PDF (4.3 MB)
Collect
Submit Manuscript
Research Article | Open Access | Online First

Safety-oriented human–robot collaboration in construction through human preference alignment

Mao TianZhengbo Zou()
Department of Civil Engineering, The University of British Columbia, Vancouver V6T 1Z4, Canada
Present address: Department of Civil Engineering and Engineering Mechanics, Columbia University, New York 10025, USA
Show Author Information

Abstract

Construction faces significant challenges, including high incident rates and shortage of skilled labor. With the sector’s increasing willingness to integrate robotics to improve productivity, this paper addresses the emerging safety challenges in human–robot collaboration (HRC). We present a novel approach that leverages human feedback regarding robot behaviors to define safety-oriented control actions. By training a preference prediction model with human input, we demonstrate the effectiveness of our approach in guiding robots towards safer behaviors in complex construction tasks. The approach begins with designing an online labeling tool tailored for collecting human preference data regarding robot behaviors in collaborative tasks. A score model is then trained to enable prioritization of safer robot behaviors. Finally, safety-oriented robot behaviors can be inferred. This research underscores the importance of aligning construction robot behaviors with human preferences, offering a scalable solution to enhance occupational safety for construction.

References

[1]
F. Barbosa, J. Woetzel, J. Mischke, et al. Reinventing Construction: A Route to Higher Productivity. New York, USA: McKinsey & Company, 2017.
[2]
S. Abdalla, S. S. Apramian, L. F. Cantley, et al. Occupation and risk for injuries. In: Injury Prevention and Environmental Health, 3rd ed. C. N. Mock, R. Nugent, O. Kobusingye, et al., Eds. Washington, USA: The World Bank, 2017.
[3]
O. M. Aroke. Measuring attention, working memory and visual perception to reduce the risk of injuries in the construction industry. Ph.D. Thesis, Fairfax, USA: George Mason University, 2022.
[4]

A. Albert, B. Pandit, Y. Patil. Focus on the fatal-four: Implications for construction hazard recognition. Saf Sci, 2020, 128: 104774.

[5]

A. H. Hilmi, A. R. Hamid. Musculoskeletal disorders: Industrial insights and ergonomic interventions. Malays J Ergon, 2023, 5: 61–78.

[6]

N. Melenbrink, J. Werfel, A. Menges. On-site autonomous construction robots: Towards unsupervised building. Autom Constr, 2020, 119: 103312.

[7]

T. Bock. The future of construction automation: Technological disruption and the upcoming ubiquity of robotics. Autom Constr, 2015, 59: 113–121.

[8]

J. M. D. Delgado, L. Oyedele, A. Ajayi, et al. Robotics and automated systems in construction: Understanding industry-specific challenges for adoption. J Build Eng, 2019, 26: 100868.

[9]

A. Chibani, Y. Amirat, S. Mohammed, et al. Ubiquitous robotics: Recent challenges and future trends. Robot Auton Syst, 2013, 61: 1162–1172.

[10]
J. Schmidtler, A. Sezgin, T. Illa, et al. Black or white? Influence of robot arm contrast on distraction in human–robot interaction. In: Proceedings of the 12th International Conference on Engineering Psychology and Cognitive Ergonomics, Los Angeles, USA, 2015: pp 188–199.
[11]

M. Safeea, P. Neto, R. Bearee. On-line collision avoidance for collaborative robot manipulators by adjusting off-line generated paths: An industrial use case. Robot Auton Syst, 2019, 119: 278–288.

[12]
ISO/TS 15066: 2016. Robots and robotic devices—Collaborative robots. ISO, Switzerland, 2016.
[13]

P. Chemweno, L. Pintelon, W. Decre. Orienting safety assurance with outcomes of hazard analysis and risk assessment: A review of the ISO 15066 standard for collaborative robot systems. Saf Sci, 2020, 129: 104832.

[14]
R. Inam, K. Raizer, A. Hata, et al. Risk assessment for human–robot collaboration in an automated warehouse scenario. In: Proceedings of the 2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA), Turin, Italy, 2018: pp 743–751.
[15]

L. F. González-Böhme, E. Valenzuela-Astudillo. Mixed reality for safe and reliable human–robot collaboration in timber frame construction. Buildings, 2023, 13: 1965.

[16]

S. You, J. H. Kim, S. H. Lee, et al. Enhancing perceived safety in human–robot collaborative construction using immersive virtual environments. Autom Constr, 2018, 96: 161–170.

[17]

Y. Sun, I. Jeelani, M. Gheisari. Safe human–robot collaboration in construction: A conceptual perspective. J Saf Res, 2023, 86: 39–51.

[18]

A. C. Bavelos, E. Anastasiou, N. Dimitropoulos, et al. Virtual reality‐based dynamic scene recreation and robot teleoperation for hazardous environments. Comput Aided Civil Infrastruct Eng, 2025, 40: 392–408.

[19]

A. C. Bavelos, E. Anastasiou, N. Dimitropoulos, et al. Augmented reality‐based method for road maintenance operators in human–robot collaborative interventions. Comput Aided Civil Infrastruct Eng, 2024, 39: 1077–1095.

[20]

M. Zhang, R. Xu, H. T. Wu, et al. Human–robot collaboration for on-site construction. Autom Constr, 2023, 150: 104812.

[21]

R. M. Molfino, M. Zoppi. A robotic system for underwater eco-sustainable wire-cutting. Autom Constr, 2012, 24: 213–223.

[22]

R. M. Molfino, R. P. Razzoli, M. Zoppi. Autonomous drilling robot for landslide monitoring and consolidation. Autom Constr, 2008, 17: 111–121.

[23]

Q. H. Le, J. W. Lee, S. Y. Yang. Remote control of excavator using head tracking and flexible monitoring method. Autom Constr, 2017, 81: 99–111.

[24]
L. Prasch, F. Top, J. Schmidtler, et al. User-centered interface design and evaluation for teleoperated cranes with boom tip control. In: Proceedings of the 19th International Conference on Engineering Psychology and Cognitive Ergonomics. Online, 2022: pp 189–211.
[25]

T. Y. Zhou, Q. Zhu, J. Du. Intuitive robot teleoperation for civil engineering operations with virtual reality and deep learning scene reconstruction. Adv Eng Inf, 2020, 46: 101170.

[26]

L. Yang, Y. H. Liu, J. Z. Peng. Advances techniques of the structured light sensing in intelligent welding robots: A review. Int J Adv Manuf Technol, 2020, 110: 1027–1046.

[27]

S. Y. Chen, D. T. Stevenson, S. Y. Yu, et al. Wearable knee assistive devices for kneeling tasks in construction. IEEE/ASME Trans Mechatron, 2021, 26: 1989–1996.

[28]

M. S. Gil, M. S. Kang, S. Lee, et al. Installation of heavy duty glass using an intuitive manipulation device. Autom Constr, 2013, 35: 579–586.

[29]

Y. Ye, T. Y. Zhou, J. Du. Robot-assisted immersive kinematic experience transfer for welding training. J Comput Civ Eng, 2023, 37: 04023002.

[30]

B. Xiao, C. Chen, X. F. Yin. Recent advancements of robotics in construction. Autom Constr, 2022, 144: 104591.

[31]

J. N. Cai, A. Du, X. Y. Liang, et al. Prediction-based path planning for safe and efficient human–robot collaboration in construction via deep reinforcement learning. J Comput Civ Eng, 2023, 37: 04022046.

[32]
R. Mahbub. An investigation into the barriers to the implementation of automation and robotics technologies in the construction industry. Ph.D. Thesis, Brisbane, Australia: Queensland University of Technology, 2008.
[33]

T. Y. Zhou, Q. Zhu, Y. M. Shi, et al. Construction robot teleoperation safeguard based on real-time human hand motion prediction. J Constr Eng Manage, 2022, 148: 04022040.

[34]

A. Vysocky, P. Novak. Human–robot collaboration in industry. MM Sci J, 2016, 2016: 903–906.

[35]

P. Salvini, D. Paez-Granados, A. Billard. Safety concerns emerging from robots navigating in crowded pedestrian areas. Int J Soc Robot, 2022, 14: 441–462.

[36]

C. Feng, Y. Xiao, A. Willette, et al. Vision guided autonomous robotic assembly and as-built scanning on unstructured construction sites. Autom Constr, 2015, 59: 128–138.

[37]
M. Vasic, A. Billard. Safety issues in human–robot interactions. In: Proceedings of the 2013 IEEE International Conference on Robotics and Automation, Karlsruhe, Germany, 2013: pp 197–204.
[38]
A. de Luca, F. Flacco. Integrated control for pHRI: Collision avoidance, detection, reaction and collaboration. In: Proceedings of the 2012 4th IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob), Rome, Italy, 2012: pp 288–295.
[39]

Y. Ye, H. X. You, J. Du. Improved trust in human–robot collaboration with ChatGPT. IEEE Access, 2023, 11: 55748–55754.

[40]
E. Gambao, M. Hernando, D. Surdilovic. A new generation of collaborative robots for material handling. In: Proceedings of the International Symposium on Automation and Robotics in Construction, Eindhoven, Netherlands, 2012.
[41]

A. Leite, A. Pinto, A. Matos. A safety monitoring model for a faulty mobile robot. Robotics, 2018, 7: 32.

[42]

H. Rajnathsing, C. G. Li. A neural network based monitoring system for safety in shared work-space human–robot collaboration. Ind Robot, 2018, 45: 481–491.

[43]

P. Karagiannis, N. Kousi, G. Michalos, et al. Adaptive speed and separation monitoring based on switching of safety zones for effective human robot collaboration. Robot Comput Integr Manuf, 2022, 77: 102361.

[44]

S. Park, H. R. Yu, C. C. Menassa, et al. A comprehensive evaluation of factors influencing acceptance of robotic assistants in field construction work. J Manage Eng, 2023, 39: 04023010.

[45]
A. Khalid, P. Kirisci, Z. Ghrairi, et al. Safety requirements in collaborative human–robot cyber-physical system. In: Proceedings of the 5th International Conference on Dynamics in Logistics, Bremen, Germany, 2017: pp 41–51.
[46]

F. Bonnin-Pascual, A. Ortiz. On the use of robots and vision technologies for the inspection of vessels: A survey on recent advances. Ocean Eng, 2019, 190: 106420.

[47]

I. Okpala, C. Nnaji, J. Gambatese. Assessment tool for human–robot interaction safety risks during construction operations. J Constr Eng Manage, 2023, 149: 04022145.

[48]

Y. Z. Liu, M. Habibnezhad, H. Jebelli. Brainwave-driven human–robot collaboration in construction. Autom Constr, 2021, 124: 103556.

[49]

O. Kroemer, S. Niekum, G. Konidaris. A review of robot learning for manipulation: Challenges, representations, and algorithms. J Mach Learn Res, 2021, 22: 30.

[50]
J. E. Grunig. The Role of Information in Economic Decision Making. Madison, USA: University of Wisconsin, 1966.
[51]

D. T. Kenrick, V. Griskevicius, J. M. Sundie, et al. Deep rationality: The evolutionary economics of decision making. Soc Cognit, 2009, 27: 764–785.

[52]

F. R. Johnson, E. Lancsar, D. Marshall, et al. Constructing experimental designs for discrete-choice experiments: Report of the ISPOR conjoint analysis experimental design good research practices task force. Value Health, 2013, 16: 3–13.

[53]
J. Fürnkranz, E. Hüllermeier. Preference learning and ranking by pairwise comparison. In: Preference Learning. J. Fürnkranz, E. Hüllermeier, Eds. Berlin, Germany: Springer, 2011: pp 65–82.
[54]

G. O. Odu. Weighting methods for multi-criteria decision making technique. J Appl Sci Environ Manage, 2019, 23: 1449–1457.

[55]

Y. M. Ying, D. X. Zhou. Online pairwise learning algorithms. Neural Comput, 2016, 28: 743–777.

[56]
P. F. Christiano, J. Leike, T. B. Brown, et al. Deep reinforcement learning from human preferences. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, USA, 2017: pp 4302–4310.
[57]
C. J. C. Burges. From RankNet to LambdaRank to LambdaMART: An Overview. Redmond, USA: Microsoft Research, 2010: pp 1–19.
[58]

Q. Sun, B. Pfahringer. Pairwise meta-rules for better meta-learning-based algorithm ranking. Mach Learn, 2013, 93: 141–161.

[59]

C. L. Dym, W. H. Wood, M. J. Scott. Rank ordering engineering designs: Pairwise comparison charts and Borda counts. Res Eng Des, 2002, 13: 236–242.

[60]
D. G. Saari. The Optimal Ranking Method is the Borda Count. Evanston, USA: Northwestern University, 1985.
[61]

N. B. Shah, M. J. Wainwright. Simple, robust and optimal ranking from pairwise comparisons. J Mach Learn Res, 2017, 18: 7246–7283.

[62]

P. Sedgwick. Spearman’s rank correlation coefficient. BMJ, 2014, 349: g7327.

[63]
Ufactory. xArm user manual-software section [Online]. https://www.ufactory.cc/wp-content/uploads/2023/05/xArm-User-Manual-V2.0.0.pdf (accessed 2024-01-06
[64]
C. Lugaresi, J. Q. Tang, H. Nash, et al. MediaPipe: A framework for building perception pipelines. 2019, arXiv: 1906.08172. arXiv.org e-print archive. https://arxiv.org/abs/1906.08172 (accessed 2024-01-06
[65]

S. I. Amari. Backpropagation and stochastic gradient descent method. Neurocomputing, 1993, 5: 185–196.

[66]

L. Qian, J. Y. Gao, H. V. Jagadish. Learning user preferences by adaptive pairwise comparison. Proc VLDB Endow, 2015, 8: 1322–1333.

Journal of Intelligent Construction
Cite this article:
Tian M, Zou Z. Safety-oriented human–robot collaboration in construction through human preference alignment. Journal of Intelligent Construction, 2025, https://doi.org/10.26599/JIC.2025.9180092
Metrics & Citations  
Article History
Copyright
Rights and Permissions
Return