Insect Killing Robot for Agricultural Purposes
Hammed Obasekore, Mohammad Fanni, Sabah M. Ahmed
- Year
- 2019
- Citations
- 7
Abstract
There is no doubt that prevention is better than cure, preventing insect infestation on farm will save more than 40% of agricultural farm destruction [1]. Therefore, this paper presents the design and simulation of an agricultural robot. It is based on the execution of a harmful insect detection algorithm and equipped with non-chemical based killing mechanism. Previous agricultural insect/pest killing robots aim at reducing bulk chemical application on farm by dosing chemical (pesticide) on the agricultural farm after it has been affected. However, this work took a natural approach by adopting killing method of a bird scientifically refer to as BUBULCUS ibis. The objective of the proposed system is to detect the insect at early stage (larvae) and then kill it. This approach shows that we could handle several insects with simple robot and ecofriendly killing mechanism. The designed mobile manipulator robot has a 4-DOF manipulator mounted on a 2-DOF skid driven mobile platform Seekur Jr. The manipulator link lengths have been optimized to cover the workspace with maximum manipulability, and the cross sections have been designed for minimum deflection. The robot has been equipped with an eco-friendly laser light of 480 nm wavelength, 7W power as a killing mechanism and 2 RGB cameras feeds into our detection algorithm. Results from the co-simulation of ADAMS MSC and MATLAB/SIMULINK with computer vision toolbox shows a good detection capability and controller response with minimal tracking error. Significant correction of the approximate initial position was achieved with image-based visual servoing. The simulation results indicates the success of our proposed system.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002