发表机构
University of Canberra（堪培拉大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究为自主机器人在动态环境中的行为规划，提出生成式部分指定有限状态机（GPSFSM）神经符号架构，利用Fabric等组件实现标准化语义能力描述，实验表明该方法计划生成成功率高、延迟低，还能生成复杂行为，且开源堆栈使其实用可重复。
AI 中文摘要
在动态环境中运行的自主机器人需要结合反应性、可解释性和适应性的行为规划系统。尽管大语言模型已成功与行为树集成用于动态重新规划，但有限状态机虽被广泛采用且计算效率高，却未被用于生成式方法。我们提出了一种生成式部分指定有限状态机（GPSFSM）神经符号架构，利用有限状态机的符号和语义结构来实现行为规划。本文介绍了首个用于机器人技术的GPSFSM框架，包括用于解析、验证和执行包含多种控制结构的行为计划的FSM引擎Fabric。我们用异步事件系统扩展了ROS2中的Capabilities2包，用于行为链接和运行时参数注入，解决了限制当前生成系统的临时函数表示问题。PromptTools提供了到本地和云大语言模型的统一ROS 2接口，具有提示缓冲功能，可实现任务和上下文信息的动态异步组合。这些组件共同实现了与机器人无关的标准化语义能力描述。对导航任务的实验评估表明，我们的GPSFSM方法比现有BTGenBot系统具有更高的计划生成成功率，在零样本场景中表现出色，同时保持与前沿大语言模型相当或更低的规划延迟。我们还证明了我们的系统可以生成复杂行为。我们发布了一个开源ROS2堆栈，使生成式有限状态机规划对机器人系统实用且可重复。
英文摘要
Autonomous robots operating in dynamic environments require behaviour planning systems that combine reactivity, interpretability, and adaptability. While Large Language Models have been successfully integrated with Behaviour Trees for dynamic replanning, Finite State Machines, despite their widespread adoption and computational efficiency, remain unexplored for generative approaches. We propose a Generative Partially Specified Finite State Machine (GPSFSM) neurosymbolic architecture that utilises the symbolic and semantic structure of FSMs, including states and event-triggered transitions, to implement Behaviour Planning. This paper introduces the first GPSFSM framework for robotics, featuring Fabric, an FSM engine that parses, validates, and executes behaviour plans that contain Sequential, Recovery, Parallel-Any, and Parallel-All control structures. We extend the Capabilities2 package in ROS2 with an asynchronous event system for behaviour chaining and runtime parameter injection for configurable execution, addressing the ad-hoc function representations that limit current generative systems. PromptTools provides a unified ROS 2 interface to local and cloud LLMs, with prompt buffering, enabling dynamic asynchronous composition of task and context information. Together, these components enable standardised semantic capability descriptions for robot-agnostic development. Experimental evaluation on navigation tasks demonstrates that our GPSFSM approach achieves consistently higher plan-generation success rates than the state-of-the-art BTGenBot system, particularly excelling in zero-shot scenarios where BTs typically struggle, while maintaining comparable or lower planning latency to frontier LLMs. We also demonstrate that our system can generate complex behaviours. We release an open-source ROS2 stack that makes generative FSM planning practical and reproducible for robotic systems.
CommentsAccepted for publication in the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 9 pages, 10 figures, 1 table
