IDEAS home Printed from https://ideas.repec.org/a/gam/jsusta/v15y2023i18p13799-d1240934.html
   My bibliography  Save this article

Improving the Performance of Autonomous Driving through Deep Reinforcement Learning

Author

Listed:
  • Akshaj Tammewar

    (Symbiosis Institute of Technology, Pune Campus, Symbiosis International (Deemed University) (SIU), Lavale, Pune 412115, India)

  • Nikita Chaudhari

    (Symbiosis Institute of Technology, Pune Campus, Symbiosis International (Deemed University) (SIU), Lavale, Pune 412115, India)

  • Bunny Saini

    (Symbiosis Institute of Technology, Pune Campus, Symbiosis International (Deemed University) (SIU), Lavale, Pune 412115, India)

  • Divya Venkatesh

    (Symbiosis Institute of Technology, Pune Campus, Symbiosis International (Deemed University) (SIU), Lavale, Pune 412115, India)

  • Ganpathiraju Dharahas

    (Symbiosis Institute of Technology, Pune Campus, Symbiosis International (Deemed University) (SIU), Lavale, Pune 412115, India)

  • Deepali Vora

    (Symbiosis Institute of Technology, Pune Campus, Symbiosis International (Deemed University) (SIU), Lavale, Pune 412115, India)

  • Shruti Patil

    (Symbiosis Centre for Applied Artificial Intelligence (SCAAI), Symbiosis Institute of Technology, Pune Campus, Symbiosis International (Deemed University) (SIU), Lavale, Pune 412115, India)

  • Ketan Kotecha

    (Symbiosis Centre for Applied Artificial Intelligence (SCAAI), Symbiosis Institute of Technology, Pune Campus, Symbiosis International (Deemed University) (SIU), Lavale, Pune 412115, India)

  • Sultan Alfarhood

    (Department of Computer Science, College of Computer and Information Sciences, King Saud University, P.O. Box 51178, Riyadh 11543, Saudi Arabia)

Abstract

Reinforcement learning (RL) is revolutionizing the artificial intelligence (AI) domain and significantly aiding in building autonomous systems with a higher level comprehension of the world as we observe it. Deep learning (DL) facilitates RL to scale and resolve previously intractable problems, for instance, allowing supervision principles designed for robots to be acquired directly from visual data, developing video game proficiency from pixel-level information, etc. Recent research shows that RL algorithms help represent problems dealing with high-dimensional, unprocessed data input and can have successful applications in computer vision, pattern identification, natural language analysis, and speech parsing. This research paper focuses on training a simulation model of a car to navigate autonomously on a racetrack using RL. The study explores several fundamental algorithms in Deep RL, namely Proximal Policy Optimization (PPO), Deep Q-network (DQN), and Deep Deterministic Policy Gradient (DDPG). The paper documents a comparative analysis of these three prominent algorithms—based on their speed, accuracy, and overall performance. After a thorough evaluation, the research indicates that the DQN surpassed the other existing algorithms. This study further examined the performance of the DQN with and without ε-decay and observed that the DQN with ε-decay is better suited for our objective and is significantly more stable than its non ε-decay counterpart. The findings from this research could assist in improving the performance and stability of autonomous vehicles using the DQN with ε -decay. It concludes by discussing the fine-tuning of the model for future real-world applications and the potential research areas within the field of autonomous driving.

Suggested Citation

  • Akshaj Tammewar & Nikita Chaudhari & Bunny Saini & Divya Venkatesh & Ganpathiraju Dharahas & Deepali Vora & Shruti Patil & Ketan Kotecha & Sultan Alfarhood, 2023. "Improving the Performance of Autonomous Driving through Deep Reinforcement Learning," Sustainability, MDPI, vol. 15(18), pages 1-18, September.
  • Handle: RePEc:gam:jsusta:v:15:y:2023:i:18:p:13799-:d:1240934
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2071-1050/15/18/13799/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2071-1050/15/18/13799/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Abhijit Gosavi, 2009. "Reinforcement Learning: A Tutorial Survey and Recent Advances," INFORMS Journal on Computing, INFORMS, vol. 21(2), pages 178-192, May.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Voelkel, Michael A. & Sachs, Anna-Lena & Thonemann, Ulrich W., 2020. "An aggregation-based approximate dynamic programming approach for the periodic review model with random yield," European Journal of Operational Research, Elsevier, vol. 281(2), pages 286-298.
    2. Fang, Jianhao & Hu, Weifei & Liu, Zhenyu & Chen, Weiyi & Tan, Jianrong & Jiang, Zhiyu & Verma, Amrit Shankar, 2022. "Wind turbine rotor speed design optimization considering rain erosion based on deep reinforcement learning," Renewable and Sustainable Energy Reviews, Elsevier, vol. 168(C).
    3. Dieter Hendricks & Diane Wilcox, 2014. "A reinforcement learning extension to the Almgren-Chriss model for optimal trade execution," Papers 1403.2229, arXiv.org.
    4. Wang, Xianjia & Yang, Zhipeng & Liu, Yanli & Chen, Guici, 2023. "A reinforcement learning-based strategy updating model for the cooperative evolution," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 618(C).
    5. Bunn, Derek W. & Oliveira, Fernando S., 2016. "Dynamic capacity planning using strategic slack valuation," European Journal of Operational Research, Elsevier, vol. 253(1), pages 40-50.
    6. Andreas Rauh & Marit Lahme & Oussama Benzinane, 2022. "A Comparison of the Use of Pontryagin’s Maximum Principle and Reinforcement Learning Techniques for the Optimal Charging of Lithium-Ion Batteries," Clean Technol., MDPI, vol. 4(4), pages 1-21, December.
    7. Puwei Lu & Wenkai Huang & Junlong Xiao & Fobao Zhou & Wei Hu, 2021. "Adaptive Proportional Integral Robust Control of an Uncertain Robotic Manipulator Based on Deep Deterministic Policy Gradient," Mathematics, MDPI, vol. 9(17), pages 1-16, August.
    8. Jia, Liangyue & Hao, Jia & Hall, John & Nejadkhaki, Hamid Khakpour & Wang, Guoxin & Yan, Yan & Sun, Mengyuan, 2021. "A reinforcement learning based blade twist angle distribution searching method for optimizing wind turbine energy power," Energy, Elsevier, vol. 215(PA).
    9. Zhang, Xiaoshun & Chen, Yixuan & Yu, Tao & Yang, Bo & Qu, Kaiping & Mao, Senmao, 2017. "Equilibrium-inspired multiagent optimizer with extreme transfer learning for decentralized optimal carbon-energy combined-flow of large-scale power systems," Applied Energy, Elsevier, vol. 189(C), pages 157-176.
    10. Justin Dumouchelle & Emma Frejinger & Andrea Lodi, 2024. "Reinforcement learning for freight booking control problems," Journal of Revenue and Pricing Management, Palgrave Macmillan, vol. 23(4), pages 318-345, August.
    11. M. Saqlain & S. Ali & J. Y. Lee, 2023. "A Monte-Carlo tree search algorithm for the flexible job-shop scheduling in manufacturing systems," Flexible Services and Manufacturing Journal, Springer, vol. 35(2), pages 548-571, June.
    12. Li, Munan & Wang, Wenshu & Zhou, Keyu, 2021. "Exploring the technology emergence related to artificial intelligence: A perspective of coupling analyses," Technological Forecasting and Social Change, Elsevier, vol. 172(C).
    13. Hoai An Le Thi & Vinh Thanh Ho & Tao Pham Dinh, 2019. "A unified DC programming framework and efficient DCA based approaches for large scale batch reinforcement learning," Journal of Global Optimization, Springer, vol. 73(2), pages 279-310, February.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jsusta:v:15:y:2023:i:18:p:13799-:d:1240934. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.