Robot guide with multi-agent control and automatic scenario generation with LLM
This work addresses the challenge of creating flexible and natural behavior for social robots like tour guides, representing an incremental improvement over traditional manual configuration approaches.
The authors tackled the problem of manual tuning and inflexibility in tour guide robot behavior by developing a hybrid control architecture combining multi-agent resource management with LLM-based automatic scenario generation, resulting in more natural robot behavior and demonstrating potential for automating social robot control systems.
The work describes the development of a hybrid control architecture for an anthropomorphic tour guide robot, combining a multi-agent resource management system with automatic behavior scenario generation based on large language models. The proposed approach aims to overcome the limitations of traditional systems, which rely on manual tuning of behavior scenarios. These limitations include manual configuration, low flexibility, and lack of naturalness in robot behavior. The process of preparing tour scenarios is implemented through a two-stage generation: first, a stylized narrative is created, then non-verbal action tags are integrated into the text. The multi-agent system ensures coordination and conflict resolution during the execution of parallel actions, as well as maintaining default behavior after the completion of main operations, contributing to more natural robot behavior. The results obtained from the trial demonstrate the potential of the proposed approach for automating and scaling social robot control systems.