VISUAL FEEDBACK GUIDED ROBOTIC CHERRY TOMATO HARVESTING

Harvesting cherry tomatoes is more laborious than harvesting larger si ze tomatoes because of the high fruit density in every cluster: To sav e labor costs, robotic harvesting of cherry tomatoes has been studied in Japan. An effective vision algorithm, to detect positions of many s mall fruits, was developed for guidance of robotically harvested cherr y tomatoes. A spectral reflectance in the visible region war identifie d and extracted to provide high contrast images for the fruit cluster identification. The 3-D position of each fruit cluster was determined using a binocular stereo vision technique. The robot harvested one fru it at a time and the position of the next target fruit was updated bas ed on a newly acquired image and the latest manipulator position. The experimental results showed that this visual feedback control bared ha rvesting method was effective, with a success rate of 70%.