Agricultural rout planning with variable rate pesticide application in a greenhouse environment
The use of robotics in executing agricultural tasks has significantly improved productivity over the years as a result of automation in performing such activities as spray, harvesting, planting etc. In order to optimize both crop yield and quality while minimizing costs, there will be need for the a...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier B.V.
2021
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/96490/1/UmarZangina2021_AgriculturalRoutPlanningwithVariableRate.pdf http://eprints.utm.my/id/eprint/96490/ http://dx.doi.org/10.1016/j.aej.2021.01.010 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The use of robotics in executing agricultural tasks has significantly improved productivity over the years as a result of automation in performing such activities as spray, harvesting, planting etc. In order to optimize both crop yield and quality while minimizing costs, there will be need for the application of navigation strategies. These will provide optimal as well as autonomous navigation capability which is built entirely upon field coverage plan thereby making robot navigation approach a paramount scheme. In this paper, the autonomy of an agricultural mobile robot is enhanced in a structured environment (greenhouse farm) to locate an optimum route such that the robot performs a selective and variable spray of pesticides to the plants. To realize this, a robust vehicle routing problem (VRP) scheme is designed to navigate the robot autonomously while making intelligent decisions to fulfil the pesticide demands at each node (infected plants). The improved non-dominated sorting genetic algorithm (INSGA-III) is adopted to solve this fully integer problem based on three (3) test cases carried out with 8, 32 and 56 infected plants respectively for validation. The results obtained show a trade-off solution as the Optimal INSGA-III is significantly lower than NSGA-III in terms of solution quality. On the other hand, a significant reduction in run times of between 66% and 76% and 76–93% was obtained for all test case scenarios for population sizes of 100 and 1500 respectively. |
|---|