Agricultural robot will become a powerful tool to save a lot of human resources in the future, which can reduce the labor intensity and cost of workers, and improve the efficiency of picking operations. The purpose of this paper is to study the path planning and positioning technology of cotton picking robot based on the complex cotton field environment. Firstly, based on the research of common path planning technology, according to the known degree of the target to the environment, the common path planning algorithms are roughly divided into two categories: global and local planning, and its characteristics, advantages and disadvantages in application are briefly analyzed. The parallel binocular vision measurement system is selected as the positioning tool of the cotton peach to simulate the complex cotton field environment. The experimental results show that after error compensation, the measurement errors in the X and Z directions are within 5mm. The measurement error prediction model for the vision system well expresses the nonlinear model between the original measurement value and the measurement error. The global optimization rate of hybrid particle swarm optimization algorithm is 50%, but the result is the most unstable; the global optimization rate of basic genetic algorithm is 20%, the global optimization rate of multi population genetic algorithm is 70%, the global optimization rate of improved multi population genetic algorithm is 90%, the global optimization rate and speed of improved multi population genetic algorithm are the best of the several algorithms studied in this paper, Therefore, this algorithm is used to optimize the path in practical application.

Nan Wang. Path Planning and Positioning Technology of Cotton Picking Robot in Complex Cotton Field. Machine Learning Theory and Practice (2021), Vol. 2, Issue 2: 32-45. https://doi.org/10.38007/ML.2021.020204.

[1] Luo, Lufeng, Zou, Xiangjun, Xiong, Juntao. Automatic positioning for picking point of grape picking robot in natural environment. Nongye Gongcheng Xuebao/transactions of the Chinese Society of Agricultural Engineering, 2015, 31(2):14-21(8).

[2] D. Wang, H. Song, D. He. Research advance on vision system of apple picking robot. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33(10):59-69.

[3] Jie C , Zhen-Jie G . An Improved Ant Colony Algorithm and Application in Picking Robot Multi-objective Path Planning. Journal of Chinese Computer Systems, 2015, 4(4):160-169.

[4] C. Zhang, L. Li, Q. Dong. Recognition for machine picking seed cotton impurities based on GA-SVM model. Nongye Gongcheng Xuebao/transactions of the Chinese Society of Agricultural Engineering, 2016, 32(24):189-196.

[5] Krug R , Stoyanov T , Tincani V , et al. The Next Step in Robot Commissioning: Autonomous Picking and Palletizing. IEEE Robotics & Automation Letters, 2017, 1(1):546-553. https://doi.org/10.1109/LRA.2016.2519944.

[6] Giovanni Boschetti. A Picking Strategy for Circular Conveyor Tracking. Journal of Intelligent & Robotic Systems, 2015, 81(2):1-15. https://doi.org/10.1007/s10846-015-0242-y.

[7] Fakoor, Mahdi, Kosari, Amirreza, Jafarzadeh, Mohsen. Humanoid Robot Path Planning with Fuzzy Markov Decision Processes. Journal of Applied Research & Technology, 2016, 14(5):300-310. https://doi.org/10.1016/j.jart.2016.06.006.

[8] J. Liu, J. Yang, H. Liu. Robot global path planning based on ant colony optimization with artificial potential field. Transactions of the Chinese Society for Agricultural Machinery, 2015, 46(9):18-27.

[9] H. Qu, L.-W. Huang, X. Ke. Research of improved ant colony based robot path planning under dynamic environment. Dianzi Keji Daxue Xuebao/journal of the University of Electronic Science & Technology of China, 2015, 44(2):260-265.

[10] Tiffany Hwu, Alexander Y. Wang, Nicolas Oros. Adaptive Robot Path Planning Using a Spiking Neuron Algorithm With Axonal Delays. IEEE Transactions on Cognitive & Developmental Systems, 2018, 10(2):126-137. https://doi.org/10.1109/TCDS.2017.2655539.

[11] Cheng Zhang. Path Planning for Robot based on Chaotic Artificial Potential Field Method. Science Technology & Engineering, 2018, 317(1):012056. https://doi.org/10.1088/1757-899X/317/1/012056.

[12] Gang Wang，Jun Zhou. Dynamic robot path planning system using neural network, Journal of Intelligent & Fuzzy Systems, 2021, 40(2):3055-3063. https://doi.org/10.3233/JIFS-189344.

[13] WAN Xiaofeng, HU Wei, ZHENG Bojia. Robot path planning method based on improved ant colony algorithm and Morphin algorithm. Science & Technology Review, 2015, 33(3):84-89.

[14] Kaplan A , Kingry N , Uhing P , et al. Time-Optimal Path Planning With Power Schedules for a Solar-Powered Ground Robot. Automation Science and Engineering, IEEE Transactions on, 2017, 14(2):1235-1244. https://doi.org/10.1109/TASE.2016.2533418.

[15] Khan, A. N., Cao, X., & Pitafi, A. H. Personality Traits as Predictor of M-Payment Systems: A SEM-Neural Networks Approach. Journal of Organizational and End User Computing (JOEUC), 2019, 31(4), 89-110. http://doi.org/10.4018/JOEUC.2019100105.

[16] Z. Wang, Z. Feng, G. Ye. Analysis of dual-robot path planning based on artificial bee colony algorithm. Hanjie Xuebao/transactions of the China Welding Institution, 2015, 36(2):97-100.

[17] Wei-Jen Chen, Bing-Gang Jhong, Mei-Yung Chen. Design of Path Planning and Obstacle Avoidance for a Wheeled Mobile Robot. International Journal of Fuzzy Systems, 2016, 18(6):1-12. https://doi.org/10.1007/s40815-016-0224-7.

[18] F. Zhang, N. Li, R. Yuan. Robot path planning algorithm based on reinforcement learning. Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition), 2018, 46(12):65-70.

[19] Chi-Lun Lo, Chi-Hua Chen*, Jin-Li Hu, Kuen-Rong Lo, Hsun-Jung Cho, “A Fuel-Efficient Route Plan Method Based on Game Theory,” Journal of Internet Technology, 2019, 20(3):925-932.

[20] Rayssa Almeida Garcia, Leonardo Lima Pepino Macedo, Danila Cabral do Nascimento. Nucleases as a barrier to gene silencing in the cotton boll weevil, Anthonomus grandis. Plos One, 2017, 12(12):e0189600. https://doi.org/10.1371/journal.pone.0189600.

[21] I. Ali, A. Shakeel, A. Saeed. Combining ability analysis and heterotic studies for within-boll yield components and fibre quality in cotton. Journal of Animal & Plant Sciences, 2016, 26(1):156-162.

[22] Khan, A. N., Cao, X., & Pitafi, A. H. Personality Traits as Predictor of M-Payment Systems: A SEM-Neural Networks Approach. Journal of Organizational and End User Computing (JOEUC), 2019, 31(4), 89-110. http://doi.org/10.4018/JOEUC.2019100105.

[23] Enrique Gino Medrano, Alois A. Bell, Sara E. Duke. Cotton ( Gossypium hirsutum L.) boll rotting bacteria vectored by the brown stink bug, Euschistus servus (Say) (Hemiptera: Pentatomidae). Journal of Applied Microbiology, 2016, 121(3):757-766. https://doi.org/10.1111/jam.13197.

[24] Muhammad Farrukh Saleem, Muhammad Shahid, Abdul Shakoor. Removal of early fruit branches triggered regulations in senescence, boll attributes and yield of Bt cotton genotypes. Annals of Applied Biology, 2018, 172(2):224-235. https://doi.org/10.1111/aab.12415.

[25] Spurgeon D W . Captures of Boll Weevils (Coleoptera: Curculionidae) in Relation to Trap Distance From Cotton Fields. Journal of Economic Entomology, 2016, 109(2):676-683. https://doi.org/10.1093/jee/tov392.

[26] Meiling Zhang, Xianliang Song, Hong Ji. Carbon partitioning in the boll plays an important role in fiber quality in colored cotton. Cellulose, 2016, 24(2):1-11. https://doi.org/10.1007/s10570-016-1139-z.

[27] WU You, ZHAO Wen-qing, MENG Ya-li. Relationships between temperature-light meteorological factors and seedcotton biomass per boll at different boll positions. Journal of Integrative Agriculture, 2018, 17(6):1315-1326. https://doi.org/10.1016/S2095-3119(17)61820-3.

[28] Dominic D. Reisig, F. P. F. Reay-Jones, A. D. Meijer. Aggregation and Association of NDVI, Boll Injury, and Stink Bugs in North Carolina Cotton. Journal of Insect Science, 2015, 15(1):134. https://doi.org/10.1093/jisesa/iev119.

[29] M. Huang, L. Shi, Y. Zhang. Revised design and experiments on brush-rolling cotton harvester. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33(20):41-47.