Mitsuji Monta

Machine vision based quality evaluation of Iyokan orange fruit using neural networks

It is a common belief that a sweet Iyokan orange fruit is reddish in color, of medium size, with a height to width ratio less than one, and having a glossy surface. However, the criteria are ambiguous and vary from people to people and locations to locations. In this paper, sugar content and acid content of Iyokan orange fruit were evaluated using a machine vision system. Images of 30 Iyokan orange fruits were acquired by a color TV camera. Features representing fruit color, shape, and roughness of fruit surface were extracted from the images. The features included R/G color component ratio, Ferets diameter ratio, and textural features. These features and weight of the fruit were entered to the input layers of neural networks, while sugar content or pH of the fruit was used as the values of the output layers. Several neural networks were found to be able to predict the sugar content or pH from the fruit appearance with a reasonable accuracy.

End-Effectors for Tomato Harvesting Robot

Two types of robotic end-effectors capable of harvesting tomato fruits were manufactured based on the physical properties of tomato plant and tested. The first prototype end-effector consisted of two parallel plate fingers and a suction pad. The fingers pick a fruit off at the joint of its peduncle after the suction cup singulates it by vacuum from other fruits in the same cluster. From the results of harvesting experiment, the end-effector could not harvest fruits with a short peduncle because the fruits were detached from the suction pad before they were gripped by the fingers. Therefore, the second prototype in which the functions to detect the fruit position and the air pressure in the pad were installed, was made, so that the fruits were harvested regardless of the length of their peduncle. Experimental results using the improved end-effector showed that the fruits were harvested successfully with no damage.

Fruit harvesting robots in Japan

We have developed harvesting robots for tomato, petty-tomato, cucumber and grape in Japan. These robots mainly consist of manipulators, end-effectors, visual sensors and traveling devices. These mechanisms of the robot components were developed based on the physical properties of the work objects. The robots must work automatically by themselves in greenhouses or fields, since we are considering for one operator to tend several robots in the production system. The system is modeled after Japanese agriculture which is commonly seen to produce many kinds of crops in greenhouses and in many small fields intensively. Bioproduction in space is somewhat similar to the agricultural system in Japan, because few operators have to work in a small space. Employing robots for bioproduction in space is considered desirable in near future. The following is a description of the harvesting robots.

Agricultural robot in grape production system

A multipurpose agricultural robot which works in vineyard has been studied. This robot, which consists of a manipulator, a visual sensor, a travelling device and end-effecters, is able to do several works by changing the end-effecters. Four end-effectors for harvesting, berry thinning, spraying and bagging have been developed for this robot system. The harvesting end-effector which grasps and cuts rachis was able to harvest bunches with no damage. The berry thinning end-effector which consists of three unified bunch shape parts. The spraying end-effector sprays the target uniformly, and the bagging end-effector is able to put bags on growing bunches one by one continuously. From the experimental results in a field and laboratory, it was observed that each end-effector could perform efficiently.

Features Extraction for Eggplant Fruit Grading System Using Machine Vision

Machine vision based grading for agricultural crops has been well developed and accepted as an attractive grading method. However, machine vision based grading for eggplant fruit is not available yet. This study reports on the attempt to develop an eggplant grading machine using six CCD cameras as the sensing device. Feature extraction algorithms were developed to extract eggplants features, i.e., length, diameter, volume, curvature, color homogeneity, calyx color, calyx area, and surface defect. The system could acquire six images per fruits covering the entire surface of the eggplant fruits. An agreement rate of 78.0% was achieved in the feasibility study where the machine vision based grading was compared with manual grading. The throughput of the developed system was 0.3 second per fruit. Details of the system, an outline of the algorithm, and performance results are reported in this article.

n End-Effector and Manipulator Control for Tomato Cluster Harvesting Robot

An end-effector and a control method for tomato-cluster harvesting manipulator are proposed in this study. When fruit cluster harvesting is conducted, peduncle direction is necessary to cut, but is not easy to detect because peduncles are often occluded by leaves, stems and fruits. The end-effector needs to grasp the peduncle without its direction information. An end-effector which can surround main stem and can grasp and cut the peduncle by fingers was made as a trial. When a tomato cluster is transported into a container with the manipulator, both its transportation speed and vibration damping are required. Such a control problem is generally called a motion and vibration control (MOVIC). An input shaping method is one of the representative control methods for the MOVIC. It requires accurate natural frequencies of the manipulating target fruit cluster to damp the flexible vibration when the robot is accelerating the target. The tomato clusters, however, have individual variation with natural frequencies; hence, it is not easy to apply the input shaping method directly. To overcome this problem, identification method of natural frequency was combined with the input shaping method in the proposed method. This identification was based on real time sensing data from a machine vision and a force sensor and database of physical properties of the tomato clusters. Usefulness of the proposed method was verified through both numerical simulations and hardware experiments.

Strawberry Harvesting Robot on Table-top Culture

In this paper, it is reported that a robot was developed for harvesting strawberry grown on table top culture. The robot mainly consisted of a 4 DOF manipulator, a harvesting end-effector using sucking force and a visual sensor. As its manipulator, a Cartesian coordinate type was adopted and it was suspended under the planting bed of strawberry. The robot was capable of moving along the planting bed without a traveling device because one prismatic joint of the manipulator played the role of a traveling device. The end-effector could suck a fruit using a vacuum device and it could compensate detecting errors caused by the visual sensor. The visual sensor gave the robot two dimensional information based on an acquired image and fruit depth was calculated as an average value of previously harvested fruit depths obtained from end-effector positions when the robot actually harvested. The end-effector moved toward a target fruit based on the three dimensional position of the target fruit until the fruit was detected by three pairs of photo-interrupters on sucking head. After cutting the peduncle by using the robots wrist joint, the fruits passed the tube and were transported to the tray. From the results of the harvesting experiments, it was observed that the robot could harvest all target fruits with no injury, and that depth measurement by a visual sensor was simplified because a distance between the robot and the fruits was kept an approximately constant by suspending the robot under the planting bed.

Chrysanthemum Cutting Sticking Robot System

Cutting sticking operation is essential on a chrysanthemum production to enhance its productivity, since many cuttings can be obtained from one mother plant. Usually, human being manually sticks the cuttings to plug tray, however, it takes a lot of time and much labor, since the number of cuttings is said to be about 200 million in a district where yields the highest number of chrysanthemums in Japan, so automation of this operation is desired. The robotic cutting sticking system mainly consisted of three sections; a cutting providing system, a leaf removing device and a planting device. First, a bundle of cuttings was put into a water tank. The cuttings were spread out on the water by vibration of the water tank. The cuttings were picked by a manipulator based on information of cutting position from TV camera. Secondly, another TV camera detected the position and direction of cutting transferred from the water tank by the manipulator and indicated the grasp position of the cutting for the other 5 DOF manipulator moving. Thirdly, the manipulator moved the cutting to a planting device through the leaf removing device and then the cuttings were stuck into a tray by the planting device. In this paper, outline of the robotic components is described.

Development of an End-Effector for a Tomato Cluster Harvesting Robot

Abstract An end-effector was developed for a tomato cluster harvesting robot. This end-effector can harvest not individual fruits but a whole fruit cluster to improve the robots harvest efficiency. Experiments for harvesting tomato clusters were conducted in a high-density plant training system. According to a harvesting algorithm, the end-effector was able to perform well, even when target peduncle orientations were not given. Although the success rate of harvesting tomato clusters was 50 %, it is considered that this rate would improve if an end-effector is used for the high-wire tomato plant training systems in Dutch systems where the node lengths of plants are long enough to loosely hold the main stems.

Basic constitution of a robot for agricultural use

Many studies on agricultural robots and on robot components such as manipulators, visual sensors, end-effectors and traveling devices have been performed to solve problems when robots work in fields or in greenhouses. In addition, productivity should also be considered in the agricultural production system in the case that the cultivation method and plant training system are changed so that the robot can work without trouble. In this study, a tomato harvesting robot is described as a example of an agricultural robot. First, the basic mechanism of the robot and the details of the robot components are developed based on the physical properties of the tomato plant and on the environmental conditions. Secondly, a cherry tomato harvesting end-effector is also developed so that the robot can harvest not only normal size tomatoes but also cherry tomatoes by changing the end-effector to make it a multi-purpose robot. Lastly, horticultural methods such as suitable cultivation methods and plant training methods for...