Authors : Shaikh Husain Bavasab; Raisul Hasan

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/yn5d2z38

Scribd : https://tinyurl.com/mpvhxb4c

DOI : https://doi.org/10.38124/ijisrt/26apr041

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Modern manufacturing facilities have robotic assembly systems that need high precision, flexibility, and durability to manage the changing operating environments. Control methods that are traditional, using fixed parameters, can often fail to ductilely control performance in the face of sensor noise, disturbances and environmental uncertainties. This paper does a performance analysis of an adaptive assembly system of a robot which combines sensor fusion and control enhanced with reinforcement learning. The sensor fusion system employs a Kalman filter-based sensor fusion system, which involves the fused data of both the vision and force sensors to provide precise state estimation. The PID controller is an adaptive controller under the control architecture with a reinforcement learning module to optimize control activities and enhance system adaptability. The experiments was carried out as simulation experiments within a MATLAB/Simulink environment (with a robotic manipulator model with disturbances like sensor noise and external factors). The suggested solution was tested using accuracy of the tracking of a trajectory, ability to reject disturbances and convergence of learning. Experimental findings indicate that the adaptive PID with the reinforcement learning is very effective in enhancing the tracking performance and disturbance recovery as opposed to the conventional PID which includes the use of a static PID and the adaptive PID. The results reveal the possibilities associated with the combination of sensor fusion and learning-based control to improve the reliability and efficiency of intelligent robotic assembly systems.

Keywords : Adaptive Robotics, Sensor Fusion, Reinforcement Learning, Industrial Automation, Robotic Assembly, Intelligent Manufacturing.

References :

1. Soori, M., Dastres, R., Arezoo, B. & Ghayour-Hosseinabadi, M. Intelligent robotic systems in Industry 40: A review. J. Adv. Manuf. Sci. Technol. 4(3), 2024007. https://doi.org/10.51393/j.jamst.2024007 (2024).
2. Dhanda, M., Rogers, B. A., Hall, S., Dekoninck, E. & Dhokia, V. Reviewing human-robot collaboration in manufacturing: Opportunities and challenges in the context of industry 5.0. Robot. Comput. Integr. Manuf. 93, 102937, (2025).
3. Soori, M., Arezoo, B. & Dastres, R. Substantial capabilities of robotics in enhancing industry 4.0 implementation. Cogn. Robot. 3, 58–75. https://doi.org/10.1016/j.cogr.2023.04.003 (2023).
4. Timothy, M. Robotic pick and pack sorting with computer vision. Roboflow Blog. (2025).
5. Chen, L., Wang, H., Zhang, Y. & Liu, X. Adaptive control algorithms for collaborative robotic systems in manufacturing environments. Int. J. Cogn. Comput. Eng. 6(2), 045–058. https://doi.org/10.1016/j.ijcce.2025.02.005 (2025).
6. Rigatos, G. G. Extended Kalman and particle filtering for sensor fusion in motion control of mobile robots. Math. Comput. Simul. 81(3), 590–607. https://doi.org/10.1016/j.matcom.2010.05.003 (2010).
7. Kumar, S., Patel, R., Thompson, A., & Rodriguez, M. Machine learning approaches for real-time collaborative robotics in Industry 4.0. In 2025 7th International Conference on Advanced Automation and Computing Engineering (ICAACE) 1–6 (IEEE, 2025). https://doi.org/10.1109/ICAACE65325.2025.11018968.
8. Singh, A., Brown, J., Lee, K. & Wilson, D. Edge computing integration for enhanced collaborative robot performance in smart manufacturing. Res. Eng. 19, 101346. https://doi.org/10.1016/j.rineng.2023.101346 (2023).
9. Liu, S., Liu, D., Srivastava, G., Polap, D. & Woźniak, M. Overview and methods of correlation filter algorithms in object tracking. Complex Intell. Syst. 7, 1895–1917. https://doi.org/10.1007/s40747-020-00161-4 (2021).
10. Carvalho, G., Cabral, F., Falcão, A. X. & Susano, M. Edge computing applications in industrial IoT: A literature review. Digit. Commun. Netw. 8(3), 360–382. https://doi.org/10.1016/j.dcan.2021.08.006 (2021).
11. Huang, Z. et al. Application of multi-sensor fusion localization algorithm based on recurrent neural networks. Sci. Rep. 15, 8195. https://doi.org/10.1038/s41598-025-90492-4 (2025).
12. Mao, Q., Liao, Z., Yuan, J. & Zhu, R. Multimodal tactile sensing fused with vision for dexterous robotic housekeeping. Nat. Commun. 15, 6871. https://doi.org/10.1038/s41467-024-51261-5 (2024).
13. Duan, H., Li, Y., Shao, K., Zhao, Y. & Wang, X. Multimodal sensors and ML-based data fusion for advanced robots. Adv. Intell. Syst. 4(10), 2200213. https://doi.org/10.1002/aisy.202200213 (2022).
14. García-Martínez, J. R., Cruz-Miguel, E. E., Carrasco-Ochoa, J. A. & Martínez-Trinidad, J. F. A comparative review on multi-modal sensors fusion based on deep learning. J. Vis. Commun. Image Represent. 95, 103896. https://doi.org/10.1016/j.jvcir.2023.103896 (2023).
15. Srivastava, P. et al. Multi-sensor fusion and segmentation for autonomous vehicle multi-object tracking using deep Q networks. Sci. Rep. 14, 31130. https://doi.org/10.1038/s41598-024-82356-0 (2024).
16. Zhou, H. et al. Deep multimodal data fusion. ACM Comput. Surv. 57(4), 1–36. https://doi.org/10.1145/3649447 (2024).
17. Timothy, M. Automated sorting with computer vision. Roboflow Blog. (2024).
18. Sani, D., Iyer, A. R., Rai, P., Anand, S., Srivastava, A. & Kalyanaraman, K. Sensor-agnostic graph-aware Kalman filter for multi-modal multi-object tracking. In Proceedings of the 27th International Conference on Pattern Recognition (2024).
19. Voltactive Data. How edge and industrial IoT will converge in 2025: A new era for smart manufacturing. Voltactive Data Blog. (2024).
20. 5G Hub Technologies. Edge computing in IIoT: Enhancing real-time data processing. 5G Hub Technologies. (2023).
21. Edge AI and Vision Alliance. Optimizing edge AI for effective real-time decision making in robotics. Edge AI and Vision Alliance. (2025).
22. Roman, R.-C., Precup, R.-E., Petriu, E. M. & Borlea, A.-I. Hybrid data-driven active disturbance rejection sliding mode control with tower crane systems validation. Roman. J. Inf. Sci. Technol. 27(1), 50–64. https://doi.org/10.59277/ROMJIST.2024.1.04 (2024).
23. Kholodilin, I., Zhang, Z., Guo, Q., Chen, L. & Xu, K. Calibration of the omnidirectional vision system for robotics sorting system. Sci. Rep. 15, 10256. https://doi.org/10.1038/s41598-025-94723-6 (2025).
24. Standard Bots. How sorting robots improve efficiency & accuracy in 2025. Standard Bots Blog. (2025).
25. Dewesoft. What is sensor fusion? Dewesoft Blog. https://dewesoft.com/blog/what-is-sensor-fusion (2025).
26. Zouari, F., Boulkroune, A., Ibeas, A. & Arefi, M. M. Observer-based adaptive neural network control for a class of MIMO uncertain nonlinear time-delay non-integer-order systems with asymmetric actuator saturation. Neural Comput. Appl. 28(Suppl 1), 993–1010. https://doi.org/10.1007/s00521-016-2369-6 (2017).
27. Khan, A., Abdeljawad, T. & Thinakaran, R. Computational analysis by artificial intelligence of the fractional-order plant virus spread model. Fractals 33(4), 2540141. https://doi.org/10.1142/S0218348X25401413 (2025).
28. Khan, A., Abdeljawad, T. & Alkhawar, H. M. Digital analysis of discrete fractional order worms transmission in wireless sensor systems: Performance validation by artificial intelligence. Model. Earth Syst. Environ. 11, 25. (2025).
29. Business Wire. Edge AI market research report 2025. ResearchAndMarkets.com.
30. Automation.com. Edge computing adoption in IIoT. Automation.com.