Slope path tracking control of agricultural wheel-legged robot based on virtual sensing radar and two-level deep neural network

Authors

  • Yongchun Zhao 1. College of Engineering, China Agricultural University, Haidian 100083, Beijing, China 2. Research Center of Intelligent Grassland Industry and Intelligent Grassland Equipment, China Agricultural University, Haidian 100083, Beijing, China
  • Qing Zhang 1. College of Engineering, China Agricultural University, Haidian 100083, Beijing, China 2. Research Center of Intelligent Grassland Industry and Intelligent Grassland Equipment, China Agricultural University, Haidian 100083, Beijing, China
  • Yong You 1. College of Engineering, China Agricultural University, Haidian 100083, Beijing, China 2. Research Center of Intelligent Grassland Industry and Intelligent Grassland Equipment, China Agricultural University, Haidian 100083, Beijing, China

DOI:

https://doi.org/10.25165/ijabe.v18i3.8737

Keywords:

deep neural network, virtual sensing radar, slope path tracking, wheel-legged robot

Abstract

The continuous development of smart agriculture puts forward the requirement of high accuracy slope path tracking for the agricultural wheel-legged robot. Compared to flat terrain, path tracking control on sloped terrain faces the obstacle of motion instability of the wheel-legged robot induced by the slope gravitational force component, which causes instantaneous steering center to offset. To address this problem, this study proposed a slope path tracking control algorithm by combining the methods of virtual sensing radar and two-level neural network. Firstly, the kinematic and dynamic models of the wheel-legged robot are deduced, from which the crucial factors affecting control accuracy of slope path tracking are recognized. Secondly, this study constructs the slope path tracking control algorithm, in which the virtual sensing radar is utilized to realize route perception, and the two-level neural network is employed to provide drive motors’ speeds to adapt to path tracking on different slopes. Furthermore, the corresponding compensation methods of the identified impacting factors are embedded in the proposed algorithm, including the lateral tracking deviation factor, heading angle deviation factor, slope change factor, and slip rate factor. Finally, the co-simulation model of slope path tracking control is constructed, including the multi-body dynamic model of the wheel-legged robot in RecurDyn and the proposed slope path tracking algorithm complied by Python. Subsequently, the simulation tests of the wheel-legged robot are carried out under various slope angles and velocities. The results reveal that the proposed algorithm’s effectiveness and accuracy are superior, with tracking errors reduced by more than 47.2% compared to an optimized pure pursuit algorithm. Keywords: deep neural network, virtual sensing radar, slope path tracking, wheel-legged robot DOI: 10.25165/j.ijabe.20251803.8737 Citation: Zhao Y C, Zhang Q, You Y. Slope path tracking control of agricultural wheel-legged robot based on virtual sensing radar and two-level deep neural network. Int J Agric & Biol Eng, 2025; 18(3): 223–235.

References

D’Auria D, Ristorto G, Raimondo G, Mazzetto F. Tracked robot over a slope path: Dynamic stability control. In: 2016 IEEE 17th International Conference on Information Reuse and Integration （IRI）, Pittsburgh, PA, USA: IEEE, 2016; pp.496-499.

Dogan M U, Guvenc U, Elmas C. Genetic PI based model and path tracking control of four traction electrical robot vehicle. Electrical Engineering, 2020; 102: 2059-2073.

Jeong Y. Path tracking control for four-wheel-steering autonomous vehicle based on adaptive sliding mode control with control allocation. In: 2021 21st International Conference on Control, Automation and Systems （ICCAS）, South Korea: IEEE, 2021; pp.1741-1746.

Qi H Y, Shangguan J Y, Fang C, Yue M. Path tracking control of car-like wheeled mobile robot on the slope based on nonlinear model predictive control. In: 2022 International Conference on Advanced Robotics and Mechatronics （ICARM）, Guilin, China: IEEE, 2022; pp.465-470.

Hu J T, Li T C. Cascaded navigation control for agricultural vehicles tracking straight paths. Int J Agric & Biol Eng, 2014; 7（1）: 36-44.

Yue X, Chen J K, Li Y Q, Zou R, Sun Z H, Cao X C, et al. Path tracking control of skid-steered mobile robot on the slope based on fuzzy system and model predictive control. International Journal of Control, Automation and Systems, 2022; 20（4）: 1365-1376.

Yang Z J, Mao L, Yan B, Wang J, Gao W. Performance analysis and prediction of asymmetric two-level priority polling system based on BP neural network. Applied Soft Computing, 2021; 99: 106880.

Zhou Z B, Zhang X M, Li Z J, Huang F R, Xu J. Multilevel attention networks and policy reinforcement learning for image caption generation. Big Data, 2022; 10（6）: 481-492.

Li Y W, Zang L G, Shi T, Lv T, Lin F. Design and dynamic simulation analysis of a wheel-Track composite chassis based on RecurDyn. World Electric Robot Journal, 2022; 13（1）: 12.

Bai G X, Meng Y, Liu L, Gu Q, Huang J X, Liang G D, et al. Path tracking for car-like robots based on neural networks with NMPC as learning samples. Electronics, 2022; 11: 4232.

Liu Z J, Wang X L, Ren Z G, Mao W J, Yang F Z. Crawler tractor navigation path tracking control algorithm based on virtual sensing radar model. Transactions of the Chinese Society for Agricultural Machinery, 2021; 52（6）: 376-385.

Yang Y, Li Y K, Wen X, Zhang G, Ma Q L, Cheng S K, et al. An optimal goal point determination algorithm for automatic navigation of agricultural machinery: Improving the tracking accuracy of the Pure Pursuit algorithm. Computers and Electronics in Agriculture, 2022; 194: 106760.

Zhang F, Zheng L M, Wang W, Wang Y F, Wang J J. Development of agricultural bionic mechanisms: Investigation of the effects of joint angle and pressure on the stability of goats moving on sloping lands. Int J Agric & Biol Eng, 2018; 11（3）: 35-41.

Liu Z D, Zheng W X, Wang N, Lyu Z Q, Zhang W Z. Trajectory tracking control of agricultural vehicles based on disturbance test. Int J Agric & Biol Eng, 2020; 13（2）: 138-145.

Yin X, Wang Y X, Chen Y L, Jin C Q, Du J. Development of autonomous navigation controller for agricultural vehicles. Int J Agric & Biol Eng, 2020; 13（4）: 70-76.

Bayar G, Bergerman M, Koku A B, Konukseven E I. Localization and control of an autonomous orchard vehicle. Computers and Electronics in Agriculture, 2015; 115: 118-128.

Backman J, Oksanen T, Visala A. Navigation system for agricultural machines: Nonlinear Model Predictive path tracking. Computers and Electronics in Agriculture, 2012; 82: 32-43.

Chaudhary N, Gupta A. Multi-body analysis for a four-bar mechanism using RecurDyn and MATLAB. In: Kumar R, Chauhan V S, Talha M, Pathak H. （eds）. Machines, Mechanism and Robotics. Singapore: Springer. 2022; pp.1813-1823.

Deng J, Zhou H R, Lv X, Yang L J, Shang J L, Sun Q, et al. Applying convolutional neural networks for detecting wheat stripe rust transmission centers under complex field conditions using RGB-based high spatial resolution images from UAVs. Computers and Electronics in Agriculture, 2022; 200: 107211.

Ding Y, Wang L, Li Y W, Li D L. Model predictive control and its application in agriculture: A review. Computers and Electronics in Agriculture, 2018; 151: 104-117.

Gratton S, Kopaničáková A, Toint P L. Multilevel objective-function-free optimization with an application to neural networks training. arXiv: 2302.07049, 2023; In press.

Graf Plessen M M, Bemporad A. Reference trajectory planning under constraints and path tracking using linear time-varying model predictive control for agricultural machines. Biosystems Engineering, 2017; 153: 28-41.

Han X, Kim H J, Jeon C W, Moon H C, Kim J H, Seo I H. Design and field testing of a polygonal paddy infield path planner for unmanned tillage operations. Computers and Electronics in Agriculture, 2021; 191: 106567.

He Y Q, Zhou J, Yuan L C, Zheng P Y, Liang Z A. Local tracking path planning based on steering characteristics of Crawler-type combine harvester. Transactions of the Chinese Society for Agricultural Machinery, 2022; 53（11）: 13-21.

Hussain M, Qazi E U H, Aboalsamh H A, Ullah I. Emotion recognition system based on two-level ensemble of deep-convolutional neural network models. IEEE Access, 2023; 11: 16875-16895.

He J, Hu L, Wang P, Liu Y X, Man Z X, Tu T P, et al. Path tracking control method and performance test based on agricultural machinery pose correction. Computers and Electronics in Agriculture, 2022; 200: 107185.

Han X Z, Kim H J, Kim J Y, Yi S Y, Moon H C, Kim J H, et al. Path-tracking simulation and field tests for an auto-guidance tillage tractor for a paddy field. Computers and Electronics in Agriculture, 2015; 112: 161-171.

Liu F, Meng W, Yao D Y. Bounded antisynchronization of multiple neural networks via multilevel hybrid control. IEEE Transactions on Neural Networks and Learning Systems, 2023; 34（11）: 8250-8261.

Li D, Kwak S, Geroliminis N. TwoResNet: Two-level resolution neural network for traffic forecasting on freeway networks. In: 2022 IEEE 25th International Conference on Intelligent Transportation Systems （ITSC）, Macau, China: IEEE, 2022; pp.3963-3969.

Murillo M, Sánchez G, Deniz N, Genzelis L, Giovanini L. Improving path-tracking performance of an articulated tractor-trailer system using a non-linear kinematic model. Computers and Electronics in Agriculture, 2022; 196: 106826.

Milo V, Anzalone F, Zambelli C, Perez E, Mahadevaiah M K, Ossorio O G, et al. Optimized programming algorithms for multilevel RRAM in hardware neural networks. In: 2021 IEEE International Reliability Physics Symposium （IRPS）, Monterey, CA, USA: IEEE, 2021; pp.1-6. doi: 10.1109/IRPS46558.2021.9405119.

Naqi M, Kang M S, Liu N, Kim T, Baek S, Bala A, et al. Multilevel artificial electronic synaptic device of direct grown robust MoS2 based memristor array for in-memory deep neural network. Npj 2D Materials and Applications, 2022; 6: 53.

Sohn J H, Lee C H, Kim Y J, Kim S S. Evaluation of path tracking performance of a self-driving tracked vehicle. Transactions of the Korean Society of Mechanical Engineers, 2022; 45（12）: 1167-1176.

Wu Y H, Duan Y H, Wei Y G, An D, Liu J C. Application of intelligent and unmanned equipment in aquaculture: A review. Computers and Electronics in Agriculture, 2022; 199: 107201.

Zyarah A M, Soures N, Hays L, Jacobs-Gedrim R B, Agarwal S, Marinella M, et al. Ziksa: On-chip learning accelerator with memristor crossbars for multilevel neural networks. In: 2017 IEEE International Symposium on Circuits and Systems （ISCAS）, Baltimore, MD, USA: IEEE, 2017; pp.1-4.

Zhan Z Q, Si G M, Zhi J J, Liu L. Design and analysis based on RecurDyn of the electric crawler type remote controlled hedge trimmer. Journal of Physics: Conference Series, 2020; 1633（1）: 012010.

Zhang L H, Zhang R R, Li L L, Ding C C, Zhang D Z, Chen L P. Research on virtual Ackerman steering model based navigation system for tracked vehicles. Computers and Electronics in Agriculture, 2022; 192: 106615.

Zhang W Y, Gai J Y, Zhang Z G, Tang L, Liao Q X, Ding Y C. Double-DQN based path smoothing and tracking control method for robotic vehicle navigation. Computers and Electronics in Agriculture, 2019; 166: 104985.

Downloads

Published

2025-06-30

How to Cite

Zhao, Y., Zhang, Q., & You, Y. (2025). Slope path tracking control of agricultural wheel-legged robot based on virtual sensing radar and two-level deep neural network. International Journal of Agricultural and Biological Engineering, 18(3), 223–235. https://doi.org/10.25165/ijabe.v18i3.8737

Issue

Vol. 18 No. 3 (2025): IJABE

Section

Information Technology, Sensors and Control Systems

License

IJABE is an international peer reviewed open access journal, adopting Creative Commons Copyright Notices as follows.


Authors who publish with this journal agree to the following terms:


  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

  2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

  3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).