aiqbench analysis
This research applies Neural Hamiltonian ODEs to model gravity field irregularities around small celestial bodies, demonstrating superior accuracy over traditional spherical harmonics for landing trajectory planning. By embedding a neural network directly into the system's physical equations of motion, the method enables continual learning from tracking data without requiring explicit acceleration labels. This approach represents a significant convergence of machine learning techniques with astrophysics and orbital mechanics to solve complex dynamical estimation problems.
Continuous Learning of Gravity Field Irregularities Around Small Bodies via Neural Hamiltonian ODEs
arXiv:2609.12022v1 Announce Type: cross Abstract: We propose to learn the unknown dynamics in the proximity of a small body directly from tracking data, representing them as a feed-forward neural network embedded in the system Hamiltonian. The equations of motion form a Neural Hamiltonian Ordinary Differential Equation, whose variational equations provide exact training gradients: estimation uses position and velocity arcs at realistic noise levels, without acceleration or potential labels, and a continual learning approach warm-starts the network as new data are acquired. The known part of the Hamiltonian carries whatever is available, from the central term and spin state to the constant-density model of the imaged shape. We assess the method against a normalized spherical harmonics expansion estimated from identical arcs through the same machinery, on scenarios built on the shapes of Itokawa, 67P, Bennu and Eros. The network remains usable inside the Brillouin sphere: it plans ballistic descents at Itokawa to \SI{4.6}{m} median touchdown error from tracking alone, against 5.1--\SI{48.9}{m} for harmonics of degree 4--12, and to \SI{0.9}{m} with the imaged shape as prior, a configuration that also recovers localised density anomalies invisible to any harmonics degree. The two representations are complementary, and we discuss their combined use across the phases of a small-body mission.
Abstract:We propose to learn the unknown dynamics in the proximity of a small body directly from tracking data, representing them as a feed-forward neural network embedded in the system Hamiltonian. The equations of motion form a Neural Hamiltonian Ordinary Differential Equation, whose variational equations provide exact training gradients: estimation uses position and velocity arcs at realistic noise levels, without acceleration or potential labels, and a continual learning approach warm-starts the network as new data are acquired. The known part of the Hamiltonian carries whatever is available, from the central term and spin state to the constant-density model of the imaged shape. We assess the method against a normalized spherical harmonics expansion estimated from identical arcs through the same machinery, on scenarios built on the shapes of Itokawa, 67P, Bennu and Eros. The network remains usable inside the Brillouin sphere: it plans ballistic descents at Itokawa to \SI{4.6}{m} median touchdown error from tracking alone, against 5.1--\SI{48.9}{m} for harmonics of degree 4--12, and to \SI{0.9}{m} with the imaged shape as prior, a configuration that also recovers localised density anomalies invisible to any harmonics degree. The two representations are complementary, and we discuss their combined use across the phases of a small-body mission.
Instrumentation and Methods for Astrophysics (astro-ph.IM); Earth and Planetary Astrophysics (astro-ph.EP); Artificial Intelligence (cs.AI); Optimization and Control (math.OC); Space Physics (physics.space-ph)
arXiv:2609.12022 [astro-ph.IM]
(or arXiv:2609.12022v1 [astro-ph.IM] for this version)
https://doi.org/10.48550/arXiv.2609.12022 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 236 words
Related coverage
Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics
Latent Space · Oct 13, 2026
Does preservation make sense before we know how to revive?
LessWrong · Jun 15, 2026
Synthesis Superintelligence: from Semiconductors to Superconductors — Periodic Labs’ Liam Fedus and Ekin Dogus Cubuk
Latent Space · Oct 8, 2026
How to build a cancer vaccine, and whether they will work this time
LessWrong · Jun 8, 2026