Robotic date fruit harvesting using machine vision and a 5-DOF manipulator |
| |
Authors: | Parvin Mohammadi Jafar Massah Keyvan Asefpour Vakilian |
| |
Affiliation: | 1. Department of Agrotechnology, College of Abouraihan, University of Tehran, Tehran, Iran;2. Department of Biosystems Engineering, Gorgan University of Agricultural Sciences and Natural Resources, Gorgan, Iran |
| |
Abstract: | Date fruits can be found at the highest point of the palm tree, so harvesting can be a dangerous task for humans. In this study, a robotic arm is presented to harvest date fruits. A manipulator, traveling on a U-shaped rail with four prismatic joints and one revolute joint, was designed and constructed to approach the fruits efficiently. The end-effector of the manipulator was an electric chainsaw capable of cutting the date bunch. Two cameras were located on the manipulator in perpendicular directions to capture images, which were then transmitted to a decision-making unit to control the speed of the manipulator links. The decision-making unit included three fuzzy inference systems that used the location data of the fruit bunch stems and the area of tree leaves in the images to determine the speed of electromotors of the trolley, horizontal link, and vertical link. An artificial palm tree with dimensions similar to a real palm tree was constructed to evaluate the performance of the robot. The performance of the robot was evaluated in various lighting conditions. The results showed that the introduced image processing algorithm could adequately detect the stems of the date bunches with accuracy, precision, and recall of 0.88, 0.92, and 0.96, respectively, in suitable lighting, that is, when there was sufficient natural lighting. Moreover, the experimental results revealed that the accuracy of the control system in cutting the stems was 87%, with a production loss of 5%. The proposed robot makes it possible to improve the capacity of using mechanized harvesting in date palm fields. |
| |
Keywords: | date palm tree fuzzy inference system image processing robotic harvesting |
|
|