Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Survey
Pranav Singh Chib [ Pravendra Singh
Abstract
End-to-End driving is a promising paradigm as it circumvents the drawbacks associated with modular systems, such as their overwhelming complexity and propensity for error propagation. Autonomous driving transcends conventional traffic patterns by proactively recognizing critical events in advance, ensuring passengers safety and providing them with comfortable transportation, particularly in highly stochastic and variable traffic settings. This paper presents a comprehensive review of the End-to-End autonomous driving stack. It provides a taxonomy of automated driving tasks wherein neural networks have been employed in an End-to-End manner, encompassing the entire driving process from perception to control. Recent developments in End-to-End autonomous driving are analyzed, and research is categorized based on underlying principles, methodologies, and core functionality. These categories encompass sensorial input, main and auxiliary output, learning approaches ranging from imitation to reinforcement learning, and model evaluation techniques. The survey incorporates a detailed discussion of the explainability and safety aspects. Furthermore, it assesses the state-of-the-art, identifie
中文速览
自动驾驶领域长期依赖"模块化"流水线（感知→定位→规划→控制），但各模块间的误差会层层传递，整体系统也越来越臃肿低效。这篇综述聚焦于"端到端自动驾驶"（End-to-End Autonomous Driving）这一新范式——用深度神经网络直接将原始传感器输入映射为驾驶控制信号，从根本上绕过了模块间的误差传播问题。作者系统梳理了该领域的输入模态（摄像头、LiDAR等）、输出形式、模仿学习与强化学习等训练方法、领域自适应、安全性、可解释性以及开/闭环评估体系，并整理了主流数据集与仿真平台，同时总结了当前挑战与未来方向。这份全面的分类梳理为研究者提供了清晰的技术地图，有助于推动端到端自动驾驶从实验室走向可靠的真实场景部署。
原文 arXiv:2307.04370;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2307.04370v2