Abstract
This study uses deep reinforcement learning (DRL) combined with computer vision technology to investigate vehicle fuel economy. In a driving cycle with car-following and traffic light scenarios, the vehicle fuel-saving control strategy based on DRL can realize the cooperative control of the engine and continuously variable transmission. The visual processing method of the convolutional neural network is used to extract available visual information from an on-board camera, and other types of information are obtained through the vehicle’s inherent sensor. The various detected types of information are further used as the state of DRL, and the fuel-saving control strategy is built. A Carla–Simulink co-simulation model is established to evaluate the proposed strategy. An urban road driving cycle and highway road driving cycle model with visual information is built in Carla, and the vehicle power system is constructed in Simulink. Results show that the fuel-saving control strategy based on DRL and computer vision achieves improved fuel economy. In addition, in the Carla–Simulink co-simulation model, the fuel-saving control strategy based on DRL and computer vision consumes an average time of 17.55 ms to output control actions, indicating its potential for use in real-time applications.
Similar content being viewed by others
References
Fagnant, D. J. and Kockelman, K. (2015). Preparing a nation for autonomous vehicles: Opportunities, barriers and policy recommendations. Transportation Research Part A: Policy and Practice, 77, 167–181.
Gao, H., Cheng, B., Wang, J., Li, K., Zhao, J. and Li, D. (2018). Object classification using CNN-based fusion of vision and LIDAR in autonomous vehicle environment. IEEE Trans. Industrial Informatics 14, 9, 4224–4231.
Han, J., Vahidi, A. and Sciarretta, A. (2019). Fundamentals of energy efficient driving for combustion engine and electric vehicles: An optimal control perspective. Automatica, 103, 558–572.
Hongwen, H., Jinquan, G., Jiankun, P., Huachun, T. and Chao, S. (2018). Real-time global driving cycle construction and the application to economy driving pro system in plug-in hybrid electric vehicles. Energy, 152, 95–107.
Lee, H., Sung, J., Lee, H., Zheng, C., Lim, W., and Cha, S. W. (2018). Model-based integrated control of engine and CVT to minimize fuel use. Int. J. Automotive Technology 19, 4, 687–694.
Li, J., Zhou, Q., He, Y., Shuai, B., Li, Z., Williams, H. and Xu, H. (2019). Dual-loop online intelligent programming for driver-oriented predict energy management of plug-in hybrid electric vehicles. Applied Energy, 253, 113617.
Li, K., Chen, T., Luo, Y. and Wang, J. (2012). Intelligent environment-friendly vehicles: Concept and case studies. IEEE Trans. Intelligent Transportation Systems 13, 1, 318–328.
Li, Y., He, H., Peng, J. and Wang H. (2019). Deep reinforcement learning-based energy management for a series hybrid electric vehicle enabled by history cumulative trip information. IEEE Trans. Vehicular Technology 68, 8, 7416–7430.
Lutsey, N. (2012). Regulatory and technology lead-time: The case of US automobile greenhouse gas emission standards. Transport Policy, 21, 179–190.
Pyun, B., Seo, M., Kim, S. and Choi, H. (2022). Development of an autonomous driving controller for articulated bus using model predictive control algorithm with inner model. Int. J. Automotive Technology 23, 2, 357–336.
Sulaiman, N., Hannan, M. A., Mohamed, A., Ker, P. J., Majlan, E. H. and Daud, W. R. W. (2018). Optimization of energy management system for fuel-cell hybrid electric vehicles: Issues and recommendations. Applied Energy, 228, 2061–2079.
Sun, C., Moura, S. J., Hu, X., Hedrick, J. K. and Sun, F. (2015). Dynamic traffic feedback data enabled energy management in plug-in hybrid electric vehicles. IEEE Trans. Control Systems Technology 23, 3, 1075–1086.
Tan, H., Zhang, H., Peng, J., Jiang, Z. and Wu, Y. (2019). Energy management of hybrid electric bus based on deep reinforcement learning in continuous state and action space. Energy Conversion and Management, 195, 548–560.
Tang, T.-Q., Liao, P., Ou, H, and Zhang, J. (2018). A fuel-optimal driving strategy for a single vehicle with CVT. Physica A: Statistical Mechanics and its Applications, 505, 114–123.
Tang, X., Chen, J., Liu, T., Li, J. and Hu, X. (2021). Research on deep reinforcement learning-based intelligent car-following control and energy management strategy for hybrid electric vehicles. J. Mechanical Engineering 57, 22, 237–246.
Van der Meulen, S., De Jager, B., Veldpaus, F., Van der Noll, E., Van Der Sluis, F. and Steinbuch, M. (2012). Improving continuously variable transmission efficiency with extremum seeking control. IEEE Trans. Control Systems Technology 20, 5, 1376–1383.
Wang, Y., Tan, H., Wu, Y. and Peng, J. (2021). Hybrid electric vehicle energy management with computer vision and deep reinforcement learning. IEEE Trans. Industrial Informatics 17, 6, 3857–3868.
Wu, J., He, H., Peng, J., Li, Y. and Li, Z. (2018). Continuous reinforcement learning of energy management with deep Q network for a power split hybrid electric bus. Applied Energy, 222, 799–811.
Wu, Y., Tan, H., Peng, J., Zhang, H. and He, H. (2019). Deep reinforcement learning of energy management with continuous control strategy and traffic information for a series-parallel plug-in hybrid electric bus. Applied Energy, 247, 454–466.
Yang, W., Ruan, J., Yang, J. and Zhang, N. (2020). Investigation of integrated uninterrupted dual input transmission and hybrid energy storage system for electric vehicles. Applied Energy, 262, 114446.
Zhang, F., Xi, J. and Langari, R. (2017). Real-time energy management strategy based on velocity forecasts using V2V and V2I communications. IEEE Trans. Intelligent Transportation Systems 18, 2, 416–430.
Zhang, S., Wu, Y., Un, P., Fu, L., and Hao, J. (2016). Modeling real-world fuel consumption and carbon dioxide emissions with high resolution for light-duty passenger vehicles in a traffic populated city. Energy, 113, 461–471.
Zhang, Y. and Ioannou, P. A. (2017). Combined variable speed limit and lane change control for highway traffic. IEEE Trans. Intelligent Transportation Systems 18, 7, 1812–1823.
Acknowledgement
The authors gratefully acknowledge the financial support of the science and technology Foundation of Jilin Province under Project No. 20220508151RC.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Han, L., Liu, G., Zhang, H. et al. Fuel-Saving Control Strategy for Fuel Vehicles with Deep Reinforcement Learning and Computer Vision. Int.J Automot. Technol. 24, 609–621 (2023). https://doi.org/10.1007/s12239-023-0051-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12239-023-0051-4