Robust visual navigation and adaptive control decision-making for autonomous agricultural robots in mature wheat fields: an improved RT-DETRv2 and Fuzzy-PID framework

https://doi.org/10.55529/ijaap.51.129.144

Authors

  • Madhusmita Swain Research Scholar, Kalinga University, Raipur & Postgraduate Teacher (Zoology), Govt. Higher Secondary School, Tudalaga, Sundargarh, Odisha., India.

Keywords:

Visual Navigation, Wheat Crop Row Detection, RT-DETRv2, Multi-Scale Attention, Adaptive Fuzzy-PID, Precision Agriculture

Abstract

Perceptual challenges are extreme in mature wheat due to dense canopy occlusion, specular reflections from senescent awns, wind lodging and therefore variable inter-row spacing, and the challenge of having to operate a combine in real time. In this situation, the authors propose a framework, RT-DETRv2-MSCA-SCGE with Adaptive Fuzzy-PID (RTMS-AFP), which combines the visual crop-row detection and real-time control decision-making for an autonomous agricultural machine. From the perceptual perspective, two modules are added: a Multi-Scale Channel Attention (MSCA) module in the transformer encoder backbone to improve the receptive field coverage and a Spatial Context Global Encoder (SCGE) module in the feature pyramid neck, to improve the edge-feature discrimination in dense canopy scenarios. The detection model was trained using a custom-made dataset of 7,846 annotated wheat-field images (2,134 images captured at original locations and 5,712 images created with diverse conditions), across seven environmental conditions in three wheat-growing regions in India and China. A PID controller with adaptive gains is implemented on the control side to adaptively adjust PID gains continuously through real-time fuzzy inference, which is derived from lateral deviation and heading angle error obtained from the detection pipeline. With a real-time processing time of 26.4 ms per frame, the proposed model achieved a mAP@50 of 97.1%, a mAP@50-95 of 89.4%, 3.84 px mean lateral error and 2.46° mean heading error, meeting real-time requirements with improvements of +2.96%, +4.93%, and -25.0% over baseline RT-DETRv2. Field trials over three wheat growing seasons in Yangling, China and Coimbatore, India resulted in an average crop row recognition accuracy of 97.8 % and RMSE of 0.041 m for forward speeds up to 1.1 m/s. One-way ANOVA (F = 74.2, p < 0.001) and Mann-Whitney U tests (p < 0.001) showed that the proposed framework was significantly superior to all the baseline frameworks. These findings demonstrate the ability of RTMS-AFP to solve the autonomous navigation problem in the most difficult part of the cereal harvest process, while being efficient in terms of computational power.

Downloads

Download data is not yet available.

References

V. Marinoudi, "Robotics and labour in agriculture. A context consideration", Biosyst. Eng, vol. 184, pp. 111-121, Aug. 2019. 10.1016/j.biosystemseng.2019.06.013

S. G. Vougioukas, "Agricultural robotics", Annu. Rev. Control Robot. Auton. Syst., vol. 2, no. 1, pp. 365-392, May 2019. 10.1146/annurev-control-053018-023617

D. Bochtis, C. G. C. Sørensen, and P. Busato, "Advances in agricultural machinery management: A review", Biosyst. Eng., vol. 126, pp. 69-81, Oct. 2014. 10.1016/j.biosystemseng.2014.07.012

D. Romano and C. Stefanini, "Individual neon tetras (Paracheirodon innesi, Myers) optimise their position in the group depending on external selective contexts: Lesson learned from a fish-robot hybrid school", Biosyst. Eng., vol. 204, pp. 170-180, Apr. 2021. 10.1016/j.biosystemseng.2021.01.021

H. Mousazadeh, "A technical review on navigation systems of agricultural autonomous off-road vehicles", J. Terramech., vol. 50, no. 3, pp. 211-232, June 2013. 10.1016/j.jterra.2013.03.004

S. Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN: Towards real-time object detection with region proposal networks", IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 6, pp. 1137-1149, June 2017. 10.1109/TPAMI.2016.2577031

Z. Ma, X. Wang, X. Chen, B. Hu, and J. Li, "Advances in crop row detection for agricultural robots: Methods, performance indicators, and scene adaptability", Agriculture, vol. 15, no. 20, p. 2151, Oct. 2025. 10.3390/agriculture15202151

N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, and S. Zagoruyko, "End-to-end object detection with transformers", in Lecture Notes in Computer Science, Cham: Springer International Publishing, 2020, pp. 213-229. 10.1007/978-3-030-58452-8_13

Y. Jia, K. Fu, H. Lan, X. Wang, and Z. Su, "Maize tassel detection with CA-YOLO for UAV images in complex field environments", Comput. Electron. Agric., vol. 217, no. 108562, 2024. 10.1016/j.compag.2023.108562

H. Xu, J. Lai, R. Guo, X. Lu, and L. Xu, "Efficiency-oriented MPC algorithm for path tracking in autonomous agricultural machinery," Agronomy, vol. 12, no. 7, p. 1662, Jul. 2022. 10.3390/agronomy12071662

Y. Zhao et al., "DETRs beat YOLOs on real-time object detection", arXiv [cs.CV], 17-Apr-2023. 10.1109/CVPR52733.2024.01605

Z. Diao, P. Guo, B. Zhang, D. Zhang, J. Yan, Z. He, S. Zhao, and C. Zhao, "Navigation line detection algorithm for corn spraying robot based on improved LT-YOLOv10s," Precis. Agric., vol. 26, no. 3, pp. 1-23, 2025. 10.1007/s11119-025-10243-3

J. Bai, F. Hao, G. Cheng, and C. Li, "Machine vision-based supplemental seeding device for plug seedling of sweet corn", Comput. Electron. Agric., vol. 188, no. 106345, Sept. 2021. 10.1016/j.compag.2021.106345

B. Zhang et al., "Precise visual navigation and control decision making in complex agricultural environments: Studies on mature soybeans using improved YOLOv10n", Agriculture, vol. 16, no. 10, p. 1062, May 2026. 10.3390/agriculture16101062

D. C. Slaughter, D. K. Giles, and D. Downey, "Autonomous robotic weed control systems: A review", Comput. Electron. Agric., vol. 61, no. 1, pp. 63-78, Apr. 2008. 10.1016/j.compag.2007.05.008

H. Wu, S. Niu, Y. Zhou, J. Sun, J. Lv, and Y. He, "Characteristics of raindrop size distributions in the southwest mountain areas of China according to seasonal variation and rain types", Remote Sens. (Basel), vol. 15, no. 5, p. 1246, Feb. 2023. 10.3390/rs15051246

J. Li, "Design and experiment of an adaptive cruise weeding robot for paddy fields based on improved YOLOv5", Comput. Electron. Agric, vol. 219, Apr. 2024. 10.1016/j.compag.2024.108824

A. Ahmadi, L. Nardi, N. Chebrolu, and C. Stachniss, "Visual servoing-based navigation for monitoring row-crop fields," in Proc. IEEE Int. Conf. Robot. Autom. (ICRA), Paris, France, May-Jun. 2020, pp. 4920-4926. 10.1109/ICRA40945.2020.9197114

E. van Wyngaard, E. Blancquaert, H. Nieuwoudt, and J. L. Aleixandre-Tudo, "A novel approach to upgrade infrared spectroscopy calibrations for nutritional contents in fresh grapevine organs", Biosyst. Eng., vol. 232, pp. 141-154, Aug. 2023. 10.1016/j.biosystemseng.2023.07.008

Z. Ma, C. Yin, X. Du, L. Zhao, L. Lin, G. Zhang, and C. Wu, "Rice row tracking control of crawler tractor based on the satellite and visual integrated navigation," Comput. Electron. Agric., vol. 197, p. 106978, Jun. 2022. 10.1016/j.compag.2022.106935

L. Liu et al., "Trailer hopper automatic detection method for silage harvesting based improved U-Net", Comput. Electron. Agric., vol. 198, no. 107046, July 2022. 10.1016/j.compag.2022.107046

J. J. Ruan, "Row detection based navigation and guidance for agricultural robots and autonomous vehicles in row-crop fields: Methods and applications", Agronomy, vol. 13, no. 7, June 2023. 10.3390/agronomy13071780

L. He et al., "Remote estimation of leaf water concentration in winter wheat under different nitrogen treatments and plant growth stages", Precis. Agric., vol. 24, no. 3, pp. 986-1013, June 2024. 10.1007/s11119-022-09983-3

R. Wei, H. Lin, Q. Chen, G. Huang, and W. Hu, "A CMOS temperature sensor with a smart calibrated inaccuracy of ±0.11° (3σ)", Sensors (Basel), vol. 23, no. 11, p. 5132, May 2023. 10.3390/s23115132

S. Mauget and G. Leiker, "The Ogallala Agro-climate tool", Comput. Electron. Agric., vol. 74, no. 1, pp. 155-162, Oct. 2010. 10.1016/j.compag.2010.08.002

Published

2025-05-19

How to Cite

Swain, M. (2025). Robust visual navigation and adaptive control decision-making for autonomous agricultural robots in mature wheat fields: an improved RT-DETRv2 and Fuzzy-PID framework. International Journal of Agriculture and Animal Production, 5(1), 129–144. https://doi.org/10.55529/ijaap.51.129.144