用轻量网络实时预测死胡同，让无人机避障更智能
DPNet: Efficient Dead-End Prediction and Avoidance for Vision-Based UAV Navigation
- 基于RGB-D输入，用轻量网络预测死胡同距离和方向
- 50Hz高频重规划，仿真中成功率高、飞行时间短
- 无需标注或微调，真实场景也能直接用
基于视觉的无人机在死胡同中常因感知精度和范围受限而导航失败。本文提出一种高效死胡同预测与规避系统，引入轻量神经网络，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，据此修剪预定义的紧凑轨迹库，使规划器能主动避开死胡同并保持飞行平滑。该方法无需真实数据标注或微调即可跨场景迁移。系统实现50 Hz的高频重规划，大量仿真基准测试显示其在成功率、飞行时间和轨迹长度上表现优异，真实实验进一步验证了其在复杂场景下的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。