OpenTechnical
This is a record of a document published elsewhere, first published by the United States Patent and Trademark Office, as US-2026061610-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-2026-000002223

System and Method for Object Segmentation for Task Performance

Published
Permanent URL
Classification
Robotics & Automation › Robot Architectures
Inventors
CHERIAN ANOOP, JAIN SIDDARTH, MARKS TIM
Assignee
MITSUBISHI ELECTRIC RES LABORATORIES INC
Original source
US-2026061610-A1, the United States Patent and Trademark Office, 5 March 2026
Document SHA-256
c5c2a7aca492507da0f4e6a6c0767a185afa722e8d60a9d7efe7c30db97745b1

Abstract

Embodiments disclosing a controller for controlling a robot to perform a task are provided. The task is performed in an environment that is represented by an input image. The controller causes segmenting of an object in the input image. A confidence level of segmentation is updated by comparing the segmented object with constrained affined transformations of a template of the object. The constrained affine transformations are based on constraints indicative of a property of the object. The property of the object and the updated confidence level of segmentation are then used for performing the task.

Publication information

Plain textMarkdownManifestIntegrity record

Citation

OpenTechnical Publication OT-2026-000002223, “System and Method for Object Segmentation for Task Performance,” published September 15, 2026 at 19:11:34 UTC, https://opentechnical.org/p/OT-2026-000002223.

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.