DEEP REINFORCEMENT LEARNING FOR AUTONOMOUS DRIVING: CHALLENGES, SOLUTIONS, AND FUTURE DIRECTIONS

Authors

  • Durgapal d Asst. Prof., ITM SLS Baroda University
  • Matieda S Asst. Prof., ITM SLS Baroda University
  • Shah A Asst. Prof., Parul University

Keywords:

Deep Reinforcement Learning, Autonomous Driving, Artificial Intelligence, Machine Learning, Simulation

Abstract

Autonomous driving has emerged as a transformative application of artificial intelligence and machine learning. Deep Reinforcement Learning (DRL) is particularly promising for autonomous driving due to its capacity to optimize decision-making through interactions with the environment. This paper reviews the state-of-the-art in DRL for autonomous driving as of 2021, discussing key challenges, proposed solutions, and future research directions. We examine DRL’s integration with sensor technologies, simulation environments, and real-world applications. A case study utilizing a DRL-based model in a simulated urban driving environment is presented, including performance metrics and data visualizations.

References

. Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., ... & Hassabis, D. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529-533.

. Sallab, A. E., Abdou, M., Perot, E., & Yogamani, S. (2017). Deep reinforcement learning framework for autonomous driving. Electronic Imaging, 2017(19), 70-76.

. Kiran, B. R., Sobh, I., Talpaert, V., Mannion, P., Al Sallab, A., Yogamani, S., & Pérez, P. (2021). Deep reinforcement learning for autonomous driving: A survey. IEEE Transactions on Intelligent Transportation Systems, 22(6), 3601-3622.

. Li, Y., Song, L., Ermon, S., & Xing, E. P. (2019). A value-decomposition framework for cooperative multi-agent reinforcement learning. arXiv preprint arXiv:1902.06381.

. Chen, C., Seff, A., Kornhauser, A., & Xiao, J. (2020). DeepDriving: Learning affordance for direct perception in autonomous driving. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2722-2730.

Downloads

Published

2021-12-31

How to Cite

Durgapal, D., Matieda, S., & Shah, A. (2021). DEEP REINFORCEMENT LEARNING FOR AUTONOMOUS DRIVING: CHALLENGES, SOLUTIONS, AND FUTURE DIRECTIONS. COMPUSOFT: An International Journal of Advanced Computer Technology, 10(00), 3978–3980. Retrieved from https://ijact.in/index.php/j/article/view/616

Issue

Section

Original Research Article

Similar Articles

<< < 7 8 9 10 11 12 13 14 > >> 

You may also start an advanced similarity search for this article.