giacomo acciarini

High-order expansion of neural ordinary differential equation flows | Science Advances science.org/doi/10.1126/sc…

Just secured 2nd place in #GTOC13! 🚀 Proud of our team’s advanced interplanetary mission design. Celebrate with this exclusive fly-through of our final trajectory👇 youtube.com/watch?v=yVqnrV… #TrajectoryOptimization #Astrodynamics #SpaceMission

EclipseNETs: Learning irregular small celestial body silhouettes sciencedirect.com/science/articl…

Nonlinear Propagation of Non-Gaussian Uncertainties | Journal of Guidance, Control, and Dynamics arc.aiaa.org/doi/10.2514/1.…

@atilimgunes @darioizzo_ @UniofOxford @esaACT

We hope it will be a valuable resource for satellite operators and researchers.

Happy to share our latest publication in Acta Astronautica: "Closing the gap between SGP4 and high-precision propagation via differentiable programming" doi.org/10.1016/j.acta…

The result: an orbital propagator that bridges the gap between traditional models and high-precision numerical methods.

What’s even more exciting is ML-∂SGP4, a paradigm enabled by the differentiability of our model. Using #ML models within ∂SGP4, users can fine-tune the model using observed or high-fidelity simulation data.

and also gradient-based optimization to find the #TLE that best matches a given state. All while supporting batch processing of TLEs and modern hardware acceleration (GPUs/TPUs)

Don't hesitate to let us know if you have any questions or interest in the work.

This approach effectively decouples time and state-dependent components, allowing us to perform computations on the state 'offline' and then rapidly evaluate the entire shape of the probability density function through time, with deterministic and stochastic dynamics.

Our journal publication is now available online: sciencedirect.com/science/articl…. This was one of my first works, and I had a lot of fun working on this with @cristiangreco94 some years ago :) #astrodynamics #uncertainty #propagation #fokkerplanck