基于预设标靶与因子图优化的隧道内车辆定位方法
By deploying targets inside the tunnel and combining them with factor map optimization, the problem of insufficient vehicle positioning accuracy inside the tunnel was solved, achieving high-precision and low-cost vehicle positioning that is adaptable to the complex environment inside the tunnel.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA RAILWAY 14TH BUREAU GRP LARGE SHIELD ENG CO LTD
- Filing Date
- 2026-04-28
- Publication Date
- 2026-07-17
AI Technical Summary
In enclosed underground spaces such as mines, subways, and railway tunnels, existing positioning technologies struggle to achieve centimeter-level high-precision vehicle positioning. In particular, in environments with weak or no GPS signals, inertial navigation and laser SLAM solutions suffer from error accumulation and failure in dusty or low-light conditions.
The method of pre-set target and factor graph optimization is adopted. By setting up targets in the tunnel, using lidar to identify visible targets and calculate absolute corrected pose, and combining the factor graph SLAM optimization framework for joint optimization, the vehicle pose trajectory is output.
It achieves high-precision vehicle positioning in long tunnels, reduces positioning errors, adapts to the low light and dust environment inside tunnels, reduces operation and maintenance costs and technical complexity, and meets the accuracy requirements of unmanned mining trucks.
Smart Images
Figure CN122108163B_ABST