Reducing Mental Workload through On-Demand Human Assistance for Physical Action Failures in LLM-based Multi-Robot Coordination
This addresses the challenge of task stagnation due to physical failures in multi-robot systems, though it appears incremental as it builds on existing human-in-the-loop concepts for a specific domain.
The paper tackles the problem of physical execution failures in LLM-based multi-robot coordination by proposing REPAIR, a human-in-the-loop framework that requests operator assistance for irrecoverable failures. Results show REPAIR significantly improves task progress in a real-world trash collection task compared to fully autonomous methods, achieving performance equivalent to full remote control for easily collectable items.
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/.