一种类脑的具身智能用于流体和快速反射式机器人控制
NeuroVLA: A Brain-inspired Embodied Intelligence for Fluid and Fast Reflexive Robotics Control
AI总结：
NeuroVLA是一种类脑具身智能框架，通过生物启发设计实现机器人快速反射和动态稳定性控制，首次在物理机器人上实现先进性能。
摘要：
最近的具身智能进展利用大规模的数据和模型参数规模来掌握自然语言命令跟随和多任务控制。相比之下，生物系统表现出从稀疏经验中快速获取技能的固有能力。关键的是，当前的机器人策略难以复制生物运动中固有的动态稳定性、反射响应性和时间记忆。在这里，我们提出了神经形态视觉-语言-动作（NeuroVLA）框架，该框架模仿生物神经系统在皮层、小脑和脊髓之间的结构组织。我们采用系统层面的生物启发设计：高层模型规划目标，适应性小脑模块利用高频传感器反馈稳定运动，生物启发脊髓层执行闪电般的动作生成。NeuroVLA代表了首个在物理机器人上部署的神经形态VLA，实现了最先进的性能。我们观察到生物运动特征的出现，而无需额外数据或特殊指导：它能停止机器人的震颤，节省显著能量（仅0.4瓦在神经形态处理器上），表现出时间记忆能力，并在不到20毫秒内触发安全反射。
英文摘要：
Vision-language-action (VLA) models inherit powerful semantic representations from large language models, but carrying over their design priorities can leave the demands of physical control under-specified. Stable manipulation requires high-frequency proprioceptive feedback and persistent motor state, in addition to instruction understanding. Here we introduce Neuromorphic Vision-Language-Action (NeuroVLA), a brain-inspired architecture that couples a cortical vision-language planner to recurrent cerebellar modulation and a stateful spiking spinal controller. These components translate semantic intent into actions while incorporating high-frequency proprioceptive and force feedback, maintaining short-term motor memory, and enabling local responses to unexpected contact. In simulated and physical manipulation tasks, the cerebellar module reduces mean commanded jerk by 75.6%, and NeuroVLA achieves a 54.8% collision-recovery rate compared with 0.0% for the evaluated VLA baselines. The spinal controller implemented on an FPGA-based neuromorphic processor achieves 2.19 ms inference latency and 0.87 mJ per inference, corresponding to approximately 0.4 W during inference. These results motivate moving beyond inherited language-model design priorities toward embodied architectures that explicitly integrate semantic planning, high-frequency bodily feedback, motor memory, and local correction.
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。
