Multi-agent robotic systems are prone to deadlocks in an obstacle environment where the system can get stuck away from its desired location under a smooth low-level control policy. Without an external intervention, often in terms of a high-level command, it is not possible to guarantee that just a low-level control policy can resolve such deadlocks. Utilizing the generalizability and low data requirements of large language models (LLMs), this paper explores the possibility of using LLMs for deadlock resolution. We propose a hierarchical control framework where an LLM resolves deadlocks by assigning a leader and direction for the leader to move along. A graph neural network (GNN) based low-level distributed control policy executes the assigned plan. We systematically study various prompting techniques to improve LLM's performance in resolving deadlocks. In particular, as part of prompt engineering, we provide in-context examples for LLMs. We conducted extensive experiments on various multi-robot environments with up to 15 agents and 40 obstacles. Our results demonstrate that LLM-based high-level planners are effective in resolving deadlocks in MRS.

翻译：多智能体机器人系统在障碍环境中容易陷入死锁状态，即系统在平滑的低层控制策略作用下，可能被困于远离目标位置的位置。若无外部干预（通常表现为高层指令），仅靠低层控制策略无法保证解决此类死锁。本文利用大型语言模型（LLM）的泛化能力和低数据需求，探索了将其用于死锁解决的可能性。我们提出一种分层控制框架：其中LLM通过指定领导者和领导者移动方向来解除死锁，基于图神经网络（GNN）的低层分布式控制策略负责执行所分配的计划。我们系统研究了多种提示技术以提升LLM在解决死锁时的性能，特别是通过提示工程为LLM提供上下文示例。我们在包含多达15个智能体和40个障碍物的多种多机器人环境中进行了大量实验，结果表明基于LLM的高层规划器可有效解决多机器人系统（MRS）中的死锁问题。