This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Vehicle Following Hybrid Control Algorithm Based on DRL and PID in Intelligent Network Environment
Technical Paper
2022-01-7113
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
Deep reinforcement learning (DRL) has not been widely used in the engineering field yet because RL needs to be learned through ‘trial and error’, which makes the application of this kind of algorithm in real physical environment more difficult, and it is impossible to carry out ‘trial and error’ learning on real vehicles. By analyzing the motion state of the vehicle in the car following mode, the algorithm that combined traditional longitudinal motion control with DRL improves the safety of RL in the real physical environment and the poor adaptability of the traditional longitudinal motion control algorithm. In this paper, the longitudinal motion of the unmanned vehicle is taken as the research object, and the PID algorithm is combined with the Deep Deterministic Policy Gradient (DDPG) algorithm to control the longitudinal motion of the unmanned vehicle. The research results show that the longitudinal motion control hybrid algorithm performed better than the single PID algorithm or DDPG algorithm in the vehicle following control. This strategy establishes the relationship between the vehicle longitudinal control and the state of both the ego vehicle and the front vehicle, while also considers the randomness of the front vehicle motion in the iterative learning process, which improves the safety, comfort and following performance.
Authors
Citation
Hu, B., Chen, J., Lin, Y., and Tan, S., "Vehicle Following Hybrid Control Algorithm Based on DRL and PID in Intelligent Network Environment," SAE Technical Paper 2022-01-7113, 2022, https://doi.org/10.4271/2022-01-7113.Also In
References
- Pang , Z.J. , Liu , R.Z. , and Meng , Z.Y. On Reinforcement Learning for Full-Length Game of Star-Craft Proceedings of the AAAI Conference o1n Artificial Intelligence 33 4691 4698 2019 10.1609/aaai.v33i01.33014691
- Wei , J. , Dolan , J.M. , and Litkouhi , B. A Learning-Based Autonomous Driver: Emulate Human Driver’s Intelligence in Low-Speed Car Following Unattended Ground, Sea, and Air Sensor Technologies and Applications XII. International Society for Optics and Photonics 7693 76930L 2010 10.1117/12.852413
- Paden , B. , Čáp , M. , and Yong , S.Z. A Survey of Motion Planning and Control Techniques for Self-Driving Urban Vehicles IEEE Transactions on Intelligent Vehicles 1 1 2016 33 55 10.1109/tiv.2016.2578706
- Zhu , M. et al. Safe, Efficient, and Comfortable Velocity Control Based on Reinforcement Learning for Autonomous Driving Transportation Research Part C 117 2020 102662 10.1016/j.trc.2020.102662
- Linlin , G. , Hui , R. , Fengmin , T. , Peng , G. et al. Research on Longitudinal Motion Control Method of Intelligent Unmanned Vehicle Automotive Electrical Appliances 11 2019 1 3
- Chan , Y.F. , Moallem , M. , and Wang , W. Efficient Implementation of PID Control Algorithm Using FPGA Technology 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601) 5 4885 4890 2004 10.1109/CDC.2004.1429572
- Zhenhai , G. , and Daxing , C. Fuzzy Self-Tuning Control Algorithm for Automobile Adaptive Cruise System Proceedings of 2010 Annual Meeting of China Society of Automotive Engineering 4 2010
- Qun , W. , Weichao , Z. , Liangmo , W. , and Fei , J. Lane Keeping Assist for an Autonomous Vehicle Based on Deep Reinforcement Learning SAE Technical Paper 2020-01-0728 2020 https://doi.org/10.4271/2020-01-0728
- Al-Gabalawy , M. , Hosny , N.S. , and Aborisha , A.-h.S. Model Predictive Control for a Basic Adaptive Cruise Control International Journal of Dynamics and Control 2021 10.1007/s40435-020-00732-w
- Xubin , D. , Tao , S. , and Wei , X. Research on Improvement of Adaptive Cruise Algorithm Based on MPC Electromechanical Engineering 35 6 2018 644 648+657 10.3969/j.issn.1001–4551.2018.06.019
- Yang , S. , Xiaodi , C. , Yan , T. , and Tinglun , S. Research on Hierarchical Control of Automotive Adaptive Cruise System Based on Fuzzy PID Proceedings of 2018 Annual Meeting of China Society of Automotive Engineers 4 2018
- Desjardins , C. and Chaib-Draa , B. Cooperative Adaptive Cruise Control: A Reinforcement Learning Approach IEEE Transactions on Intelligent Transportation Systems 12 4 2011 1248 1260
- Ge , Y. , Zhu , F. , Ling , X. , and Liu , Q. Safe Q-Learning Method Based on Constrained Markov Decision Processes IEEE Access 7 2019 165007 165017 10.1109/ACCESS.2019.2952651
- Chae , H. , Kang , C.M. , and Kim , B. Autonomous Braking System via Deep Reinforcement Learning 2017 10.1109/ITSC.2017.8317839
- Sallab , A.E. , Abdou , M. , and Perot , E. Deep Reinforcement Learning Framework for Autonomous Driving Electronic Imaging 2017 19 2017 70 76 10.2352/issn.2470-1173.2017.19.avm-023
- Hoel , C.J. , Wolff , K. , and Laine , L. Automated Speed and Lane Change Decision Making using Deep Reinforcement Learning 2018 10.1109/itsc.2018.8569568
- Mo , S. , Pei , X. , and Wu , C. Safe Reinforcement Learning for Autonomous Vehicle Using Monte Carlo Tree Search IEEE Transactions on Intelligent Transportation Systems 10.1109/TITS.2021.3061627
- Karimpanal , T.G. , Rana , S. , Gupta , S. , Tran , T. et al. Learning Transferable Domain Priors for Safe Exploration in Reinforcement Learning 2020 International Joint Conference on Neural Networks (IJCNN) 1 10 2020 10.1109/IJCNN48605.2020.9207344
- Jin , M. , Yang Lei , H. , Yuanbo , L.K. , and Jinfu , D. Research on Vehicle Adaptive Cruise Control Method Based on Fuzzy Model Predictive Control Machines 9 8 2021 160 10.3390/MACHINES9080160
- Biagio , C. , Konstantinos , M. , Michail , M. , Giovanni , A. et al. Requiem on the Positive Effects of Commercial Adaptive Cruise Control on Motorway Traffic and Recommendations for Future Automated Driving Systems Transportation Research Part C 130 2021 103305 10.1016/J.TRC.2021.103305