A Survey on Imitation Learning Techniques for End-to-End Autonomous Vehicles
A Survey on Imitation Learning Techniques for End-to-End Autonomous Vehicles
复制标题
DOI：
10.1109/tits.2022.3144867
复制
发表时间：
2022-01-31
影响因子：
8.5
通讯作者：
Mouzakitis, Alexandros
中科院分区：
文献类型：
--
作者：
Le Mero, Luc;Yi, Dewei;Mouzakitis, Alexandros
自动驾驶汽车的最先进的决策和规划方法已经不再是人工设计的系统，而是专注于通过模仿学习(IL)利用大规模专家演示数据集。在这篇文章中，我们对IL方法进行了全面的回顾，主要针对自主车辆中基于端到端系统的范例。我们将文献分为三类：1)行为克隆(BC)，2)直接策略学习(DPL)和3)反向强化学习(IRL)。对于这些类别中的每一类，都全面回顾和总结了当前的最新文献，并确定了未来的研究方向，以促进基于模拟学习的端到端自动驾驶车辆系统的开发。由于深度学习技术具有数据密集型的特性，本文还对目前可用于端到端自动驾驶的数据集和模拟器进行了综述。
The state-of-the-art decision and planning approaches for autonomous vehicles have moved away from manually designed systems, instead focusing on the utilisation of large-scale datasets of expert demonstration via Imitation Learning (IL). In this paper, we present a comprehensive review of IL approaches, primarily for the paradigm of end-to-end based systems in autonomous vehicles. We classify the literature into three distinct categories: 1) Behavioural Cloning (BC), 2) Direct Policy Learning (DPL) and 3) Inverse Reinforcement Learning (IRL). For each of these categories, the current state-of-the-art literature is comprehensively reviewed and summarised, with future directions of research identified to facilitate the development of imitation learning based systems for end-to-end autonomous vehicles. Due to the data-intensive nature of deep learning techniques, currently available datasets and simulators for end-to-end autonomous driving are also reviewed.