Conditional normalizing flows model the posterior over initial states from short-arc angles-only measurements in cislunar NRHOs and supply warm starts for nonlinear least-squares refinement.
Golombek, Roland Brockers, Michael Mischna, and Martin R
8 Pith papers cite this work, alongside 127 external citations. Polarity classification is still indexing.
8
Pith papers citing it
127
external citations · external index
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 8roles
background 2polarities
background 2representative citing papers
Introduces a lunar cross-view geo-localization benchmark with rendered panoramas and overhead tiles, then evaluates a transformer-based retrieval method on it.
A graph-based framework using sequences of lobe dynamics constructs low-energy transfer trajectories in the Earth-Moon CR3BP, refines them via multiple shooting in the bicircular four-body problem, and demonstrates effectiveness against existing solutions.
SuNeRF-CME uses physics-informed NeRFs with ray-tracing for Thomson scattering and constraints on plasma continuity, direction, and speed to enable tomographic 3D reconstruction of CMEs from as few as two viewpoints, validated on synthetic data with low parameter errors.
A new aerocapture guidance method uses a probabilistic indicator function to estimate and mitigate failure risks, saving 71.43% to 100% of recoverable cases in high-uncertainty simulations across varied initial conditions and atmosphere models.
Geo-LoFTR is a geometry-aided deep learning model for map-based localization that outperforms prior methods under large illumination and scale variations on simulated and real Mars imagery.
The authors analyze low-thrust transfer trajectories and science orbits for a 3m class space telescope, comparing a 2:1 lunar resonant orbit and Sun-Earth L2 halo orbit for exoplanet detection performance.
The paper reviews ML applications for sequence modeling, pattern recognition, and generative Bayesian analysis to tackle heterogeneous data challenges in (exo)planetary science.
citing papers explorer
-
Physics-informed Conditional Normalizing Flows for Angles-only Cislunar Orbit Determination
Conditional normalizing flows model the posterior over initial states from short-arc angles-only measurements in cislunar NRHOs and supply warm starts for nonlinear least-squares refinement.
-
Learning Cross-view Correspondences for Geo-localization on Planetary Surfaces
Introduces a lunar cross-view geo-localization benchmark with rendered panoramas and overhead tiles, then evaluates a transformer-based retrieval method on it.
-
Design of low-energy transfers in cislunar space using sequences of lobe dynamics
A graph-based framework using sequences of lobe dynamics constructs low-energy transfer trajectories in the Earth-Moon CR3BP, refines them via multiple shooting in the bicircular four-body problem, and demonstrates effectiveness against existing solutions.
-
SuNeRF-CME: Physics-Informed Neural Radiance Fields for Tomographic Reconstruction of Coronal Mass Ejections
SuNeRF-CME uses physics-informed NeRFs with ray-tracing for Thomson scattering and constraints on plasma continuity, direction, and speed to enable tomographic 3D reconstruction of CMEs from as few as two viewpoints, validated on synthetic data with low parameter errors.
-
Risk-Aware Aerocapture Guidance Through a Probabilistic Indicator Function
A new aerocapture guidance method uses a probabilistic indicator function to estimate and mitigate failure risks, saving 71.43% to 100% of recoverable cases in high-uncertainty simulations across varied initial conditions and atmosphere models.
-
Geometry-aided Vision-based Localization of Future Mars Helicopters in Challenging Illumination Conditions
Geo-LoFTR is a geometry-aided deep learning model for map-based localization that outperforms prior methods under large illumination and scale variations on simulated and real Mars imagery.
-
Low Thrust Electric Propulsion Mission Concepts For a 3-Meter Class Space Telescope
The authors analyze low-thrust transfer trajectories and science orbits for a 3m class space telescope, comparing a 2:1 lunar resonant orbit and Sun-Earth L2 halo orbit for exoplanet detection performance.
-
Machine Learning as a Transformative Tool for (Exo-)Planetary Science
The paper reviews ML applications for sequence modeling, pattern recognition, and generative Bayesian analysis to tackle heterogeneous data challenges in (exo)planetary science.