Mivar expert system for identifying challenging observation conditions and selecting image correction methods for a single-camera vision system of an autonomous delivery robot

The paper addresses the problem of intelligent decision support for the vision subsystem of a mobile autonomous delivery robot equipped with a single camera and operating under limited onboard computational resources without relying on cloud computing. The relevance of the study is determined by the degradation of image perception under insufficient illumination, overexposure, precipitation, haze, glare, digital noise, blur, partial occlusion, and lens contamination. A mivar expert system is proposed to formalize the domain knowledge in terms of parameters, relations, rules, and constraints. The user specifies 13 input parameters: ten normalized image features and three contextual attributes – location, time of day, and season. The system produces two semantically interpretable outputs: the current challenging observation condition and the recommended image enhancement action. A key feature of the model is its atomic relation structure: each relation contains no more than one conditional operator, while complex logic is represented as a chain of simple rules. Additional contextual service features are introduced to account for dense urban environment, nighttime city illumination, and seasonal effects when selecting the inference branch. A pretrained YOLO detector is used as the object recognition module, while the MES serves as an explainable and computationally efficient layer for interpreting challenging observation conditions. This combination makes the proposed approach suitable for local onboard deployment in an autonomous delivery robot. The obtained results confirm the feasibility of an explainable, modular, and extensible expert system for supporting a single-camera autonomous delivery robot under adverse observation conditions.

1. Shadrin S.S., Varlamov O.O., Ivanov A.M. Experimental autonomous road vehicle with logical artificial intelligence. Journal of Advanced Transportation. 2017;2017:2492765. https://doi.org/10.1155/2017/2492765

2. Varlamov O.O. "Brains" for Robots: Application of the Mivar Expert Systems for Implementation of Autonomous Intelligent Robots. Big Data Research. 2021;25:100241. https://doi.org/10.1016/j.bdr.2021.100241

3. Varlamov O., Aladin D. A New Generation of Rules-based Approach: Mivar-based Intelligent Planning of Robot Actions (MIPRA) and Brains for Autonomous Robots. Machine Intelligence Research. 2024;21(5):919–940. https://doi.org/10.1007/s11633-023-1473-1

4. Gong S. Mivar Decision-Making System for Distribution and Transportation of Cargo by a Team of Warehouse Robots. Management Systems and Information Technology. 2025;(2):23–29. (In Russ.).

5. Redmon J., Divvala S., Girshick R., et al. You Only Look Once: Unified, Real-Time Object Detection. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 27–30 June 2016, Las Vegas, NV, USA. IEEE; 2016. P. 779–788. https://doi.org/10.1109/CVPR.2016.91

6. Wang Ch.-Y., Bochkovskiy A., Liao H.-Y.M. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 17–24 June 2023, Vancouver, BC, Canada. IEEE; 2023. P. 7464–7475. https://doi.org/10.1109/CVPR52729.2023.00721

7. Michaelis C., Mitzkus B., Geirhos R., et al. Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming. arXiv. URL: https://doi.org/10.48550/arXiv.1907.07484 [Accessed 15th May 2026].

8. Bijelic M., Gruber T., Mannan F., et al. Seeing Through Fog Without Seeing Fog: Deep Multimodal Sensor Fusion in Unseen Adverse Weather. In: Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 13–19 June 2020, Seattle, WA, USA. IEEE; 2020. P. 11679–11689. https://doi.org/10.1109/CVPR42600.2020.01170

9. Sakaridis Ch., Dai D., Van Gool L. Semantic Foggy Scene Understanding with Synthetic Data. International Journal of Computer Vision. 2018;126(9):973–992. https://doi.org/10.1007/s11263-018-1072-8

10. He K., Sun J., Tang X. Single Image Haze Removal Using Dark Channel Prior. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2011;33(12):2341–2353. https://doi.org/10.1109/TPAMI.2010.168

11. Fu X., Huang J., Zeng D., et al. Removing Rain from Single Images via a Deep Detail Network. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 21–26 July 2017, Honolulu, HI, USA. IEEE; 2017. P. 1715–1723. https://doi.org/10.1109/CVPR.2017.186

12. Guo X. LIME: A Method for Low-light Image Enhancement. In: Proceedings of the 24th ACM International Conference on Multimedia, 15–19 October 2016, Amsterdam, The Netherlands. New York: ACM; 2016. P. 87–91. https://doi.org/10.1145/2964284.2967188

13. Shen Q., Gong Sh., Kotsenko A.A., et al. Algorithm for Dynamic Robot Trajectory Planning Based on Semantic Object Detection Using a Mivar Expert System. In: Proceedings of the 2025 7th International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE), 08–10 April 2025, Moscow, Russia. IEEE; 2025. https://doi.org/10.1109/REEPE63962.2025.10971158

14. Dou L., Varlamov O.O., Kotsenko A.A. A Multimodal Target Detection Method Based on the MES and the Improved BEV Perception Algorithm. In: Proceedings of the 2025 7th International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE), 08–10 April 2025, Moscow, Russia. IEEE; 2025. https://doi.org/10.1109/REEPE63962.2025.10970859

15. Aladin D.V., Varlamov O.O., Adamova L.E., et al. Control of vehicles and robots: creating of knowledge bases for mivar decision making systems robots and vehicles. In: IOP Conference Series: Materials Science and Engineering: Proceedings of the International Conference of Young Scientists and Students "Topical Problems of Mechanical Engineering" (ToPME-2019): Volume 747, 04–06 December 2019, Moscow, Russia. IOP Publishing; 2020. No. 012099. https://doi.org/10.1088/1757-899X/747/1/012099

16. Chuvikov D.A., Aladin D.V., Adamova L.E., et al. A new method for creating Mivar knowledge bases in tabular-matrix form for ground intelligent vehicle control systems. In: Journal of Physics: Conference Series: Proceedings of the International Conference on Actual Issues of Mechanical Engineering (AIME 2021): Volume 2061, 15–16 June 2021, Novorossiysk, Russia. IOP Publishing; 2021. No. 012123. https://doi.org/10.1088/1742-6596/2061/1/012123

17. Aladin D.V. Mivar knowledge base automatic generation method for solving management tasks in state space. Problems of Artificial Intelligence. 2025;(3):88–99. (In Russ.). https://doi.org/10.24412/2413-7383-2025-3-38-88-99

18. Dou L. Decision-making model for fire detection based on pattern recognition and mivar expert system. Management Systems and Information Technology. 2025;(3):59–65. (In Russ.).

19. Selvaraju R.R., Cogswell M., Das A., et al. Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. In: Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), 22–29 October 2017, Venice, Italy. IEEE; 2017. P. 618–626. https://doi.org/10.1109/ICCV.2017.74

20. Ribeiro M.T., Singh S., Guestrin C. "Why Should I Trust You?": Explaining the Predictions of Any Classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 13–17 August 2016, San Francisco, CA, USA. New York: ACM; 2016. P. 1135–1144. https://doi.org/10.1145/2939672.2939778

21. Lundberg S.M., Lee S.-I. A Unified Approach to Interpreting Model Predictions. In: Advances in Neural Information Processing Systems 30: Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), 04–09 December 2017, Long Beach, CA, USA. 2017. P. 4765–4774.

22. Doshi-Velez F., Kim B. Towards A Rigorous Science of Interpretable Machine Learning. arXiv. URL: https://doi.org/10.48550/arXiv.1702.08608 [Accessed 15th May 2026].

23. Mittal A., Moorthy A.K., Bovik A.C. No-reference image quality assessment in the spatial domain. IEEE Transactions on Image Processing. 2012;21(12):4695–4708. https://doi.org/10.1109/TIP.2012.2214050

24. Wang Zh., Bovik A.C., Sheikh H.R., et al. Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing. 2004;13(4):600–612. https://doi.org/10.1109/TIP.2003.819861

25. Jobson D.J., Rahman Z., Woodell G.A. A Multiscale Retinex for Bridging the Gap Between Color Images and the Human Observation of Scenes. IEEE Transactions on Image Processing. 1997;6(7):965–976. https://doi.org/10.1109/83.597272

26. Guo Ch., Li Ch., Guo J., et al. Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement. In: Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 13–19 June 2020, Seattle, WA, USA. IEEE; 2020. P. 1777–1786. https://doi.org/10.1109/CVPR42600.2020.00185

27. Zhang K., Zuo W., Chen Y., et al. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising. IEEE Transactions on Image Processing. 2017;26(7):3142–3155. https://doi.org/10.1109/TIP.2017.2662206

28. Nah S., Kim T.H., Lee K.M. Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 21–26 July 2017, Honolulu, HI, USA. IEEE; 2017. P. 257–265. https://doi.org/10.1109/CVPR.2017.35

29. Kupyn O., Budzan V., Mykhailych M., et al. DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks. In: Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 18–23 June 2018, Salt Lake City, UT, USA. IEEE; 2018. P. 8183–8192. https://doi.org/10.1109/CVPR.2018.00854

30. Ren W., Liu S., Zhang H., et al. Single Image Dehazing via Multi-scale Convolutional Neural Networks. In: Computer Vision – ECCV 2016: Proceedings of the 14th European Conference on Computer Vision: Part II, 11–14 October 2016, Amsterdam, The Netherlands. Cham: Springer; 2016. P. 154–169. https://doi.org/10.1007/978-3-319-46475-6_10

31. Zhang H., Patel V.M. Density-aware Single Image De-raining Using a Multi-stream Dense Network. In: Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 18–23 June 2018, Salt Lake City, UT, USA. IEEE; 2018. P. 695–704. https://doi.org/10.1109/CVPR.2018.00079

32. Tian Y., Ye Q., Doermann D. YOLOv12: Attention-Centric Real-Time Object Detectors. arXiv. URL: https://doi.org/10.48550/arXiv.2502.12524 [Accessed 15th May 2026].

33. Liu W., Anguelov D., Erhan D., et al. SSD: Single Shot MultiBox Detector. In: Computer Vision – ECCV 2016: Proceedings of the 14th European Conference on Computer Vision: Part I, 11–14 October 2016, Amsterdam, The Netherlands. Cham: Springer; 2016. P. 21–37. https://doi.org/10.1007/978-3-319-46448-0_2

34. Lin T.-Y., Goyal P., Girshick R., et al. Focal Loss for Dense Object Detection. In: Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), 22–29 October 2017, Venice, Italy. IEEE; 2017. P. 2999–3007. https://doi.org/10.1109/ICCV.2017.324

35. Hendrycks D., Dietterich Th.G. Benchmarking Neural Network Robustness to Common Corruptions and Perturbations. In: Proceedings of the 7th International Conference on Learning Representations (ICLR), 06–09 May 2019, New Orleans, LA, USA. 2019. URL: https://openreview.net/forum?id=HJz6tiCqYm