Liang Ken-Fu, Kao Jonathan C
bioRxiv. 2024 Nov 26:2024.11.25.625180. doi: 10.1101/2024.11.25.625180.
Intracortical motor brain-computer interfaces (BCIs) are expensive and time-consuming to design because accurate evaluation traditionally requires real-time experiments. In a BCI system, a user interacts with an imperfect decoder and continuously changes motor commands in response to unexpected decoded movements. This "closed-loop" nature of BCI leads to emergent interactions between the user and decoder that are challenging to model. The gold standard for BCI evaluation is therefore real-time experiments, which significantly limits the speed and community of BCI research. We present a new BCI simulator that enables researchers to accurately and quickly design BCIs for cursor control entirely in software. Our simulator replaces the BCI user with a deep reinforcement learning (RL) agent that interacts with a simulated BCI system and learns to optimally control it. We demonstrate that our simulator is accurate and versatile, reproducing the published results of three distinct types of BCI decoders: (1) a state-of-the-art linear decoder (FIT-KF), (2) a "two-stage" BCI decoder requiring closed-loop decoder adaptation (ReFIT-KF), and (3) a nonlinear recurrent neural network decoder (FORCE).
皮质内运动脑机接口（BCI）设计成本高且耗时，因为传统上准确评估需要进行实时实验。在BCI系统中，用户与不完善的解码器交互，并根据意外的解码动作不断改变运动指令。BCI的这种“闭环”特性导致用户与解码器之间出现难以建模的新兴交互。因此，BCI评估的金标准是实时实验，这极大地限制了BCI研究的速度和群体。我们提出了一种新的BCI模拟器，使研究人员能够完全在软件中准确、快速地设计用于光标控制的BCI。我们的模拟器用深度强化学习（RL）智能体取代了BCI用户，该智能体与模拟的BCI系统交互并学习对其进行最优控制。我们证明了我们的模拟器准确且通用，重现了三种不同类型BCI解码器已发表的结果：（1）一种先进的线性解码器（FIT-KF），（2）一种需要闭环解码器自适应的“两阶段”BCI解码器（ReFIT-KF），以及（3）一种非线性递归神经网络解码器（FORCE）。
