Faculty Profiles - WAGATSUMA Hiroaki

Papers - WAGATSUMA Hiroaki

Division display1 - 20 of about 272／ All the affair displays >>

バイオメカトロニクスから生体レジリエンスへ Reviewed

我妻広明, 笠井慎太郎

情報・システムソサイエティ誌 ( 一般社団法人電子情報通信学会 ) 28 ( 3 ) 4 - 5 2023.11

Self-Growth Task Ontology Design Toward Realization of Artificial General Intelligence Invited

HIROAKI Wagatsuma

JSAI Technical Report, Type 2 SIG ( The Japanese Society for Artificial Intelligence ) 2023 ( AGI-023 ) 04 2023.03

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

<p>Artificial general intelligence (AGI) was defined as the ability of an intelligent agent to understand or learn intellectual tasks that human can do. As an actual goal to realize the agent, milestones or a fundamental principle is necessary to proceed in the engineering field. According to Marcus Hutter (2000), AGI was formulated as the agent maximizes "the ability to satisfy goals in a wide range of environments," which is assumed to be supported by a reinforcement learning scheme. However, there is a serious lack in the formulation, especially in the form of knowledge. Replacing of white-collar jobs by AI, an appropriate utilization of human expert knowledge depending on the current situation including context and common knowledge is crucial. Contextual knowledge utilization is a hard problem of AI as Hubert Dreyfus (1992) and Douglas Hofstadter (1979) noticed. In the present study, we have designed knowledge- based representation systems for assistance to workers in expert fields and verified its performance in the implementation to automated driving systems, failure diagnosis and programming-less planning in industrial robots for executing interactive missions with human workers. Our results contribute to the elucidation of the fundamental principle of AGI and then AGI will solve ill-posed problems in the real world in the near future.</p>

DOI： 10.11517/jsaisigtwo.2023.agi-023_04

CiNii Research

A Nonlinear Oscillator Coupling Model to Provide the Hough Transform Function Without the Discrete Voting Procedure Reviewed International journal

Purev Amarbold, Wagatsuma Hiroaki

Journal of Advances in Artificial Life Robotics ( ALife Robotics Corporation Ltd ) 3 ( 4 ) 185 - 192 2023.01

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

The most common algorithm for detecting straight lines in a digital image is the Hough Transform method. The method involves two consecutive steps: transforming the image edge location onto parameter space and voting procedure to acquire line characteristics. The former deals in continuous space, and the latter counts votes in a discrete matrix, making the algorithm sensitive to noise. We transformed each image pixel location to the parameter space as a Hough line and generated a nonlinear oscillator to attract them into the intersection with other lines. This concept could contribute to a line detection problem in image processing using a consistent mathematical description.

DOI： 10.57417/jaalr.3.4_185

CiNii Research

A Basic Concept of the Nonlinear Oscillator-Based Hough Transform Implementation to Improve the Voting Procedure in the Scheme of Continuous Dual Spaces Reviewed International journal

Purev A., Wagatsuma H.

Proceedings of International Conference on Artificial Life and Robotics 994 - 1003 2023.01

A Comparative Analysis of Numerical Integration in Explicit and Implicit Methods to be Evaluated in the Linkage Model with Multibody Dynamics Toward an Optimum Design of Support Devices for Human Joint Workload Reduction Reviewed International journal

Kasai Shintaro, Wagatsuma Hiroaki

Journal of Robotics, Networking and Artificial Life ( ALife Robotics Corporation Ltd. ) 10 ( 2 ) 198 - 203 2023.01

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

In the analysis based on multibody dynamics (MBD), the MBD models are described by ordinary
differential equations, and the numerical integration methods applied to the analysis nonnegligibly
affect the accuracy of the results. In consideration of models containing dynamic
components such as spring dampers and flexible elements, the selection of integration methods is
highly important not only for accuracy but also computational costs of the analysis, because it
easily causes integration errors. For the development of exoskeleton-type assistive devices using
flexible elements, an accurate assessment of the effect of their elastic properties is required. In the
present study, we applied the implicit integration method in order to improve the accuracy of
MBD-based analysis, and numerical errors in computer experiments were significantly reduced
in the case of implicit methods with respect to those caused by explicit methods. This verification
result can lead to the improvement of the accuracy of the inverse dynamics analysis based on the
flexible multibody dynamics (fMBD) theory.

DOI： 10.57417/jrnal.10.2_198

Scopus

CiNii Research

Other Link： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85194290245&origin=inward

A Comparative Analysis of Serial and Parallel Models in the Morphological Component Analysis-Based Structure Pattern Extraction for Aerial Image Edge Detections Reviewed International journal

我妻広明

Journal of Robotics, Networking and Artificial Life in press 2023.01

A Kamm’s Circle-Based Potential Risk Estimation Scheme in the Local Dynamic Map Computation Enhanced by Binary Decision Diagrams Reviewed International journal

Kumar A., Wagatsuma H.

Sensors 22 ( 19 ) 2022.10

Artificial Neural Network Approach to Guarantee the Positioning Accuracy of Moving Robots by Using the Integration of IMU/UWB with Motion Capture System Data Fusion Reviewed International journal

Almassri A.M.M., Shirasawa N., Purev A., Uehara K., Oshiumi W., Mishima S., Wagatsuma H.

Sensors 22 ( 15 ) 2022.08

A Computational Model of 3D Printing Orthoses Associated with a Systematic Structural Analysis toward Reverse Engineering Oriented Production Reviewed International journal

Dachkinov Pancho, Kasai Shintaro, Tanaka Kohei, Wagatsuma Hiroaki

ICIC Express Letters, Part B: Applications ( ICIC International ) 13 ( 7 ) 705 - 713 2022.07

A Validation Analysis of the Submillimeter-Width Concrete Crack Detection Based on Morphological Component Analysis and Anisotropic Diffusion Reviewed International journal

Dixit Ankur, Oshiumi Wataru, Wagatsuma Hiroaki

International Journal of Innovative Computing, Information and Control ( ICIC International ) 18 ( 3 ) 1009 - 1018 2022.01

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

Abnormality detection in an early stage is a crucial issue to maintain social concrete infrastructures. The submillimeter-width concrete crack detection is the inevitable mission to significantly reduce the human burden; however, conventional image processing methods do not reach the same level of human inspections in senses of coverage ratios and hit rates. In the present study, we hypothesized that a concrete crack detection based on the morphological component analysis (MCA) can be upgraded with after-treatments for contrast enhancements by using anisotropic diffusion and related techniques, to be able to detect cracks on images even for less than 10 pixels in width as a submillimeter range. The traditional MCA method was modified to decompose the image into its coarse and fine components and the coefficient of anisotropic diffusion was designed to find cracks in high gradient and low gray level regions. The modified MCA and anisotropic diffusion with the Sobel edge detector were embedded to a consistent workflow to detect submillimeter cracks in image. In the accuracy verification, comparisons among the proposed method, conventional methods and the human detection demonstrated that the proposed method had a noteworthy detection efficiency with high coverage ratios and hit rates over 60% in total. It can contribute to the actual field work of the concrete crack detection.

DOI： 10.24507/ijicic.18.03.1009

Scopus

CiNii Research

Other Link： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85129743643&origin=inward

A Binary Decision Diagram Based Approach for Refining Road Safety Scenarios in the Local Dynamic Map Reviewed International journal

Kumar Arvind, Kawano Keita, Trung Huynh Le Phu, Wagatsuma Hiroaki

ICIC Express Letters, Part B: Applications ( ICIC International ) 13 ( 6 ) 597 - 605 2022.01

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

In international automobile communities, cooperative, connected and automated mobility have been discussed. For actual implementations of those schemes in the road infrastructure, an effective separation of information types such as static geographical
properties and dynamic vehicle movements and its integration is necessary to prevent potential accidents in an early stage. As a de facto international standard in progress, European Commission has supported the layered data structure depending on the spatio-temporal characteristics of things on the road to manage static and dynamic data with different updating time cycles, known as Local Dynamic Map, and recently technical problems to realize its actual implementation were discussed as issues need to be solved. In this paper, we proposed a compact representation method of geographical vehicle positions by using Binary Decision Diagrams (BDDs) integrated with the Geohash geographical encoding of target vehicles in the aim of a significant reduction of computational cost to prevent a serious communication delay. In the computer experiment, our proposed method was validated in the platform of the Robot Operating System (ROS). The comparative analysis with other traditional methods demonstrated that the proposed method clearly reduced the computational time three times smaller than others in cases of two vehicles and the same tendency was observed even if the number of vehicles increases.
Therefore, the BDD-based formulation might be applicable not only for an effective
geographical encoding but also for conflict management in traffic scenarios.

DOI： 10.24507/icicelb.13.06.597

Scopus

CiNii Research

Other Link： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85129838887&origin=inward

A MBD-based Knee Link Model to Analyze Singular Postures to Find Necessary Restrictions Toward Personalized Knee Support Exoskeleton Reviewed International journal

Kasai Shintaro, Dachkinov Pancho, Tanaka Kohei, Wagatsuma Hiroaki

Journal of Robotics, Networking and Artificial Life ( ALife Robotics Corporation Ltd. ) 9 ( 2 ) 128 - 135 2022.01

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

Assistive devices have been studied in the senses of the universal design and a possible simplification for mass production, and such a concept can be extended to the personalization by using advanced 3D printing technologies, which allows to provide suitable exoskeleton-type devices to fit for the subject’s body to achieve symptom relief. A systematic analytical mechanics is highly important for the investigation of proposed integrative systems and multibody dynamics and its computer simulation enhance the capability to find potential problems in design, for example risky postures for the subject. We introduced multibody dynamics to analyze a knee support exoskeleton by using a linkage system newly designed as a simplification of the device. In the computer experiment, a singular posture was successfully found as the limitation of the device to move safely for subjects having joint dysfunctions.

DOI： 10.57417/jrnal.9.2_128

Scopus

CiNii Research

Other Link： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85149464507&origin=inward

Flexible Bar Geometric Designs for Personalized Knee Orthoses Inspired by Compliant Mechanisms Reviewed International journal

Dachkinov Pancho, Kasai Shintaro, Tanaka Kouhei, Wagatsuma Hiroaki

Journal of Robotics, Networking and Artificial Life ( ALife Robotics Corporation Ltd. ) 9 ( 1 ) 59 - 65 2022.01

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

Recently, 3D printed compliant mechanisms have been expected not only in engineering purposes, but also in supportive devices of human motions especially for human joint problems. On the other hand, the establishment of a systematic design principle is the issue to provide an actual solution for the target body problem, i.e. the personalization. In the present study, we proposed a systematic method to design flexible bars to reduce the burden of the human joint. The proposed concept was verified in computational analyses and the 3D printer productions were demonstrated in an actual implementation as prototypes. In computational analyses, larger deformations of the bars were analyzed to absorb the stress occurring a flexing action in joint’s motion. Theoretical analysis and experiments were demonstrated its flexibility and support functions during the flexion and extension of the knee motion. It indicates that high importance of the geometrical analysis of the orthosis design in the sense of compliant mechanisms.

DOI： 10.57417/jrnal.9.1_59

Scopus

CiNii Research

Other Link： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85178309391&origin=inward

A Multi-Material Joint System as a Three-Dimensional Spring-Damper Compliant Mechanism Toward Functional Versatility Reviewed International journal

Dachkinov Pancho, Bhattacharjee Anirudha, Bhattacharya Bishakh, Wagatsuma Hiroaki

Journal of Advances in Artificial Life Robotics ( ALife Robotics Corporation Ltd ) 3 ( 2 ) 66 - 72 2022.01

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

3D printed material designs have a large capability in the functional aspect. A cross-spring compliant joint is a hot topic in the sense of multipurpose applications in various engineering fields. A combination of flexible materials embedded in the structural form performs a motion of the system according to deformation of parts elastically, which may fit to a specific engineering purpose. In the present study, a traditional cross-spring pivot (CSP) was improved to provide effectively frictionless and wear free in-plane motion. The behavior of the joint was analyzed based on a non-linear FEA computer analysis to focus the properties with various loading conditions. Improved compliant joints will open a new door for designs of high-precision actuators and robotic manipulators.

DOI： 10.57417/jaalr.3.2_66

CiNii Research

A Concrete Crack Inspection Embedded in the Drone-Based System by Using Sub-Pixel Width Estimation and Morphological Component Analysis Reviewed International journal

Dixit Ankur, Oshiumi Wataru, Wagatsuma Hiroaki

Journal of Advances in Artificial Life Robotics ( ALife Robotics Corporation Ltd ) 2 ( 4 ) 177 - 183 2022.01

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

Human experts have assured social infrastructure inspections, and recently an automated inspection is expected as an integrated system of the flight vehicle with software algorithms of the image processing. For the submillimeter-width concrete-crack detection, we have introduced Morphological Component Analysis (MCA) to be able to find those positions. Conventional image processing methods work well for thick-width crack detections, while the thin-width crack detection is highly difficult. We successfully demonstrated a concrete crack detection from images through proximity cameras in a specialized multi-copter and MCA-based crack position estimations and the linear regression-based sub-pixel width estimation were integrated together. It will open a new door to engineering in the actual field work, which can be widely applicable for social infrastructure inspections in general.

DOI： 10.57417/jaalr.2.4_177

CiNii Research

A Comparative Analysis of Serial and Parallel Models in the Morphological Component Analysis-Based Structure Pattern Extraction for Aerial Image Edge Detections Reviewed International journal

Oshiumi Wataru, Dixit Ankur, Wagatsuma Hiroaki

Journal of Advances in Artificial Life Robotics ( ALife Robotics Corporation Ltd ) 3 ( 3 ) 163 - 168 2022.01

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

A refinement process by human experts is still needed for areas/feature extractions of interest from aerial images in multiple map makers. The construction/road edge extraction is one of them which is highly important in the preprocessing stage for map-making, while it is difficult to isolate man-made structures from a natural landscape involving different size objects. In the present study, we focused on an actual procedure in the decomposition of the Morphological Component Analysis known as MCA to extract specific patterns as serial and parallel models. In our computer experiments, dictionaries of Curvelet and Local Discrete Cosine Transform known as LDCT were introduced for the MCA decomposition and then two models demonstrated a non-negligible difference in the feature extraction performance. This result may contribute to the extension of future possibilities of structural data analyses especially for buildings and roads from shapes in nature.

DOI： 10.57417/jaalr.3.3_163

CiNii Research

Other Link： https://kyutech.repo.nii.ac.jp/records/2000720

Computational Model of 3D Printing Orthoses Associated with a Systematic Structural Analysis Toward Reverse Engineering Oriented Production Reviewed International journal

我妻広明

ICIC Express Letters, Part B: Applications (ICIC-ELB) 13(7) 705 - 713 2022.01

A Binary Decision Diagram Based Approach for Refining Road Safety Scenarios in the Local Dynamic Map Reviewed International journal

我妻広明

ICIC Express Letters, Part B: Applications (ICIC-ELB) 13(6) 597 - 605 2022.01

A Validation Analysis of the Submillimeter-Width Concrete Crack Detection Based on Morphological Component Analysis and Anisotropic Diffusion Reviewed International journal

我妻広明

International Journal of Innovative Computing, Information and Control (IJICIC) 18(3) 1009 - 1018 2022.01

A Systematic Recording System to Analyze ERD/ERS in EEG to Focus Individual Timing Differences in a Three-Grasping-Type Task Reviewed International journal

Shibata Kosei, Fujiwara Masayuki, Duc Phan Hoang Huu, Bougrain Laurent, Henaff Patrick, Wagatsuma Hiroaki

ICIC Express Letters, Part B: Applications ( ICIC International ) 15 ( 10 ) 1009 - 1016 2024.10

　PREV- NEXT 　

<WAGATSUMA Hiroaki>

Papers - WAGATSUMA Hiroaki