发表机构
Huzhou Institute of Zhejiang University; University of Electronic Science and Technology of China; Institute of Cyber-Systems and Control, College of Control Science and Engineering, Zhejiang University; Differential Robotics Technology Company（浙江大学湖州研究院; 电子科技大学; 浙江大学控制科学与工程学院 cyber系统与控制研究所; 差分机器人技术公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对基于视觉的无人机导航死胡同问题，提出轻量级神经网络DPNet，利用RGB-D输入预测死胡同并修剪轨迹库，实现50Hz高频重规划，跨场景无需标注微调，仿真与真实实验验证其优异性能。
AI 中文摘要
基于视觉的无人机（UAV）常因感知精度和范围有限，在死胡同处出现导航故障。为解决该挑战，本文提出一种用于高效死胡同预测与规避的系统性方案。所提方法引入轻量级神经网络，利用RGB-D输入预测当前视场内潜在死胡同的相对距离与方位角。这些预测会修剪预定义的紧凑轨迹库，使规划器能主动规避死胡同，同时保持导航平滑性。值得注意的是，该方法可跨真实场景迁移，无需对真实数据进行手动标注或微调。系统在机载实现50Hz的高频重规划。大量仿真基准测试表明其在成功率、飞行时间及轨迹长度上的优异性能，真实场景实验进一步验证了其在复杂场景中的有效性。
英文摘要
Vision-based Unmanned Aerial Vehicles (UAVs) often suffer from navigation failures in dead ends due to limited sensing accuracy and range. To address this challenge, this paper proposes a systematic solution for efficient dead-end prediction and avoidance. The proposed method introduces a lightweight neural network to predict the relative distance and bearing of potential dead ends within the current field of view using RGB-D inputs. These predictions prune a predefined, compact trajectory library, enabling the planner to proactively avoid dead ends while maintaining navigational smoothness. Notably, our approach transfers across real-world scenarios without manual annotation or fine-tuning on real-world data. The system achieves high-frequency replanning at 50 Hz onboard. Extensive simulation benchmarks demonstrate superior performance in success rate, flight time, and trajectory length, and real-world experiments further validate its effectiveness in complex scenarios.
