一种用于无人机的避障方法及系统
By using multi-source sensor fusion and an adaptive fuzzy decision tree model, high-precision obstacle avoidance of UAVs in complex environments was achieved, solving the problems of low obstacle avoidance accuracy and insufficient stability in existing technologies and improving the autonomous flight capability of UAVs.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- JIANGSU YOUYOUJIA TECH CO LTD
- Filing Date
- 2025-08-15
- Publication Date
- 2026-07-17
AI Technical Summary
Existing drone obstacle avoidance technologies have poor real-time adaptability in complex environments, limited single-dimensional perception features, and poor generalization performance, making it difficult to achieve effective obstacle avoidance decisions and smooth transitions.
The system employs multi-source sensor fusion technology to acquire obstacle information through lidar, binocular vision, and millimeter-wave radar, constructs obstacle avoidance feature vectors, and uses a dual-membership adaptive fuzzy decision tree model to make real-time obstacle avoidance action decisions. It also combines a trajectory generator and a propulsion motor to perform maneuvering operations.
It improves the obstacle avoidance accuracy and stability of UAVs in complex environments, ensures the accuracy and rapid recovery of obstacle avoidance actions, and enhances the safety and adaptability of autonomous flight.
Smart Images
Figure CN120872001B_ABST