<p>Effective bimanual collaboration represents a significant research objective for Large Language Model (LLM)-driven nursing robots. However, current approaches are constrained by critical limitations: the single-thread LLM task planner (ST-Planner) lacks co-scheduling, while the conventional multi-agent framework (DABICO) suffers from inefficient information interaction between agents, consequently compromising performance in bimanual collaboration tasks. To overcome these limitations, this study introduces Role-playing Dual Agents (RoDA), a novel dual-agent collaboration framework augmented by LLM Role-Playing. This framework implements the nursing robot as an LLM-based dual-agent system wherein each agent assumes the role of either the left or right arm. Through meticulously crafted contextual prompts explicitly defining specific identity attributes and conversational protocols for each limb, these agents facilitate high-quality collaborative dialogue reflective of their designated roles. Evaluation of RoDA was conducted through four MuJoCo simulation scenarios encompassing all four categories of bimanual collaboration, diverse task sequences, and different degrees of workspace overlap. The experimental results demonstrate that the role-playing mechanism enhances dialogue normalization, accuracy, and information richness. This high-quality interaction enables superior task planning performance, with RoDA surpassing both the ST-Planner and the baseline DABICO framework. Specifically, RoDA achieved a <InlineEquation ID="IEq1"><EquationSource Format="TEX">\({\textbf {100\%}}\)</EquationSource><EquationSource Format="MATHML"><math><mrow><mn mathvariant="bold">100</mn><mo>%</mo></mrow></math></EquationSource></InlineEquation> success rate across all scenarios, exhibiting an average performance improvement of <InlineEquation ID="IEq2"><EquationSource Format="TEX">\({\textbf {16.3\%}}\)</EquationSource><EquationSource Format="MATHML"><math><mrow><mn mathvariant="bold">16.3</mn><mo>%</mo></mrow></math></EquationSource></InlineEquation> in the Step metric and <InlineEquation ID="IEq3"><EquationSource Format="TEX">\({\textbf {70.2\%}}\)</EquationSource><EquationSource Format="MATHML"><math><mrow><mn mathvariant="bold">70.2</mn><mo>%</mo></mrow></math></EquationSource></InlineEquation> in the Restep metric relative to DABICO. Furthermore, enhancement of performance is achieved without the requirement for LLM fine-tuning, offering advantages including flexibility, immediacy, and low development cost. Finally, RoDA was demonstrated through practical experiments on a dual-arm nursing robot.</p>

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

RoDA: A Role-Playing Dual-Agent Framework to Drive Nursing Robots in Bimanual Coordination Tasks

  • Zhendong Zhao,
  • Yang Li,
  • Jiexin Xie,
  • Tonghui Zhang,
  • Shijie Guo

摘要

Effective bimanual collaboration represents a significant research objective for Large Language Model (LLM)-driven nursing robots. However, current approaches are constrained by critical limitations: the single-thread LLM task planner (ST-Planner) lacks co-scheduling, while the conventional multi-agent framework (DABICO) suffers from inefficient information interaction between agents, consequently compromising performance in bimanual collaboration tasks. To overcome these limitations, this study introduces Role-playing Dual Agents (RoDA), a novel dual-agent collaboration framework augmented by LLM Role-Playing. This framework implements the nursing robot as an LLM-based dual-agent system wherein each agent assumes the role of either the left or right arm. Through meticulously crafted contextual prompts explicitly defining specific identity attributes and conversational protocols for each limb, these agents facilitate high-quality collaborative dialogue reflective of their designated roles. Evaluation of RoDA was conducted through four MuJoCo simulation scenarios encompassing all four categories of bimanual collaboration, diverse task sequences, and different degrees of workspace overlap. The experimental results demonstrate that the role-playing mechanism enhances dialogue normalization, accuracy, and information richness. This high-quality interaction enables superior task planning performance, with RoDA surpassing both the ST-Planner and the baseline DABICO framework. Specifically, RoDA achieved a \({\textbf {100\%}}\)100% success rate across all scenarios, exhibiting an average performance improvement of \({\textbf {16.3\%}}\)16.3% in the Step metric and \({\textbf {70.2\%}}\)70.2% in the Restep metric relative to DABICO. Furthermore, enhancement of performance is achieved without the requirement for LLM fine-tuning, offering advantages including flexibility, immediacy, and low development cost. Finally, RoDA was demonstrated through practical experiments on a dual-arm nursing robot.