Learning Residual Kinematic Corrections for Continuous Neural Decoding via Reinforcement Learning

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.

Embodied Virtual Reality Feedback Reshapes Neural Representations to Support Continuous Three-Dimensional Motor Imagery Decoding

Continuous brain-computer interfaces (BCIs) that decode motion trajectories from imagined movement offer intuitive motor control, yet how feedback modality and longitudinal training shape neural representations and decoding performance remains poorly understood. We present the first systematic investigation of embodied virtual reality (VR) feedback during real-time 3D virtual limb control driven by motor imagery, across ten longitudinal sessions in ten participants. Performance was evaluated using three strategies: actual online performance (Fixed Decoder Generalisation, FDG), periodic retraining (Sequential Adaptive Training, SAT), and within-session upper-bound estimation (Within-Session Reconstruction, WSR). A CNN-LSTM decoder achieved within-session imagined movement correlations of r = 0.762 under VR and r = 0.672 under screen feedback. VR significantly outperformed screen feedback across all strategies and movement dimensions (improvements of 8.9-13.0%, all p <= 0.002, d = 1.42-2.05). This advantage persisted under fixed decoders without retraining, demonstrating that embodied VR feedback elicits inherently more decodable and generalisable neural representations. Linear mixed-effects modelling confirmed robust main effects of feedback modality and movement axis with no interaction. Neurophysiologically, VR produced stronger sensorimotor-parietal desynchronisation and enhanced motor-frontal functional connectivity, with pervasive anterior insula engagement across all frequency bands and increased superior parietal lobule coupling, paralleling patterns associated with real movement execution. These findings establish embodied spatial feedback as a key design principle for next-generation continuous BCIs targeting intuitive motor control and neurorehabilitation.