Faculty Profiles - ISHII Kazuo

Other Link： https://ci.nii.ac.jp/naid/130008134856

3D Plane Detection Algorithm for Detection of Station Platform Edge

KATAYAMA Daigo, ISHII Kazuo, YASUKAWA Shinsuke, NAKADOMARI Satoshi, WADA Koichi, BEFU Akane, YAMADA Chikako

The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) ( The Japan Society of Mechanical Engineers ) 2021 ( 0 ) 1P1 - F11 2021.06

Authorship：Corresponding author Language：Japanese Publishing type：Research paper (conference, symposium, etc.)

In this paper, in order to evaluate the plane detection algorithm for detecting the edge of a station platform, we verified the algorithm by running it on the 3D distance data measured at the actual station platform. As the result, we were able to detect the plane with the error that is small enough to distinguish it from steps such as stairs. However, the correct answer rate and the true negative rate were greatly reduced by the distant point clouds and the movement of the sensor itself, so it is necessary to remove the distant point clouds and to reduce the error caused by the movement of the sensor itself in the current algorithm. In the future, we will verify the algorithm in other situations, and implement and verify additional processing.

DOI： 10.1299/jsmermd.2021.1P1-F11

Other Link： https://ci.nii.ac.jp/naid/130008134919

Vision-Based Behavior Strategy for Tomato Harvesting Robot (V):-Estimation of total harvesting time using the tomato growth state map-

FUJINAGA Takuya, ISHII Kazuo

The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) ( The Japan Society of Mechanical Engineers ) 2021 ( 0 ) 1P2 - A04 2021.06

Authorship：Last author,　Corresponding author Language：Japanese Publishing type：Research paper (conference, symposium, etc.)

This paper presents an estimation method of total harvesting time using the tomato harvesting robot developed in this study. In this robot, the occlusion ratio of obstacles to the target tomato is one of the factors for harvestability. The occlusion ratio was quantified, and the criteria for tomatoes that are easy for this robot to harvest was determined based on the results of the harvesting experiment. Using the tomato growth state map, the total harvesting time was estimated from the location data of the tomatoes that can be shipped with the occlusion ratio of 0.07 or less.

DOI： 10.1299/jsmermd.2021.1P2-A04

Other Link： https://ci.nii.ac.jp/naid/130008135064

Research on human-robot cooperative systems for a robot symbiotic society

TOMINAGA Moeko, TAKEMURA Yasunori, ISHII Kazuo

The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) ( The Japan Society of Mechanical Engineers ) 2021 ( 0 ) 1A1 - K04 2021.06

Authorship：Last author,　Corresponding author Language：Japanese Publishing type：Research paper (conference, symposium, etc.)

In the realization of symbiosis between humans and robots, how robots can understand human behavior is an important issue. In the soccer robot, it is possible to show that human-robot symbiosis in a dynamic environment is possible if humans and robots share the same understanding of behavior. In this paper, a robot in a simulator that behaves according to a certain rule is analyzed using a self-organizing map, and the rule is mapped to two dimensions as a feature map and evaluated. By using this map, a system that selects the next action from the position of each player is completed. This system can also be adapted to humans who act according to certain action decision rules.

DOI： 10.1299/jsmermd.2021.1A1-K04

Other Link： https://ci.nii.ac.jp/naid/130008134930

Motion Estimation of Visual Target Using Event-Based Vision and Spiking Neural Network

YASUKAWA Shinsuke, YOSHIMATSU Hidetaka, ISHII Kazuo

The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) ( The Japan Society of Mechanical Engineers ) 2021 ( 0 ) 2P2 - H05 2021.06

Authorship：Last author,　Corresponding author Language：Japanese Publishing type：Research paper (conference, symposium, etc.)

We proposed a method for estimating the angular velocity of a rotating visual target robustly to changes in illumination conditions using event-based vision and spiking neural networks (SNNs). By using the output of the event-based vision directly as input to the SNN, the image processing function can be achieved by keeping the advantages of the vision sensor in the previous stage. A board printed with natural images was placed at a certain distance from the vision system as a viewing target. The vision system captured rotating objects at various angular velocities under multiple lighting conditions to generate a data set. Using this data set, we verified whether the SNN can estimate the visual target. We achieved about 80% accuracy on both the training and test datasets in both bright and dark lighting environments.

DOI： 10.1299/jsmermd.2021.2P2-H05

Other Link： https://ci.nii.ac.jp/naid/130008135692

Towards building of an underwater robot monitoring fish appetite for feeding management:Development of sensors for measuring fish-generated underwater currents as indicator for feeding behavior

SOLPICO Dominic, NISHIDA Yuya, ISHII Kazuo

ロボティクス・メカトロニクス講演会講演概要集 ( The Japan Society of Mechanical Engineers ) 2021 ( 0 ) 1P1 - B17 2021.06

Authorship：Last author,　Corresponding author Language：English Publishing type：Research paper (conference, symposium, etc.)

Predicting fish feeding behavior is crucial in improving marine aquaculture production. We are addressing this problem using a novel approach – measuring underwater currents generated by fish, especially at feeding times. In this paper, we present our development of a suite of sensors that will collect these measurements, as we investigate their relationship with fish behavior during feeding. We added we have further developed our sensor suite by adding another current sensor for calibrating the previously developed propeller sensors and tested them along a narrow river to examine the relationship of their measurements. While a strong linear relationship was observed between the measurements, it is difficult for the propeller sensors to measure currents accurately at slower currents. Experiment at the fish farm is still needed to determine if this constraint is acceptable in our application.

DOI： 10.1299/jsmermd.2021.1P1-B17

Other Link： https://ci.nii.ac.jp/naid/130008134963

団体スポーツにおける自己組織化マップを用いたコーチング

富永萌子，武村泰範，石井和男

第33回自律分散システム・シンポジウム ( 計測自動制御学会システム・情報部門 ) 2021.03

Acoustic impedance measurement through the modelling of ultrasonic wave transmission Reviewed International journal

Mochizuki R., Nishida Y., Ishii K.

Proceedings of International Conference on Artificial Life and Robotics ( ALife Robotics Corporation Ltd. ) 2021 271 - 274 2021.01

Authorship：Last author,　Corresponding author Language：English Publishing type：Research paper (international conference proceedings)

2021.01.21 - 2021.01.24

In food industry, shortage of workers is a serious problem. Automation of food handling is a critical nowadays. To alleviate the damage during food picking by robotic hand, we propose non-contact acoustic impedance estimation with ultrasonic wave. We have the assumption of the correlation between hardness and acoustic impedance, and, built up ultrasonic transmission model considering attenuation by reflection and absorption, then, made an experiment to estimate the impedance. As the result, we succeeded in detecting acoustic impedance without contact.

DOI： 10.5954/ICAROB.2021.OS23-6

Other Link： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85108800024&origin=inward

A Greenhouse Project toward Smart Agriculture Reviewed International journal

Ishii Kazuo, Nishida Yuya, Yasukawa Shinsuke, Shirahashi Kanako, Takemura Yasunori, Matsuo Takayuki

Proceedings of International Conference on Artificial Life and Robotics ( ALife Robotics Corporation Ltd. ) 26 409 - 412 2021.01

Authorship：Lead author,　Corresponding author Language：English Publishing type：Research paper (international conference proceedings)

2021.01.22 - 2021.01.24

In the future estimation of 2050, the food demand increases 70% and the production decreases 15% caused by global warming, and farmer population be 1/5 of current workers. Until 2050, we need an agricultural system of twice production with the same farmland area and 5 times effective operations. To realize the sustainable society, smart agriculture including robot technology, AI, IoT is one of the solutions for food issues. We have been working for a greenhouse project under enPiT-everi for implementation of robotic, AI and IoT technologies to agriculture. In this paper, we introduce the project and robotic applications.

DOI： 10.5954/ICAROB.2021.OS22-5

Other Link： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85108793739&origin=inward

Tomato-harvesting-robot competition towards smart agriculture Invited Reviewed International journal

Kazuo Ishii, Takayuki Matsuo, Yasunori Takemura, Takashi Sonoda, Yuya Nishida, Shinsuke Yasukawa, Takuya Fujinaga

Proc. of ICAROB2021 1 - 5 2021.01

Authorship：Lead author Language：English Publishing type：Research paper (international conference proceedings)

2021.01.21 - 2021.01.24

In agriculture, the aging and depopulation of farmers cause the shortages of farmers and manpower. Most of commercialized robots are industrial robots for factory automation, and most of robots for the first industry, agriculture, forestry and fisheries are still under developing. The reasons are cost-efficiency of the robotization, safety of the works using robots, difficulty of outdoor operations, and knowledge transfer problem from farmers to computer, etc. As one of solutions for the problems, robot technology into the agriculture is expected to contribute to the laborsaving, improvement of production, production line automation, and also the management toward smart-agriculture. We organize the Tomato-harvesting-robot competition to offer the research field and welcome researchers into agricultural robotics.

DOI： 10.5954/ICAROB.2021.PS-1

Crack detection in a concrete structure using an underwater vehicle Reviewed International journal

Nishida Y., Sohara N., Yasukawa S., Ishii K.

Proceedings of International Conference on Artificial Life and Robotics ( ALife Robotics Corporation Ltd. ) 2021 777 - 781 2021.01

Authorship：Last author,　Corresponding author Language：English Publishing type：Research paper (international conference proceedings)

2021.01.21 - 2021.01.24

In this paper, to realize efficient underwater infrastructure inspection, automatic crack detection by image processing is proposed. In first process of our method generates enhanced image based on the absorbance from the turbidity meter and removes background component, and then detects crack from the enhanced image by using decision tree learning algorithm. This paper explains the algorithm of our method and shows evaluation experiment results.

DOI： 10.5954/ICAROB.2021.OS23-1

Other Link： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85108855210&origin=inward

Underwater image reconstruction using convolutional auto-encoder Reviewed International journal

Yasukawa S., Raghura S.S., Nishida Y., Ishii K.

Proceedings of International Conference on Artificial Life and Robotics ( ALife Robotics Corporation Ltd. ) 2021 262 - 265 2021.01

Authorship：Last author,　Corresponding author Language：English Publishing type：Research paper (international conference proceedings)

2021.01.21 - 2021.01.24

One of the main tasks of AUVs is to capture deep-sea images like fishes, crabs, other living organisms and resources for information leading to research on deep-sea ecosystems. Acoustic transmission are used to establish wireless underwater communications between the AUV and the ship. However, there are some limitations in the communication channels due to limited bandwidth, multi-path, temperature distribution and change in the direction of transmitting source and receiving sensor which results in losses in data being transmitted. Initially, the captured images are enhanced to reduce the effect of light attenuation and then compressed for transmission through acoustic modems. Only an important part of image is being transmitted through set of data packets. The received data packets in the ship will be reconstructed to predict the presence of living organisms. The loss in data during transmission creates a difficulty for the operators to predict the exact information. In this research, to compensate this transmission loss, an efficient compression and reconstruction technique using convolutional autoencoder with minimal distortion is proposed. Finally, for evaluation of the proposed image compression technique, the quality of reconstruction of images with and without data loss will be compared using the quality metrics signal to noise ratio (PSNR), structural similarity index(SSIM) and perceptual quality of image.

DOI： 10.5954/ICAROB.2021.OS23-4

Other Link： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85108853723&origin=inward

Tomato-harvesting robot competition: Aims and developed robot of 6th competitions Reviewed International journal

Matsuo T., Takemura Y., Sonoda T., Nishida Y., Yasukawa S., Ishii K.

Proceedings of International Conference on Artificial Life and Robotics ( ALife Robotics Corporation Ltd. ) 2021 397 - 400 2021.01

Authorship：Last author,　Corresponding author Language：English Publishing type：Research paper (international conference proceedings)

2021.01.21 - 2021.01.24

In general, farm work is often hard work. In recent years, the number of farm laborers has been decreasing due to the aging of the workforce. Therefore, there is a need to automate agricultural work, and we are organizing a tomato harvesting robot competition to automate tomato harvesting. The competition includes a Junior Division for high school students and a Senior Division for college students. In this paper, we report on the results of 6th tomato harvesting robot competition.

DOI： 10.5954/ICAROB.2021.OS22-2