CoCAtt: A Cognitive-Conditioned Driver Attention Dataset

TL;DR

This paper introduces CoCAtt, a comprehensive driver attention dataset that includes driver distraction and intention annotations, capturing attention data in manual and autopilot modes to improve attention prediction models.

Contribution

The paper presents the first autopilot attention dataset with per-frame distraction and intention annotations, enhancing driver attention prediction research.

Findings

Incorporating driver states improves attention prediction accuracy.

CoCAtt is the largest and most diverse driver attention dataset.

Autopilot attention data is provided for the first time.

Abstract

The task of driver attention prediction has drawn considerable interest among researchers in robotics and the autonomous vehicle industry. Driver attention prediction can play an instrumental role in mitigating and preventing high-risk events, like collisions and casualties. However, existing driver attention prediction models neglect the distraction state and intention of the driver, which can significantly influence how they observe their surroundings. To address these issues, we present a new driver attention dataset, CoCAtt (Cognitive-Conditioned Attention). Unlike previous driver attention datasets, CoCAtt includes per-frame annotations that describe the distraction state and intention of the driver. In addition, the attention data in our dataset is captured in both manual and autopilot modes using eye-tracking devices of different resolutions. Our results demonstrate that incorporating the above two driver states into attention modeling can improve the performance of driver attention prediction. To the best of our knowledge, this work is the first to provide autopilot attention data. Furthermore, CoCAtt is currently the largest and the most diverse driver attention dataset in terms of autonomy levels, eye tracker resolutions, and driving scenarios.