Machine Learning-Based Cost Optimization and Investment Decision Support for Human-Robot Collaborative Construction Operations
Keywords:
human-robot collaboration; construction cost estimation; probabilistic machine learning; stochastic optimization; real options; investment decision supportAbstract
Human-robot collaborative construction operations can improve productivity and safety, but their economics are difficult to evaluate because task durations, labor substitution, safety clearances, and technology prices are uncertain and interdependent. Existing cost-estimation models rarely connect probabilistic machine-learning forecasts to the discrete choice of robot configurations and the timing of partially irreversible investment. This manuscript develops a decision-support framework that links three components: a hierarchical probabilistic learner that predicts task-level cost and duration distributions from project, crew, site, and robot features; a stochastic mixed-integer cost-optimization model that selects collaborative configurations and task allocations under joint cycle-time and safety chance constraints; and a real-option investment rule that values staged adoption and deferral. The framework treats forecasts as distributions rather than point estimates, propagates predictive uncertainty into the cost objective, and separates technical feasibility from economic acceptability. Analytically, the formulation shows why point-estimate cost comparisons can reverse configuration rankings when variance and safety constraints differ, and why waiting has value when robot prices, wage rates, or task-mix conditions are volatile. The contribution is a coherent, auditable decision architecture rather than a claim of field performance. It helps construction firms, robotics vendors, and project planners align prediction, scheduling, and capital allocation, and it identifies where calibration, distribution-shift monitoring, and human oversight assumptions matter most.
References
1. Bock, T. (2007). Construction robotics. Autonomous Robots, 22(3), 201–210.
2. Davila Delgado, J. M., Oyedele, L., Ajayi, A., Akanbi, L., Akinade, O., Bilal, M., & Owolabi, H. (2019). Robotics and automated systems in construction: Understanding industry-specific challenges for adoption. Journal of Building Engineering, 26, 100868.
3. You, S., Kim, J. H., Lee, S., Kamat, V., & Robert, L. P. (2018). Enhancing perceived safety in human–robot collaborative construction using immersive virtual environments. Automation in Construction, 96, 161–170.
4. Kim, G. H., An, S. H., & Kang, K. I. (2004). Comparison of construction cost estimating models based on regression analysis, neural networks, and case-based reasoning. Building and Environment, 39(10), 1235–1242.
5. Gondia, A., Siam, A., El-Dakhakhni, W., & Nassar, A. H. (2020). Machine learning algorithms for construction projects delay risk prediction. Journal of Construction Engineering and Management, 146(1), 04019085.
6. Dixit, A. K., & Pindyck, R. S. (1994). Investment under uncertainty. Princeton University Press.
7. Trigeorgis, L. (1996). Real options: Managerial flexibility and strategy in resource allocation. MIT Press.
8. Luo, D., & Yu, L. (2021). From factory to site—designing for industrial robots used in on-site construction. In Automating cities: design, construction, operation and future impact (pp. 87-109). Singapore: Springer Singapore.
9. Bock, T., & Linner, T. (2016). Construction robots: Elementary technologies for offsite and onsite automation. Cambridge University Press.
10. Birge, J. R., & Louveaux, F. (2011). Introduction to stochastic programming. Springer.
11. Bertsimas, D., & Sim, M. (2004). The price of robustness. Operations Research, 52(1), 35–53.
12. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
13. Lakshminarayanan, B., Pritzel, A., & Blundell, C. (2017). Simple and scalable predictive uncertainty estimation using deep ensembles. In Advances in Neural Information Processing Systems (Vol. 30, pp. 6402–6413).
14. Gal, Y., & Ghahramani, Z. (2016). Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. In Proceedings of the 33rd International Conference on Machine Learning (pp. 1050–1059).
15. Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning: Data mining, inference, and prediction (2nd ed.). Springer.
16. McDonald, R., & Siegel, D. (1986). The value of waiting to invest. Quarterly Journal of Economics, 101(4), 707–727.
17. Shapiro, A., Dentcheva, D., & Ruszczyński, A. (2009). Lectures on stochastic programming: Modeling and theory. SIAM.
18. Ben-Tal, A., El Ghaoui, L., & Nemirovski, A. (2009). Robust optimization. Princeton University Press.
19. Koller, D., & Friedman, N. (2009). Probabilistic graphical models: Principles and techniques. MIT Press.
20. Elfaki, A. O., Alatawi, S., & Abushandi, E. (2014). Using intelligent techniques in construction project cost estimation: 10-year survey. Advances in Civil Engineering, 2014, 107926.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Global Financial Analytics Research Review

This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.



