arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.02002cs.RO
收藏

基于大型语言模型的纠正性机器人操作代码生成与静态文本模拟

LLM-Driven Corrective Robot Operation Code Generation with Static Text-Based Simulation

Department of CIS, University of Massachusetts Dartmouth(大学马萨诸塞州达特茅斯分校计算机信息科学系);Department of CSIS, California State University San Marcos(加州州立大学桑马科斯分校计算机科学与信息系统系)

Wenhao Wang, Yi Rong, Yanyan Li, Long Jiao, Jiawei Yuan

AI总结:

本文提出了一种基于LLM的纠正性机器人操作代码生成框架,利用静态文本模拟提升代码生成的可靠性,无需依赖动态执行环境。

摘要:

近年来,大型语言模型(LLMs)在生成机器人操作代码方面展现出令人瞩目的潜力,能够使LLM驱动的机器人成为可能。为了提高由LLMs生成的操作代码的可靠性,现有研究越来越多地采用带有代码执行观察反馈的纠正设计。然而,这些设计中的代码执行依赖于物理实验或定制的模拟环境,这限制了其部署,因为环境的高配置要求和潜在的长时间执行时间。在本文中,我们探讨了直接利用LLM来实现机器人操作代码的静态模拟的可能性,并利用这一方法设计了一个新的可靠的LLM驱动纠正性机器人操作代码生成框架。我们的框架将LLM配置为具有增强能力的静态模拟器,通过解释动作、推理状态转换、分析执行结果以及生成准确捕捉轨迹动态的语义观察,可靠地模拟机器人代码的执行。为了验证我们框架的性能,我们在不同类型的机器人上进行了各种操作任务的实验,包括无人机和小型地面车辆。实验结果不仅展示了我们基于静态文本的模拟的高准确性,还展示了我们LLM驱动的纠正框架的可靠代码生成能力,该框架在性能上与最先进的研究相当,同时不依赖于使用物理实验或模拟器的动态代码执行。

英文摘要:

Recent advances in Large language models (LLMs) have demonstrated their promising capabilities of generating robot operation code to enable LLM-driven robots. To enhance the reliability of operation code generated by LLMs, corrective designs with feedback from the observation of executing code have been increasingly adopted in existing research. However, the code execution in these designs relies on either a physical experiment or a customized simulation environment, which limits their deployment due to the high configuration effort of the environment and the potential long execution time. In this paper, we explore the possibility of directly leveraging LLM to enable static simulation of robot operation code, and then leverage it to design a new reliable LLM-driven corrective robot operation code generation framework. Our framework configures the LLM as a static simulator with enhanced capabilities that reliably simulate robot code execution by interpreting actions, reasoning over state transitions, analyzing execution outcomes, and generating semantic observations that accurately capture trajectory dynamics. To validate the performance of our framework, we performed experiments on various operation tasks for different robots, including UAVs and small ground vehicles. The experiment results not only demonstrated the high accuracy of our static text-based simulation but also the reliable code generation of our LLM-driven corrective framework, which achieves a comparable performance with state-of-the-art research while does not rely on dynamic code execution using physical experiments or simulators.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑