双模态耦合感知的无人机避障控制方法及系统
By fusing image and radar information to construct an adaptive risk ellipsoid, a dual-modal coupled perception method is proposed to solve the static problem of obstacle risk modeling in UAV obstacle avoidance, improve the refinement and safety of obstacle avoidance strategies, and realize efficient obstacle avoidance of UAVs in complex environments.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANDONG UNIV
- Filing Date
- 2026-04-22
- Publication Date
- 2026-07-17
AI Technical Summary
In existing drone obstacle avoidance technologies, obstacle risk modeling is static and coarse-grained, failing to provide a refined and adaptive understanding of the environmental situation. This results in drone obstacle avoidance strategies lacking specificity and foresight, affecting the system's safety and intelligence.
A dual-modal coupled sensing method is adopted, which integrates image information and radar information. The three-dimensional centroid and geometric dimensions of obstacles are extracted through target detection and point cloud data processing. Combined with semantic risk prior coefficients and UAV status, an adaptive three-dimensional risk ellipsoid is constructed, and obstacle avoidance control commands are generated using a reinforcement learning decision network.
It enables refined and differentiated modeling of obstacle and danger zones, improves the autonomous obstacle avoidance capability and flight intelligence of UAVs in complex dynamic scenarios, and enhances the safety and generalization capability of obstacle avoidance strategies.
Smart Images
Figure CN122064102B_ABST