科技创新与应用2025，Vol.15Issue(34)：37-40,4.DOI:10.19981/j.CN23-1581/G3.2025.34.009
基于多传感器融合的无人机自主避障技术研究
摘要
Abstract
In response to the autonomous obstacle avoidance needs of UAVs in complex environments,this research proposes a collaborative sensing and decision-making architecture based on multi-sensor fusion.Through heterogeneous sensor spatio-temporal calibration and feature-level fusion methods,a LiDAR-vision-IMU joint sensing model is constructed,and a hybrid path planning strategy of dynamic threat balls and rolling time domain optimization is designed.Simulation tests show that the system achieves an obstacle avoidance success rate of 89.7%in dynamic obstacle raid scenarios,and the trajectory length ratio is optimized to 1.23.In the actual flight verification,the fusion positioning error in the urban building complex environment was controlled within 1.2 m,and the identification accuracy of dead branches and obstacles in forest scenes reached 92%.The research results provide technical support for safe navigation of UAVs in GNSS denial environments.关键词
多传感器融合/自主避障/路径规划/动态障碍/无人机导航Key words
multi-sensor fusion/autonomous obstacle avoidance/path planning/dynamic obstacle/UAV navigation分类
航空航天引用本文复制引用
王丽明,辛朝阳..基于多传感器融合的无人机自主避障技术研究[J].科技创新与应用,2025,15(34):37-40,4.基金项目
黄河交通学院2023年度"航空概论课程教学资源库"(HHJTXY-2023kczyk16) （HHJTXY-2023kczyk16）
