用可逆神经网络实现无人机精准控制，效果接近经典方法。
Conditional Invertible Neural Networks for Data-Driven UAV Control: A 2-D Proof of Concept
- 设计条件可逆网络建模无人机逆动力学，支持概率控制决策。
- 闭环测试中位置误差仅略高于经典方法（9.7 vs 9.5米），47%场景跟踪达标。
- 揭示控制失败主因：指令带宽不足与数据覆盖不全，指导系统优化。
本文研究条件可逆神经网络（cINNs）作为多旋翼无人机的统计逆动力学模型。针对平面X8共轴多旋翼，利用增量非线性动态逆（INDI）教师模型，通过有理二次样条耦合与可逆线性混合学习 $p(u ackslashmid s_t, c_t)$。开环复现达到 $R^2 = 0.944$，平均CRPS为0.0915，对数似然误差相关系数 $ρ= -0.60$。在超过15个闭环场景中，位置均方根误差与INDI相当（9.7米 vs 9.5米），47%场景实现可接受跟踪；失败模式分为激进指令下的姿态发散与高频参考下的相位滞后，明确指出指令带宽和数据覆盖是主要失效机制。
原文摘要 · Abstract (English)
We investigate conditional invertible neural networks (cINNs) as probabilistic inverse-dynamics models for multirotor control. For a planar X8 coaxial multicopter, we learn $p(u \mid s_t, c_t)$ from an incremental nonlinear dynamic inversion (INDI) teacher using rational-quadratic spline coupling and invertible linear mixing. Open-loop reproduction reaches $R^2 = 0.944$, mean CRPS 0.0915, and log-probability-error correlation $ρ= -0.60$. Over 15 closed-loop scenarios, position RMSE matches INDI (9.7 vs. 9.5 m), with 47 percent tracking acceptably; failures separate into attitude divergence under aggressive steps and phase lag under high-frequency references, isolating command bandwidth and data coverage as dominant failure mechanisms.
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。