---
publication_id: "OT-2026-000002846"
title: "System and method for unknown object manipulation from pure synthetic stereo data"
published_at: "2026-09-15T19:15:44.079556Z"
canonical_url: "https://opentechnical.org/p/OT-2026-000002846"
categories:
  - "robotics-automation/robot-architectures"
keywords:
  - "b25j9/1697"
  - "b25j9/1697"
  - "b25j9/1697"
  - "b25j9/16"
  - "b25j9/1612"
  - "b25j9/1661"
---

# System and method for unknown object manipulation from pure synthetic stereo data

## Abstract

A method for training a neural network to perform 3D object manipulation is described. The method includes extracting features from each image of a synthetic stereo pair of images. The method also includes generating a low-resolution disparity image based on the features extracted from each image of the synthetic stereo pair of images. The method further includes generating, by the neural network, a feature map based on the low-resolution disparity image and one of the synthetic stereo pair of images. The method also includes manipulating an unknown object perceived from the feature map according to a perception prediction from a prediction head.