用大模型提升多机器人长任务规划能力，成功率提升超一倍。
LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Planner
- 结合大模型推理与传统搜索算法，实现任务自动分解与分配。
- 在复杂家庭任务上成功率达94.5%，效率提升36%。
- 适用于多类型机器人协作，适合研究智能机器人系统者参考。
语言模型（LM）具备强大的自然语言理解能力，可将人类指令转化为简单机器人任务的详细计划。然而，在处理长时序任务时，尤其是协同异构机器人团队的子任务识别与分配方面仍面临重大挑战。为此，我们提出一种基于语言模型驱动的多智能体PDDL规划框架LaMMA-P，该框架在长时序任务上达到当前最优性能。LaMMA-P融合了语言模型的推理能力与传统启发式搜索规划器的优势，在保持高成功率和高效性的同时，展现出优异的任务泛化能力。此外，我们构建了MAT-THOR基准数据集，基于AI2-THOR环境设计了两种复杂度的家庭任务。实验结果表明，相较于现有基于语言模型的多智能体规划器，LaMMA-P的成功率提升105%，效率提高36%。项目相关视频、代码、数据集及各模块详细提示词均可在官网获取：https://lamma-p.github.io。
原文摘要 · Abstract (English)
Language models (LMs) possess a strong capability to comprehend natural language, making them effective in translating human instructions into detailed plans for simple robot tasks. Nevertheless, it remains a significant challenge to handle long-horizon tasks, especially in subtask identification and allocation for cooperative heterogeneous robot teams. To address this issue, we propose a Language Model-Driven Multi-Agent PDDL Planner (LaMMA-P), a novel multi-agent task planning framework that achieves state-of-the-art performance on long-horizon tasks. LaMMA-P integrates the strengths of the LMs' reasoning capability and the traditional heuristic search planner to achieve a high success rate and efficiency while demonstrating strong generalization across tasks. Additionally, we create MAT-THOR, a comprehensive benchmark that features household tasks with two different levels of complexity based on the AI2-THOR environment. The experimental results demonstrate that LaMMA-P achieves a 105% higher success rate and 36% higher efficiency than existing LM-based multiagent planners. The experimental videos, code, datasets, and detailed prompts used in each module can be found on the project website: https://lamma-p.github.io.
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。