Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?
Preprint
Abstract
A flurry of recent work has demonstrated that pre-trained large language models (LLMs) can be effective task planners for a variety of single-robot tasks. The planning performance of LLMs is significantly improved via prompting techniques, such as in-context learning or re-prompting with state feedback, placing new importance on the token budget for the context window. An under-explored but natural next direction is to investigate LLMs as multi-robot task planners. However, long-horizon, heterogeneous multi-robot planning introduces new challenges of coordination while also pushing up against the limits of context window length. It is therefore critical to find token-efficient LLM planning frameworks that are also able to reason about the complexities of multi-robot coordination. In this work, we compare the task success rate and token efficiency of four multi-agent communication frameworks (centralized, decentralized, and two hybrid) as applied to four coordination-dependent multi-agent 2D task scenarios for increasing numbers of agents. We find that a hybrid framework achieves better task success rates across all four tasks and scales better to more agents. We further demonstrate the hybrid frameworks in 3D simulations where the vision-to-text problem and dynamical errors are considered. See our project website https://yongchao98.github.io/MIT-REALM-Multi-Robot/ for prompts, videos, and code.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- RoCo: Dialectic Multi-Robot Collaboration with Large Language Models2024
- AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers2024
- Lost in the Middle: How Language Models Use Long ContextsTransactions of the Association for Computational Linguistics, 2024
- Text2Motion: from natural language instructions to feasible plansAutonomous Robots, 2023
- Time minimization and online synchronization for multi-agent systems under collaborative temporal logic tasksAutomatica, 2023
- ChatGPT Empowered Long-Step Robot Control in Various Environments: A Case ApplicationIEEE Access, 2023
- Code as Policies: Language Model Programs for Embodied Control2023
- NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models2023
- Long-Horizon Multi-Robot Rearrangement Planning for Construction AssemblyIEEE Transactions on Robotics, 2022
- Motion Planning for Dual-Arm Robot Based on Soft Actor-CriticIEEE Access, 2021