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.

翻译：利用大语言模型（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令人瞩目的成果。然而，现有方法主要关注简单任务场景下的单个或同构多机器人系统。在实际应用中，复杂的长期任务往往需要多个异构机器人（尤其是具有更复杂动作空间的机器人）之间的协同合作，这使得任务规划更具挑战性。为此，我们提出COHERENT——一种新颖的基于LLM的任务规划框架，用于实现包含四旋翼无人机、机器狗和机械臂的异构多机器人系统协同。具体而言，我们设计了一种“提案-执行-反馈-调整”（PEFA）机制来分解和分配各机器人的动作：中央任务分配器生成任务规划提案，将复杂任务分解为子任务，随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动作以执行分配的子任务，并向任务分配器反馈自省信息用于规划调整。PEFA循环运行直至任务完成。此外，我们构建了一个包含100项复杂长期任务的异构多机器人任务规划基准测试集。实验结果表明，我们的方法在成功率和执行效率方面均显著超越现有方法。实验视频、代码及基准测试集已发布于https://github.com/MrKeee/COHERENT。