EmboTeam: 通过PDDL将LLM推理接地为反应式行为树以实现具身多机器人协作
EmboTeam: Grounding LLM Reasoning into Reactive Behavior Trees via PDDL for Embodied Multi-Robot Collaboration
AI总结：
EmboTeam通过PDDL将LLM推理转化为反应式行为树，提升多机器人协作任务的成功率和目标回忆率
摘要：
在具身人工智能中，使异构机器人团队能够从高层指令中执行长周期任务仍然是一个关键挑战。尽管大语言模型（LLMs）在指令解析和初步规划方面表现出潜力，但它们在长期推理和动态多机器人协调方面存在局限。我们提出了EmboTeam，一种新的具身多机器人任务规划框架，通过三阶段级联架构解决这些问题：1）它利用LLM解析指令并生成规划领域定义语言（PDDL）问题描述，从而将命令转换为形式化规划问题；2）它将LLM的语义推理能力与经典规划器的搜索能力相结合，生成优化的动作序列；3）它将生成的计划编译成行为树以进行反应式控制。该框架通过共享黑板机制实现动态大小的异构机器人团队的通信和状态同步。为了验证我们的方法，我们引入了MACE-THOR基准数据集，包含42个复杂任务，覆盖8种不同的家庭布局。实验表明，EmboTeam在任务成功率方面从12%提升到55%，目标条件回忆率从32%提升到72%。
英文摘要：
In embodied artificial intelligence, enabling heterogeneous robot teams to execute long-horizon tasks from high-level instructions remains a critical challenge. While large language models (LLMs) show promise in instruction parsing and preliminary planning, they exhibit limitations in long-term reasoning and dynamic multi-robot coordination. We propose EmboTeam, a novel embodied multi-robot task planning framework that addresses these issues through a three-stage cascaded architecture: 1) It leverages an LLM to parse instructions and generate Planning Domain Definition Language (PDDL) problem descriptions, thereby transforming commands into formal planning problems; 2) It combines the semantic reasoning of LLMs with the search capabilities of a classical planner to produce optimized action sequences; 3) It compiles the resulting plan into behavior trees for reactive control. The framework supports dynamically sized heterogeneous robot teams via a shared blackboard mechanism for communication and state synchronization. To validate our approach, we introduce the MACE-THOR benchmark dataset, comprising 42 complex tasks across 8 distinct household layouts. Experiments show EmboTeam improves the task success rate from 12% to 55% and goal condition recall from 32% to 72% over the LaMMA-P baseline.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
