Research Status of End-or-End Autonomous Driving Technology

Shixin  Zhao; Feng  Pan

doi:10.54097/r64m6026

Authors

Shixin Zhao
Feng Pan

DOI:

https://doi.org/10.54097/r64m6026

Keywords:

Autonomous vehicles; end-or-end; reinforcement learning; vehicle control.

Abstract

With the continuous development of autonomous driving technology, it holds significant potential in reducing the risk of traffic accidents, alleviating traffic congestion, and im-proving traffic efficiency. Traditional autonomous driving systems employ a modular deployment strategy, dividing the development into separate modules for perception, decision-making, planning, and control, which are then integrated into the vehicle. Currently, end-to-end autonomous driving methods have emerged as a research trend in the field of autonomous driving. This approach directly maps input data from the perception stage to driving behavior, simplifying the overall architecture of the autonomous driving system to reduce complexity. This paper provides a summary of research progress in end-to-end methods in the field of autonomous driving control and concludes by discussing future research directions and challenges in end-to-end autonomous driving technology.

References

LIU Y F,HU X M,CHEN G W.Review of end-to-end motion planning for autonomous driving with visual perception[J].Journal of Image and Graphics, 2021,26(01):49-66.

Teng S, Hu X, Deng P, et al. Motion planning for autonomous driving: The state of the art and future perspectives[J]. IEEE Transactions on Intelligent Vehicles, 2023.

Zhang Z, Tian R, Sherony R, et al. Attention-based interrelation modeling for explainable automated driving[J]. IEEE Transactions on Intelligent Vehicles, 2022, 8(2): 1564-1573.

Bojarski M, Del Testa D, Dworakowski D, et al. End to end learning for self-driving cars[J]. arXiv preprint arXiv: 1604.07316, 2016.

Codevilla F, Müller M, López A, et al. End-to-end driving via conditional imitation learning[C]//2018 IEEE international conference on robotics and automation (ICRA). IEEE, 2018: 4693-4700.

Chen C, Seff A, Kornhauser A, et al. Deepdriving: Learning affordance for direct perception in autonomous driving[C]/ /Proceedings of the IEEE international conference on computer vision. 2015: 2722-2730.

Sauer A, Savinov N, Geiger A. Conditional affordance learning for driving in urban environments[C]//Conference on Robot Learning. PMLR, 2018: 237-252.

Zeng W, Luo W, Suo S, et al. End-to-end interpretable neural motion planner[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019: 8660-8669.

Sadat A, Casas S, Ren M, et al. Perceive, predict, and plan: Safe motion planning through interpretable semantic representations[C]//Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXIII 16. Springer International Publishing, 2020: 414-430.

Mnih V, Kavukcuoglu K, Silver D, et al. Playing atari with deep reinforcement learning[J]. arXiv preprint arXiv: 1312.5602, 2013.

Wolf P, Hubschneider C, Weber M, et al. Learning how to drive in a real world simulation with deep q-networks[C]//2017 IEEE Intelligent Vehicles Symposium (IV). IEEE, 2017: 244-250.

Koenig N, Howard A. Design and use paradigms for gazebo, an open-source multi-robot simulator[C]//2004 IEEE/RSJ international conference on intelligent robots and systems (IROS)(IEEE Cat. No. 04CH37566). IEEE, 2004, 3: 2149-2154.

Saxena D M, Bae S, Nakhaei A, et al. Driving in dense traffic with model-free reinforcement learning[C]//2020 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2020: 5385-5392.

Schulman J, Wolski F, Dhariwal P, et al. Proximal policy optimization algorithms[J]. arXiv preprint arXiv:1707.06347, 2017.

Ye F, Cheng X, Wang P, et al. Automated lane change strategy using proximal policy optimization-based deep reinforcement learning[C]//2020 IEEE Intelligent Vehicles Symposium (IV). IEEE, 2020: 1746-1752.

Hu Y, Yang J, Chen L, et al. Planning-oriented autonomous driving[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023: 17853-17862.

Zheng W, Song R, Guo X, et al. GenAD: Generative End-to-End Autonomous Driving[J]. arXiv preprint arXiv:2402.11502, 2024.

Kendall A, Hawke J, Janz D, et al. Learning to drive in a day[C]//2019 International Conference on Robotics and Automation (ICRA). IEEE, 2019: 8248-8254.

Lillicrap T P, Hunt J J, Pritzel A, et al. Continuous control with deep reinforcement