---
publication_id: "OT-2026-000002169"
title: "Configuring a visual language model with spatial understanding for robotics"
published_at: "2026-09-15T19:11:13.887898Z"
canonical_url: "https://opentechnical.org/p/OT-2026-000002169"
categories:
  - "robotics-automation/robot-architectures"
keywords:
  - "b25j9/163"
  - "b25j9/163"
  - "b25j9/1697"
  - "b25j9/16"
  - "b25j9/163"
  - "b25j9/1697"
---

# Configuring a visual language model with spatial understanding for robotics

## 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.