arXiv：cs.AI· Weiyu Guo, He Zhang, Pengteng Li, Tiefu Cai, Ziyang Chen, Yandong Guo, Xiao He, Yongkui Yang, Ying Sun, Hui Xiong·· 22 小时前
NeuroVLA：面向流畅快速反射式机器人控制的类脑具身智能架构
NeuroVLA: A Brain-inspired Embodied Intelligence for Fluid and Fast Reflexive Robotics Control
AI 导读
研究者提出类脑架构 NeuroVLA，将皮层视觉语言规划器与循环小脑调制模块、有状态脉冲脊髓控制器耦合，以融入高频本体感觉与力反馈并保持运动记忆。小脑模块将平均指令 jerk 降低 75.6%，碰撞恢复率达 54.8%，而所评估的 VLA 基线为 0.0%。基于 FPGA 神经形态处理器的脊髓控制器推理延迟 2.19 ms、每次推理 0.87 mJ，推理功耗约 0.4 W。
正文
Abstract: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.
| Comments: | 14 pages, 8 figures. Added NeuroVLA to the title; clarified language-model design inertia, high-frequency proprioception, motor memory and local feedback; revised biological analogies; corrected figure captions and references. Experimental figures and main quantitative results are unchanged |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2601.14628 [cs.RO] |
| (or arXiv:2601.14628v2 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2601.14628 arXiv-issued DOI via DataCite |
Submission history
From: Weiyu- Guo [view email]
[v1]
Wed, 21 Jan 2026 04:04:44 UTC (20,739 KB)
[v2]
Tue, 13 Oct 2026 01:40:33 UTC (20,727 KB)
来源：arXiv：cs.AI · arxiv.org