面向自主智能系统中BT与FSM的LLM驱动统一转换框架

中文摘要 AI 辅助

有限状态机（FSM）和行为树（BT）是自主智能系统中广泛采用的行为建模范式。尽管两者在功能上等价且原则上可相互转换，但现有的FSM与BT之间的转换方法在保持行为完整性和避免模型复杂度爆炸方面面临重大挑战。为克服这些问题，我们提出了一种由大语言模型（LLM）驱动的统一转换框架，能够实现FSM与BT之间自动、高效且语义一致的转换。具体而言，设计了一种新颖的循环执行BT结构，使LLM能够准确捕获FSM中的循环结构，从而保持行为完整性。为缓解BT到FSM转换中的状态爆炸问题，引入了一种结合LLM提示的深度压缩策略，以消除冗余控制节点，并辅以差异化的分层转换规则，共同减少所需子FSM的数量。在多个自主决策场景中的仿真实验表明，所提出的框架能够实现FSM与BT之间准确且自动的双向转换。此外，与传统方法相比，该框架显著增强了生成模型的可扩展性和可维护性，为消费级自主智能系统（如服务机器人、游戏代理和智能家居设备）中的行为模型转换提供了一种实用解决方案。

英文摘要

Finite state machine (FSM) and behavior trees (BT) are widely adopted behavioral modeling paradigms for autonomous intelligent systems. While functionally equivalent and inter-convertible in principle, existing transformation methods between FSM and BT face major challenges in preserving behavioral completeness and avoiding model complexity explosion. To overcome these issues, we propose an LLM-driven unified conversion framework that enables automatic, efficient, and semantically consistent transformation between FSM and BT. Specifically, a novel loop execution BT structure is designed for LLM to accurately capture the loop structure in FSM, thereby preserving behavioral completeness. To mitigate the state explosion problem in BT-to-FSM conversion, a depth compression strategy is introduced with LLM prompt to eliminate redundant control nodes, complemented by differentiated hierarchical conversion rules that collectively reduce the number of required sub-FSM. Simulation experiments in multiple autonomous decision-making scenarios demonstrate that the proposed framework enables an accurate and automated bidirectional conversion between FSM and BT. Furthermore, it significantly enhances the scalability and maintainability of generated models compared to traditional approaches, providing a practical solution for behavior model conversion in consumer-grade autonomous intelligent systems such as service robots, game agents, and smart home devices

发表机构

• College of Systems Engineering, National University of Defense Technology（国防科技大学系统工程学院）

机构由 AI 辅助整理，请以论文原文为准。