Deep Reinforcement Learning for Computerized Steering Angle Control of Pollution-Free Autonomous Vehicle

  IJETT-book-cover  International Journal of Engineering Trends and Technology (IJETT)          
© 2021 by IJETT Journal
Volume-69 Issue-4
Year of Publication : 2021
Authors : M.Karthikeyan, S.Sathiamoorthy
DOI :  10.14445/22315381/IJETT-V69I4P228


MLA Style: M.Karthikeyan, S.Sathiamoorthy  "Deep Reinforcement Learning for Computerized Steering Angle Control of Pollution-Free Autonomous Vehicle" International Journal of Engineering Trends and Technology 69.4(2021):204-208. 

APA Style:M.Karthikeyan, S.Sathiamoorthy. Deep Reinforcement Learning for Computerized Steering Angle Control of Pollution-Free Autonomous Vehicle  International Journal of Engineering Trends and Technology, 69(4),204-208.

Manpower cost is the major expense in Industrial and domestic applications, and hence the whole world is moving towards automation with the help of Artificial Intelligence (AI). AI techniques have a major role in making the process automated and advanced in modern industrial requirements. Smart devices, Smart vehicles, Smart home, Smart Factory, Smart home appliances, etc., are working with automated process based on the principle of artificial intelligence, and hence in this paper, one of the advanced AI techniques is chosen for the automated vehicle (AV) where steering angle is controlled in order to keep the vehicle within the lane. In this paper, an adaptive deep reinforcement learning algorithm for autonomous vehicles is presented, and the results have been analyzed. In this paper deep Q learning algorithm is used to control the steering angle of an autonomous vehicle. A transition model estimator is also developed to emulate the learning process using neural networks. This model helped this research work to utilize the available test data efficiently. This paper mainly focused on the objectives (i) Optimal learning policy as an adaptive learning system, (ii) Markov decision process (MDP) as a learning process in the learning system, and (iii) Numerical simulation of Deep Reinforcement algorithm with autonomous vehicle model. Continuation of this work would be the final stage of autonomous vehicle development.

[1] Krogh, Bruce, and Charles Thorpe., Integrated path planning and dynamic steering control for autonomous vehicles., In Proceedings. 1986 IEEE International Conference on Robotics and Automation, 3(1986) 1664-1669. IEEE.
[2] Ma, Yifang, Zhenyu Wang, Hong Yang, and Lin Yang., Artificial intelligence applications in the development of autonomous vehicles: a survey., IEEE/CAA Journal of Automatica Sinica 7(2)(2020) 315-329.
[3] Xia, Wei, Huiyun Li, and Baopu Li., A control strategy of autonomous vehicles based on deep reinforcement learning., In 2016 9th International Symposium on Computational Intelligence and Design (ISCID), 2(2016) 198-201. IEEE.
[4] Li, Xiao, Hanchen Xu, Jinming Zhang, and Hua-hua Chang., Deep Reinforcement Learning for Adaptive Learning Systems., arXiv preprint arXiv:2004.08410 (2020).
[5] Sallab, Ahmad EL, Mohammed Abdou, Etienne Perot, and Senthil Yogamani., Deep reinforcement learning framework for autonomous driving., Electronic Imaging 19(2017) 70-76.
[6] Wang, Sen, Daoyuan Jia, and Xinshuo Weng., Deep reinforcement learning for autonomous driving., arXiv preprint arXiv:1811.11329 (2018).
[7] Kiran, B. Ravi, Ibrahim Sobh, Victor Talpaert, Patrick Mannion, Ahmad A. Al Sallab, Senthil Yogamani, and Patrick Pérez., Deep reinforcement learning for autonomous driving: A survey., IEEE Transactions on Intelligent Transportation Systems (2021).
[8] François-Lavet, Vincent, Peter Henderson, Riashat Islam, Marc G. Bellemare, and Joelle Pineau., An introduction to deep reinforcement learning., arXiv preprint arXiv:1811.12560 (2018).
[9] Duan, Yan, Xi Chen, Rein Houthooft, John Schulman, and Pieter Abbeel., Benchmarking deep reinforcement learning for continuous control., In International conference on machine learning, (2016) 1329-1338. PMLR.
[10] Van Hasselt, Hado, Arthur Guez, and David Silver., Deep reinforcement learning with double q-learning., In Proceedings of the AAAI Conference on Artificial Intelligence, 30(1)(2016).
[11] Gupta, Jayesh K., Maxim Egorov, and Mykel Kochenderfer., Cooperative multi-agent control using deep reinforcement learning., In International Conference on Autonomous Agents and Multiagent Systems,(2017) 66-83. Springer, Cham.
[12] Tampuu, Ardi, Tambet Matiisen, Dorian Kodelja, Ilya Kuzovkin, Kristjan Korjus, Juhan Aru, Jaan Aru, and Raul Vicente., Multiagent cooperation and competition with deep reinforcement learning., PloS one 12(4)(2017) e0172395.
[13] Li, Hongjia, Tianshu Wei, Ao Ren, Qi Zhu, and Yanzhi Wang., Deep reinforcement learning: Framework, applications, and embedded implementations., In 2017 IEEE/ACM International Conference on Computer-Aided Design (ICCAD), (2017) 847-854. IEEE.
[14] Wei, Shiyin, Yuequan Bao, and Hui Li., Optimal policy for structure maintenance: A deep reinforcement learning framework., Structural Safety 83(2020) 101906.
[15] Nguyen, Thanh Thi, Ngoc Duy Nguyen, Peter Vamplew, Saeid Nahavandi, Richard Dazeley, and Chee Peng Lim., A multi-objective deep reinforcement learning framework., Engineering Applications of Artificial Intelligence 96 (2020) 103915.
[16] Schwarting, Wilko, Javier Alonso-Mora, and Daniela Rus., Planning and decision-making for autonomous vehicles., Annual Review of Control, Robotics, and Autonomous Systems (2018).
[17] P.Suguna, B. Kirubagari, R. Umamaheswari., An Effective Cluster-Based Outlier Detection with Optimized Deep Neural Network for Epileptic Seizure Detection and Classification Model., International Journal of Engineering Trends and Technology 69.3(2021) 76-84.
[18] Amit Sagu, Nasib Singh Gill, Preeti Gulia., Artificial Neural Network for the Internet of Things Security., International Journal of Engineering Trends and Technology 68.11(2020) 129-136.

Autonomous vehicle, Deep Reinforcement Algorithm, Steering Angle Control, Transition Model Estimator, and Adaptive learning.