LiLib:无人机漂移触发模型库持续学习路径损耗预测
Get the story
2026年10月7日,arXiv Machine Learning Theory 发布一手报道,介绍 LiLib——一种面向无人机的轻量持续学习方案。该方案通过窗口残差检测漂移,并维护一个递归最小二乘专家库,根据空地路径损耗变化决定复用已有专家或新建专家。仿真结果显示,LiLib 将预测 RMSE 从 5.89 dB 降至 4.03 dB;重返已知环境后的误差从 12.3 dB 降至 5.7 dB;速率适配恢复至 regime-aware oracle 吞吐的 99%。目前报道仅涉及仿真验证,未提及其他独立复现或实际部署信息。
Generated from reports · updated 3 hr ago
Timeline
Follow the coverage from different angles.
- arXiv · Machine Learning TheoryLiLib:基于漂移触发模型库的无人机终身空地路径损耗预测
LiLib 是一种面向无人机的轻量持续学习方案,用窗口残差检测漂移并维护一个递归最小二乘专家库,复用或新建专家以应对空地路径损耗变化。仿真中,LiLib 将预测 RMSE 从 5.89 dB 降至 4.03 dB,重返已知环境后的误差从 12.3 dB 降至 5.7 dB,速率适配恢复至 regime-aware oracle 吞吐的 99%。
Heat trend
Current heat 9·Comparable peak 10(Oct 7)·Comparable change over 24 hours –
The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.