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

Dimensions overall score 7.0

GitHub Code Pulse

No public code linked for this paper yet.

• The REPAIR framework, which integrates on-demand human assistance for physical failures, significantly improves task progress in LLM-based multi-robot coordination compared to fully autonomous methods.result 90%
• For easily collectable items, the REPAIR framework achieves task progress equivalent to full remote control.result 85%
• The mental workload on the operator in the REPAIR framework differs in terms of physical demand and effort compared to other control methods.result 75%
• REPAIR incorporates a human-in-the-loop mechanism where an LLM requests operator assistance when an irrecoverable physical failure occurs, enabling task continuity through remote intervention.method 95%
• Recovering from physical execution failures in LLM-based multi-robot coordination remains difficult, often causing tasks to stagnate due to repetition of unsuccessful actions.limitation 90%
• In multi-robot coordination, the failure of one robot can stall overall progress because tasks are often interdependent.technical 85%
• The REPAIR framework consists of two components: (1) LLM-based task decomposition, allocation, and action planning, and (2) remote error resolution triggered by operator assistance.method 95%
• There have been few attempts to implement remote error resolution specifically for physical failures in multi-robot environments, despite proposed frameworks for remote operation using Mixed Reality.technical 80%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card