THE DEVELOPMENT OF AUTONOMOUS TOMATO HARVESTING ROBOT ARM BY IMAGE PROCESSING

Article Sidebar

pdf
Published: Apr 30, 2022
Keywords:
SCARA Robot Arm Autonomous Robots Image Processing Tomato Harvesting

Main Article Content

Phubet Phiphithirankarn
Teerawat Sattaso
Wipaporn Boonla
Wirasak Wiriyanamchai

Abstract

The objective of this research were to design and invent an autonomous tomato harvesting robot arm by image processing, and to determine the efficiency of the robot arm invented. The research was divided into 5 steps: designing and inventing of the robot arm, developing an image processing software and calculating the position of the tomato, an experiment the robot arm movement, an experiment tomato harvesting on a simulated screen, and an experiment tomato harvesting on the real tomato plant.


The results of research found that (1) the robot arm is SCARA with 4 degrees of freedom (PPRR), consisting of links, joints, gripper, cameras and infrared sensor. Using the stepping motors to move the robot arm in vertical, horizontal and angular displacement. (2) The developed image processing software consists of 9 control sections, all sections working correctly and the position of the tomato can be transmitted to the microcontroller without error. (3) The robot arm can move along the y axis in the correct direction, the largest +y axis percentage error was y = 5.00 %, gif.latex?\theta_{1} = 3.73 %, gif.latex?\theta_{2} = 2.15 %, and the largest -y axis percentage error was y = 0.00 %, gif.latex?\theta_{1} = 3.73 %, gif.latex?\theta_{2} = 1.65 %. (4) The robot arm can accurately harvest all the tomatoes on the simulated screen in order of detection without error. (5) The robot arm was able to accurately harvest all the tomatoes on the real tomato plant in the order of detection without error. All the experimental results showed that an autonomous tomato harvesting robot arm by image processing can works accurately and efficiently.

Article Details

Issue
Vol. 10 No. 1 (2022): January - April
Section
Research Article

References

Afonso, M., Fonteijn, H., Fiorentin, F. S., & Lensink, D. (2020). Tomato Fruit Detection and Counting in Greenhouses Using Deep Learning. Frontiers in Plant Science, 11. 571299. DOI:10.3389/fpls.2020.571299.

Corke. (2017). Inverse Kinematics for a 2-Joint Robot Arm Using Geometry. Australian Centre for Robotic Vision (ACRV).

Khoshroo, A., Arefi, A., & Khodaei, J. (2014). Detection of Red Tomato on Plants using Image Processing Techniques. Agricultural Communications, 2, 9-15.

Malik, M. H., Zhang, T., Li, H., Zhang, M., Shabbir, S., & Saeed, A. (2018). Mature Tomato Fruit Detection Algorithm Based on improved HSV and Watershed Algorithm. IFAC-PapersOnLine, 51(17), 431-436.

Xiong, Y., Peng, C., Grimstad, L., From, P. J., & Isler, V. (2019). Development and field evaluation of a strawberry harvesting robot with a cable-driven gripper. Computers and Electronics in Agriculture, 157, 392-402.

Zhao, Y., Gong, L., Liu, C., & Huang, Y. (2016). Dual-arm Robot Design and Testing for Harvesting Tomato in Greenhouse. IFAC-PapersOnLine, 49(16),

-165.