Current Affiliation Organization 【 display / non-display 】

Current Affiliation Organization 【 display / non-display 】

University 【 display / non-display 】

University 【 display / non-display 】

Academic degree 【 display / non-display 】

Academic degree 【 display / non-display 】

External Career 【 display / non-display 】

External Career 【 display / non-display 】

Affiliated academic organizations 【 display / non-display 】

Affiliated academic organizations 【 display / non-display 】

Research Interests 【 display / non-display 】

Research Interests 【 display / non-display 】

Research Areas 【 display / non-display 】

Research Areas 【 display / non-display 】

Acquisition of a qualification 【 display / non-display 】

Acquisition of a qualification 【 display / non-display 】

Thesis 【 display / non-display 】

Thesis 【 display / non-display 】

• 中心窩視覚に基づくアクティブステレオビジョンに関する研究

  2000.03

Published Papers 【 display / non-display 】

Published Papers 【 display / non-display 】

• Adaptive Control Simulation of AUV Using Neural Controllers Trained by GA

  Kinjo Hiroshi, Nakazono Kunihiko, Uezato Eiho, Oshiro Naoki

  IEEJ Transactions on Electronics, Information and Systems ( The Institute of Electrical Engineers of Japan )  144 ( 3 ) 169 - 178   2024.03 [ Peer Review Accepted ]

  Type of publication: Research paper (scientific journal)

  　View Summary

  <p>In this research, we propose a method to adaptively generate AUV trajectories using a neural controller that learns by applying a genetic algorithm. The method uses two neuro-controllers. One is learned in advance as a controller. The other is learning at the same time as redesigning a new trajectory when the AUV deviates from the planned trajectory during navigation. The two neural controllers are evolutionarily learned using genetic algorithms. In the navigation simulation, the multi-point search problem of AUV under the tidal current environment was taken up. Numerical experiments have shown the effectiveness of the proposed method.</p>

  • Access this article
    DOI
  • Search related information
    CiNii Research

• Tracking Control for AUV by Fuzzy Controller with Extended Kalman Filter

  YAMADA Toya, KINJO Hiroshi, NAKAZONO Kunihiko, UEZATO Eiho, OSHIRO Naoki

  Transactions of the Society of Instrument and Control Engineers ( The Society of Instrument and Control Engineers )  60 ( 6 ) 407 - 415   2024

  Type of publication: Research paper (scientific journal)

  　View Summary

  <p>In this paper, we verify whether a fuzzy control system designed for a small autonomous under water vehicle (AUV) robot can be controlled by inputting state estimates obtained by using an Extended Kalman filter. The fuzzy controller determines a set of rules similar to those used by humans to steer the robot, and quantifies them in the form of a membership function to obtain a control value. The state estimator uses an EKF to reduce noise from noisy velocity measurements. The current position, which cannot be measured, is estimated and input to the controller for control simulation. As a result, the AUV succeeded in tracking the target value moving in three dimensions in time.</p>

  • Access this article
    DOI
  • Search related information
    CiNii Research

• Performance evaluation of schedule plan for cuckoo search applied to the neural network controller of a rotary crane

  Rui Kinjo, Kunihiko Nakazono, Naoki Oshiro, Hiroshi Kinjo

  Artifcial Life and Robotics ( Springer Nature )  29 ( 1 ) 129 - 135   2023.11 [ Peer Review Accepted ]

  Type of publication: Research paper (scientific journal)

  　View Summary

  Here, an optimized neural network controller (NC) was developed with the cuckoo search (CS) method. This was inspired by the mending behavior of the cuckoo bird, which lays eggs similar to those of their putative parents in their nests and allows the putative parents to raise them. CS is an evolutionary computation algorithm that mimics the ecological behavior of organisms to optimize a controller. Previous studies have demonstrated good evolutionary processes for NCs when the value of the scaling index varies in steps during a scheduled period. Therefore, the proposed CS scheduling plan adjusts the scaling index as a linear function, nonlinear function, or stairs. Computer simulations demonstrated that an NC optimized with the scheduled CS method had superior control performance compared to the original CS method. The best results were obtained when the schedule plan was set to a linear or nonlinear function rather than a stair plan.

  • Access this article
    DOI

• Fuzzy controller for AUV robots based on machine learning and genetic algorithm

  Yamada, T; Kinjo, H; Nakazono, K; Oshiro, N; Uezato, E

  ARTIFICIAL LIFE AND ROBOTICS ( Artificial Life and Robotics )  28 ( 3 ) 632 - 641   2023.08 [ Peer Review Accepted ]

  Type of publication: Research paper (scientific journal)

  • Access this article
    DOI

• Design of Machine Learning Solutions to Post-Harvest Classification of Vegetal Species

  Papa Moussa Diop, Naoki Oshiro, Morikazu Nakamura, Jin Takamoto, Yuji Nakamura

  AgriEngineering   5 ( 2 ) 1005 - 1019   2023.06 [ Peer Review Accepted ]

  Type of publication: Research paper (scientific journal)

  　View Summary

  <jats:p>This paper presents a machine learning approach to automatically classifying post-harvest vegetal species. Color images of vegetal species were applied to convolutional neural networks (CNNs) and support vector machine (SVM) classifiers. We focused on okra as the target vegetal species and classified it into two quality types. However, our approach could also be applied to other species. The machine learning solution consists of several components, and each design process and its combinations are essential for classification quality. Therefore, we carefully investigated their effects on classification accuracy. Through our experimental evaluation, we confirmed the following: (1) in color space selection, HLG (hue, lightness, and green) and HSL (hue, saturation, and lightness) are essential for vegetal species; (2) suitable preprocessing techniques are required owing to the complexity of the data and noise load; and (3) the diversity extension of learning image data by mixing different datasets obtained under different conditions is quite effective in reducing the overfitting possibility. The results of this study will assist AI practitioners in the design and development of post-harvest classifications based on machine learning.</jats:p>

  • Access this article
    DOI

display all >>

Presentations 【 display / non-display 】

Presentations 【 display / non-display 】

• Control Simulation of Marine Robot Using Fuzzy and PID Control

  山田桃也, 金城寛, 中園邦彦, 上里英輔, 大城尚紀

  計測自動制御学会九州支部学術講演会予稿集(CD-ROM)  2021  -  2021 

• Efficiency of Seabed Rock Levelling Device Using Hydraulic Breaker

  金山佳広, 金城寛, 大城尚紀, 平林丈嗣, 喜夛司, 上山淳

  計測自動制御学会九州支部学術講演会予稿集(CD-ROM)  2020  -  2020 

• Sea Experiment on Tele-operation System of Underwater Excavator

  Tsukasa Kita, Taketsugu Hirabayashi, Atsushi Ueyama, Hiroshi Kinjo, Naoki Oshiro, Nobuyuki Kinjo

  Proceedings of the 37th International Symposium on Automation and Robotics in Construction, ISARC 2020: From Demonstration to Practical Use - To New Stage of Construction Robot  2020  -  2020 

• Adaptation of Acoustic Sensor in Information Presentation System for Underwater Excavator

  平林丈嗣, 喜夛司, 吉江宗生, 上山淳, 鈴木正己, 金城寛, 大城尚紀, 金城信之

  海洋工学シンポジウム(CD-ROM)  2018  -  2018 

• Underwater modeling of rammer

  田場大貴, 金城寛, 大城尚紀, 鈴木正己, 平林丈嗣, 吉江宗生, 上山淳

  計測自動制御学会九州支部学術講演会予稿集(CD-ROM)  2018  -  2018 

Academic Awards 【 display / non-display 】

Academic Awards 【 display / non-display 】

• Best Paper Award

  2006   International Symposium on Artificial Life and Robotics