Dynamic object pose recognition and mechanical arm grabbing control algorithm

By deeply integrating perception, prediction, and planning through an integrated closed-loop control framework, the problems of information fragmentation and timing mismatch in dynamic object pose recognition and grasping control are solved. It achieves high-precision tracking and high-success-rate grasping of high-speed, non-uniform moving objects, and is suitable for intelligent manufacturing, logistics warehousing, and human-machine collaborative environments.

CN121625151APending Publication Date: 2026-03-10NORTH CHINA UNIVERSITY OF TECHNOLOGY
8 Cites 8 Cited by

Patent Information

Application Number
CN202511997478.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-27
Publication Date
2026-03-10

AI Technical Summary

Technical Problem

In existing technologies, the pose recognition and grasping control of dynamic objects suffer from information fragmentation and timing mismatch, leading to grasping failure and low efficiency, especially when dealing with objects moving at high speed or non-uniform speed.

Method used

An integrated closed-loop control framework is constructed, which achieves deep integration of perception, prediction and planning through a multi-source heterogeneous perception fusion module, a motion state joint estimation engine, an online grasping feasibility evaluator and a rolling time-domain grasping controller. A joint estimation and rolling optimization strategy with a unified state space is adopted to eliminate information silos and improve robustness and success rate.

Benefits of technology

While ensuring computational efficiency, it significantly improves the robustness and success rate of grasping objects with high speed, non-uniform speed and sudden change of direction, and reduces system latency, making it suitable for complex application scenarios in intelligent manufacturing, logistics warehousing and human-machine collaborative environments.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the technical field of dynamic object pose recognition and mechanical arm grabbing control algorithms, and discloses a dynamic object pose recognition and mechanical arm grabbing control algorithm. The framework comprises a multi-source heterogeneous sensing fusion module, a motion state joint estimation engine, a grabbing feasibility online evaluator and a rolling time domain grabbing controller, and low-delay collaboration is achieved through unified state space modeling and event-driven scheduling. Wherein the sensing module fuses RGB-D and inertial data to output a six-degree-of-freedom pose with covariance, the estimation engine adopts self-adaptive unscented Kalman filtering to recursion a complete motion state, the evaluator combines dynamic constraints to screen feasible grabbing postures, and the controller solves an optimal joint trajectory with obstacle avoidance constraints on line based on a self-adaptive target trajectory. And feedforward compensation is introduced to suppress dynamic disturbance. According to the technical scheme, the real-time performance is guaranteed, and meanwhile the grabbing success rate and robustness of high-speed, non-uniform-speed and sudden turning dynamic objects are remarkably improved.
Need to check novelty before this filing date? Find Prior Art