Intention Recognition of Space Noncooperative Targets Using Large Language Models

This study proposes a novel method for intention recognition of space noncooperative targets using large language models (LLMs). Traditional methods rely on motion data to assess orbital motion intentions but cannot infer operation and task intentions from multi-source information like images. LLMs,...

Full description

Saved in:
Bibliographic Details
Main Authors: Heng Jing, Qinbo Sun, Zhaohui Dang, Hua Wang
Format: Article
Language:English
Published: American Association for the Advancement of Science (AAAS) 2025-01-01
Series:Space: Science & Technology
Online Access:https://spj.science.org/doi/10.34133/space.0271
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849467799560257536
author Heng Jing
Qinbo Sun
Zhaohui Dang
Hua Wang
author_facet Heng Jing
Qinbo Sun
Zhaohui Dang
Hua Wang
author_sort Heng Jing
collection DOAJ
description This study proposes a novel method for intention recognition of space noncooperative targets using large language models (LLMs). Traditional methods rely on motion data to assess orbital motion intentions but cannot infer operation and task intentions from multi-source information like images. LLMs, with their logical reasoning capabilities, can address this limitation. The intentions are categorized into 3 types and 23 subtypes based on multi-source information and their characteristics: motion intentions (e.g., “hovering”, “flyby”, and “rendezvous”), operation intentions (e.g., “docking”, “refueling”, and “repair”), and task intentions (e.g., “detection”, “surveillance”, and “attack”). The proposed method constructs LLMs for spacecraft intention recognition, involving prompt classification, template design, and test sample generation. The use of prompt tuning V2 (P-tuning V2) and low-rank adaptation (LoRA) fine-tuning enhances the models’ performance. A dataset of 50,688 nominal samples and 8,448 perturbed samples was created through computer simulation based on expert knowledge, focusing on intention recognition of approaching targets in space station on-orbit operation and surveillance scenarios. The models were tested under 3 prompt conditions: basic, instruction, and chain-of-thought (CoT). The performance of 6 models (ChatGLM2-6B and ChatGLM3-6B base and fine-tuned models) was analyzed. Notably, the LoRA fine-tuned ChatGLM3-6B model on instruction prompts achieved 99.9% accuracy, with improved robustness compared to the base model. This work presents a pioneering application of LLMs for spacecraft intention recognition, offering valuable insights for future research and applications.
format Article
id doaj-art-10106cb4d9ab405dbf3ffb5fe7e5f001
institution Kabale University
issn 2692-7659
language English
publishDate 2025-01-01
publisher American Association for the Advancement of Science (AAAS)
record_format Article
series Space: Science & Technology
spelling doaj-art-10106cb4d9ab405dbf3ffb5fe7e5f0012025-08-20T03:26:04ZengAmerican Association for the Advancement of Science (AAAS)Space: Science & Technology2692-76592025-01-01510.34133/space.0271Intention Recognition of Space Noncooperative Targets Using Large Language ModelsHeng Jing0Qinbo Sun1Zhaohui Dang2Hua Wang3National University of Defense Technology, Changsha 410073, China.School of Astronautics, Northwestern Polytechnical University, Xi’an 710072, China.School of Astronautics, Northwestern Polytechnical University, Xi’an 710072, China.National University of Defense Technology, Changsha 410073, China.This study proposes a novel method for intention recognition of space noncooperative targets using large language models (LLMs). Traditional methods rely on motion data to assess orbital motion intentions but cannot infer operation and task intentions from multi-source information like images. LLMs, with their logical reasoning capabilities, can address this limitation. The intentions are categorized into 3 types and 23 subtypes based on multi-source information and their characteristics: motion intentions (e.g., “hovering”, “flyby”, and “rendezvous”), operation intentions (e.g., “docking”, “refueling”, and “repair”), and task intentions (e.g., “detection”, “surveillance”, and “attack”). The proposed method constructs LLMs for spacecraft intention recognition, involving prompt classification, template design, and test sample generation. The use of prompt tuning V2 (P-tuning V2) and low-rank adaptation (LoRA) fine-tuning enhances the models’ performance. A dataset of 50,688 nominal samples and 8,448 perturbed samples was created through computer simulation based on expert knowledge, focusing on intention recognition of approaching targets in space station on-orbit operation and surveillance scenarios. The models were tested under 3 prompt conditions: basic, instruction, and chain-of-thought (CoT). The performance of 6 models (ChatGLM2-6B and ChatGLM3-6B base and fine-tuned models) was analyzed. Notably, the LoRA fine-tuned ChatGLM3-6B model on instruction prompts achieved 99.9% accuracy, with improved robustness compared to the base model. This work presents a pioneering application of LLMs for spacecraft intention recognition, offering valuable insights for future research and applications.https://spj.science.org/doi/10.34133/space.0271
spellingShingle Heng Jing
Qinbo Sun
Zhaohui Dang
Hua Wang
Intention Recognition of Space Noncooperative Targets Using Large Language Models
Space: Science & Technology
title Intention Recognition of Space Noncooperative Targets Using Large Language Models
title_full Intention Recognition of Space Noncooperative Targets Using Large Language Models
title_fullStr Intention Recognition of Space Noncooperative Targets Using Large Language Models
title_full_unstemmed Intention Recognition of Space Noncooperative Targets Using Large Language Models
title_short Intention Recognition of Space Noncooperative Targets Using Large Language Models
title_sort intention recognition of space noncooperative targets using large language models
url https://spj.science.org/doi/10.34133/space.0271
work_keys_str_mv AT hengjing intentionrecognitionofspacenoncooperativetargetsusinglargelanguagemodels
AT qinbosun intentionrecognitionofspacenoncooperativetargetsusinglargelanguagemodels
AT zhaohuidang intentionrecognitionofspacenoncooperativetargetsusinglargelanguagemodels
AT huawang intentionrecognitionofspacenoncooperativetargetsusinglargelanguagemodels