EEG-Driven Intention Decoding: Offline Deep Learning Benchmarking on a Robotic Rover

TL;DR

This study benchmarks deep learning models for offline EEG-based intention decoding during robotic rover control, providing insights into model performance and design for real-world BCI applications.

Contribution

It introduces a reproducible benchmark for EEG intention decoding in robotic navigation and compares various deep learning architectures for this task.

Findings

ShallowConvNet achieved the highest prediction accuracy.

Multi-horizon EEG decoding enhances intention prediction.

Provides key design insights for deep learning-based BCI systems.

Abstract

Brain-computer interfaces (BCIs) provide a hands-free control modality for mobile robotics, yet decoding user intent during real-world navigation remains challenging. This work presents a brain-robot control framework for offline decoding of driving commands during robotic rover operation. A 4WD Rover Pro platform was remotely operated by 12 participants who navigated a predefined route using a joystick, executing the commands forward, reverse, left, right, and stop. Electroencephalogram (EEG) signals were recorded with a 16-channel OpenBCI cap and aligned with motor actions at Delta = 0 ms and future prediction horizons (Delta > 0 ms). After preprocessing, several deep learning models were benchmarked, including convolutional neural networks, recurrent neural networks, and Transformer architectures. ShallowConvNet achieved the highest performance for both action prediction and intent prediction. By combining real-world robotic control with multi-horizon EEG intention decoding, this study introduces a reproducible benchmark and reveals key design insights for predictive deep learning-based BCI systems.