Brain-Computer Interface

2 summarised stories about Brain-Computer Interface, each linking back to the original source. Browse all topics →

Friday, 17 July 2026

EEG-based AI-BCI Wheelchair Advancement: Transformer-Based Learning with Motor Imagery for Brain Computer Interface

arXiv cs.AI 6 hours ago

Researchers developed TFormerEEG, a Transformer-based deep learning model for classifying motor imagery from EEG signals to control a wheelchair via brain-computer interface. The model achieved 93.04% test accuracy and 91.18% mean cross-validation accuracy when trained on 19x200 segmented EEG arrays sampled at 200Hz, outperforming baseline models like XGBoost and EEGNet. The system enables wheelchair navigation through detected right and left-hand motor imagery, with a Tkinter interface for simulation.

Accessibility AI & Healthcare Brain-Computer Interface Deep Learning & Transformers

An offline approach to fNIRS-guided reinforcement learning for robot behavior

arXiv cs.AI 6 hours ago

Researchers developed a method to train robots using reinforcement learning guided by brain signals from functional near-infrared spectroscopy, comparing passive observation and active demonstration approaches. The system improved learning by augmenting trajectory priorities and Q-values with neural signals, and achieved successful results working with offline data rather than requiring real-time brain-computer interface setups. This approach enables robot behavior training in scenarios where continuous brain signal monitoring is impractical.

Brain-Computer Interface Human-in-the-Loop AI Reinforcement Learning Robotics