Mobile Fruit Grading Robot -Concept and prototype-

Abstract

In this study, a mobile fruit grading robot for information-added product in precisionagriculture was developed. The prototype robot, which consisted of a manipulator, an endeffector,a machine vision system, and a mobile mechanism, was made. The robot couldacquire five fruit images from four sides and the top while its manipulator transported the fruitreceived from the operator. A preliminary experiment was conducted with 372 samples of sweetpepper in variety of TosahikariD in laboratory. A fruit mass prediction method was developedby use of the five images. Results indicated that the fruit mass was successfully estimated withprojection areas for the variety.