A Survey of End-to-End Driving: Architectures and Training Methods
This is a survey paper, providing a comprehensive overview for researchers and practitioners in autonomous driving, but it is incremental as it synthesizes existing work without new experimental results.
The paper surveys end-to-end autonomous driving approaches, where a single neural network replaces the entire driving pipeline, reviewing learning methods, architectures, and evaluation schemes, and concludes by proposing a combined architecture from the most promising elements.
Autonomous driving is of great interest to industry and academia alike. The use of machine learning approaches for autonomous driving has long been studied, but mostly in the context of perception. In this paper we take a deeper look on the so called end-to-end approaches for autonomous driving, where the entire driving pipeline is replaced with a single neural network. We review the learning methods, input and output modalities, network architectures and evaluation schemes in end-to-end driving literature. Interpretability and safety are discussed separately, as they remain challenging for this approach. Beyond providing a comprehensive overview of existing methods, we conclude the review with an architecture that combines the most promising elements of the end-to-end autonomous driving systems.