Industrial solid waste intelligent sorting and resource processing system

By combining multimodal perception and data preprocessing, physical feature decoupling extraction and material stiffness prediction with impedance control planning, adaptive compliant grasping under complex working conditions is achieved. This solves the problem of identification and grasping under heavy stacking and deformation conditions in existing systems, and improves the reliability and efficiency of industrial solid waste sorting.

CN121921316BActive Publication Date: 2026-06-05LUOYANG INST OF SCI & TECH +2
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
LUOYANG INST OF SCI & TECH
Filing Date
2026-03-25
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

Existing intelligent sorting systems struggle to accurately extract the complete outline and spatial location of target objects when faced with heavily stacked, obstructed, or severely deformed industrial solid waste, leading to grasping failures or damage to the objects and affecting the system's reliability and adaptability.

Method used

Spatiotemporal registration and micro-enhancement are performed through a multimodal perception and data preprocessing module. Combined with physical feature decoupling extraction and material property stiffness prediction, adaptive compliant grasping is achieved by using impedance control planning. The motor output torque is dynamically adjusted to complete the grasping process.

Benefits of technology

It significantly improves the recognition success rate and grasping stability, avoids object damage and slippage, and enhances the stability and efficiency of resource utilization on the production line.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121921316B_ABST
    Figure CN121921316B_ABST
Patent Text Reader

Abstract

The application discloses an industrial solid waste intelligent sorting and resource processing system, which is characterized in that: the system is capable of complementarily fusing rich textures of RGB images and accurate geometric information of depth point clouds, and combining a graph convolution network to model topological relationships of unstructured and severely deformed solid wastes, and then mapping decoupled macro-micro physical characteristics to material stiffness parameters through a multi-physical field network to guide the planning of grasping force under impedance control. In this way, not only can the recognition success rate under the stacking working condition be significantly improved, but also adaptive compliant grasping can be completed when processing mixed materials of rigidity and flexibility, effectively preventing object damage caused by clamping overload or sliding caused by dynamic swinging, and greatly enhancing the stability and operation efficiency of the production line resource processing.
Need to check novelty before this filing date? Find Prior Art