End-to-end Autonomous Driving: Advancements and Challenges

被引：0
|
作者：
Chu, Duan-Feng [1 ,2 ]
Wang, Ru-Kang [1 ,2 ]
Wang, Jing-Yi [3 ]
Hua, Qiao-Zhi [4 ]
Lu, Li-Ping [5 ]
Wu, Chao-Zhong [1 ,2 ]
机构：
[1] Intelligent Transportation Systems Research Center, Wuhan University of Technology, Hubei, Wuhan
[2] Engineering Research Center for Transportation Information and Safety, Ministry of Education, Wuhan University of Technology, Hubei, Wuhan
[3] School of Mechanical and Electronic Engineering, Wuhan University of Technology, Hubei, Wuhan
[4] Computer School, Hubei University of Arts and Science, Hubei, Xiangyang
[5] School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Hubei, Wuhan
来源：
Zhongguo Gonglu Xuebao/China Journal of Highway and Transport | 2024年 / 37卷 / 10期
基金：
中国国家自然科学基金;
关键词：
automotive engineering; autonomous driving; end-to-end autonomous driving; generalization; generative artificial intelligence; interpretability; review;
D O I：
10.19721/j.cnki.1001-7372.2024.10.019
中图分类号：
学科分类号：
摘要：
End-to-end autonomous driving methodologies eliminate the need for manually defined rules and explicit module interfaces. Instead, these approaches directly map trajectory points or control signals from raw sensor data, thereby addressing the inherent shortcomings associated with traditional modular methods, such as information loss and cascading errors, and overcoming the performance limitations imposed by rule-driven frameworks. Recent advancements in self-supervised-learning-based generative artificial intelligence have exhibited substantial emergent intelligence capabilities, significantly promoting the evolution of end-to-cnd methodologies. However, the existing literature lacks a comprehensive synthesis of the advancements in generative end-to-end autonomous driving. Consequently, this paper systematically reviews the research progress, technical challenges, and developmental trends in end-to-end autonomous driving. Initially, the input and output modalities of the end-to-end models are delineated. Based on the historical progression of end-to-end autonomous driving, this paper provides an overview and comparative analysis of the foundational concepts, current research status, and technical challenges of traditional, modular, and generative end-to-end methods. Subsequently, the evaluation methodologies and training datasets utilized for end-to-end models are summarized. Furthermore, this paper explores the challenges currently faced by end-to-end autonomous driving technologies in relation to generalization, interpretability, causality, safety, and comfort. Finally, predictions are made for the future trends of end-to-end autonomous driving, emphasizing the fact that edge scenarios provide critical support for the training of end-to-end models, which can enhance the generalization capabilities. In addition, self-supervised learning can effectively improve training efficiency, personalized driving can optimize user experience, and world models represent a pivotal direction for the further advancement of end-to-end autonomous driving. The findings of this research serve as a significant reference for refining the theoretical framework and enhancing the performance of end-to-end autonomous driving systems. © 2024 Chang'an University. All rights reserved.
引用
收藏
页码：209 / 232
页数：23
相关论文
共 184 条
  • [1] LI Sheng-bo, LIU Chang, YIN Yu-ming, Et al., Key technology and development trend of end-to-end auto-driving system [J], Al-view, 10, 5, pp. 1-16, (2023)
  • [2] ZENG W Y, LUO W J, SUO S, Et al., End-to-end mterpret-able neural motion planner, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8652-8661, (2019)
  • [3] CHEN L, WU P H, CHITTA K, Et al., End-to-end autonomous driving
  • [4] Challenges and frontiers [J/OL]
  • [5] HU Y H, YANG J Z, CHEN L, Et al., Planmng-orlented autonomous driving, IEEE. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 17853-17862, (2023)
  • [6] LI Zhong-yang, DING Xiao, LIU Ting, Yann LeCun's speech at the opening ceremony of IJCAI-2018: We need a world model [J], Communications of the Chinese Computer Society, 14, 8, pp. 86-88, (2018)
  • [7] ZHU Z Y, ZHAO H J., A survey of deep RL and II. for autonomous driving policy learning [J], IEEE Transactions on Intelligent Transportation Systems, 23, 9, pp. 14043-14065, (2022)
  • [8] WU J D, HUANG C, HUANG H L, Et al., Recent advances in reinforcement learning-based autonomous driving behavior planning
  • [9] A survey, Transportation Research Part C: Emerging Technologies, 164, (2024)
  • [10] LY A O, AKHLOUFI M., Learning to drive by imitation: An overview of deep behavior cloning methods [J], IEEE Transactions on Intelligent Vehicles, 6, 2, pp. 195-209, (2021)
12345678910