论文/arXiv 2609.34561·1 个月前

用于神经运动解码的脑条件动作策略

BrainVLA通过语言对齐将神经活动接入预训练VLA策略，在两个神经运动数据集上验证运动解码。

AI 整理

• 硬件零部件
• 本体 SDK 与控制
• 感知与导航

原文链接：Brain-Conditioned Action Policies for Neural Motor Decoding（arXiv 2609.34561 · 发布日期：2026-09-28）

Brain-Conditioned Action Policies for Neural Motor Decoding

BrainVLA通过语言对齐将神经活动接入预训练VLA策略，在两个神经运动数据集上验证运动解码。

核心要点

• 运动BCI需解码运动意图，但任务特定神经到运动映射受配对神经-动作数据稀缺限制。
• 方法构建兼容VLA的数据，并用LoRA微调OpenVLA-OFT以适配目标动作空间。
• 通过神经-语言对齐训练神经编码器，以神经表征引导VLA策略生成可执行动作。
• 在两个神经运动数据集上，跨会话解码R^2和任务成功率优于所评估基线，并显示较高数据效率。

验证范围与局限：验证限于两个不同动作维度的神经运动数据集上的因果rollout解码。

英文摘要 (Abstract)

Motor brain-computer interfaces (BCIs) aim to decode motor intention, enabling people with paralysis to control external devices. Neural motor decoding typically learns task-specific mappings from neural activity to kinematics, yet remains constrained by scarce paired neural-action data. We propose BrainVLA, a framework that enables neural motor decoding by drawing on a pretrained vision-language-action (VLA) model through language-mediated alignment. BrainVLA mitigates reliance on scarce paired neural-action data by leveraging VLA policies. We first construct VLA-compatible datasets including paired neural activity, action signals, language instructions, and rendered visual observations. Then, we adapt the OpenVLA-OFT policy to the target action spaces through LoRA fine-tuning. To establish an effective interface through which neural activity can convey motor intention to adapted VLA policies and guide action generation, we train a neural encoder via neural-language alignment, using language representations as semantic targets to capture latent motor intent from neural activity. The resulting neural representations serve as an endogenous intention signal to guide VLA policies to generate executable actions, while visual observations provide complementary information about the evolving task state. BrainVLA is evaluated on two neural motor datasets with different action dimensionalities using causal rollout decoding. It outperforms the evaluated baselines in cross-session decoding $R^2$ and task success rate, while demonstrating high training data efficiency. These results establish a route for neural motor decoding to draw on large-scale robotic priors through brain-conditioned VLA policies.

作者：Luyao Jin, Running Zhao, Huan Zhao, Vincent C. K. Cheung, Wei-Hsin Liao

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2609.34561：Brain-Conditioned Action Policies for Neural Motor Decoding访问 2026-10-21