用大模型自动构建机器人决策模型，降低开发门槛。
Automated Generation of MDPs Using Logic Programming and LLMs for Robotic Applications
- 用大模型从自然语言提取知识，生成逻辑规则库
- 自动构建马尔可夫决策过程并合成最优策略
- 适合想快速实现机器人决策的开发者
我们提出一种新框架，将大语言模型（LLMs）与自动化规划和形式化验证结合，以简化马尔可夫决策过程（MDP）的创建与使用。系统利用大模型从自然语言描述中提取结构化知识，形成Prolog知识库，再通过可达性分析自动生成MDP，并使用Storm模型检测器合成最优策略。最终策略以状态-动作表形式导出，可供执行。我们在三个有人-机器人交互场景中验证了该框架，证明其能在极小人工干预下生成可执行策略。这项工作展示了将语言模型与形式方法结合，在机器人领域实现更易用、可扩展的概率规划的巨大潜力。
原文摘要 · Abstract (English)
We present a novel framework that integrates Large Language Models (LLMs) with automated planning and formal verification to streamline the creation and use of Markov Decision Processes (MDP). Our system leverages LLMs to extract structured knowledge in the form of a Prolog knowledge base from natural language (NL) descriptions. It then automatically constructs an MDP through reachability analysis, and synthesises optimal policies using the Storm model checker. The resulting policy is exported as a state-action table for execution. We validate the framework in three human-robot interaction scenarios, demonstrating its ability to produce executable policies with minimal manual effort. This work highlights the potential of combining language models with formal methods to enable more accessible and scalable probabilistic planning in robotics.
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。