Modified SLAM for Agricultural Robot Navigation

The study proposes a novel method for reconstructing missing regions in depth maps, aimed at improving the accuracy of autonomous navigation in agricultural robotic systems. (Research purpose) The primary objective is to develop a method capable of compensating for data loss in depth maps, thereby improving the performance of Simultaneous Localization and Mapping (SLAM) systems. (Materials and methods) The depth map reconstruction method consists of three main stages: computation of the anisotropic gradient; identification of similar blocks based on a novel similarity criterion; and merging of the detected blocks using a neural network architecture composed of an encoder, a fusion layer, and a decoder. The method was tested using the Rosario dataset, which includes scenarios representative of complex agricultural environments. (Results and discussion) The proposed depth map reconstruction method demonstrates a significant improvement in quality metrics. Specifically, Root Mean Square Error (RMSE), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index Measure (SSIM) improved by 20–30 percent compared to the existing techniques. The method preserves the structure and texture features of the reconstructed regions, enabling accurate restoration of large areas with missing pixel data. To evaluate the impact on SLAM performance, the Stereo Multi-State Constraint Kalman Filter (S-MSCKF) algorithm was employed. Quantitative analysis of Absolute Trajectory Error (ATE) and mean RMSE was conducted both before and after applying the depth map reconstruction. The results show a reduction in Absolute Trajectory Error from 0.62 meters to 0.25 meters, and a decrease in Root Mean Square Error from 0.85 meters to 0.39 meters. (Conclusions) The proposed method substantially enhances SLAM system accuracy, particularly in challenging agricultural environments, characterized by uneven terrain, variable lighting conditions, and long-distance navigation. Its robust performance suggests strong potential for large-scale integration into autonomous agricultural machinery, contributing to improved reliability, operational efficiency, and safety in robotic field operations.

1. Izmaylov А.Yu., Lobachevsky Ya.Р., Tsench Yu.S. et al. About synthesis of robotic agriculture mobile machine. Vestnik of the Russian Agricultural Science. 2019. N4. 6368 (In Russian). DOI: 10.30850/vrsn/2019/4/63-68.

2. Smirnov I.G., Khort D.O., Kutyrev A.I. Intelligent technologies and robotic machines for cultivating horticultu­ral crops. Agricultural Machinery and Technologies. 2021. Vol. 15. N4. 35-41 (In Russian). DOI: 10.22314/2073-7599-2021-15-4-35-41.

3. Tsench Yu.S., Kurbanov R.K., Zakharova N.I. Evolution of flight control systems and aerial photography in unmanned agricultural aircraft. Agricultural Machinery and Technologies. 2024. Vol. 18. N2. 11-19 (In Russian). 10.22314/2073-7599-2024-18-2-11-19.DOI: 10.22314/2073-7599-2024-18-2-11-19. EDN: JPLEGX

4. Smirnov I.G., Dyshekov A.I., Devyatkin F.V. Operation algorithm for the autonomous robotic weed monitoring system. Electrical Engineering and Electrical Equipment in Agriculture. 2024. Vol. 71. N1(54). 71-75 (In Russian). DOI: 10.22314/2658-4859-2024-71-1-71-75.

5. Zelensky A.A., Gapon N.V., Zhdanova M.M. et al. Depth map reconstruction method in control problems for robots and mechatronic systems. Mechatronics, Automation, Control. 2022. Vol. 23. N2. 104-112 (In Russian). DOI: 10.17587/mau.23.104-112.

6. Pavlov A.S. Methodology for planning the trajectory of a group of mobile robots in unknown closed environment with obstacles. Systems of Control, Communication and Security. 2021. N3. 38-59 (In Russian). DOI: 10.24412/2410-9916-2021-3-38-59.

7. Teterev A.V. Rationale for the choice of a positioning system for mobile agricultural robot movement controlling. Agricultural Machinery and Technologies. 2020. Vol. 14. N4. 63-70 (In Russian). DOI: 10.22314/2073-7599-2020-14-4-63-70.

8. Kutyrev A.I., Dyshekov A.I. Development a motion control system for a robotic platform based on laser ranging methods (LiDAR). Agricultural Engineering. 2023. Vol. 25. N2. 19-27 (In Russian). DOI: 10.26897/2687-1149-2023-2-19-27.

9. Panetta K., Sanghavi F., Agaian S., Madan N. Automated detection of COVID-19 cases on radiographs using shape-­dependent Fibonacci-p patterns. IEEE Journal of Biomedical and Health Informatics. 2021. Vol. 25. N6. 1852-1863 (In English). DOI: 10.1109/JBHI.2021.3069798.

10. Yang S., Liang H., Wang Y. et al. Image inpainting based on multi-patch match with adaptive size. Applied Scien­ces. 2020. Vol. 10. N14. 4921 (In English). DOI: 10.3390/app10144921.

11. Voronin V., Gapon N., Khamidullin I. et al. A vision system using depth inpainting for virtual content reconstruction in Augmented Reality. ProcSPIE. 2022. Vol. 12275. 146-156 (In English). DOI: 10.1117/12.2642007.

12. Podtikhov A.V., Saveliev A.I. Open dataset for testing of Visual SLAM algorithms under different weather conditions. Proceedings of Telecommun. Univ. 2024. Vol. 10. N1. 97-106 (In Russian). DOI: 10.31854/1813-324X-2024-10-1-97-106.

13. Kim H., Kim C., Kim H. et. al. Panoptic blind image inpainting. ISA transactions. 2023. Vol. 132. 208-221 (In Eng­lish). DOI: 10.1016/j.isatra.2022.10.030.

14. Zhang Z., Dong P., Wan, J., Sun Y. Improving S-MSCKF with variational Bayesian adaptive nonlinear filter. IEEE Sensors Journal. 2020. Vol. 20. N16. 9437-9448 (In English). DOI: 10.1109/jsen.2020.2989206.

15. Bokovoy A.V., Muraviev K.F., Yakovlev K.S. Vision-based simultaneous localization, mapping and exploration system. Journal of Information Technologies and Computation Systems. 2020. N2. 51-61 (In Russian). DOI: 10.14357/20718632200205.