Faculty Profiles - ISHII Kazuo

Other Link： https://ci.nii.ac.jp/naid/130007944448

Long-term observation method using Cable-restricted Underwater Vehicle:-Self-localization based on cable constraints-

TANAKA Yoshiki, NISHIDA Yuya, ISHII Kazuo

The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) ( The Japan Society of Mechanical Engineers ) 2020 ( 0 ) 1P1 - C07 2020.05

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

There are many marine resources including mineral and energy resources in Japanese EEZ and those have been surveyed by Underwater vehicles. It is expected that time-varying data will be continuously obtained with low risk in environmental surveys of the seabed. Therefore, we proposed the long-term observation method using Cable-restricted Underwater vehicles.

DOI： 10.1299/jsmermd.2020.1P1-C07

Other Link： https://ci.nii.ac.jp/naid/130007943421

Behavior Learning System for Robot Soccer Using Neural Network

TOMINAGA Moeko, TAKEMURA Yasunori, ISHII Kazuo

The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) ( The Japan Society of Mechanical Engineers ) 2020 ( 0 ) 2A1 - R06 2020.05

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

With the progress of technology, the realization of a symbiotic society with human beings and robots sharing the same environment has become an important subject. An example of this kind of systems is soccer game. Soccer is a multi-agent game that requires strategies by taking into account each member's position and actions. In this paper, we discuss the results of the development of a learning system that uses SOM to select behaviors depending on the situation.This system can reproduce the action selection algorithm of all players in a certain team, and the robot can instantly select the next cooperative action from the information obtained during the game.Because of this system, common sense rules was shared to learn an action selection algorithm for a set of agents, not only a team consisting of robots alone, but also a group of heterogeneous agents consisting of humans and robots.

DOI： 10.1299/jsmermd.2020.2A1-R06

Other Link： https://ci.nii.ac.jp/naid/130007943934

Stiffness Measurement of Object Targeted for Robotic Hand

MOCHIZUKI Ryuugo, NISHIDA Yuya, ISHII Kazuo

The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) ( The Japan Society of Mechanical Engineers ) 2020 ( 0 ) 1A1 - K06 2020.05

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

In food industry, autonomous food arrangement is expected. For the achievement of safety food arrangement by robots, in order to prevent from damaging food, rigidity of the hands is hopeful to be adjusted according to the food stiffness. Measurement of the food stiffness should be estimated before handling. In this research, we propose non-contact stiffness measurement with ultrasound to enable variable rigidity of hands while food handling is ongoing.We measured power spectrum of ultrasound reflected on food. As the result of the experiment, the spectrum varied according to the stiffness.

DOI： 10.1299/jsmermd.2020.1A1-K06

Other Link： https://ci.nii.ac.jp/naid/130007943408

An Optical Image Transmission System for Deep Sea Creature Sampling Missions Using Autonomous Underwater Vehicle Reviewed International journal

Ahn J., Yasukawa S., Sonoda T., Nishida Y., Ishii K., Ura T.

IEEE Journal of Oceanic Engineering 45 ( 2 ) 350 - 361 2020.04

Sea trials for benthos sampling using autonomous underwater vehicle Reviewed International journal

Nishida Y., Yasukawa S., Sonoda T., Watanabe K., Ishii K.

Proceedings of International Conference on Artificial Life and Robotics 2020 167 - 170 2020.01

Development of subsea creature monitoring station for auv exploration assistance Reviewed International journal

Watanabe K., Utsunomiya K., Harada K., Sadiq A., Ishii K.

Proceedings of International Conference on Artificial Life and Robotics 25 175 - 178 2020.01

Evaluation of the relationships between saliency maps and keypoints Reviewed International journal

Mochizuki R., Ishii K.

Proceedings of International Conference on Artificial Life and Robotics ( ALife Robotics Corporation Ltd. ) 2020 249 - 254 2020.01

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

2020.01.13 - 2020.01.16

Saliency is a property of images that triggers bottom-up attention. For example, if a location in an image is sufficiently different from its surrounding and worthy of paying attention, such characteristic of image is saliency. From the point of view, the location of larger saliency is outstanding visually. On the other hand, As Image Feature extraction method, such as SIFT or SURF, robust feature matching has been realized under the existence of changing size or rotation of observed target. For the consequence, its advantage has been introduced into image stitching and Visual SRAM. However, the amount of image features is susceptive to changing photographing condition, such as luminance variety, defocus-ing etc. We assumed that feature extraction stability is large in salient region because of steep bright-ness gradient. We evaluated the relationship between saliency and feature extraction stability.

DOI： 10.5954/ICAROB.2020.OS24-3

Other Link： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85108857253&origin=inward

Field experiments of underwater image transmission for auv Reviewed International journal

Yasukawa S., Nishida Y., Ahn J., Sonoda T., Yanagise K., Watanabe K., Ishii K.

Proceedings of International Conference on Artificial Life and Robotics ( ALife Robotics Corporation Ltd. ) 2020 171 - 174 2020.01

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

2020.01.13 - 2020.01.16

In order to improve the efficiency of the seafloor survey, it is necessary for AUV to report the state of the seafloor to the operators on board reasonably. We have been developing seafloor image selection and image compression technology for the seafloor image transmission using the underwater acoustic communication device. In this paper, we report the results of underwater image selection and transmission in biological sampling experiments conducted in November 2019 off the coast of Suruga-bay, Shizuoka, Japan.

DOI： 10.5954/ICAROB.2020.OS23-2

Other Link： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85095943054&origin=inward

Report on the 5th tomato-harvesting robot competition Reviewed International journal

Takemura Y., Matsuo T., Sonoda T., Ishii K.

Proceedings of International Conference on Artificial Life and Robotics ( ALife Robotics Corporation Ltd. ) 2020 106 - 109 2020.01

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

2020.01.13 - 2020.01.16

Tomato is one of the important fruit vegetables and most tomatoes are produced in the greenhouses, or large-scale farms, where the high temperature and humidity, and long harvest age force the farmer heavy works. To develop the tomato harvesting robot, many research issues exist such as manipulator design, end-effector design, collaborative behavior, artificial intelligence, motor control, image processing, target recognition and so on. With an aim to promote the automation of tomato harvesting, we have organized the tomato harvesting robot competition since 2014. In this paper, we report on the results of 5th tomato harvesting robot competition in 2018.

DOI： 10.5954/ICAROB.2020.OS22-4

Other Link： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85108825800&origin=inward

Reports of 7th underwater robot festival in kitakyushu Reviewed International journal

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

Proceedings of International Conference on Artificial Life and Robotics 2020 110 - 113 2020.01

Development of antagonistic high power joint mechanism with cams Reviewed International journal

Suzuki K., Nishida Y., Sonoda T., Ishii K.

Proceedings of International Conference on Artificial Life and Robotics ( ALife Robotics Corporation Ltd. ) 2020 263 - 266 2020.01

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

2020.01.13 - 2020.01.16

Acquiring flexible and agile behaviors as seen in biological systems, the robot can achieve acrobatic movements such as jumping and throwing. These acrobatic movements are expected to extend the range of robot activity. In this research, we propose a special mechanism using a pair of motors, springs and cams, which has three functions: normal operation, instantaneous operation and variable rigidity. Then, we derived a mathematical model of the mechanism and discussed the input-output characteristics of the mechanism by changing the design parameters, and analyzed the difference between the theoretical and measured results.

DOI： 10.5954/ICAROB.2020.OS24-6

Other Link： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85108843059&origin=inward

Behavior selection system for robot using neural network Reviewed International journal

Tominaga M., Takemura Y., Ishii K.

Proceedings of International Conference on Artificial Life and Robotics ( ALife Robotics Corporation Ltd. ) 2020 98 - 101 2020.01

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

2020.01.13 - 2020.01.16

With the progress of technology, the realization of a symbiotic society with human beings and robots sharing the same environment has become an important subject. An example of this kind of systems is soccer game. Soccer is a multi-agent game that requires strategies by taking into account each member's position and actions. In this paper, we discuss the results of the development of a learning system that uses SOM to select behaviors depending on the situation.

DOI： 10.5954/ICAROB.2020.OS22-2

Other Link： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85108850030&origin=inward

A new rotary actuator capable of rapid motion using an antagonistic cam mechanism Reviewed International journal

Suzuki Katsuaki, Nishida Yuya, Sonoda Takashi, Ishii Kazuo

Journal of Advances in Artificial Life Robotics ( ALife Robotics Corporation Ltd ) 1 ( 3 ) 144 - 152 2020.01

Authorship：Last author,　Corresponding author Language：English Publishing type：Research paper (scientific journal)

Animals can achieve agile behaviors such as jumping and throwing in addition to flexible behaviors with the same musculoskeletal systems, and those movements can extend the range of their activities. We have been working on actuators capable of rapid and flexible motions learning the musculoskeletal systems. In this paper, we propose a new rotary actuator using a pair of motors, springs, and cams to perform three functions, namely, normal motion, rapid or instantaneous motion, and rigidity control using an antagonistic cam mechanism, and describe the operating principle of the proposed mechanism, the mathematical model of the mechanism during rapid motion, and the design principle of the cam, which is a key mechanical element in this mechanism. Finally, we present an analysis of the error between the theoretical the measurement results during rapid motion.

DOI： 10.57417/jaalr.1.3_144