scispace - formally typeset
Search or ask a question
Author

Fumio Kojima

Bio: Fumio Kojima is an academic researcher from Kobe University. The author has contributed to research in topics: Mobile robot & Robot control. The author has an hindex of 13, co-authored 124 publications receiving 793 citations.


Papers
More filters
Book
01 Jan 1999
TL;DR: In this paper, improved and novel methods of electromagnetic nondestructive testing, the solution of direct and inverse problems, advanced sensing technology, proposals and results of benchmark problems, and various related industrial applications.
Abstract: This text covers improved and novel methods of electromagnetic nondestructive testing, the solution of direct and inverse problems, advanced sensing technology, proposals and results of benchmark problems, and various related industrial applications.

140 citations

Journal ArticleDOI
TL;DR: In this paper, the authors proposed an anisotropic strain sensor, which is composed of three elastomer films and two carbon-nanotube electrodes, and it is applied to estimate the angle of a wrist joint.
Abstract: Flexible and stretchable strain sensors are expected to significantly contribute to new technologies and be applied in various applications, including human interfaces, smart clothes, and robotic skin. Hence, we have proposed a flexible film-shaped strain sensor that is composed of three elastomer films and two carbon-nanotube electrodes. It is thin, lightweight, and has low elasticity. Strain measurements taken by the sensor are based on changes in capacitance, which is proportional to the square of the area of the sensor’s sensing part. Consequently, the capacitance of the strain sensor does not show the direction of the strain. As some applications require the measurement of strain in a fixed direction, this paper proposes an anisotropic strain sensor. This anisotropic strain sensor decreases the effect of the strain in the fixed direction to less than 10%. The model of the anisotropic strain sensor and experimental results show that its capacitance is proportional to the square of the length of the sensing part in the stretch direction. To check the anisotropic strain sensor’s practicality, it is applied to estimate the angle of a wrist joint. The results show that the anisotropy decreases the root-mean-square error of the estimated angle to less than 3°.

37 citations

Journal ArticleDOI
TL;DR: This paper proposes a GA based on the perceiving information about the dynamic environment, called a Perception-Based GA (PerGA), and applies the proposed method for acquiring collision avoidance behaviors of a mobile robot in a dynamic environment.

34 citations

Journal ArticleDOI
TL;DR: In this paper, a flexible stretching sensor from urethane elastomer and conductive electrodes from single-walled carbon nanotubes (CNTs) is presented. But the sensor is tested on a cloth fabric, and is confirmed to measure the stretch area of flexible materials.
Abstract: Conventional strain sensors measure strains exerted on solid metals and have been widely applied Stretch measurements of flexible objects require strain sensors with wide dynamic range (stretch exceeding 100%) that can also measure areal changes Flexible strain sensors are expected to realize a wide range of technologies, such as human interfaces, smart clothes, skin-motion monitoring, and robotic skin Recently, carbon nanotubes (CNTs) have been assembled into stretchable conductors, and are potential base materials for various flexible sensors Herein, we construct a flexible stretching sensor from urethane elastomer and conductive electrodes from single-walled CNTs This sensor is extremely thin (thickness: $150~\mu $ m), and characterized by high elasticity (up to 100%), low stress (08 MPa at 100%), durability (1000 cycles at 50%), light weight (approx 11 g/ $\mathrm{cm}^{3}$ ), and sensitivity (1 pF/ $\mathrm{mm}^{2}$ ) The strain sensor is tested on a cloth fabric, and is confirmed to measure the stretch area of flexible materials

31 citations


Cited by
More filters
Journal ArticleDOI
01 Sep 2001
TL;DR: This paper features a survey of about 250 IEC research papers and discusses the IEC from the point of the future research direction of computational intelligence.
Abstract: We survey the research on interactive evolutionary computation (IEC). The IEC is an EC that optimizes systems based on subjective human evaluation. The definition and features of the IEC are first described and then followed by an overview of the IEC research. The overview primarily consists of application research and interface research. In this survey the IEC application fields include graphic arts and animation, 3D computer graphics lighting, music, editorial design, industrial design, facial image generation, speed processing and synthesis, hearing aid fitting, virtual reality, media database retrieval, data mining, image processing, control and robotics, food industry, geophysics, education, entertainment, social system, and so on. The interface research to reduce human fatigue is also included. Finally, we discuss the IEC from the point of the future research direction of computational intelligence. This paper features a survey of about 250 IEC research papers.

1,416 citations

Journal ArticleDOI
TL;DR: Current state-of-the-art of manipulation and grasping applications that involve artificial sense of touch that involve algorithms and tactile feedback-based control systems that exploit signals from the sensors are reviewed.

599 citations

Journal ArticleDOI
TL;DR: This article surveys algorithms designed for sequential decision-making problems with multiple objectives and proposes a taxonomy that classifies multi-objective methods according to the applicable scenario, the nature of the scalarization function, and the type of policies considered.
Abstract: Sequential decision-making problems with multiple objectives arise naturally in practice and pose unique challenges for research in decision-theoretic planning and learning, which has largely focused on single-objective settings. This article surveys algorithms designed for sequential decision-making problems with multiple objectives. Though there is a growing body of literature on this subject, little of it makes explicit under what circumstances special methods are needed to solve multi-objective problems. Therefore, we identify three distinct scenarios in which converting such a problem to a single-objective one is impossible, infeasible, or undesirable. Furthermore, we propose a taxonomy that classifies multi-objective methods according to the applicable scenario, the nature of the scalarization function (which projects multi-objective values to scalar ones), and the type of policies considered. We show how these factors determine the nature of an optimal solution, which can be a single policy, a convex hull, or a Pareto front. Using this taxonomy, we survey the literature on multi-objective methods for planning and learning. Finally, we discuss key applications of such methods and outline opportunities for future work.

462 citations

Proceedings ArticleDOI
05 Dec 2005
TL;DR: The key issues in formation control are reviewed with a focus on the main control strategies for formation control under different kinds of scenarios and some important open questions are pointed out.
Abstract: In this paper, we presented a review on the current control issues and strategies on a group of unmanned autonomous vehicles/robots formation Formation control has broad applications and becomes an active research topic in the recent years In this paper, we attempt to review the key issues in formation control with a focus on the main control strategies for formation control under different kinds of scenarios Then, we point out some important open questions and the possible future research directions on formation control This paper contributes with a new and interesting consideration on formation control and its application in distributed parameter systems We pointed out that formation control should be classified as formation regulation control and formation tracking control, similar to regulator and tracker in conventional control

418 citations

Book
18 Oct 2016
TL;DR: This book presents the most up-to-date coverage of procedural content generation (PCG) for games, specifically the procedural generation of levels, landscapes, items, rules, quests, or other types of content.
Abstract: This book presents the most up-to-date coverage of procedural content generation (PCG) for games, specifically the procedural generation of levels, landscapes, items, rules, quests, or other types of content. Each chapter explains an algorithm type or domain, including fractal methods, grammar-based methods, search-based and evolutionary methods, constraint-based methods, and narrative, terrain, and dungeon generation. The authors are active academic researchers and game developers, and the book is appropriate for undergraduate and graduate students of courses on games and creativity; game developers who want to learn new methods for content generation; and researchers in related areas of artificial intelligence and computational intelligence.

354 citations