Amortized Inference for Model Rocket Aerodynamics: Learning to Estimate Physical Parameters from Simulation

TL;DR

This paper introduces a neural network-based amortized inference method trained on simulated rocket flights to accurately estimate aerodynamic parameters from minimal real flight data, enabling effective sim-to-real transfer.

Contribution

The authors develop a novel simulation-trained neural network that directly predicts aerodynamic parameters from single-flight measurements without real data fine-tuning.

Findings

Achieved a mean absolute error of 12.3 m in apogee prediction on real flights.

Demonstrated effective sim-to-real transfer with zero real flight training data.

Compared favorably against OpenRocket baseline predictions.

Abstract

Accurate prediction of model rocket flight performance requires estimating aerodynamic parameters that are difficult to measure directly. Traditional approaches rely on computational fluid dynamics or empirical correlations, while data-driven methods require extensive real flight data that is expensive and time-consuming to collect. We present a simulation-based amortized inference approach that trains a neural network on synthetic flight data generated from a physics simulator, then applies the learned model to real flights without any fine-tuning. Our method learns to invert the forward physics model, directly predicting drag coefficient and thrust correction factor from a single apogee measurement combined with motor and configuration features. In this proof-of-concept study, we train on 10,000 synthetic flights and evaluate on 8 real flights, achieving a mean absolute error of 12.3 m in apogee prediction - demonstrating promising sim-to-real transfer with zero real training examples. Analysis reveals a systematic positive bias in predictions, providing quantitative insight into the gap between idealized physics and real-world flight conditions. We additionally compare against OpenRocket baseline predictions, showing that our learned approach reduces apogee prediction error. Our implementation is publicly available to support reproducibility and adoption in the amateur rocketry community.