Optimizing the Path of Plug Tray Seedling Transplanting by Using the Improved A* Algorithm
Abstract
:1. Introduction
- The A* algorithm was optimized and improved in combination with the ACA, an improved A* algorithm (Imp-A*) was obtained, and the algorithm model was applied to the field of plug tray seedling transplantation successfully, and it provided the optimal path for replanting seedlings of the manipulator.
- The path planning length and calculation time data of the Imp-A* model were obtained through simulation tests, and compared with simulation data of other algorithm models, the optimal route length and calculation time of the algorithm model were obtained.
- Based on the simulation model, the transplanting trials of replanting were designed, the Imp-A* in this paper was applied to the practical operation, and the robustness of the algorithm was tested; the efficiency and practicability of the Imp-A* were verified.
2. Materials and Methods
2.1. Structure of the Device and Path Planning Principles
2.2. Path Planning Methods
2.2.1. Common Sequence Method (CSM)
2.2.2. Dijkstra Algorithm (DA)
2.2.3. Ant Colony Algorithm (ACA)
2.2.4. A* Algorithm (A*)
2.2.5. Improved A* Algorithm (Imp-A*)
- Calculate the cost of each successor node using the concurrent reward-based ACA:
- Set visiting rules to give priority to all nodes with status “1” in the S grid and then to those with status “0” in the T grid.
- Search for the target node and add it to the Openlist.
3. Results
3.1. Randomized Comparative Simulation Test
3.2. Analysis of Randomized Comparative Simulation Test Results
3.3. Test Verification
4. Discussion
5. Conclusions
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Hu, J.P.; Yan, X.Y.; Ma, J.; Qi, C.H.; Francis, K.; Mao, H. Dimensional synthesis and kinematics simulation of a high-speed plug seedling transplanting robot. Comput. Electron. Agric. 2014, 107, 64–72. [Google Scholar] [CrossRef]
- Yu, X.; Zhao, Y.; Chen, B.; Zhou, M.; Zhang, Z. Current situation and prospect of transplanter. Trans. Chin. Soc. Agric. Mach. 2014, 45, 44–53. [Google Scholar]
- Wang, Y.W.; He, Z.L.; Wang, J.; Wu, C.Y.; Yu, G.H.; Tang, Y.H. Experiment on transplanting performance of automatic vegetable pot seedling transplanter for dry land. Trans. Chin. Soc. Agric. Eng. 2018, 34, 19–25. [Google Scholar]
- Huang, M.; Fang, S.L.; Cao, F.; Chen, J.N. Early sowing increases grain yield of machine-transplanted late-season rice under single-seed sowing. Field Crops Res. 2020, 253, 107832. [Google Scholar] [CrossRef]
- Tong, J.H.; Jiang, H.Y.; Zhou, M. Optimization of Seedling Transplanting Path Based on Genetic Algorithm. Trans. Chin. Soc. Agric. Mach. 2013, 44, 45–49+26. [Google Scholar]
- Tong, J.H.; Jiang, H.Y.; Wei, Z. Development of automatic system for the seedling transplanter based on machine vision technology. In Proceedings of the 2012 IEEE International Conference on Computer Science and Automation Engineering (CSAE), Zhangjiajie, China, 25–27 May 2012; pp. 742–746. [Google Scholar]
- Ureña, R.; Rodríguez, F.; Berenguel, M. A machine vision system for seeds quality evaluation using fuzzy logic. Comput. Electron. Agric. 2001, 32, 1–20. [Google Scholar] [CrossRef]
- Tong, J.H.; Shi, H.F.; Wu, C.Y.; Jiang, H.Y.; Yang, T.W. Skewness correction and quality evaluation of plug seedling images based on Canny operator and Hough transform. Comput. Electron. Agric. 2018, 155, 461–472. [Google Scholar] [CrossRef]
- Syed, T.N.; Liu, J.Z.; Zhou, X.; Zhao, S.Y. Seedling-lump integrated non-destructive monitoring for automatic transplanting with Intel RealSense depth camera. Artif. Intell. 2019, 3, 18–32. [Google Scholar] [CrossRef]
- Tai, Y.W.; Ling, P.P.; Ting, K.C. Machine vision assisted robotic seedling transplanting. ASAE 1994, 31, 661–667. [Google Scholar] [CrossRef]
- Tong, J.H.; Yu, J.L.; Wu, C.Y.; Yu, G.H.; Shi, H.Q. Health information acquisition and position calculation of plug seedling in greenhouse seedling bed. Comput. Electron. Agric. 2021, 185, 106146. [Google Scholar] [CrossRef]
- Tong, J.H.; Li, J.B.; Jiang, H.Y. Machine vision techniques for the evaluation of seedling quality based on leaf area. Biosys. Eng. 2013, 115, 369–379. [Google Scholar] [CrossRef]
- Mavrovouniotis, M.; Yang, S.X. Ant colony optimization with immigrants schemes for the dynamic travelling salesman problem with traffic factors. Appl. Soft Comput. 2013, 13, 4023–4037. [Google Scholar] [CrossRef]
- Saad, S.; Wan, N.; Jamil, S.J. Solving standard traveling salesman problem and multiple traveling salesman problem by using branch-and-bound. Am. Inst. Phys. 2013, 1522, 1406–1411. [Google Scholar]
- Chen, Y.M. Management of water resources using improved genetic algorithms. Comput. Electron. Agric. 1997, 18, 117–127. [Google Scholar] [CrossRef]
- Choi, I.C.; Kim, S.I.; Kim, H.S. A genetic algorithm with a mixed region search for the asymmetric traveling salesman problem. Comput. Oper. Res. 2003, 30, 773–786. [Google Scholar] [CrossRef]
- Tong, J.H.; Yu, G.H.; Wu, C.Y. Greedy Algorithm & Fixed Sequence Methods Comparison for Seedlings Lower Density Transplanting Path Planning. In Proceedings of the American Society of Agricultural and Biological Engineers 2016 ASABE International Meeting, Lake Buena Vista, FL, USA, 16–20 July 2016; Volume 17, pp. 1–6. [Google Scholar]
- Keshanchi, B.; Souri, A.; Navimipour, N.J. An improved genetic algorithm for task scheduling in the cloud environments using the priority queues. J. Syst. Softw. 2017, 124, 1–21. [Google Scholar] [CrossRef]
- Tong, J.H.; Wu, C.Y.; Jiang, H.Y.; Yu, Y.X.; Rao, X.Q. Optimizing the path of seedling low-density transplanting by using greedy genetic algorithm. Comput. Electron. Agric. 2017, 142, 356–368. [Google Scholar] [CrossRef]
- He, L.Y.; Yang, T.W.; Wu, C.Y. Optimization of Replanting Tour Planning Based on Greedy Genetic Algorithm. Trans. Chin. Soc. Agric. Mach. 2017, 48, 36–43. [Google Scholar]
- Tong, J.H.; Jiang, H.Y.; Wu, C.Y. Optimization of Seedlings Lower Density Transplanting Path Based on Greedy Algorithm. Trans. Chin. Soc. Agric. Mach. 2016, 43, 8–13. [Google Scholar]
- Ghafurian, S.; Javadian, N. An ant colony algorithm for solving fixed destination multi-depot multiple traveling salesmen problems. Appl. Soft Comput. 2011, 11, 1256–1262. [Google Scholar] [CrossRef]
- Jiang, Z.H.; Zhou, M.C.; Tong, J.H.; Jiang, H.Y.; Yang, Y.F.; Wang, A.C.; You, Z.H. Comparing an ant colony algorithm with a genetic algorithm for replanting tour planning of seedling transplanter. Comput. Electron. Agric. 2015, 11, 225–233. [Google Scholar] [CrossRef]
- Keskinturk, T.; Yildirim, M.B.; Barut, M. An ant colony optimization algorithm for load balancing in parallel machines with sequence-dependent setup times. Comput. Oper. Res. 2012, 39, 1225–1235. [Google Scholar] [CrossRef]
- Rada-Vilela, J.; Chica, M.; Cordón, Ó.; Damas, S. A comparative study of Multi-Objective Ant Colony Optimization algorithms for the Time and Space Assembly Line Balancing Problem. Appl. Soft Comput. 2013, 13, 4370–4382. [Google Scholar] [CrossRef]
- Zhang, A.B.; Qian, T.H.; Wu, X.C. An improved ant colony algorithm for path planning of manipulator. In Proceedings of the International Information Technology and Artificial Intelligence Conference (ITAIC), Chongqing, China, 11–13 December 2020; pp. 1358–1362. [Google Scholar]
- Chen, Y.Q.; Guo, J.L.; Yang, H.D.; Wang, Z.Q.; Liu, H.L. Research on navigation of bidirectional A* algorithm based on ant colony algorithm. J. Supercomput. 2020, 77, 1958–1975. [Google Scholar] [CrossRef]
- Sang, H.; You, Y.; Sun, X.; Zhou, Y.; Liu, F. The hybrid path planning algorithm based on improved A* and artificial potential field for unmanned surface vehicle formations. Ocean Eng. 2021, 223, 108709. [Google Scholar] [CrossRef]
Plug Tray Size/Hole | Test Groups | The Number of T Tray | Total | |||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | |||
32 | 1 | 5 | 6 | 6 | 3 | 5 | - | - | - | - | - | 25 |
2 | 3 | 6 | 4 | 5 | 3 | 5 | - | - | - | - | 26 | |
3 | 6 | 3 | 4 | 6 | 5 | 3 | - | - | - | - | 27 | |
4 | 2 | 4 | 5 | 5 | 3 | 5 | 4 | - | - | - | 28 | |
5 | 4 | 3 | 5 | 6 | 2 | 4 | 5 | - | - | - | 29 | |
6 | 5 | 4 | 4 | 3 | 6 | 5 | 3 | - | - | - | 30 | |
50 | 1 | 7 | 6 | 3 | 5 | 4 | 9 | 6 | - | - | - | 40 |
2 | 5 | 4 | 4 | 7 | 6 | 3 | 8 | 4 | - | - | 41 | |
3 | 7 | 5 | 6 | 8 | 9 | 7 | - | - | - | - | 42 | |
4 | 3 | 3 | 7 | 6 | 4 | 9 | 5 | 7 | - | - | 44 | |
5 | 10 | 6 | 4 | 4 | 7 | 5 | 7 | 3 | - | - | 46 | |
6 | 6 | 9 | 7 | 4 | 5 | 7 | 3 | 6 | - | - | 47 | |
72 | 1 | 8 | 5 | 6 | 4 | 11 | 7 | 9 | 5 | - | - | 55 |
2 | 11 | 7 | 8 | 8 | 5 | 6 | 6 | 7 | - | - | 58 | |
3 | 9 | 5 | 7 | 8 | 7 | 6 | 10 | 8 | - | - | 60 | |
4 | 7 | 5 | 5 | 6 | 8 | 10 | 6 | 4 | 10 | - | 63 | |
5 | 10 | 8 | 10 | 5 | 6 | 7 | 8 | 7 | 5 | - | 65 | |
6 | 6 | 11 | 9 | 10 | 9 | 5 | 7 | 11 | - | - | 68 | |
128 | 1 | 12 | 9 | 15 | 11 | 8 | 10 | 9 | 13 | 15 | - | 102 |
2 | 16 | 10 | 12 | 9 | 13 | 9 | 11 | 10 | 16 | - | 106 | |
3 | 11 | 14 | 10 | 9 | 15 | 12 | 14 | 8 | 9 | 9 | 111 | |
4 | 15 | 9 | 12 | 11 | 9 | 12 | 13 | 11 | 14 | 9 | 114 | |
5 | 12 | 14 | 8 | 19 | 10 | 11 | 9 | 12 | 8 | 15 | 118 | |
6 | 18 | 11 | 9 | 9 | 10 | 13 | 8 | 12 | 17 | 14 | 121 |
No. of T Tray | Number of Transplanted Seedlings | Path Planning Length (mm) | Calculation Time (s) | Replanting Time (s) | |||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
CSM | DA | ACA | A* | Imp-A* | DA | ACA | A* | Imp-A* | CSM | DA | ACA | A* | Imp-A* | ||
1 | 3 | 2912.0 | 2686.0 | 2804.0 | 2642.0 | 2596.0 | 0.40 | 0.36 | 0.31 | 0.24 | 36.56 | 35.43 | 36.02 | 32.21 | 30.98 |
2 | 4 | 4536.0 | 4262.0 | 4398.0 | 4236.0 | 4210.0 | 0.45 | 0.44 | 0.40 | 0.28 | 44.68 | 43.31 | 43.99 | 39.18 | 38.05 |
3 | 6 | 6108.0 | 5230.0 | 5620.0 | 5186.0 | 5186.0 | 0.66 | 0.62 | 0.58 | 0.44 | 52.54 | 48.15 | 50.10 | 41.93 | 40.37 |
4 | 7 | 7088.0 | 6770.0 | 6906.0 | 6724.0 | 6708.0 | 0.71 | 0.68 | 0.63 | 0.48 | 77.44 | 75.86 | 76.53 | 68.62 | 67.54 |
5 | 9 | 8662.0 | 8466.0 | 8512.0 | 8396.0 | 8372.0 | 1.09 | 1.02 | 0.96 | 0.72 | 95.31 | 94.33 | 94.56 | 85.98 | 84.06 |
6 | 10 | 9680.0 | 9024.0 | 9346.0 | 8986.0 | 8924.0 | 1.22 | 1.21 | 1.04 | 0.79 | 120.40 | 117.12 | 118.73 | 106.93 | 105.02 |
Total | 39 | 38,986.0 | 36,438.0 | 37,586.0 | 36,170.0 | 35,996.0 | 4.53 | 4.33 | 3.92 | 2.95 | 426.93 | 414.20 | 419.93 | 374.85 | 366.02 |
Average | 999.6 | 934.3 | 963.7 | 927.4 | 923.0 | 0.12 | 0.11 | 0.10 | 0.08 | 10.95 | 10.62 | 10.77 | 9.61 | 9.39 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Li, X.; Wang, W.; Liu, G.; Li, R.; Li, F. Optimizing the Path of Plug Tray Seedling Transplanting by Using the Improved A* Algorithm. Agriculture 2022, 12, 1302. https://doi.org/10.3390/agriculture12091302
Li X, Wang W, Liu G, Li R, Li F. Optimizing the Path of Plug Tray Seedling Transplanting by Using the Improved A* Algorithm. Agriculture. 2022; 12(9):1302. https://doi.org/10.3390/agriculture12091302
Chicago/Turabian StyleLi, Xiaojun, Weibing Wang, Ganghui Liu, Runze Li, and Fei Li. 2022. "Optimizing the Path of Plug Tray Seedling Transplanting by Using the Improved A* Algorithm" Agriculture 12, no. 9: 1302. https://doi.org/10.3390/agriculture12091302