A Prefixed Patch Time Series Transformer for Two-Point Boundary Value Problems in Three-Body Problems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908296331395072 |
|---|---|
| author | Hatakeyama, Akira Ito, Shota Yanase, Toshihiko Ozaki, Naoya |
| author_facet | Hatakeyama, Akira Ito, Shota Yanase, Toshihiko Ozaki, Naoya |
| contents | Two-point boundary value problems for cislunar trajectories present significant challenges in circler restricted three body problem, making traditional analytical methods like Lambert's problem inapplicable. This study proposes a novel approach using a prefixed patch time series Transformer model that automates the solution of two-point boundary value problems from lunar flyby to arbitrary terminal conditions. Using prefix tokens of terminal conditions in our deep generative model enables solving boundary value problems in three-body dynamics. The training dataset consists of trajectories obtained through forward propagation rather than solving boundary value problems directly. The model demonstrates potential practical utility for preliminary trajectory design in cislunar mission scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_01464 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Prefixed Patch Time Series Transformer for Two-Point Boundary Value Problems in Three-Body Problems Hatakeyama, Akira Ito, Shota Yanase, Toshihiko Ozaki, Naoya Machine Learning Two-point boundary value problems for cislunar trajectories present significant challenges in circler restricted three body problem, making traditional analytical methods like Lambert's problem inapplicable. This study proposes a novel approach using a prefixed patch time series Transformer model that automates the solution of two-point boundary value problems from lunar flyby to arbitrary terminal conditions. Using prefix tokens of terminal conditions in our deep generative model enables solving boundary value problems in three-body dynamics. The training dataset consists of trajectories obtained through forward propagation rather than solving boundary value problems directly. The model demonstrates potential practical utility for preliminary trajectory design in cislunar mission scenarios. |
| title | A Prefixed Patch Time Series Transformer for Two-Point Boundary Value Problems in Three-Body Problems |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2504.01464 |