The reduced number of employments in agriculture, and the increased number of cherry farms required the development of cherry automation solutions. Cherries are sorted manually for size and graded visually by farmer experts. A Hanedashi cherry sorting system was developed to collect the not good fruits from a cherry processing line using a robotic arm and a camera. Performance resulted in a successful collection rate of 90% and collection time of one cherry per 3.5 seconds. Moreover, a dataset containing images of healthy cherries and images of cherries with eleven different anomalies (bird damage, bowl crack, brown, crack, insect damage, malformation, malformation twins, mold, twins, unripe, wilt) with their respective ground truth parts was created. At the same time, an anomalous cherry detection model was trained using Anomalib to further enhance the sorting of cherries, obtaining a correct classification rate of 0.94 and correct anomaly segmentation Accuracy of 0.76. The sorting system achieved Accuracy, Precision, and Recall scores of 0.94, 1.00, and 0.87, respectively, while the detection model achieved scores of 0.95, 0.95, and 0.99, respectively.

An endoscopy capsule is a device with a diameter of approximately 11 mm and a length of approximately 26 mm; it is ingested to capture images within the gastrointestinal tract. Compared with conventional endoscopy, capsule endoscopy places a lesser burden on patients and enables the observation of the small intestine. This noninvasive technique generates more than 50,000 images in a single examination. Because of the necessity for physicians to visually inspect each image, the diagnostic process is time-consuming and labor-intensive. In this study, our objective was to alleviate the workload of medical professionals, prevent the oversight of lesions, and provide diagnostic support through the automatic detection of abnormalities. We used You Only Look Once version 5 (YOLOv5), a widely used object-detection model. Following training of the model using four types of lesion images, two types of diagnostically inconclusive images, and background images, it autonomously detected lesion candidates and diagnostically inconclusive images. The accuracies for polyps, ulcers, telangiectasia type A, telangiectasia type B, bubble images, and images with intestinal fluid adhesion were 96%, 99%, 74%, 98%, 98%, and 87%, respectively. In the future, we plan to increase accuracy by further training the model with additional images of other abnormalities and diagnostically inconclusive images.

We are conducting research on operating a motorized wheelchair using gaze input to help a person with multiple physical disabilities, who cannot move their hands and feet, and whose speech is unclear, to move at their own will. To operate a motorized wheelchair by gaze input and to move around in a real environment, the ability to move and stop the eye and spatial awareness is critical. In this study, we report the results of an evaluation of gaze input on a monitor using a small mobile robot and a drone. We proposed a score of gaze input calculated from the tracking time and the distance between the tracking target and gazing point and used the proposed score to evaluate the ability for gaze input. Evaluation experiments were conducted continuously over a long period of time, eight months for the experiments using the robot and five months for the experiments using the drone. From the experimental results, we confirmed that the score of gaze input improved with continuous training and evaluation of gaze input. We compared the results between subjects with multiple physical disabilities and able-bodied subjects and found significant differences. In addition, subjects with multiple physical disabilities had difficulty maintaining their posture and their head movement was a factor in the lower scores.

The sorting operations of cherry are conducted manually by cherry farmers; however, they require skillful workers to examine each fruit, and evaluation is subject to variation. This study analyzed the performance of an automatic cherry sorting system. The key to sorting cherries is to sort the fruits accurately without producing damage, along with quick size estimation and grade identification. An image analysis system using the hue saturation lightness (HSL) color model to identify the grade of cherries was implemented. Size was estimated by the equator diameter of the fruit, and grade was determined by the percentage of colored area on the surface of the fruit. A prototype system for automatic cherry sorting into three grades was developed. A second version of the prototype was developed to include size estimation. In both prototypes, an air eject mechanism with individual collection bins were prepared for a non-invasive handling of the fruits. A stable accuracy of 72.4% for size estimation and 82.5% for grade identification were achieved. The findings favor the use of automatic systems for the sorting of cherries according to fruit grade in combination with fruit size.

The accuracy of the inspection of the capsule endoscope is increased, if it can be manipulated by the operator with wireless communication. To develop it, the feasibility is important, however there are various studies. We consider the behavior of the endoscope in the broken-down. Therefore, this paper describes the manipulatable capsule endoscope that can behaves as the normal endoscope even if it is broken in the body of the patient, and that is not modified from the normal endoscope drastically. The fin for the maneuverability is knit using the biodegradable string for the surgical operation which is dissolved in the body, since the various shape can be realized. The safety is guaranteed, since the fin is dissolved in case that it comes off in the body. And, the small motor is employed as the actuator for the movement of the fin in the fundamental experiment to prevent from changing the shape of the capsule endoscope. The proposed endoscpoe can behave as the normal capsule endoscope, since the shape is similar to the normal capsule endoscope. Using it, the feasibility of the proposed endoscope is confirmed by the fundamental experiments.

This paper presents the proto-flight model test results of X band synthetic aperture radar for small satellites with 130kg mass. The specification of SAR performance is single polarization SAR with 3m ground resolution for strip map mode. Optional 1 m ground resolution can be achieved with sliding spot light mode under condition of limited valus of NESZ. The paper describes the unique antenna system, the RF power amplifier, high speed data storage/transmission system, and the ground SAR response test results.

Increasing the export of fruit is vital for the Japanese economy. In this study, we focused on the peach trade as it is the third most transported fruit in Japan. The peach is a very sensitive fruit; therefore, proper packaging is important. We proposed a special packing sheet that we named the “concavo-convex sheet” developed through a simple mechanism. However, there were some problems in creating this sheet. This study describes the new mechanism for creating the concavo-convex sheet, and a real machine using the installed mechanism was developed. As a result, it was confirmed that the sheet can be realized by the new machine.

An important goal for the Japanese economy involves increasing the export of fruits. Especially, the export of peaches to Taiwan is an important part of trade for Japan. However, the peach fruit moth poses a serious problem. The moth is not native to Taiwan. Therefore, the moths that are exported with peaches may cause ecological damage in Taiwan. We are in the process of developing a peach fruit inspection system involving the use of X-rays. A handling unit that is a part of the inspection system is required to softly hold the peach without damaging it. This study describes a concavo-convex sheet developed by two nonwoven fabric clothes that is adapted for the inspection system. There are two important factors involved for incorporating the sheet in the inspection system, namely, the friction coefficient of the sheet and damage protection for the peaches. These factors are investigated by performing experiments that use several real, fresh peaches. The results confirm that the concavo-convex sheet satisfies the important properties necessary to employ the system for peach fruit inspection.

This paper describes an unique sheet developed from non-woven fabric that can be used to reduce transportation shock experienced by fruits that are easily damaged, such as peaches or strawberries, when transporting to foreign countries where there is a significant demand for these fruits. The proposed sheet comprises two non-woven fabric cloths suitable for packing these types of fruit. The non-woven cloth has useful characteristics such as air permeability, sealing properties, and X-ray transmission properties that make it suitable for transporting easily damaged fruit. In this paper, the application of the proposed sheet is applied for the packing of the fruits, however, the sheet that has the air permeability and shock resistance property is useful for the assistive robot and human interaction robot. And, the sheet is made manually, since the method to produce it is not constructed. The task of the human is reduced, if the mechanism for making the sheet can be realized. This paper describes that the properties of the sheet are introduced, and that the performance is investigated by experimental methods. Finally, the mechanism for producing the sheet is described and investigated using an experimental prototype.

During a disaster, it may be difficult for the visually impaired to use infrastructure or to obtain care worker's support. To support the independence of the visually impaired, we have developed a wearable travel aid that assists in safe travel, including navigating stairs, without special infrastructure. Because safe navigation requires accurate position estimation, our system fuses data from different sensors to estimate a pedestrian's position. In this paper, we propose a floor estimation method based on fuzzy inference with a laser range finder (LRF). When walking on a floor, an image processing system and a LRF are used together to estimate the position, but when walking on stairs, a second LRF is used to estimate the floor and detect obstacles. The experimental results show that our floor estimation is also useful for position estimation.

This paper describes proficiency evaluations of three Japanese Input Methods using a portable eye-controlled communication device for users with disabilities such as Cerebral Palsy or ALS (Amyotrophic Lateral Sclerosis). We proposed three Japanese Input Methods and implemented them. Our quantitative evaluation, subjective evaluation by questionnaire and physiologic evaluation with NIRS (Near Infra-Red Spectroscopic) show the effectiveness of the “Roman letters” input method and the “modified beeper” input method. The results of proficiency evaluation show the effectiveness of the “Roman letters” input method.

This paper describes the Japanese Input Method using a portable eye-controlled communication device for users with disabilities such as Cerebral Palsy or ALS (Amyotrophic Lateral Sclerosis). We proposed three Japanese Input Method and implemented them. Our quantitative evaluation, subjective evaluation by questionnaire and physiologic evaluation with NIRS (Near Infra-Red Spectroscopic) show the effectiveness of the “Roman letters” input method and the “modified beeper” input method.

We research and develop it aiming at the realization of a scooping goldfish robot copied from the method that a human being takes. This paper describes estimation method of the 3D position of a goldfish in a water tank. What is important and basic in distinguishing a timing to scoop a goldfish is to estimate the 3D position.

A wearable travel aid to guide visually impaired without special infrastructures has been developed. We call this system WEarable walKing mate system (WEK). The WEK has three functions that 1) Create courses data, 2) Guide a visually impaired to the destinations, and 3) Warm the dangerous places. This paper described the estimation method of travel distance using Optical Flow in the WEK, which is effective for various ways of walking. The experimental results in an indoor environment show the each error of estimated travel distance is less than at previous method to three kinds of how, a shuffle, a natural walking, and a march. There are shown that the WEK is efficient for guiding the visually impaired to the destinations.

A stick diagram extraction program SKELETON has been developed to make use of an existing handcrafted layout in a symbolic circuit layout system. It transforms a physical layout into an equivalent stick diagram. The concepts of centralized terminals and dispersed terminals are used for technology change and scaling. A heuristic procedure is presented to reduce jogs.>