Mind2Drive: Predicting Driver Intentions from EEG in Real-world On-Road Driving

2026-04-21

AI Summary

This study addresses the challenge of accurately predicting driver intention in real-world road driving, where the non-stationarity of electroencephalographic (EEG) signals and the complexity of cognitive-motor preparation pose significant obstacles. The authors propose an EEG-based intention prediction framework built upon a synchronized multi-sensor platform deployed in an actual vehicle, systematically evaluating twelve deep learning models under realistic driving conditions. Their approach achieves stable intention prediction up to 1000 milliseconds in advance, identifies the 400–600 ms interval as a critical neural preparation window, and demonstrates that simplified preprocessing outperforms elaborate artifact removal techniques. Among the models tested, TSCeption yields the best performance, attaining an average accuracy of 0.907 and a Macro-F1 score of 0.901, thereby confirming the feasibility of early and reliable decoding of driver intention in naturalistic environments.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Intelligent Robots: State Estimation

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Predicting driver intention from neurophysiological signals offers a promising pathway for enhancing proactive safety in advanced driver assistance systems, yet remains challenging in real-world driving due to EEG signal non-stationarity and the complexity of cognitive-motor preparation. This study proposes and evaluates an EEG-based driver intention prediction framework using a synchronised multi-sensor platform integrated into a real electric vehicle. A real-world on-road dataset was collected across 32 driving sessions, and 12 deep learning architectures were evaluated under consistent experimental conditions. Among the evaluated architectures, TSCeption achieved the highest average accuracy (0.907) and Macro-F1 score (0.901). The proposed framework demonstrates strong temporal stability, maintaining robust decoding performance up to 1000 ms before manoeuvre execution with minimal degradation. Furthermore, additional analyses reveal that minimal EEG preprocessing outperforms artefact-handling pipelines, and prediction performance peaks within a 400-600 ms interval, corresponding to a critical neural preparatory phase preceding driving manoeuvres. Overall, these findings support the feasibility of early and stable EEG-based driver intention decoding under real-world on-road conditions. Code: https://github.com/galosaimi/Mind2Drive.

Problem

• driver intention prediction
• EEG
• real-world driving
• neurophysiological signals
• advanced driver assistance systems

Innovation

• EEG-based intention prediction
• real-world driving
• deep learning architecture
• temporal stability
• minimal preprocessing