To address the critical issues of low mechanization and high labor demand in facility agriculture production and transportation, an intelligent tracking transport vehicle adaptable to various planting modes was developed. Firstly, a differential chassis with adjustable wheel track was designed according to agronomic requirements. For positioning, a Kalman filter-based fusion method integrating Ultra-wideband (UWB) and machine vision was proposed: UWB establishes a global coordinate system to suppress cumulative errors, while the YOLOv5s model identifies the target and provides local precise pose. Static tests showed that compared with single UWB alone, the fusion method reduced the average lateral and longitudinal deviations by 78.14% and 79.82%, and decreased their standard deviations by 59.14% and 58.19%, respectively, significantly improving positioning accuracy and stability. Subsequently, a Proportional-Integral-Derivative(PID)-based controller was designed for longitudinal distance and tracking angle. Field test results indicated that under the conditions of target speed 0.4 m/s and vehicle speed limit of 0.5 m/s, the average lateral deviation during straight-line tracking was 0.017 8 m, with a maximum of 0.042 1 m. The turning process was smooth and could quickly converge to a steady state. The positioning accuracy and dynamic response characteristics of this system meet the operational requirements inside facility agriculture greenhouses, providing a reference for autonomous tracking technology in agricultural equipment.
GuoN, GuoH E, YangR S, XuN, ChengJ. Analysis on development status of facility agriculture in Shandong Province and improvement strategies[J]. Agricultural Equipment & Vehicle Engineering, 2024, 62(7): 153-156 (in Chinese)
[3]
van HentenE J. Greenhouse mechanization: State of the art and future perspective[J]. Acta Horticulturae, 2006(710): 55-70
[4]
王一珺. 甘肃设施农业机械化技术推广与应用[J]. 农机科技推广, 2024(1): 30-31
[5]
WangY J. Popularization and application of mechanization technology of protected agriculture in Gansu Province[J]. Agriculture Machinery Technology Extension, 2024(1): 30-31 (in Chinese)
WangS S. Agricultural mechanization analysis of facility vegetable production in Daxing district of Beijing City[J]. Agricultural Engineering, 2024, 14(5): 59-62 (in Chinese)
[8]
NørremarkM, GriepentrogH W, NielsenJ, SøgaardH T. The development and assessment of the accuracy of an autonomous GPS-based system for intra-row mechanical weed control in row crops [J]. Biosystems Engineering, 2008, 101(4): 396-410
[9]
HiremathS A, van der HeijdenG W A M, van EvertF K, SteinA, ter BraakC J F. Laser range finder model for autonomous navigation of a robot in a maize field using a particle filter[J]. Computers and Electronics in Agriculture, 2014, 100: 41-50
[10]
KrishnaveniB V, ReddyK S, ReddyP R. Wireless indoor positioning techniques based on Ultra Wideband (UWB) technology [J]. International Journal of Recent Technology and Engineering (IJRTE), 2019, 7(5c): 15-22
ZhengH, YeY X, XueX L, YuJ L, FengH D, YuG H. Facility plant protection robot based on UWB and visual integrated navigation for leafy vegetable ridge tracking control[J]. Transactions of the Chinese Society of Agricultural Engineering, 2025,41(4): 144-152 (in Chinese)
FanZ Q, ZhangQ, QiuQ, YangQ F. Locomotion modes for agricultural robot platform: A review[J]. Jiangsu Agricultural Sciences, 2018, 46(22): 35-39 (in Chinese)
[15]
冯海明. 果园和温室大棚多功能遥控作业车的研制与试验[D]. 泰安: 山东农业大学, 2016
[16]
Feng H M Research and test of multi function remote control operating vehicle in orchard and greenhouse[D]. Taian: Shandong Agricultural University, 2016 (in Chinese)
[17]
刘珂. 基于UWB的跟随行李箱研究与设计[D]. 武汉: 武汉理工大学, 2019
[18]
Liu K Research and design of following luggage based on UWB[D]. Wuhan: Wuhan University of Technology, 2019 (in Chinese)
[19]
YangB, GuoL Y, GuoR J, ZhaoM M, ZhaoT T. A novel trilateration algorithm for RSSI-based indoor localization[J]. IEEE Sensors Journal, 2020, 20(14): 8164-8172
QianJ H. NLOS UWB indoor positioning accuracy analysis based on weighted least squares[J]. Geospatial information, 2023, 21(8): 86-88 (in Chinese)
[22]
董宇. 基于超宽带室内定位系统的关键技术研究[D]. 太原: 山西大学, 2023
[23]
DongY. Research on key technologies of indoor positioning system based on UWB[D]. Taiyuan: Shanxi University, 2023 (in Chinese)
[24]
KimH. Double-sided two-way ranging algorithm to reduce ranging time [J]. IEEE Communications Letters, 2009, 13(7): 486-488
[25]
LeeJ X, LinZ W, ChinP S, LawC L. The use of symmetric multi-way two phase ranging to compensate time drift in wireless sensor network[J]. IEEE Transactions on Wireless Communications, 2009, 8(2): 613-616
XiangW T. R. Research on positioning and navigation system of scaffolding orchard robot based on UWB[D]. Hangzhou: Hangzhou Dianzi University, 2024 (in Chinese)
[28]
顾衍明. 基于UWB的室内机器人定位系统研究与设计[D]. 哈尔滨: 哈尔滨工业大学, 2018
[29]
GuY M. Research and design of indoor robot positioning system based on UWB[D]. Harbin: Harbin Institute of Technology, 2018 (in Chinese)
[30]
RedmonJ, DivvalaS, GirshickR, FarhadiA. You only look once: Unified, real-time object detection [C] In: 2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).New York: Institute of Electrical and Electronics Engineers, 2016: 779-788
ZhangK X, ZhuM. Environmental perception algorithm for multi-task autonomous driving based on YOLOv5[J]. Computer Systems & Applications, 2022, 31(9): 226-232 (in Chinese)
[33]
DalalN, TriggsB. Histograms of Oriented Gradients for human detection[C] In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR’ 05).New York: Institute of Electrical and Electronics Engineers, 2005: 886-893
[34]
MoghanianM, DobakhshariA S. Accurate Kalman filter based estimation of transmission line parameters utilizing synchronized phasor measurements[J]. Electric Power Systems Research, 2024, 230: 110218
[35]
WeiY Q, YangX, BaiX L, XuZ G. Adaptive hybrid Kalman filter for attitude motion parameters estimation of space non-cooperative tumbling target[J]. Aerospace Science and Technology, 2024, 144: 108832