发表机构
University of Bath; University of Ulster; Bath Institute for the Augmented Human（巴斯大学; 阿尔斯特大学; 巴斯增强人类研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对基于EEG的BCI连续3D运动想象解码难题，提出CNN-LSTM-RL两阶段框架，用强化学习对解码器输出校正残余运动学误差，实验表明该框架有效提升解码性能，推动相关领域发展。
AI 中文摘要
使用基于非侵入性脑电图（EEG）的脑机接口（BCI）解码连续三维（3D）运动想象（MI）具有挑战性。卷积神经网络-长短期记忆（CNN-LSTM）模型可捕捉时空动态，但预测轨迹存在系统残余误差。我们提出两阶段解码框架，应用强化学习（RL）对CNN-LSTM解码器输出进行残余运动学校正（CNN-LSTM-RL）。RL智能体离线训练，基于预测运动轨迹优化相对于目标轨迹的运动准确性。解码性能用Pearson相关系数（$r$）和均方根误差（RMSE）量化。与单独使用CNN-LSTM相比，CNN-LSTM-RL在2D中平均相关性从0.5076提高到0.7181（$p = 0.0005$），在VR中从0.6420提高到0.7780（$p = 0.0059$），RMSE也相应降低。结果表明该框架通过离线残余RL校正运动学误差增强3D BCI MI解码，推动神经康复、假肢和虚拟交互发展。
英文摘要
Decoding continuous three-dimensional (3D) motor imagery (MI) using non-invasive electroencephalography (EEG)-based brain--computer interfaces (BCIs) remains challenging due to signal variability and residual decoding errors. Deep learning architectures such as convolutional neural network--long short-term memory (CNN--LSTM) models can capture spatial and temporal dynamics for continuous kinematic decoding; however, systematic residual errors persist in predicted trajectories. We propose a two-stage decoding framework that applies reinforcement learning (RL) to perform residual kinematic correction on the outputs of a CNN--LSTM decoder (CNN--LSTM--RL). The RL agent is trained offline without direct EEG input and instead operates on predicted kinematic trajectories to optimize movement accuracy relative to target trajectories. Decoding performance was quantified using Pearson correlation coefficients ($r$) and Root Mean Square Errors (RMSE) along the $x, y$, and $z$ axes. Compared to CNN--LSTM applied alone, CNN--LSTM--RL improved the mean correlation from $0.5076$ to $0.7181$ ($p = 0.0005$) in 2D and from $0.6420$ to $0.7780$ ($p = 0.0059$) in VR, with relative gains of $41.5\%$ and $21.2\%$, respectively. Correspondingly, RMSE was reduced from $0.0890$ to $0.0532$ (2D, $p < 0.0001$) and from $0.0714$ to $0.0441$ (VR, $p < 0.0001$), representing relative reductions of $40.2\%$ and $38.2\%$. These findings demonstrate that this scalable framework enhances 3D BCI MI decoding by correcting kinematic errors via offline residual RL without extra neural data, advancing neurorehabilitation, prosthetics, and virtual interaction.
