Fruit detection system and an end effector for robotic harvesting of Fuji apples

Abstract

 The challenges in developing a fruit harvesting robot are recognizing the fruit in the foliage and detaching the fruit from the tree without damaging either the fruit or the tree.  The objectives of this study were to develop a real-time fruit detection system using machine vision and a laser ranging sensor and to develop an end effector capable of detaching the fruit in a way similar to manual pick.  The Fuji apple variety was used in this study. In the detection of the fruit, machine vision was combined with a laser ranging sensor.  The machine vision recognized the fruit and the laser ranging sensor determined the distance.  The system detected a single fruit with 100% accuracy in both front and back lighted scenes with ±3 mm accuracy in distance measurement.  To detach the fruit from the tree, an end effector was developed with a peduncle holder and a wrist; the peduncle holder pinches the peduncle of the fruit and the wrist rotates the peduncle holder to detach the fruit.  Field test results of the end effector showed more than 90% success rate in detaching the fruit with average time use of 7.1 seconds.

Keywords: apple, end effector, image processing, machine vision, robotic harvesting, Japan

Citation: Bulanon D. M., and T. Kataoka.  Fruit detection system and an end effector for robotic harvesting of Fuji apples.  Agric Eng Int: CIGR Journal, 2010, 12(1): 203-210.