Counterfactual Digital Twin: A Robust Optimization Approach for Automated Warehouses Facing Unknown Shocks
1. College of Earthquake Engineering and Architectural Safety, University of Emergency Management, Langfang 065201, China
2. Technical Department, CITIC Press Corporation Limited, Beijing 100020, China
| Abstract: | Digital twin technology provides decision support by simulating warehouse operations. Traditional approaches, however, rely on historical data to predict the future—once an extreme situation that has never occurred in history emerges (e.g., sudden order surges or simultaneous failures of multiple AGVs), the model fails. This paper proposes a counterfactual digital twin framework that proactively "imagines" various extreme scenarios within the twin model—even combinations that have never occurred in reality—and trains the decision model to learn how to respond in these "virtual extremes." This is analogous to pilots practicing engine failures in simulators rather than waiting to face them during actual flights. A warehouse model is constructed using discrete-event simulation with Python and SimPy. Experimental results show that strategies trained with counterfactual data achieve decision accuracy improved from approximately 50% to over 85%, order completion time reduced by 14%–25%, and performance degradation decreased by 43%–86% when facing unknown shocks. This paper provides a new paradigm for digital twins to transition from "passive prediction" to "proactive preparation". |
| Keywords: | Counterfactual Learning; Digital Twin; Automated Warehouse; Robust Optimization; Decision-making Under Uncertainty |
| DOI: | 10.57237/j.wjmst.2026.02.002 |
View:
Downloads:
Received: 19 June 2026
Accepted: 21 July 2026
Published Online: 5 August 2026
References
| [1] | Pearl J. Causality: Models, reasoning, and inference [M]. 2nd ed. Cambridge: Cambridge University Press, 2009. |
| [2] | Bareinboim E, Pearl J. Causal inference and the data-fusion problem [J]. Proceedings of the National Academy of Sciences, 2016, 113(27): 7345-7352. https://doi.org/10.1073/pnas.1510507113 |
| [3] | Peters J, Janzing D, Schölkopf B. Elements of causal inference: Foundations and learning algorithms [M]. Cambridge: MIT Press, 2017. |
| [4] | Tao F, Zhang M, Nee A Y C. Digital twin driven smart manufacturing [M]. London: Academic Press, 2019. |
| [5] | Tao F, Zhang H, Liu A, et al. Digital twin in industry: State-of-the-art [J]. IEEE Transactions on Industrial Informatics, 2018, 15(4): 2405-2415. https://doi.org/10.1109/TII.2018.2873186 |
| [6] | Kritzinger W, Karner M, Traar G, et al. Digital Twin in manufacturing: A systematic literature review [J]. IFAC-PapersOnLine, 2018, 51(11): 1016-1022. https://doi.org/10.1016/j.ifacol.2018.08.474 |
| [7] | Gu J, Goetschalckx M, McGinnis L F. Research on warehouse operation: A comprehensive review [J]. European Journal of Operational Research, 2007, 177(1): 1-21. https://doi.org/10.1016/j.ejor.2006.02.025 |
| [8] | de Koster R, Le-Duc T, Roodbergen K J. Design and control of warehouse order picking: A literature review [J]. European Journal of Operational Research, 2007, 182(2): 481-501. https://doi.org/10.1016/j.ejor.2006.07.009 |
| [9] | Boysen N, de Koster R, Weidinger F. Warehousing in the e-commerce era: A survey [J]. European Journal of Operational Research, 2019, 277(2): 396-411. https://doi.org/10.1016/j.ejor.2018.08.023 |
| [10] | Banks J, Carson J S, Nelson B L, et al. Discrete-event system simulation [M]. 5th ed. Upper Saddle River: Pearson, 2010. |
| [11] | Law A M. Simulation modeling and analysis [M]. 5th ed. New York: McGraw-Hill, 2015. |
| [12] | Ross S M. Simulation [M]. 5th ed. Amsterdam: Elsevier, 2013. |
| [13] | Chopra S, Meindl P. Supply chain management: Strategy, planning, and operation [M]. 7th ed. London: Pearson, 2019. |
| [14] | Muller S, Bruns R. A cost-benefit analysis framework for digital twin implementation in logistics [J]. International Journal of Production Research, 2021, 59(12): 3668-3687. |
| [15] | Rashedi R, Heidari M A. Counterfactual learning for robust inventory management [J]. European Journal of Operational Research, 2022, 301(2): 567-580. https://doi.org/10.1016/j.ejor.2021.11.028 |
Join the Editorial Board
We invite active, qualified and high profile scientists and researchers to join as Editorial Board Members.
Join UsBecome a Reviewer
Scholars with a strong interest in reviewing are invited to join the reviewer panel to ensure the quality of the research to be published.
Join Us