Autonomous driverless technology, as an emerging technology of cross-integration of multiple fields, can control vehicles through autonomous intelligent control strategies, bring more safe and reliable driving environment and efficient driving scheme, which has very important research significance for improving the safety and efficiency of real road traffic. This paper mainly studies the application of deep learning in autonomous driving. This paper first analyzes the deep reinforcement learning method, and proposes an ODDPG autonomous driving decision method based on supervised training feature network for the real complex road autonomous driving decision problem. The feature extraction network is obtained in advance from imitation learning to improve the feature sample collection efficiency of reinforcement learning. ODDPG algorithm shows faster learning speed and better reward distribution of interactive data in the training process.

Qilu Zhang and Hu Shen. Deep Learning in Autonomous Driving. International Journal of Neural Network (2020), Vol. 1, Issue 3: 1-8. https://doi.org/10.38007/NN.2020.010301.

[1] Ucar A, Demir Y, Guzelis C. Object recognition and detection with deep learning for autonomous driving applications. Simulation: Transactions of The Society for Modeling and Simulation International, 2017, 93(9):003754971770993. https://doi.org/10.1177/0037549717709932

[2] Kiran B R, Sobh I, Talpaert V, et al. Deep Reinforcement Learning for Autonomous Driving: A Survey. IEEE Transactions on Intelligent Transportation Systems, 2020, PP(99):1-18.

[3] Fujiyoshi H, Hirakawa T, Yamashita T. Deep learning-based image recognition for autonomous driving. IATSS Research, 2019, 43(4):244-252. https://doi.org/10.1016/j.iatssr.2019.11.008

[4] Makantasis K, Kontorinaki M, Nikolos I. Deep reinforcement-learning-based driving policy for autonomous road vehicles. IET Intelligent Transport Systems, 2020, 14(1):13-24. https://doi.org/10.1049/iet-its.2019.0249

[5] Hoel C J, Driggs-Campbell K, Wolff K , et al. Combining Planning and Deep Reinforcement Learning in Tactical Decision Making for Autonomous Driving. IEEE Transactions on Intelligent Vehicles, 2019, PP(99):1-1.

[6] Yi H, Park E, Kim S. Multi-agent Deep Reinforcement Learning for Autonomous Driving. KIISE Transactions on Computing Practices, 2018, 24(12):670-674. https://doi.org/10.5626/KTCP.2018.24.12.670

[7] Kim S M, Kim T H, Dong H K. Autonomous Driving Through Non-uniform Steering Angles Nodes Determination by Deep Learning. Journal of Institute of Control, 2019, 25(8):677-683. https://doi.org/10.5302/J.ICROS.2019.19.0101

[8] Sallab A ,  Abdou M ,  Perot E , et al. Deep Reinforcement Learning framework for Autonomous Driving. Electronic Imaging, 2017, 2017(19):70-76. https://doi.org/10.2352/ISSN.2470-1173.2017.19.AVM-023

[9] Schneider L, Hafner M, Franke U. The Stixel world – A comprehensive representation of traffic scenes for autonomous driving. At - Automatisierungstechnik, 2018, 66(9):745-751. https://doi.org/10.1515/auto-2018-0029

[10] Alberti E, Tavera A, Masone C, et al. IDDA: a large-scale multi-domain dataset for autonomous driving. IEEE Robotics and Automation Letters, 2020, PP(99):1-1.

[11] Greer R, Deo N, Trivedi M. Trajectory Prediction in Autonomous Driving with a Lane Heading Auxiliary Loss. IEEE Robotics and Automation Letters, 2020, PP(99):1-1.

[12] Seo E, Lee S, Shin G, et al. Hybrid Tracker Based Optimal Path Tracking System of Autonomous Driving for Complex Road Environments. IEEE Access, 2020, PP(99):1-1. https://doi.org/10.1109/ACCESS.2020.3078849

[13] Vitas D, Tomic M, Burul M. Traffic Light Detection in Autonomous Driving Systems. IEEE Consumer Electronics Magazine, 2020, 9(4):90-96. https://doi.org/10.1109/MCE.2020.2969156

[14] Devi T K, Srivatsava A, Mudgal K K, et al. Behaviour Cloning for Autonomous Driving. Webology, 2020, 17(2):694-705. https://doi.org/10.14704/WEB/V17I2/WEB17061

[15] Weon I S, Lee S G, Ryu J K. Object recognition based interpolation with 3D LIDAR and vision for autonomous driving of an intelligent vehicle. IEEE Access, 2020, PP(99):1-1. https://doi.org/10.1109/ACCESS.2020.2982681

[16] Muhammad K, Ullah A, Lloret J, et al. Deep Learning for Safe Autonomous Driving: Current Challenges and Future Directions. IEEE Transactions on Intelligent Transportation Systems, 2020, PP(99):1-21.

[17] Mehra A, Mandal M, Narang P, et al. ReViewNet: A Fast and Resource Optimized Network for Enabling Safe Autonomous Driving in Hazy Weather Conditions. IEEE Transactions on Intelligent Transportation Systems, 2020, PP(99):1-11.

[18] Mohseni F, Voronov S, Frisk E. Deep Learning Model Predictive Control for Autonomous Driving in Unknown Environments - ScienceDirect. IFAC-PapersOnLine, 2018, 51(22):447-452. https://doi.org/10.1016/j.ifacol.2018.11.593