UAV low-altitude autonomous navigation and obstacle avoidance technology based on AI and multi-sensor fusion
基于AI与多传感器融合的无人机低空自主导航与避障技术

摘要

针对无人机低空复杂场景下自主导航与避障的可靠性、实时性难题，融合激光雷达、视觉、惯性测量单元等多源传感器数据，构建多模态环境感知体系，弥补单一传感器在光照、雨雾等极端条件下的感知缺陷。引入深度学习与强化学习算法，实现障碍物高精度识别、动态轨迹预测与毫秒级路径重规划，形成感知—决策—控制闭环系统。该技术可显著提升无人机在城市街巷、森林等复杂低空环境的自主飞行能力，降低碰撞风险，适配物流配送、电力巡检、应急救援等多场景作业需求。

Abstract

Aiming at the reliability and real-time challenges of autonomous navigation and obstacle avoidance for unmanned aerial vehicles(UAVs)in complex low-altitude scenarios, this study integrates multi-source sensor data including LiDAR, vision, and inertial measurement units to establish a multimodal environmental perception system, which compensates for the perception deficiencies of single sensors under extreme conditions such as illumination variations, rain and fog. Deep learning and reinforcement learning algorithms are introduced to achieve high-precision obstacle recognition, dynamic trajectory prediction and millisecond-level path replanning, forming a closed-loop system of perception–decision–control. This technology can significantly improve the autonomous flight capability of UAVs in complex low-altitude environments such as urban streets and forests, reduce collision risks, and adapt to operational requirements in multiple scenarios including logistics distribution, power inspection and emergency rescue.