复杂环境下无人机多模态数据融合自适应导航方法
By employing multimodal data fusion and a Bayesian framework adaptive navigation method, the problem of unstable pose estimation for UAVs in GPS-denied environments was solved, achieving high-precision and robust navigation performance.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- UNIV FOR SCI & TECH ZHENGZHOU
- Filing Date
- 2026-05-12
- Publication Date
- 2026-07-17
AI Technical Summary
Existing UAV navigation methods do not establish a mapping relationship between semantic labels and environmental states in GPS-denied environments. This leads to the continued use of a uniform constraint construction method when the environment changes, reducing the stability and continuity of pose estimation results.
By collecting multimodal sensor data, performing semantic segmentation and spatial alignment, constructing a probabilistic model using a Bayesian framework to map degenerate mode variables, selectively generating and adjusting semantic-structural constraint factors, constructing a two-layer factor graph for incremental optimization, and achieving adaptive navigation.
It significantly improves the smoothness and continuity of pose estimation in complex environments, and enhances the accuracy, robustness, adaptability, and continuity of navigation methods in dynamically changing scenarios.
Smart Images
Figure CN122170899B_ABST