A method and apparatus for controlling a robotic arm using dual macro lenses for constraint.

By combining dual macro lenses and a robotic arm, binocular stereo vision technology and a hierarchical iterative approximation strategy have solved the problem of cameras being unable to accurately match target objects in confined spaces, enabling the robotic arm to perform precise operations and high-precision 3D reconstruction in confined spaces.

CN121650026BActive Publication Date: 2026-05-26LASER FUSION RES CENT CHINA ACAD OF ENG PHYSICS
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202610172503.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-02-06
Publication Date
2026-05-26
Estimated Expiration
2046-02-06

AI Technical Summary

Technical Problem

In existing technologies, cameras struggle to simultaneously obtain clear images and sufficient field of view when imaging at close range. This results in the inability to accurately match target objects and obtain their precise three-dimensional coordinates in confined spaces, affecting the operational flexibility and precision of robotic arms.

Method used

By combining dual macro lenses with a robotic arm and employing binocular stereo vision technology, the robotic arm's positioning operation is divided into two stages: far-field coarse positioning and near-field fine positioning. Visual feedback is used to control the robotic arm to perform precise operations in confined spaces.

Benefits of technology

It enables precise 3D reconstruction and target detection of robotic arms in confined spaces, meeting the needs of robotic arms for fine operation in small workspaces and improving the flexibility and accuracy of operation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121650026B_ABST
    Figure CN121650026B_ABST
Patent Text Reader

Abstract

This invention belongs to the field of robotic arm control, and relates to a method and apparatus for controlling a robotic arm using dual macro lenses. The method includes: performing system calibration on the dual macro endoscopes and the end effector of the robotic arm to obtain transformation parameters; acquiring images of a target object within the workspace to obtain original images; preprocessing and detecting the target in the original images to obtain preprocessed images containing the features of the target object; performing pose estimation on the preprocessed images to obtain the pose information of the target object in the lens coordinate system; employing a hierarchical iterative approximation strategy based on visual feedback to control the robotic arm to gradually approach the target object with the dual macro endoscopes; converting the pose information of the target object in the lens coordinate system to the base coordinate system of the robotic arm; and based on the pose information of the target object in the base coordinate system, solving and generating joint rotation commands for the robotic arm, and controlling the robotic arm to complete the grasping operation of the target object; thereby meeting the precision operation requirements of the robotic arm in a confined workspace.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Convergent binocular vision guided robot positioning method in high dynamic range

    CN113360964A

  • Visual mechanical arm material grabbing control method and system based on deep learning

    CN118003340A

  • Abdominal cavity reconstruction and focus positioning method, system and equipment based on binocular endoscope

    CN119313824A

  • Image recognition method for electric energy meter recognition

    CN119649371A

  • Robot control method and system for industrial pipeline

    CN120552077A