# ASPIRE框架：LLM智能体自主完成移动机器人非线性系统辨识

> 原文链接：https://robotics.hellobike.com/papers/2026-11-11-2611-13114-c3c17732
> 频道：papers | 更新日期：2026-11-11 | 标签：auto, arxiv
> 核心摘要：ASPIRE框架利用大模型智能体自主选择并执行非线性系统辨识，在移动机器人等三类实测系统中30次运行均生成有效模型，单次成本0.96至3.38美元，结构解释与参数文档评估达标率88%。

# ASPIRE框架：LLM智能体自主完成移动机器人非线性系统辨识

::: v-pre
> 本文由 AI 根据公开内容整理，可能有误，请以原文为准：[ASPIRE: An Agentic System-Identification Platform for Iterative Reasoning and Exploration](https://arxiv.org/abs/2611.13114)（arXiv 2611.13114）

## 核心内容

针对非线性系统辨识依赖专家经验的痛点，研究提出ASPIRE智能体框架。该系统支持自然语言或形式化物理约束输入，能从测量数据中构建闭式静态或动态模型。在移动机器人、干摩擦旋转系统及实验室发酵罐三类实测对象上进行的30次测试（含/不含描述各5次）全部成功交付有效模型，单次API调用成本控制在0.96至3.38美元区间，验证了LLM在工程建模任务中的经济可行性与鲁棒性。

ASPIRE集成了方法选择、参数估计及独立物理验证模块，支持人机交互式迭代分析。作者对30个推荐模型的评估显示，150项指标中132项完全满足结构与参数文档要求，仅9例存在结构选择依据不充分问题。该框架将非结构化先验知识转化为可验证的数学模型，为具身智能体的动力学建模提供了自动化范式，显著降低了从实测数据到控制级模型的转换门槛。

## 关键看点

- **实测验证**：在移动机器人、干摩擦旋转系统及发酵罐三类物理平台上完成30次辨识，成功率100%
- **成本效能**：单次完整辨识流程API消耗仅0.96至3.38美元，具备工程规模化应用潜力
- **质量评估**：模型结构与参数文档评估达标率88%，仅6%案例存在结构选择依据不足
- **交互机制**：支持自然语言物理约束输入与人机多轮迭代，实现闭式非线性模型自动构建

## 工程与产业观察

ASPIRE证明了LLM Agent可作为系统辨识的“算法工程师”，将非标物理实验数据自动转化为控制可用的闭式模型。对于具身智能研发，这意味着能大幅缩短从硬件组装到获取精准动力学模型的周期，尤其适用于缺乏解析模型的新型执行器或复杂接触场景的快速建模与仿真校准。

## 英文摘要 (Abstract)

System identification requires expert decisions on the identification method, incorporation of prior physical knowledge, and model validation. We propose ASPIRE, a framework for nonlinear system identification in which a large language model agent selects and executes the identification method. ASPIRE constructs closed-form, nonlinear static or dynamic models from measured data, optionally supplemented by a system description, the intended use of the model, and physical requirements expressed formally or in natural language. Each model includes its parameters, an estimation record, an interpretation of its terms, and an error evaluated on test data inaccessible to the agent. Formal physical requirements are verified independently. ASPIRE operates autonomously or interactively, allowing the agent to ask questions and the user to request further analyses and identification rounds. We evaluate ASPIRE on three measured systems: a mobile robot, a rotational system with dry friction, and a laboratory fermenter. Each system is tested with and without a description, in five runs per task. All 30 runs delivered valid models, at a cost of 0.96 to 3.38 US dollars per run. An assessment by the authors found that, for the 30 models recommended by the agent, one per run, the interpretation of the model and the documentation of its structure selection and parameter estimation fully satisfied 132 of 150 assessed items and partly satisfied 18. The most frequent discrepancy, found in nine models, concerned inaccurate or unsupported claims about model structure selection.

作者：Erik Derner, Ji\v{r}\'i Kubal\'ik, Robert Babu\v{s}ka
:::

## 原始参考来源 (Sources)

- [arXiv 2611.13114：ASPIRE: An Agentic System-Identification Platform for Iterative Reasoning and Exploration](https://arxiv.org/abs/2611.13114)