Dynamic Task Allocation, Ergonomic Optimization, and Zero-Defect Quality Assurance in Human–Robot Collaborative Assembly: A Systematic Review and Future Cyber-Physical Paradig

Author

N Govindh Rao, P. Dinesh, P. Jaya Krishna, S. Raj Kumari, L. Eswar Rao, M. Tharun

Abstract

 Human–Robot Collaboration (HRC) has emerged as the definitive cornerstone of the transition from rigid Industry 4.0 automation to adaptive, human-centric Industry 5.0 smart manufacturing. Conventional industrial assembly lines have long suffered from an acute operational dichotomy: fully manual assembly induces severe biomechanical fatigue and musculoskeletal disorders (MSDs), whereas hard-automated robotic cells lack the cognitive dexterity, tactile sensitivity, and contextual judgment required for high-mix, low-volume (HMLV) fabrication. This paper presents an exhaustive, state-of-the-art systematic review of modern HRC assembly systems, investigating the multi-disciplinary convergence of dynamic task allocation algorithms, ergonomic risk mitigation frameworks, and closed-loop zero-defect quality inspection. Synthesizing seventeen landmark research investigations spanning 2018 to 2026, this study provides a comprehensive taxonomy across five core technological pillars: (i) standardized complexity benchmarking and manual decomposition, (ii) bio-inspired hyper-heuristic optimization (QLHH-GA) and reinforcement learning for mixed-model line balancing, (iii) real-time human state monitoring utilizing physiological bio-signals and trust metrics, (iv) cloud-edge multi-sensor defect elimination integrating RGB-D vision and torque-angle telemetry with inference latency <45 ms, and (v) spatial Augmented Reality (AR) for interactive defect remediation. Quantitative meta-analysis reveals that dynamic adaptive allocation reduces overall assembly cycle times by up to 42.6%, lowers mean operator ergonomic postural risk (RULA/REBA) by >38.4% into safe action thresholds (score ≤ 3.0), and achieves defect classification accuracies exceeding 97.5% across automotive body-in-white (BIW), heavy bracket weldments, precision bolting, and mold handling. Critical implementation bottlenecks concerning edge latency, specular visual occlusion, and non-stationary operator stochasticity are identified, culminating in a forward-looking technological roadmap centered on Physics-Informed Neural Networks (PINNs), multimodal Foundation Models, and digital twin fleet orchestration.

Keywords

Human–Robot Collaboration (HRC), Dynamic Task Allocation, Zero-Defect Manufacturing (ZDM), Rapid Upper Limb Assessment (RULA), Q-Learning Hyper-Heuristic (QLHH-GA), Cloud-Edge Vision, Multi-Modal Trust, Industry 5.0.

Full Text:

Download Paper PDF

References

[1] L. Duarte, M. Neves, and P. Neto, 'Benchmarking human-robot collaborative assembly tasks,' Results in Engineering, vol. 22, p. 102042, Elsevier, 2024. DOI: 10.1016/j.rineng.2024.102042.

[2] Z. Liu et al., 'Assembly task allocation for human–robot collaboration considering stability and assembly complexity,' IEEE Access, vol. 12, pp. 154869-154881, 2024. DOI: 10.1109/ACCESS.2024.3486913.

[3] C. Petzoldt, D. Niermann, E. Maack, M. Sontopski, B. Vur, and M. Freitag, 'Implementation and evaluation of dynamic task allocation for human–robot collaboration in assembly,' Applied Sciences, vol. 12, no. 24, p. 12645, MDPI, 2022. DOI: 10.3390/app122412645.

[4] K. Brown, D. M. Asmar, M. Schwager, and M. J. Kochenderfer, 'Large-scale multi-robot assembly planning for autonomous manufacturing,' Robotics and Computer-Integrated Manufacturing, Elsevier, 2024.

[5] S. Kulaç, 'A Q-learning-based hyper-heuristic genetic algorithm for optimizing human–robot collaborative assembly lines,' Biomimetics, vol. 11, no. 4, p. 600, MDPI, 2026. DOI: 10.3390/biomimetics11040600.

[6] S. C. Akkaladevi, M. Plasch, S. Maddukuri, C. Eitzinger, A. Pichler, and B. Rinner, 'Toward an interactive reinforcement based learning framework for human robot collaborative assembly processes,' Frontiers in Robotics and AI, vol. 5, p. 126, 2018. DOI: 10.3389/frobt.2018.00126.

[7] M. Pantano, Q. Yang, A. Blumberg, R. Reisch, T. Hauser, B. Lutz, D. Regulin, T. Kamps, K. Traganos, and D. Lee, 'Influence of task decision autonomy on physical ergonomics and robot performances in an industrial human–robot collaboration scenario,' Frontiers in Robotics and AI, vol. 9, p. 943261, 2022. DOI: 10.3389/frobt.2022.943261.

[8] I. T. Freire, O. Guerrero-Rosado, A. F. Amil, and P. F. M. J. Verschure, 'Socially adaptive cognitive architecture for human-robot collaboration in industrial settings,' Frontiers in Robotics and AI, vol. 11, p. 1248646, 2024. DOI: 10.3389/frobt.2024.1248646.

[9] G. Campagna, D. Chrysostomou, and M. Rehm, 'A multi-modal model for trust evaluation in industrial human–robot collaboration,' Intelligent Service Robotics, vol. 19, p. 88, Springer, 2026. DOI: 10.1007/s11370-026-00730-5.

[10] L. Gualtieri, I. Palomba, F. A. Merati, and E. Rauch, 'Design of human-centered collaborative assembly workstations for the improvement of operators’ physical ergonomics and production efficiency: A case study,' Sustainability, vol. 12, no. 9, p. 3606, MDPI, 2020. DOI: 10.3390/su12093606.

[11] H. Karami, K. Darvish, and F. Mastrogiovanni, 'A task allocation approach for human-robot collaboration in product defects inspection scenarios,' in IEEE Sensors, pp. 1-8, 2023.

[12] A. Colim, R. Morgado, P. Carneiro, and N. Costa, 'Lean manufacturing and ergonomics integration: Defining productivity and wellbeing indicators in a human–robot workstation,' Sustainability, vol. 13, no. 4, p. 1931, MDPI, 2021. DOI: 10.3390/su13041931.

[13] H. Li, X. Wang, Y. Liu, G. Liu, Z. Zhai, X. Yan, H. Wang, and Y. Zhang, 'A novel robotic-vision-based defect inspection system for bracket weldments in a cloud–edge coordination environment,' Sustainability, vol. 15, no. 14, p. 10783, MDPI, 2023. DOI: 10.3390/su151410783.

[14] S. An, M. Xiao, D. Wang, Y. Qin, and B. Fu, 'Bolt installation defect detection based on a multi-sensor method,' Sensors, vol. 23, no. 9, p. 4386, MDPI, 2023. DOI: 10.3390/s23094386.

[15] Y. Yazid, A. Guerrero-González, A. El Oualkadi, and M. Arioua, 'Deep learning-empowered robot vision for efficient robotic grasp detection and defect elimination in Industry 4.0,' Engineering Proceedings, vol. 58, p. 63, MDPI, 2023. DOI: 10.3390/ecsa-10-16079.

[16] G. Margetis, K. Valakou, S. Ntoa, D. Gavgiotaki, and C. Stephanidis, 'Adaptive augmented reality user interfaces for real-time defect visualization and on-the-fly reconfiguration for zero-defect manufacturing,' Sensors, vol. 25, no. 9, p. 2789, MDPI, 2025. DOI: 10.3390/s25092789.

[17] S. R. S. et al., 'Task allocation in human-robot collaboration (HRC) based on ergonomic and productivity metrics in heavy mold assembly,' Procedia Manufacturing, vol. 51, pp. 179-186, Elsevier, 2020. DOI: 10.1016/j.promfg.2020.10.026.

 

 

Share your valuable work from Social Media Buttons