A Survey on Datasets for Decision-making of Autonomous Vehicle

TL;DR

This survey reviews existing datasets for autonomous vehicle decision-making, categorizing them by data sources, features, and applications, and discusses future development trends to aid researchers.

Contribution

It provides a comprehensive comparison of AV datasets across categories, highlighting their features and potential applications for decision-making research.

Findings

Datasets are categorized into vehicle, environment, and driver data.

Sensor types and annotations vary across datasets.

Future trends include enhanced sensor integration and dataset diversity.

Abstract

Autonomous vehicles (AV) are expected to reshape future transportation systems, and decision-making is one of the critical modules toward high-level automated driving. To overcome those complicated scenarios that rule-based methods could not cope with well, data-driven decision-making approaches have aroused more and more focus. The datasets to be used in developing data-driven methods dramatically influences the performance of decision-making, hence it is necessary to have a comprehensive insight into the existing datasets. From the aspects of collection sources, driving data can be divided into vehicle, environment, and driver related data. This study compares the state-of-the-art datasets of these three categories and summarizes their features including sensors used, annotation, and driving scenarios. Based on the characteristics of the datasets, this survey also concludes the potential applications of datasets on various aspects of AV decision-making, assisting researchers to find appropriate ones to support their own research. The future trends of AV dataset development are summarized.