Building full autonomous construction method based on multi-humanoid robot cluster and related equipment

By comparing the acquired 3D point cloud data with the design data, the robot's construction position was adjusted, which solved the problem of component deviation caused by the superposition of construction tolerances in fully autonomous building construction, thus improving construction quality and safety.

CN122165413APending Publication Date: 2026-06-09SHANGHAI CONSTRUCTION FIRST CONSTRUCTION (GROUP) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SHANGHAI CONSTRUCTION FIRST CONSTRUCTION (GROUP) CO LTD
Filing Date
2026-04-08
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

During the fully autonomous construction process, the cumulative construction tolerances of each process lead to an increase in the cumulative deviation between the completed components and the design coordinates, causing the risk of physical interference between components and reducing the construction quality.

Method used

By acquiring the 3D point cloud data of the construction area of ​​the preceding humanoid robot, comparing it with the initial design data, extracting the spatial deviation vector, dividing the rigid entity and flexible tolerance data, adjusting the position of the components by overall pose translation and rotation, updating the construction benchmark in real time, and generating execution instructions to mitigate the deviation.

Benefits of technology

It effectively alleviates the problem of component squeezing and interference caused by the superposition of process errors, and improves the construction quality and safety of fully autonomous construction by robot clusters.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122165413A_ABST
    Figure CN122165413A_ABST
Patent Text Reader

Abstract

This application provides a fully autonomous construction method and related equipment based on a multi-robot swarm. In this method, the control processing unit first compares the actual 3D point cloud data after the completion of previous humanoid robot operations with the theoretical installation reference plane to obtain the actual spatial deviation vector. Then, the control processing unit divides the 3D data of the component to be installed into rigid solid data and flexible tolerance data. Next, the control processing unit performs overall pose translation and rotation on the rigid solid data based on the spatial deviation vector, and converts the spatial difference generated after pose adjustment into the target filling size of the flexible tolerance data. Finally, the control processing unit generates execution instructions based on the adjusted tolerance pose data and target filling size, and updates the subsequent point cloud with the aforementioned completed state. This method alleviates the component compression interference problem caused by accumulated errors in the preceding stages and improves the construction quality of the fully autonomous relay construction by the robot swarm.
Need to check novelty before this filing date? Find Prior Art