87cf37fcd2c3760db9e65120968a9ca66285"
    },
    {
      "bytes": 1130,
      "media_type": "text/plain; charset=utf-8",
      "name": "publication.txt",
      "sha256": "9dbdfe762f659f98885c0766e71f0df03a5923cdaf1bcf018f23201e8ae1e7df"
    }
  ],
  "integrity": {
    "hash_algorithm": "sha256",
    "keys_url": "https://opentechnical.org/integrity/keys",
    "record_url": "https://opentechnical.org/p/OT-2026-000001173/integrity",
    "signature_algorithm": "Ed25519",
    "signature_file": "manifest.sig",
    "verify_url": "https://opentechnical.org/integrity/verify"
  },
  "keywords": [
    "b25j9/1697",
    "b25j9/1697",
    "b25j9/16"
  ],
  "language": "en",
  "license": {
    "name": "Creative Commons Attribution 4.0 International",
    "url": "https://creativecommons.org/licenses/by/4.0/"
  },
  "publication_id": "OT-2026-000001173",
  "published_at": "2026-09-15T19:03:58.291683Z",
  "publisher": "Nebula Innovations Limited",
  "record_type": "record",
  "schema": "opentechnical-publication-manifest/1.0",
  "source_date": "2026-04-02",
  "source_id": "US-2026091502-A1",
  "source_name": "the United States Patent and Trademark Office",
  "source_url": "https://patents.google.com/patent/US2026091502A1",
  "supersedes": null,
  "title": "Vision-language model for detecting and reasoning over failures in robotic manipulation",
  "uuid": "01a0a674-5a53-78a0-a575-5c3de9c4ef86"
}