DEXTER-LLM: Dynamic and Explainable Coordination of Multi-Robot Systems in Unknown Environments via Large Language Models

TL;DR

DEXTER-LLM introduces a novel framework that leverages large language models for dynamic, explainable, and adaptive multi-robot coordination in unknown environments, addressing key limitations of existing LLM-based approaches.

Contribution

The paper presents a comprehensive, multi-module framework integrating LLMs with optimization techniques for real-time task planning and adaptation in multi-robot systems.

Findings

100% success rate across all scenarios

Performed 3 times more tasks and subtasks than baselines

Reduced LLM queries by 62% during online adaptation

Abstract

Online coordination of multi-robot systems in open and unknown environments faces significant challenges, particularly when semantic features detected during operation dynamically trigger new tasks. Recent large language model (LLMs)-based approaches for scene reasoning and planning primarily focus on one-shot, end-to-end solutions in known environments, lacking both dynamic adaptation capabilities for online operation and explainability in the processes of planning. To address these issues, a novel framework (DEXTER-LLM) for dynamic task planning in unknown environments, integrates four modules: (i) a mission comprehension module that resolves partial ordering of tasks specified by natural languages or linear temporal logic formulas (LTL); (ii) an online subtask generator based on LLMs that improves the accuracy and explainability of task decomposition via multi-stage reasoning; (iii) an optimal subtask assigner and scheduler that allocates subtasks to robots via search-based optimization; and (iv) a dynamic adaptation and human-in-the-loop verification module that implements multi-rate, event-based updates for both subtasks and their assignments, to cope with new features and tasks detected online. The framework effectively combines LLMs' open-world reasoning capabilities with the optimality of model-based assignment methods, simultaneously addressing the critical issue of online adaptability and explainability. Experimental evaluations demonstrate exceptional performances, with 100% success rates across all scenarios, 160 tasks and 480 subtasks completed on average (3 times the baselines), 62% less queries to LLMs during adaptation, and superior plan quality (2 times higher) for compound tasks. Project page at https://tcxm.github.io/DEXTER-LLM/