将单体基础模型转化为具身体验的多智能体架构以实现人机协作
Transforming Monolithic Foundation Models into Embodied Multi-Agent Architectures for Human-Robot Collaboration
AI总结：
InteractGen通过分解机器人智能为多个智能体，提升服务机器人在人类环境中的自主性和协作能力。
摘要：
基础模型已成为统一机器人感知与规划的核心，但现实部署暴露了其单体假设与实际服务工作流分布式、动态性质之间的不匹配。视觉语言模型提供强大的语义理解，但缺乏体感感知的行动能力，且依赖手工制作的技能。视觉语言行动策略能够实现反应式操作，但跨体感表现脆弱，几何定位能力弱，缺乏主动协作机制。这些局限表明，仅扩大单一模型无法为在人类环境中操作的服务机器人提供可靠的自主性。为解决这一缺口，我们提出了InteractGen，一个基于LLM的多智能体框架，将机器人智能分解为专门的智能体，用于连续感知、依赖感知规划、决策与验证、故障反思和动态人类委托，将基础模型视为闭环集体中的受控组件。在异构机器人团队上部署，并在三个月的开放使用研究中评估，InteractGen提高了任务成功率、适应性和人机协作，提供了证据表明多智能体协调比进一步扩大独立模型更有可能实现社会感知的服务自主性。
英文摘要：
Foundation models have become central to unifying perception and planning in robotics, yet real-world deployment exposes a mismatch between their monolithic assumption that a single model can handle all cognitive functions and the distributed, dynamic nature of practical service workflows. Vision-language models offer strong semantic understanding but lack embodiment-aware action capabilities while relying on hand-crafted skills. Vision-Language-Action policies enable reactive manipulation but remain brittle across embodiments, weak in geometric grounding, and devoid of proactive collaboration mechanisms. These limitations indicate that scaling a single model alone cannot deliver reliable autonomy for service robots operating in human-populated settings. To address this gap, we present InteractGen, an LLM-powered multi-agent framework that decomposes robot intelligence into specialized agents for continuous perception, dependency-aware planning, decision and verification, failure reflection, and dynamic human delegation, treating foundation models as regulated components within a closed-loop collective. Deployed on a heterogeneous robot team and evaluated in a three-month open-use study, InteractGen improves task success, adaptability, and human-robot collaboration, providing evidence that multi-agent orchestration offers a more feasible path toward socially grounded service autonomy than further scaling standalone models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
