エンドツーエンド自動運転のサーベイ：アーキテクチャと学習手法
A Survey of End-to-End Driving: Architectures and Training Methods
自動運転のエンドツーエンド手法について、学習法・入出力・ネットワーク構造・評価手法を体系的に整理し、有望な要素を組み合わせたアーキテクチャを提案したサーベイ論文。
著者: Ardi Tampuu, Maksym Semikin, Naveed Muhammad, Dmytro Fishman, Tambet Matiisen
分類: cs.AI, cs.RO
原文アブストラクト
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.
