用行为树+大模型拆解复杂指令，让机器人更懂人话。
BT-ACTION: A Test-Driven Approach for Modular Understanding of User Instruction Leveraging Behaviour Trees and LLMs
- 用行为树模块化分解用户指令，结合大模型生成可执行动作序列。
- 45人实验表明错误率更低，用户信任度和满意度显著提升。
- 适合需要精准理解复杂任务的厨房助手机器人场景。
自然语言指令往往抽象且复杂，机器人需执行多个子任务才能完成看似简单的请求。例如，用户要求准备牛油果吐司时，需完成多个顺序步骤。此外，此类指令可能存在歧义、不可行或超出机器人知识范围。尽管大语言模型具备强大的语言推理能力，但如何有效集成至机器人系统仍是挑战。为此，我们提出BT-ACTION：一种测试驱动的方法，将行为树（Behavior Trees）的模块化结构与大语言模型结合，用于生成符合复杂用户指令的连贯机器人动作序列，特别适用于厨房辅助场景中的食谱执行。我们在包含45名参与者的综合用户研究中评估了BT-ACTION，对比直接使用大模型提示。结果表明，BT-ACTION的模块化设计减少了机器人错误，提升了用户信任度，参与者对采用该方法的机器人表现出显著偏好。代码已开源：https://github.com/1Eggbert7/BT_LLM。
原文摘要 · Abstract (English)
Natural language instructions are often abstract and complex, requiring robots to execute multiple subtasks even for seemingly simple queries. For example, when a user asks a robot to prepare avocado toast, the task involves several sequential steps. Moreover, such instructions can be ambiguous or infeasible for the robot or may exceed the robot's existing knowledge. While Large Language Models (LLMs) offer strong language reasoning capabilities to handle these challenges, effectively integrating them into robotic systems remains a key challenge. To address this, we propose BT-ACTION, a test-driven approach that combines the modular structure of Behavior Trees (BT) with LLMs to generate coherent sequences of robot actions for following complex user instructions, specifically in the context of preparing recipes in a kitchen-assistance setting. We evaluated BT-ACTION in a comprehensive user study with 45 participants, comparing its performance to direct LLM prompting. Results demonstrate that the modular design of BT-ACTION helped the robot make fewer mistakes and increased user trust, and participants showed a significant preference for the robot leveraging BT-ACTION. The code is publicly available at https://github.com/1Eggbert7/BT_LLM.
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。