大模型
arxiv.org ·
面向 AUV 故障恢复的仿真平台：探索基于 LLM 的诊断策略
论文提出 SPAR（Simulation Platform for AUV Recovery）闭环仿真架构，将实时 C 车辆软件与物理故障注入、结构化提示、语言模型交互、任务文件生成、验证、执行和 LLM-judge 评分结合，用于评估 AUV 在通信受限下的自主故障恢复。作者针对质量偏移故障进行 480 次试验，比较一个前沿模型与三个可本地部署的开源 LLM：前沿模型在 85-90% 试验中将 CG-shift 机制列入前三假设，最佳本地模型为 60-78%；推理分析显示本地模型成功与遵循完整诊断流程相关，较弱模型常在执行器仍跟踪指令时过早判定升降舵故障。该数据集未显示诊断性能与操作决策性能存在耦合。
AI推荐理由 arXiv 预印本，作者单位与实验细节明确：提出 SPAR 闭环仿真架构，将实时 C 车辆软件与物理故障注入、结构化提示、LLM 交互、任务文件生成与 LLM-judge 评分耦合，并在 480 次质量偏移故障试验中对比一个前沿模型与三个可本地部署的开源模型。具体新信息是前沿模型在 85-90% 试验中把 CG-shift 机制列入前三假设，最佳本地模型为 60-78%，且诊断与操作决策表现在该数据集中未见耦合。局限是仅单一故障类型、仿真环境、未经同行评审，不能外推为真实 AUV 部署效果。
72
正文
Computer Science > Robotics
arXiv:2609.20620 (cs)
[Submitted on 17 Sep 2026]
Title:A Simulation Platform for AUV Fault Recovery: Exploring LLM-Based Diagnostic Strategies
Authors:Khalid Halba, Kylie Cooper, James G. Bellingham
View a PDF of the paper titled A Simulation Platform for AUV Fault Recovery: Exploring LLM-Based Diagnostic Strategies, by Khalid Halba and 2 other authors
View PDF
HTML (experimental)
Abstract:Autonomous underwater vehicles (AUVs) operating beyond reliable communications must recover from failures without human intervention. We investigate an architecture in which conventional deterministic layered control autonomy manages normal operations, while an invokable large language model (LLM) serves as a diagnostic and recovery planner when onboard anomaly detection identifies performance outside expected limits. Because language models are stochastic, rigorous evaluation requires ensemble testing rather than individual demonstrations. We present a closed-loop simulation architecture that couples real-time C vehicle software with a higher-level orchestration layer for physics-based fault injection, structured prompting, language-model interaction, mission file generation, validation, execution, and LLM-judge scoring. The framework, which we call SPAR (Simulation Platform for AUV Recovery), supports evaluation across fault realizations, prompt structures, reasoning models, and mission conditions. We vary these for a mass-shift fault over 480 SPAR trials, evaluating a frontier model and three off-the-shelf locally deployable LLMs. Model choice dominates diagnosis: the frontier model places the CG-shift mechanism in its top three hypotheses in 85-90% of trials, versus 60-78% for the best local model. Reasoning analysis indicates that local-model success is associated with following the complete diagnostic procedure, whereas weaker models often commit prematurely to elevator failure even though the actuator tracks its command. Diagnosis and operational decision performance do not appear to be coupled in this dataset. The contributions are an architecture extending unanticipated-fault recovery from detection to mitigation and an ensemble methodology for evaluating LLM-assisted mission management on low-power AUVs.
Comments:
Subjects:
Robotics (cs.RO); Artificial Intelligence (cs.AI)
Cite as:
arXiv:2609.20620 [cs.RO]
(or
arXiv:2609.20620v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2609.20620
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Khalid Halba [view email]
[v1]
Thu, 17 Sep 2026 16:03:13 UTC (1,223 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled A Simulation Platform for AUV Fault Recovery: Exploring LLM-Based Diagnostic Strategies, by Khalid Halba and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.RO
new
|
recent
| 2026-09
Change to browse by:
cs
cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)