Air-ground heterogeneous cluster real-time mapping method and device for large-scale complex scene

CN120630237APending Publication Date: 2025-09-12ZHONGBING INTELLIGENT INNOVATION RES INST CO LTD

Patent Information

Application Number
CN202510561289.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-04-30
Publication Date
2025-09-12

Smart Images

  • Figure CN120630237A_ABST
    Figure CN120630237A_ABST
Patent Text Reader

Abstract

The invention discloses an air-ground heterogeneous cluster real-time mapping method and device for a large-scale complex scene, and the method aims at solving the problems of poor real-time performance, insufficient consistency and the like of an existing method, employs a stable triangular descriptor as a global descriptor of a laser radar key frame, carries out the loopback detection based on the key frame, and achieves the real-time mapping of an air-ground heterogeneous cluster. According to the method, a relative pose constraint relation between key frames of different carriers is established, and then the key frames of all the carriers are brought into the same pose map optimization for pose solution, so that a global consistent track and point cloud map is obtained, and efficient fusion of a multi-machine map is realized. According to the method, the phenomena of ghosting and structure distortion in the conventional map fusion can be effectively solved, and the mapping consistency and the mapping precision are improved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Cross-domain cooperative localization and mapping method and system based on three-dimensional point cloud

    CN113470089A

  • Outdoor scene-oriented multi-robot cooperative positioning and mapping method

    CN115420276A

  • Air-ground heterogeneous collaborative mapping method and device, equipment and storage medium

    CN117191005A

  • Laser radar SLAM method based on point cloud descriptor loopback detection

    CN117974788A

Cited By

  • Semi-distributed cross-modal relative positioning method and system

    CN121095343A

  • Semi-distributed cross-modal relative positioning method and system

    CN121095343B

  • Ground-air collaborative mapping method based on semantic feature and ground plane multi-constraint fusion

    CN121353463A

  • Ground-air collaborative mapping method based on semantic features and ground plane multi-constraint fusion

    CN121353463B

  • Multi-sensor fusion anti-degradation SLAM mapping method and system

    CN121353569A