A robotic task planning system, method and apparatus

By combining expert skill bases and vector knowledge bases in robot task planning, on-demand activation and resource loading are achieved, solving the problems of redundant inference computation and context pollution, and improving the execution efficiency and success rate of long-term tasks.

CN122263952APending Publication Date: 2026-06-23CHENGDU HUMANOID ROBOT INNOVATION CENT CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
CHENGDU HUMANOID ROBOT INNOVATION CENT CO LTD
Filing Date
2026-05-25
Publication Date
2026-06-23

AI Technical Summary

Technical Problem

Existing technologies in robot task planning suffer from problems such as redundant reasoning computation, context fragmentation, context pollution, and heavy reasoning burden, resulting in low execution efficiency and low success rate of long-term tasks.

Method used

Independent skill modules are encapsulated using an expert skill library, configured with a state machine, and the decision-making brain activates and loads resources on demand. Historical scenario data is maintained through a vector knowledge base, enabling plug-and-play functionality and physical isolation, reducing the activation of global tools, and combining state monitoring and self-healing modules for real-time monitoring and remedial measures.

Benefits of technology

It improves the efficiency and success rate of robot long-term task planning, reduces inference burden and latency, avoids context pollution and instruction deviation, and improves migration efficiency and versatility between heterogeneous platforms.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122263952A_ABST
    Figure CN122263952A_ABST
Patent Text Reader

Abstract

The application discloses a kind of robot task planning system, method and device, it is related to embodied intelligence field, to improve the success rate of robot long-range task planning efficiency and implementation.System includes expert skill base, encapsulates multiple independent skill modules;Vector knowledge base, maintain historical scene data;Decision brain, receive and understand natural language instruction, implement instruction based on historical scene data;Determine the skill module required to be called in implementation instruction;In the process of implementing instruction, according to current task progress, only activate the skill module required currently, load required resource for the activated skill module immediately, resource includes at least one of historical scene data, historical context data, current scene data;Current activated skill module and the operation result of current skill module are written into historical context data.The application greatly reduces the reasoning burden, improves the success rate of long-range task planning efficiency and execution.
Need to check novelty before this filing date? Find Prior Art