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

2026-02-23

AI Summary

This study addresses the challenge of real-time, accurate decoding of user intent for mobile robot control from electroencephalography (EEG) signals in real-world scenarios. The authors propose a brain-controlled robotic framework that leverages 16-channel EEG data under offline conditions to decode both current and future user intentions for commanding a four-wheeled robot to move forward, backward, turn left or right, or stop. This work presents the first integration of real robot control tasks with multi-timescale EEG intention decoding, establishing a reproducible offline benchmark. Experimental results demonstrate that ShallowConvNet consistently outperforms CNN, RNN, and Transformer-based models across two classification tasks, validating its efficacy in predictive brain–computer interface systems and highlighting key design principles for such applications.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

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.

Problem

• EEG
• brain-computer interface
• intention decoding
• robotic control
• mobile robotics

Innovation

• EEG-based BCI
• intention decoding
• deep learning benchmarking
• robotic control
• multi-horizon prediction