Back to results
US 2026/0061605 A1Published application
Configuring a visual language model with spatial understanding for robotics
AssigneeNVIDIA Corporation
InventorsChan Hee Song, Valts Blukis, Jonathan Tremblay, Stephen Tyree, Stanley Thomas Birchfield
Life of this patent
Estimating the term…
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.
Claims26
A system comprising:
- a vision-language model configured with a training dataset comprising 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.
1 more element
A system comprising:
- a robot;
- a vision-language model configured with a training dataset comprising images labeled with spatial question-and-answer pairs encoding object-to-object relationships and object-to-space relationships represented in the images;
- and
- logic to operate the vision-language model to generate pick-and-place steps for the robot based on a natural language prompt.
1 more element
Dependencies are inferred from the claim text.