Reducing Mental Workload through On-Demand Human Assistance for Physical Action Failures in LLM-based Multi-Robot Coordination

2026-03-30

AI Summary

Existing LLM-driven multi-robot systems often fall into repetitive, ineffective actions following physical execution failures and lack efficient mechanisms for remote human-in-the-loop correction. This work proposes the REPAIR framework, which integrates on-demand remote human intervention into LLM-based multi-robot coordination for the first time. By combining task decomposition, execution monitoring, and an interaction-triggering mechanism, the system requests human assistance upon detecting unrecoverable failures and leverages a mixed-reality interface to enable effective collaboration. Evaluated in a real-world multi-robot garbage collection task, the approach significantly improves cleaning efficiency per unit time, achieving performance on easily handled items comparable to fully teleoperated systems while reducing operator cognitive load.

Abstract

Multi-robot coordination based on large language models (LLMs) has attracted growing attention, since LLMs enable the direct translation of natural language instructions into robot action plans by decomposing tasks and generating high-level plans. However, recovering from physical execution failures remains difficult, and tasks often stagnate due to the repetition of the same unsuccessful actions. While frameworks for remote robot operation using Mixed Reality were proposed, there have been few attempts to implement remote error resolution specifically for physical failures in multi-robot environments. In this study, we propose REPAIR (Robot Execution with Planned And Interactive Recovery), a human-in-the-loop framework that integrates remote error resolution into LLM-based multi-robot planning. In this method, robots execute tasks autonomously; however, when an irrecoverable failure occurs, the LLM requests assistance from an operator, enabling task continuity through remote intervention. Evaluations using a multi-robot trash collection task in a real-world environment confirmed that REPAIR significantly improves task progress (the number of items cleared within a time limit) compared to fully autonomous methods. Furthermore, for easily collectable items, it achieved task progress equivalent to full remote control. The results also suggested that the mental workload on the operator may differ in terms of physical demand and effort. The project website is https://emergentsystemlabstudent.github.io/REPAIR/.

Problem

• mental workload
• physical action failures
• multi-robot coordination
• LLM-based planning
• remote error resolution

Innovation

• human-in-the-loop
• LLM-based planning
• multi-robot coordination
• on-demand assistance
• physical failure recovery