OpenTechnical
This is a record of a document published elsewhere, first published by the United States Patent and Trademark Office, as US-2026061605-A1, on 5 March 2026. OpenTechnical did not first disclose it. The identifier, hashes and timestamps below record what this library served and when, not when the material became public. View the original.

OT-2026-000002169

Configuring a visual language model with spatial understanding for robotics

Published
Permanent URL
Classification
Robotics & Automation › Robot Architectures
Inventors
BIRCHFIELD STANLEY THOMAS, BLUKIS VALTS, SONG CHAN HEE, TREMBLAY JONATHAN, TYREE STEPHEN
Assignee
NVIDIA CORP
Original source
US-2026061605-A1, the United States Patent and Trademark Office, 5 March 2026
Document SHA-256
eaeb42d100d6559d42147ff3326c9aa35d231cbb9219134fa3bae9778b5da415

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.

Publication information

Plain textMarkdownManifestIntegrity record

Citation

OpenTechnical Publication OT-2026-000002169, “Configuring a visual language model with spatial understanding for robotics,” published September 15, 2026 at 19:11:13 UTC, https://opentechnical.org/p/OT-2026-000002169.

To cite specific content, add the paragraph or figure numbers.

Terms

This record reproduces a document published elsewhere and is provided for reference and study. Rights in the original remain with its owner. See the publication policy.