A Symmetry-Reduced Differentiable Neural Information Field for Geometric Angle-Only Trackability Assessment Across Walker Low-Earth-Orbit Sensor Constellations

Hengguo Zhang, Kebo Li, Yangang Liang, Yunxiao Lv · 2026

Read A Symmetry-Reduced Differentiable Neural Information Field for Geometric Angle-Only Trackability Assessment Across Walker Low-Earth-Orbit Sensor Constellations by Hengguo Zhang, Kebo Li, Yangang Liang, Yunxiao Lv (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13611409.txt.

Description

Hengguo Zhang and co-authors present a 2026 paper on judging, quickly, whether a satellite constellation can track objects from angles alone. Fleets in Walker formations circle Earth in neat repeating patterns. Picking the best sensor subset for each pass is costly to compute, so the authors train a neural field to approximate the answer.

Their network exploits the constellation's symmetries, swapping raw time for bounded phase values. For a 25-by-25 fleet, the symmetry trick cut the error roughly sevenfold against a matched baseline. Checks confirmed the trick held for Delta, Star, and Rosette layouts. Accuracy stayed within bounds for thirty days under matched physics. On real Iridium paths the fields stayed valid for a day or more. The method speeds constellation design studies.

Catalog record

CREATORHengguo Zhang, Kebo Li, Yangang Liang, Yunxiao Lv
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE62 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13611409

Browse the full library · About the Tower of Babel