Fine-Tuned Language Models as Space Systems Controllers
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912206923235328 |
|---|---|
| author | Zucchelli, Enrico M. Wu, Di Briden, Julia Hofmann, Christian Rodriguez-Fernandez, Victor Linares, Richard |
| author_facet | Zucchelli, Enrico M. Wu, Di Briden, Julia Hofmann, Christian Rodriguez-Fernandez, Victor Linares, Richard |
| contents | Large language models (LLMs), or foundation models (FMs), are pretrained transformers that coherently complete sentences auto-regressively. In this paper, we show that LLMs can control simplified space systems after some additional training, called fine-tuning. We look at relatively small language models, ranging between 7 and 13 billion parameters. We focus on four problems: a three-dimensional spring toy problem, low-thrust orbit transfer, low-thrust cislunar control, and powered descent guidance. The fine-tuned LLMs are capable of controlling systems by generating sufficiently accurate outputs that are multi-dimensional vectors with up to 10 significant digits. We show that for several problems the amount of data required to perform fine-tuning is smaller than what is generally required of traditional deep neural networks (DNNs), and that fine-tuned LLMs are good at generalizing outside of the training dataset. Further, the same LLM can be fine-tuned with data from different problems, with only minor performance degradation with respect to LLMs trained for a single application. This work is intended as a first step towards the development of a general space systems controller. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_16588 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fine-Tuned Language Models as Space Systems Controllers Zucchelli, Enrico M. Wu, Di Briden, Julia Hofmann, Christian Rodriguez-Fernandez, Victor Linares, Richard Machine Learning Systems and Control Large language models (LLMs), or foundation models (FMs), are pretrained transformers that coherently complete sentences auto-regressively. In this paper, we show that LLMs can control simplified space systems after some additional training, called fine-tuning. We look at relatively small language models, ranging between 7 and 13 billion parameters. We focus on four problems: a three-dimensional spring toy problem, low-thrust orbit transfer, low-thrust cislunar control, and powered descent guidance. The fine-tuned LLMs are capable of controlling systems by generating sufficiently accurate outputs that are multi-dimensional vectors with up to 10 significant digits. We show that for several problems the amount of data required to perform fine-tuning is smaller than what is generally required of traditional deep neural networks (DNNs), and that fine-tuned LLMs are good at generalizing outside of the training dataset. Further, the same LLM can be fine-tuned with data from different problems, with only minor performance degradation with respect to LLMs trained for a single application. This work is intended as a first step towards the development of a general space systems controller. |
| title | Fine-Tuned Language Models as Space Systems Controllers |
| topic | Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2501.16588 |