International Journal of Information Technology and Computer Science (IJITCS)
IJITCS Vol. 18, No. 4, 8 Aug. 2026
Cover page and Table of Contents: PDF (size: 793KB)
Driver Behavior–aware Fuel Optimization Using a Digital Twin and Reinforcement Learning Approach for Open-pit Haul Trucks
PDF (793KB), PP.155-169
Views: 0 Downloads: 0
Author(s)
Kusnawi A.
1,*
Mochammad B. Agung Wibowo
2
Ridwan C. Sanjaya
3
Index Terms
Digital Twin, Reinforcement Learning, Fuel Efficiency, Driver Behavior Modeling, Open Pit Mining, Heavy-duty Haul Trucks, Proximal Policy Optimization
Abstract
Driver behavior, vehicle dynamics, and operating conditions strongly influence fuel consumption in open-pit mining operations. This study proposes a driver behavior–aware fuel optimization framework that integrates a digital twin architecture with reinforcement learning to improve fuel efficiency of heavy-duty haul trucks. The framework combines a data-driven vehicle dynamics surrogate, explicit modeling of driver behavior, and proximal policy optimization to enable safe and scalable policy learning within a realistic simulation environment. Historical telematics data were used to construct the digital twin and evaluate the learned policy under controlled operating conditions. Experimental results show that the reinforcement learning agent produces substantially smoother driving behavior, characterized by stable speed regulation and elimination of aggressive acceleration and braking events. Compared to historical operator driving, fuel consumption per kilometer, computed using rollout-level aggregation of cumulative fuel consumption and total traveled distance, was reduced from 4.45 L/km to 3.02 L/km, corresponding to a 32.05% improvement in fuel efficiency. The results demonstrate that explicitly modeling driver behavior within a digital twin-based reinforcement learning framework can yield significant fuel savings while maintaining realistic and interpretable driving strategies. The proposed approach provides a promising foundation for the development of decision-support and driver assistance systems aimed at improving energy efficiency in open-pit haulage operations.
Cite This Paper
Kusnawi A., Mochammad B. Agung Wibowo, Ridwan C. Sanjaya, "Driver Behavior–aware Fuel Optimization Using a Digital Twin and Reinforcement Learning Approach for Open-pit Haul Trucks", International Journal of Information Technology and Computer Science(IJITCS), Vol.18, No.4, pp.155-169, 2026. DOI:10.5815/ijitcs.2026.04.10
Reference
[1]P. Bodziony and M. Patyk, “The Influence of the Mining Operation Environment on the Energy Consumption and Technical Availability of Truck Haulage Operations in Surface Mines,” Energies , vol. 17, no. 11, 2024, doi: 10.3390/en17112654.
[2]Q. Wang, R. Zhang, S. Lv, and Y. Wang, “Open-pit mine truck fuel consumption pattern and application based on multi-dimensional features and XGBoost,” Sustainable Energy Technologies and Assessments, vol. 43, p. 100977, Feb. 2021, doi: 10.1016/j.seta.2020.100977.
[3]L. Chen et al., “Autonomous mining through cooperative driving and operations enabled by parallel intelligence,” Communications Engineering, vol. 3, no. 1, p. 75, May 2024, doi: 10.1038/s44172-024-00220-5.
[4]F. Mensing, R. Trigui, H. Tategrain, and E. Bideaux, “Ecodriving. From processing the ideal speed profile to its use during driving activity,” European Journal of Electrical Engineering, vol. 17, no. 5–6, pp. 397–418, Dec. 2014, doi: 10.3166/ejee.17.397-418.
[5]Q. Wang, R. Zhang, Y. Wang, and S. Lv, “Machine learning-based driving style identification of truck drivers in open-pit mines,” Electronics (Switzerland), vol. 9, no. 1, pp. 1–24, 2020, doi: 10.3390/electronics9010019.
[6]X. Zhu, X. Shen, K. Chen, and Z. Zhang, “Research on the prediction and influencing factors of heavy duty truck fuel consumption based on LightGBM,” Energy, vol. 296, 2024, doi: 10.1016/j.energy.2024.131221.
[7]Z. Ma, B. N. Jørgensen, and Z. Ma, “A Scoping Review of Energy-Efficient Driving Behaviors and Applied State-of-the-Art AI Methods,” Energies (Basel), vol. 17, no. 2, p. 500, Jan. 2024, doi: 10.3390/en17020500.
[8]T. Bousonville, D. Cheubou Kamga, T. Krüger, and M. Dirichs, “Data driven analysis and forecasting of medium and heavy truck fuel consumption,” Enterp. Inf. Syst., vol. 16, no. 6, 2022, doi: 10.1080/17517575.2020.1856417.
[9]S. Alamdari, M. Hossein Basiri, A. Mousavi, and A. Soofastaei, “Application of Machine Learning Techniques to Predict Haul Truck Fuel Consumption in Open-Pit Mines,” Journal of Mining and Environment, vol. 13, no. 1, pp. 69–85, 2022, doi: 10.22044/jme.2022.11577.2145.
[10]P. Fan, G. Song, Z. Zhai, Y. Wu, and L. Yu, “Fuel consumption estimation in heavy-duty trucks: Integrating vehicle weight into deep-learning frameworks,” Transp. Res. D Transp. Environ., vol. 130, no. March, p. 104157, May 2024, doi: 10.1016/j.trd.2024.104157.
[11]L. Liu, W. Li, D. Wang, Y. Wu, R. Yang, and W. Shi, “Fuel Rate Prediction for Heavy-Duty Trucks,” IEEE Transactions on Intelligent Transportation Systems, vol. 24, no. 8, pp. 8222–8235, Aug. 2023, doi: 10.1109/TITS.2023.3265007.
[12]F. Tao, J. Cheng, Q. Qi, M. Zhang, H. Zhang, and F. Sui, “Digital twin-driven product design, manufacturing and service with big data,” The International Journal of Advanced Manufacturing Technology, vol. 94, no. 9–12, pp. 3563–3576, Feb. 2018, doi: 10.1007/s00170-017-0233-1.
[13]Fei. Tao, Meng. Zhang, and A. Y. C. . Nee, Digital twin driven smart manufacturing. Academic Press, 2019.
[14]Q. Qi and F. Tao, “Digital Twin and Big Data Towards Smart Manufacturing and Industry 4.0: 360 Degree Comparison,” IEEE Access, vol. 6, pp. 3585–3593, Jan. 2018, doi: 10.1109/ACCESS.2018.2793265.
[15]D. Jones, C. Snider, A. Nassehi, J. Yon, and B. Hicks, “Characterising the Digital Twin: A systematic literature review,” CIRP J Manuf Sci Technol, vol. 29, pp. 36–52, May 2020, doi: 10.1016/j.cirpj.2020.02.002.
[16]P. Nobahar, C. Xu, P. Dowd, and R. Shirani Faradonbeh, “Exploring digital twin systems in mining operations: A review,” Green and Smart Mining Engineering, vol. 1, no. 4, pp. 474–492, Dec. 2024, doi: 10.1016/j.gsme.2024.09.003.
[17]N. Elbazi, A. Tigami, O. Laayati, A. El Maghraoui, A. Chebak, and M. Mabrouki, “Digital Twin-Enabled Monitoring of Mining Haul Trucks with Expert System Integration: A Case Study in an Experimental Open-Pit Mine,” in 2023 5th Global Power, Energy and Communication Conference (GPECOM), IEEE, Jun. 2023, pp. 168–174. doi: 10.1109/GPECOM58364.2023.10175789.
[18]H. Wu, P. Ji, H. Ma, and L. Xing, “A Comprehensive Review of Digital Twin from the Perspective of Total Process: Data, Models, Networks and Applications,” Sensors, vol. 23, no. 19, p. 8306, Oct. 2023, doi: 10.3390/s23198306.
[19]B. Li, Y. Cui, Y. Xiao, S. Fu, J. Choi, and C. Zheng, “An improved energy management strategy of fuel cell hybrid vehicles based on proximal policy optimization algorithm,” Energy, vol. 317, p. 134585, Feb. 2025, doi: 10.1016/j.energy.2025.134585.
[20]H. Chen, G. Guo, B. Tang, G. Hu, X. Tang, and T. Liu, “Data-driven transferred energy management strategy for hybrid electric vehicles via deep reinforcement learning,” Energy Reports, vol. 10, pp. 2680–2692, Nov. 2023, doi: 10.1016/j.egyr.2023.09.087.
[21]Z. Yang, Z. Zheng, J. Kim, and H. Rakha, “Eco-driving strategies using reinforcement learning for mixed traffic in the vicinity of signalized intersections,” Transp Res Part C Emerg Technol, vol. 165, p. 104683, Aug. 2024, doi: 10.1016/j.trc.2024.104683.
[22]H. Kim, H. Pyeon, J. S. Park, J. Y. Hwang, and S. Lim, “Autonomous vehicle fuel economy optimization with deep reinforcement learning,” Electronics (Switzerland), vol. 9, no. 11, pp. 1–19, 2020, doi: 10.3390/electronics9111911.
[23]Z. Zhang, R. Zhang, and J. Sun, “Research on the Comprehensive Evaluation Method of Driving Behavior of Mining Truck Drivers in an Open-Pit Mine,” Applied Sciences, vol. 13, no. 20, p. 11597, Oct. 2023, doi: 10.3390/app132011597.
[24]L. Fang, H. Li, Y. Zheng, and X. Luo, “Driving behavior recognition and fuel economy evaluation for heavy-duty vehicles,” Research in Transportation Business & Management, vol. 60, no. April, p. 101371, Jun. 2025, doi: 10.1016/j.rtbm.2025.101371.
[25]Z. Zhang, E. Demir, R. Mason, and C. Di Cairano-Gilfedder, “Understanding freight drivers’ behavior and the impact on vehicles’ fuel consumption and CO2e emissions,” Operational Research, vol. 23, no. 4, p. 59, Dec. 2023, doi: 10.1007/s12351-023-00798-2.
[26]Kusnawi, M. Agung Wibowo, and R. Sanjaya, “A Systematic Literature Review of Adaptive Machine Learning Approaches for Real-Time Fuel Efficiency Optimization in Open-Pit Mining Trucks,” Sistem Informasi dan Komputer], vol. 15, pp. 40–46, 2025, doi: 10.32736/sisfokom.v15i1.2527.
[27]H. I. Ashqar, M. Obaid, A. Jaber, R. Ashqar, N. O. Khanfar, and M. Elhenawy, “Incorporating driving behavior into vehicle fuel consumption prediction: methodology development and testing,” Discover Sustainability, vol. 5, no. 1, Dec. 2024, doi: 10.1007/s43621-024-00511-z.
[28]A. Fuller, Z. Fan, C. Day, and C. Barlow, “Digital Twin: Enabling Technologies, Challenges and Open Research,” IEEE Access, vol. 8, pp. 108952–108971, 2020, doi: 10.1109/ACCESS.2020.2998358.
[29]R. S. . Sutton and A. G. . Barto, Reinforcement learning : an introduction. The MIT Press, 2020.
[30]H. Hailemichael, B. Ayalew, L. Kerbel, A. Ivanco, and K. Loiselle, “Safe Reinforcement Learning for an Energy-Efficient Driver Assistance System,” IFAC-PapersOnLine, vol. 55, no. 37, pp. 615–620, 2022, doi: 10.1016/j.ifacol.2022.11.250.
[31]Y. Ye, B. Xu, H. Wang, J. Zhang, B. Lawler, and B. Ayalew, “Deep reinforcement learning-based energy management system enhancement using digital twin for electric vehicles,” Energy, vol. 312, no. August, p. 133384, Dec. 2024, doi: 10.1016/j.energy.2024.133384.
[32]H. Ding, W. Li, N. Xu, and J. Zhang, “An enhanced eco-driving strategy based on reinforcement learning for connected electric vehicles: cooperative velocity and lane-changing control,” Journal of Intelligent and Connected Vehicles, vol. 5, no. 3, pp. 316–332, Oct. 2022, doi: 10.1108/JICV-07-2022-0030.
[33]X. Tang et al., “Reinforcement Learning-Based Energy Management for Hybrid Power Systems: State-of-the-Art Survey, Review, and Perspectives,” Chinese Journal of Mechanical Engineering, vol. 37, no. 1, p. 43, May 2024, doi: 10.1186/s10033-024-01026-4.
[34]A. Raffin et al, “Stable-Baselines3: Reliable Reinforcement Learning Implementations,” 2021. (Online). Available: https://github.com/DLR-RM/stable-baselines3.
[35]M. Miotti, Z. A. Needell, S. Ramakrishnan, J. Heywood, and J. E. Trancik, “Quantifying the impact of driving style changes on light-duty vehicle fuel consumption,” Transp Res D Transp Environ, vol. 98, p. 102918, Sep. 2021, doi: 10.1016/j.trd.2021.102918.
[36]E. S. Sumner et al., “Personalizing driver safety interfaces via driver cognitive factors inference,” Sci. Rep., vol. 14, no. 1, p. 18058, Aug. 2024, doi: 10.1038/s41598-024-65144-8.
[37]D. L. Fisher, W. J. Horrey, J. D. Lee, and M. A. Regan, Eds., Handbook of Human Factors for Automated, Connected, and Intelligent Vehicles. Boca Raton, FL : CRC Press, 2020.: CRC Press, 2020. doi: 10.1201/b21974.
[38]E. Tomanik, A. J. Jimenez-Reyes, V. Tomanik, and B. Tormos, “Machine-Learning-Based Digital Twins for Transient Vehicle Cycles and Their Potential for Predicting Fuel Consumption,” Vehicles, vol. 5, no. 2, pp. 583–604, May 2023, doi: 10.3390/vehicles5020032.
[39]D. M. Botín-Sanabria, A.-S. Mihaita, R. E. Peimbert-García, M. A. Ramírez-Moreno, R. A. Ramírez-Mendoza, and J. de J. Lozoya-Santos, “Digital Twin Technology Challenges and Applications: A Comprehensive Review,” Remote Sens (Basel), vol. 14, no. 6, p. 1335, Mar. 2022, doi: 10.3390/rs14061335.
[40]C. K. Lo, C. H. Chen, and R. Y. Zhong, “A review of digital twin in product design and development,” Advanced Engineering Informatics, vol. 48, Apr. 2021, doi: 10.1016/j.aei.2021.101297.
[41]D. J. Joshi, I. Kale, S. Gandewar, O. Korate, D. Patwari, and S. Patil, “Reinforcement Learning: A Survey,” in Advances in Intelligent Systems and Computing, vol. 1311 AISC, 2021, pp. 297–308. doi: 10.1007/978-981-33-4859-2_29.