Proceedings of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS)

DOI: http://dx.doi.org/10.15439/2025F7988

Citation: Proceedings of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS), M. Bolanowski, M. Ganzha, L. Maciaszek, M. Paprzycki, D. Ślęzak (eds). ACSIS, Vol. 43, pages 303–308 (2025)

Full text

Abstract. This paper presents an AI-based solution for automated parcel damage detection, combining machine learning algorithms with a custom-built mobile inspection robot. A mobile robot was designed and built specifically for this task, equipped with a vision system and sensing components. We developed a dataset of over 6,800 images and applied a tailored data augmentation process to better capture the variability found in operational environments. Our approach refines a YOLOv11n-cls-based model, achieving 98.50\\% accuracy, 97.\\% precision, and 99.74\\% recall on validation data. By optimizing the model for deployment on widely available hardware via CoreML, we reached inference speeds exceeding 251 FPS, ensuring rapid processing. An interactive dashboard was also created to monitor performance and facilitate comparisons between model iterations.

References

1. Damaged and intact packages. http://web.archive.org/web/20080207010024/http://www.808multimedia.com/winnt/kernel.htm, accessed: 2025-04-23
2. Alhas, O.B., et al.: Towards developing a cyber-physical warehouse system for automated order-picking. In: Annals of Computer Science and Information Systems, Volume 32. pp. 321–328 (2022). https://doi.org/10.15439/2022F208
3. Chaudhary, K., Singh, A.: Parcel damage classification using computer vision: A deep learning approach for shipment quality assessment. In: 2024 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI). vol. 2, pp. 1–6 (2024). https://doi.org/10.1109/IATMSI60426.2024.10503363
4. Gupta, M., Garg, N., Garg, J., Gupta, V., Gautam, D.: Designing an intelligent parcel management system using iot machine learning. In: 2022 IEEE IAS Global Conference on Emerging Technologies (GlobConET). pp. 751–756 (2022). https://doi.org/10.1109/GlobConET53749.2022.9872449
5. Hussain, M.: Yolo-v1 to yolo-v8, the rise of yolo and its complementary nature toward digital manufacturing and industrial defect detection. Machines 11(7) (2023). https://doi.org/10.3390/machines11070677, https://www.mdpi.com/2075-1702/11/7/677
6. Jocher, G., Qiu, J.: Ultralytics yolo11 (2024), https://github.com/ultralytics/ultralytics
7. Keith, R., La, H.M.: Review of autonomous mobile robots for the warehouse environment (2024), https://arxiv.org/abs/2406.08333
8. Mao, M., Hong, M.: Yolo object detection for real-time fabric defect inspection in the textile industry: A review of yolov1 to yolov11. Sensors (Basel) 25(7), 2270 (Apr 2025). https://doi.org/10.3390/s25072270
9. Martinez-Carranza, J., Rojas-Perez, L.O.: Warehouse inspection with an autonomous micro air vehicle. Unmanned Systems 10(04), 329–342 (2022). https://doi.org/10.1142/S2301385022410011
10. Moore, B.E., Corso, J.J.: Fiftyone. GitHub. Note: https://github.com/voxel51/fiftyone (2020)
11. Parikh, H., Saijwal, I., Panchal, N., Sharma, A.: Autonomous mobile robot for inventory management in retail industry. In: Singh, P.K., Wierzchoń, S.T., Chhabra, J.K., Tanwar, S. (eds.) Futuristic Trends in Networks and Computing Technologies. pp. 93–103. Springer Nature Singapore, Singapore (2022)
12. Sanchez-Cubillo, J., Del Ser, J., Martin, J.L.: Toward fully automated inspection of critical assets supported by autonomous mobile robots, vision sensors, and artificial intelligence. Sensors 24(12) (2024). https://doi.org/10.3390/s24123721, https://www.mdpi.com/1424-8220/24/12/3721
13. Sodiya, E.O., Umoga, U.J., Amoo, O.O., Atadoga, A.: Aidriven warehouse automation: A comprehensive review of systems. GSC Advanced Research and Reviews 18(2), 272–282 (2024). https://doi.org/10.30574/gscarr.2024.18.2.0063
14. Vu, T.T.H., Pham, D.L., Chang, T.W.: A yolo-based real-time packaging defect detection system. Procedia Computer Science 217, 886– 894 (2023). https://doi.org/10.1016/j.procs.2022.12.285, 4th International Conference on Industry 4.0 and Smart Manufacturing
15. Wu, W., Li, Q.: Machine vision inspection of electrical connectors based on improved yolo v3. IEEE Access 8, 166184–166196 (2020). https://doi.org/10.1109/ACCESS.2020.3022405
16. Xuan, O.W., Selamat, H., Muslim, M.T.: Autonomous mobile robot for transporting goods in warehouse and production. In: Tan, A., Zhu, F., Jiang, H., Mostafa, K., Yap, E.H., Chen, L., Olule, L.J.A., Myung, H. (eds.) Advances in Intelligent Manufacturing and Robotics. pp. 555–565. Springer Nature Singapore, Singapore (2024)