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

📅 2024-09-23
🏛️ arXiv.org
📈 Citations: 4
Influential: 2
📄 PDF
🤖 AI Summary
To address the challenge of collaborative planning and execution in heterogeneous multi-robot systems for complex, long-horizon tasks, this paper proposes a large language model (LLM)-driven closed-loop framework named Proposal-Execution-Feedback-Adjustment (PEFA). PEFA enables centralized high-level task decomposition coupled with decentralized, dynamic self-reflection and adjustment across heterogeneous actuators—including quadcopters, quadruped robots, and robotic arms—by integrating LLM-based reasoning, multi-agent task allocation, cross-platform action-space alignment, and online feedback-driven optimization. We introduce the first benchmark comprising 100 real-world scenario tasks specifically designed for heterogeneous multi-robot systems. Experimental results demonstrate that our approach achieves significantly higher task success rates and execution efficiency compared to state-of-the-art methods. All code, benchmark datasets, and demonstration videos are publicly released.

Technology Category

Application Category

📝 Abstract
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.
Problem

Research questions and friction points this paper is trying to address.

Planning tasks for heterogeneous multi-robot systems
Handling complex action spaces in robot collaboration
Improving success rate and execution efficiency
Innovation

Methods, ideas, or system contributions that make the work stand out.

LLM-based framework for heterogeneous multi-robot collaboration
PEFA mechanism for task decomposition and adjustment
Benchmark with 100 complex long-horizon tasks
🔎 Similar Papers
No similar papers found.
K
Kehui Liu
Northwestern Polytechnical University, Shanghai Artificial Intelligence Laboratory
Z
Zixin Tang
Shanghai Artificial Intelligence Laboratory
D
Dong Wang
Shanghai Artificial Intelligence Laboratory
Z
Zhigang Wang
Shanghai Artificial Intelligence Laboratory
B
Bin Zhao
Northwestern Polytechnical University, Shanghai Artificial Intelligence Laboratory
X
Xuelong Li
Shanghai Artificial Intelligence Laboratory, Institute of Artificial Intelligence, China Telecom Corp Ltd