# Conditional Invertible Neural Networks for Data-Driven UAV Control: A 2-D Proof of Concept

arXiv: https://arxiv.org/abs/2607.13703 · HTML: https://mlsanity.com/paper/2607.13703/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 21 references that are in the map.
- First posted on arXiv 15 Jul 2026.

## Builds on (most cited first, 11 of 11)

- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Neural Spline Flows](https://mlsanity.com/paper/1906.04032/) (2019)
- [Analyzing Inverse Problems with Invertible Neural Networks](https://mlsanity.com/paper/1808.04730/) (2018)
- [Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learning](https://mlsanity.com/paper/2310.10943/) (2023)
- [Deep Drone Acrobatics](https://mlsanity.com/paper/2006.05768/) (2020)
- [Time-Optimal Planning for Quadrotor Waypoint Flight](https://mlsanity.com/paper/2108.04537/) (2021)
- [Model Predictive Contouring Control for Time-Optimal Quadrotor Flight](https://mlsanity.com/paper/2108.13205/) (2021)
- [Conditional Invertible Neural Networks for Medical Imaging](https://mlsanity.com/paper/2110.14520/) (2021)
- [Inverse design of two-dimensional materials with invertible neural networks](https://mlsanity.com/paper/2106.03013/) (2021)
- [Invertible Neural Networks for Uncertainty Quantification in Photoacoustic Imaging](https://mlsanity.com/paper/2011.05110/) (2020)

## Abstract (arXiv)

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 st, ct) from an incremental nonlinear dynamic inversion (INDI) teacher using rational-quadratic spline coupling and invertible linear mixing. Open-loop reproduction reaches R2 = 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.