Being-0：融合视觉-语言模型与模块化技能的人形机器人智能体
Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular Skills
AI总结：
本文提出 Being-0 分层人形机器人框架，通过 FM、轻量 VLM Connector 与模块化技能库协同，实现复杂长时程导航与操作任务的实时鲁棒执行。
摘要：
构建能够在真实世界具身任务中达到人类水平表现的自主机器人智能体，是人形机器人研究的终极目标。近期进展利用基础模型（Foundation Models，FMs）在高层认知方面，以及人形机器人的低层技能开发方面取得了显著进步。然而，由于长时程任务中的误差累积以及不同模块的延迟差异，直接组合这些组件往往会导致鲁棒性和效率不佳。我们提出 Being-0，这是一种将 FM 与模块化技能库相集成的分层智能体框架。FM 负责处理指令理解、任务规划和推理等高层认知任务，而技能库则为低层控制提供稳定的运动和灵巧操作能力。为弥合这些层级之间的鸿沟，我们提出了一个由轻量级视觉-语言模型（VLM）驱动的新型 Connector 模块。Connector 通过将基于语言的计划转换为可执行的技能命令，并动态协调运动与操作以提高任务成功率，增强了 FM 的具身能力。除 FM 外，所有组件均可部署在低成本机载计算设备上；Being-0 在配备灵巧手和主动视觉的全尺寸人形机器人上实现了高效的实时性能。在大型室内环境中开展的大量实验表明，Being-0 能够有效解决需要具有挑战性的导航和操作子任务的复杂长时程任务。更多细节和视频请访问 https://beingbeyond.github.io/Being-0。
英文摘要：
Building autonomous robotic agents capable of achieving human-level performance in real-world embodied tasks is an ultimate goal in humanoid robot research. Recent advances have made significant progress in high-level cognition with Foundation Models (FMs) and low-level skill development for humanoid robots. However, directly combining these components often results in poor robustness and efficiency due to compounding errors in long-horizon tasks and the varied latency of different modules. We introduce Being-0, a hierarchical agent framework that integrates an FM with a modular skill library. The FM handles high-level cognitive tasks such as instruction understanding, task planning, and reasoning, while the skill library provides stable locomotion and dexterous manipulation for low-level control. To bridge the gap between these levels, we propose a novel Connector module, powered by a lightweight vision-language model (VLM). The Connector enhances the FM's embodied capabilities by translating language-based plans into actionable skill commands and dynamically coordinating locomotion and manipulation to improve task success. With all components, except the FM, deployable on low-cost onboard computation devices, Being-0 achieves efficient, real-time performance on a full-sized humanoid robot equipped with dexterous hands and active vision. Extensive experiments in large indoor environments demonstrate Being-0's effectiveness in solving complex, long-horizon tasks that require challenging navigation and manipulation subtasks. For further details and videos, visit https://beingbeyond.github.io/Being-0.
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。
