An industrial sensing and transmission algorithm closed-loop scheduling method and system based on digital twinning

By combining digital twin technology with D3QN and TD3 algorithms, the perception, communication and scheduling links of multi-AGV systems are optimized, solving the global closed-loop feedback problem of perception data fidelity, scheduling response efficiency and resource consumption in multi-AGV collaborative operations, and improving the adaptive collaborative scheduling capability and resource utilization efficiency of multi-AGV systems.

CN122372944APending Publication Date: 2026-07-10NANJING UNIV OF POSTS & TELECOMM
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
NANJING UNIV OF POSTS & TELECOMM
Filing Date
2026-05-20
Publication Date
2026-07-10

AI Technical Summary

Technical Problem

Existing multi-AGV collaboration and edge computing methods lack a global closed-loop feedback mechanism, making it difficult to simultaneously consider the fidelity of environmental perception data, scheduling response efficiency, and resource consumption in industrial scenarios, thus limiting the collaborative operation efficiency of multi-AGV systems.

Method used

A closed-loop scheduling method based on digital twins for industrial sensing and computing is adopted. By constructing a state representation model and combining the closed-loop scheduling decision algorithms of D3QN and TD3, the sensing, communication, computing and scheduling feedback links are optimized to achieve adaptive collaborative scheduling of sensing frequency strategy and task allocation strategy.

Benefits of technology

It improves the closed-loop adaptive scheduling capability of multi-AGV systems in dynamic environments, reduces unnecessary sensing and processing overhead, and enhances the overall service quality and resource utilization efficiency of multi-AGV collaborative scheduling in industrial scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122372944A_ABST
    Figure CN122372944A_ABST
Patent Text Reader

Abstract

This invention belongs to the field of intelligent edge network technology and discloses an industrial sensing, communication, computing, and closed-loop scheduling method and system based on digital twins. Within the current closed-loop scheduling time slot of multiple industrial AGVs, it acquires environmental perception data, the state information of each AGV and the edge gateway, constructs a state representation model in a digital mapping space, establishes a collaborative benefit evaluation mechanism, obtains the collaborative benefit of a single time slot, and derives a comprehensive benefit function. It then employs a closed-loop scheduling decision algorithm to optimize the strategy, outputs the sensing frequency strategy and task allocation strategy for each AGV in the next time slot, and distributes them to the corresponding AGVs, updating the state representation model and realizing the collaborative scheduling of the industrial multi-AGV system. This invention can uniformly optimize multiple aspects such as perception, communication, computing, and scheduling feedback, and uses the updated state representation model in the digital mapping space to support the generation of scheduling decisions for the next time slot, thereby improving the closed-loop scheduling capability and overall operating efficiency of the industrial multi-AGV system.
Need to check novelty before this filing date? Find Prior Art