Mind to Hand: 通过具身推理实现目的性机器人控制
Mind to Hand: Purposeful Robotic Control via Embodied Reasoning
AI总结：
Lumo-1通过具身推理实现目的性机器人控制，结合视觉语言动作模型提升机器人推理与动作协调能力。
摘要：
人类的行为是在上下文和意图的驱动下进行的，推理在其中扮演着核心角色。尽管互联网级别的数据已经使AI系统具备了广泛的推理能力，但将这些能力与物理行动相结合仍然是一个重大挑战。我们介绍了Lumo-1，一个通用的视觉-语言-动作（VLA）模型，它将机器人的推理（"mind"）与机器人的行动（"hand"）统一起来。我们的方法基于预训练视觉语言模型（VLMs）的一般多模态推理能力，逐步扩展到具身推理和动作预测，并最终达到结构化推理和推理-动作对齐。这导致了一个三阶段的预训练流程：（1）在经过筛选的视觉语言数据上继续预训练VLMs，以增强诸如规划、空间理解和轨迹预测等具身推理能力；（2）在视觉语言数据和跨具身机器人数据上进行联合训练；（3）在Astribot S1上收集的轨迹上进行动作训练，Astribot S1是一款具有人形灵活性和敏捷性的双臂移动机械臂。最后，我们整合强化学习以进一步细化推理-动作一致性，并闭合语义推断与运动控制之间的回路。大量实验表明，Lumo-1在具身视觉语言推理方面实现了显著的性能提升，这是通用机器人控制的关键组成部分。现实世界评估进一步显示，Lumo-1在一系列具有挑战性的机器人任务中超越了强大的基线模型，其在新对象和环境中的泛化能力较强，在长时间跨度任务和响应人类自然指令（需要对策略、概念和空间进行推理）方面表现尤为突出。
英文摘要：
Humans act with context and intention, with reasoning playing a central role. While internet-scale data has enabled broad reasoning capabilities in AI systems, grounding these abilities in physical action remains a major challenge. We introduce Lumo-1, a generalist vision-language-action (VLA) model that unifies robot reasoning ("mind") with robot action ("hand"). Our approach builds upon the general multi-modal reasoning capabilities of pre-trained vision-language models (VLMs), progressively extending them to embodied reasoning and action prediction, and ultimately towards structured reasoning and reasoning-action alignment. This results in a three-stage pre-training pipeline: (1) Continued VLM pre-training on curated vision-language data to enhance embodied reasoning skills such as planning, spatial understanding, and trajectory prediction; (2) Co-training on cross-embodiment robot data alongside vision-language data; and (3) Action training with reasoning process on trajectories collected on Astribot S1, a bimanual mobile manipulator with human-like dexterity and agility. Finally, we integrate reinforcement learning to further refine reasoning-action consistency and close the loop between semantic inference and motor control. Extensive experiments demonstrate that Lumo-1 achieves significant performance improvements in embodied vision-language reasoning, a critical component for generalist robotic control. Real-world evaluations further show that Lumo-1 surpasses strong baselines across a wide range of challenging robotic tasks, with strong generalization to novel objects and environments, excelling particularly in long-horizon tasks and responding to human-natural instructions that require reasoning over strategy, concepts and space.
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。
