arXiv 2409.151462025-03-29cs.ROcs.AI

COHERENT：基于大型语言模型的异构多机器人系统协作

COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Models

Northwestern Polytechnical University（西北工业大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；Institute of Artificial Intelligence, China Telecom Corp Ltd（中国电信集团有限公司人工智能研究院）

Kehui Liu, Zixin Tang, Dong Wang, Zhigang Wang, Xuelong Li, Bin Zhao

备注：: Accepted by ICRA 2025

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出COHERENT框架，通过PEFA机制实现异构多机器人系统的LLM任务规划，在包含100个复杂任务的基准上大幅提升了成功率和执行效率。

摘要：

借助大型语言模型（LLMs）强大的推理能力，近期基于LLM的机器人任务规划方法取得了可喜的成果。然而，它们主要关注简单任务上的单个或多个同构机器人。实际上，复杂的长时程任务总是需要多个异构机器人之间的协作，尤其是具有更复杂的动作空间时，这使得这些任务更具挑战性。为此，我们提出了COHERENT，一种新颖的基于LLM的任务规划框架，用于异构多机器人系统的协作，包括四旋翼飞行器、机器狗和机械臂。具体而言，设计了一种提议-执行-反馈-调整（PEFA）机制来为各个机器人分解和分配动作，其中集中式任务分配器提出任务规划方案，将复杂任务分解为子任务，然后将子任务分配给机器人执行器。每个机器人执行器选择可行的动作来实施分配的子任务，并向任务分配器报告自我反思反馈以进行计划调整。PEFA循环直至任务完成。此外，我们创建了一个具有挑战性的异构多机器人任务规划基准，包含100个复杂的长时程任务。实验结果表明，我们的工作在成功率和执行效率方面大幅超越了以往的方法。实验视频、代码和基准已发布于 https://github.com/MrKeee/COHERENT。

英文摘要：

Leveraging the powerful reasoning capabilities of large language models (LLMs), recent LLM-based robot task planning methods yield promising results. However, they mainly focus on single or multiple homogeneous robots on simple tasks. Practically, complex long-horizon tasks always require collaboration among multiple heterogeneous robots especially with more complex action spaces, which makes these tasks more challenging. To this end, we propose COHERENT, a novel LLM-based task planning framework for collaboration of heterogeneous multi-robot systems including quadrotors, robotic dogs, and robotic arms. Specifically, a Proposal-Execution-Feedback-Adjustment (PEFA) mechanism is designed to decompose and assign actions for individual robots, where a centralized task assigner makes a task planning proposal to decompose the complex task into subtasks, and then assigns subtasks to robot executors. Each robot executor selects a feasible action to implement the assigned subtask and reports self-reflection feedback to the task assigner for plan adjustment. The PEFA loops until the task is completed. Moreover, we create a challenging heterogeneous multi-robot task planning benchmark encompassing 100 complex long-horizon tasks. The experimental results show that our work surpasses the previous methods by a large margin in terms of success rate and execution efficiency. The experimental videos, code, and benchmark are released at https://github.com/MrKeee/COHERENT.

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。