Field Operation of a Movable Strawberry-harvesting Robot using a Travel Platform

Abstract

This paper describes the development of a movable strawberry-harvesting robot that can be mounted on a travel platform, along with its practical operation in a greenhouse. The harvesting robot can traverse and enter an adjacent path and picking is performed with the travel platform halted on the travel path. Machine vision is used to detect a piece of red fruit and calculate its position in the three-dimensional space, whereupon its maturity level is assessed according to an area ratio determined by classifying the whole fruit into three areas: ripe, intermediate, and unripe area fractions. Sufficiently mature fruit are picked by the end-effector by cutting the peduncle. During operational tests in a greenhouse, our machine vision algorithm to assess maturity level showed a coefficient of determination of 0.84. Setting the maturity level parameter at 70 or 80% resulted in higher shippable fruit rates than the setting of 60%, because small unripe fruit positioned in front of larger ripe fruit were successfully skipped in the former case. Our results showed that a higher shippable fruit rate could be achieved later in the harvest season, reaching 97.3% in the test in June. The successful harvesting rate and work efficiency were 54.9% and 102.5 m h -1 , respectively.

An autonomous strawberry‐harvesting robot: Design, development, integration, and field evaluation

“…This problem was also pointed out by Hayashi et al (2014), who subsequently adjusted the thresholds on their system manually on the farm, as with our previous system. Raja et al (1998) proposed a statistical approach, in which light intensity was estimated over time, while other researchers have investigated how robots can learn to adapt to various lighting conditions (Sridharan & Stone, 2007).…”

“…When the 3D position of a target is obtained, its coordinates can be further utilized to instruct the movements of the manipulation. For strawberry detection, image processing based on color thresholding is a frequently applied method in research papers (Hayashi et al, ; Yamamoto et al, ), primarily due to the significant differences of color among ripe strawberries, green strawberries, and green plants. Peduncle detection is another widely researched harvesting step (Cui et al, ; Hayashi et al, ; Huang, Wane, & Parsons, ; Shiigi et al, ).…”

“…Various end‐effectors have been developed for strawberry‐harvesting robots. The most widely used is the scissor‐like end‐effector for fruit detachment purpose only (Cui et al, ; Hayashi et al, ; Yamamoto et al, ; AGROBOT Ltd.; Dogtooth Technologies Ltd.). With an additional suction device, the scissor‐like end‐effector might be able to hold fruit (Feng, Wang, Zheng, Qiu, & Jiang, ; Hayashi et al, ).…”

“…Various end-effectors have been developed for strawberry-harvesting robots. The most widely used is the scissor-like end-effector for fruit detachment purpose only (Cui et al, 2013;Hayashi et al, 2014;Yamamoto et al, 2010;AGROBOT Ltd.;Dogtooth Technologies Ltd.).…”

“…Generally, strawberry harvesting in cropping environment is very challenging. First, ripe strawberries are easily damaged and bruised (Dimeas, Sako, Moulianitis, & Aspragathos, 2015;Hayashi et al, 2014;Xiong et al, 2019). This feature requires gentle handling during manipulation procedures.…”