用大模型加速机器人高层控制器的自动修复
INPROVF: Leveraging Large Language Models to Repair High-level Robot Controllers from Assumption Violations
- 先将环境与控制器转为自然语言，再让大模型生成修复方案
- 通过形式化验证筛选正确方案，失败则反馈并迭代优化
- 在12种场景下验证有效，适合需快速修复的机器人系统
本文提出INPROVF，一个结合大语言模型（LLMs）与形式化方法的自动框架，用于加速高层机器人控制器的修复。此前仅依赖形式化方法的方法计算开销大，难以扩展至大状态空间。INPROVF利用大模型生成修复候选，再通过形式化方法验证其正确性。为提升候选质量，框架首先将环境与控制器的符号表示转换为自然语言描述；若候选不通过验证，则提供关于潜在不安全行为或未满足任务的反馈，并迭代提示大模型生成改进方案。我们在12种不同工作空间、任务及状态空间规模的假设违反情形中验证了INPROVF的有效性。
原文摘要 · Abstract (English)
This paper presents INPROVF, an automatic framework that combines large language models (LLMs) and formal methods to speed up the repair process of high-level robot controllers. Previous approaches based solely on formal methods are computationally expensive and cannot scale to large state spaces. In contrast, INPROVF uses LLMs to generate repair candidates, and formal methods to verify their correctness. To improve the quality of these candidates, our framework first translates the symbolic representations of the environment and controllers into natural language descriptions. If a candidate fails the verification, INPROVF provides feedback on potential unsafe behaviors or unsatisfied tasks, and iteratively prompts LLMs to generate improved solutions. We demonstrate the effectiveness of INPROVF through 12 violations with various workspaces, tasks, and state space sizes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。