# Adapting a Foundation Model for Space-based Tasks

**Authors:** Matthew Foutter, Praneet Bhoj, Rohan Sinha, Amine Elhafsi, Somrita Banerjee, Christopher Agia, Justin Kruger, Tommaso Guffanti, Daniele Gammelli, Simone D'Amico, Marco Pavone  
**arXiv:** [2408.05924](https://arxiv.org/abs/2408.05924)  
**Date:** 2024-08-12  
**Summary page:** https://www.summarizepaper.com/fr/arxiv-id/2408.05924v1/

## Abstract

Foundation models, e.g., large language models, possess attributes of intelligence which offer promise to endow a robot with the contextual understanding necessary to navigate complex, unstructured tasks in the wild. In the future of space robotics, we see three core challenges which motivate the use of a foundation model adapted to space-based applications: 1) Scalability of ground-in-the-loop operations; 2) Generalizing prior knowledge to novel environments; and 3) Multi-modality in tasks and sensor data. Therefore, as a first-step towards building a foundation model for space-based applications, we automatically label the AI4Mars dataset to curate a language annotated dataset of visual-question-answer tuples. We fine-tune a pretrained LLaVA checkpoint on this dataset to endow a vision-language model with the ability to perform spatial reasoning and navigation on Mars' surface. In this work, we demonstrate that 1) existing vision-language models are deficient visual reasoners in space-based applications, and 2) fine-tuning a vision-language model on extraterrestrial data significantly improves the quality of responses even with a limited training dataset of only a few thousand samples.