Masami Iwatsuki
Hosei University
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Masami Iwatsuki.
IEEE Transactions on Robotics | 2005
Masami Iwatsuki; Norimitsu Okiyama
Image-based visual servoing is a flexible and robust technique to control a robot and guide it to a desired position only by using two-dimensional visual data. However, it is well known that the classical visual servoing based on the Cartesian coordinate system has one crucial problem, that the camera moves backward at infinity, in case that the camera motion from the initial to desired poses is a pure rotation of 1800 around the optical axis. This paper proposes a new formulation of visual servoing, based on a cylindrical coordinate system that can shift the position of the origin. The proposed approach can interpret from a pure rotation around an arbitrary axis to the proper camera rotational motion. It is shown that this formulation contains the classical approach based on the Cartesian coordinate system as an extreme case with the origin located at infinity. Furthermore, we propose a decision method of the origin-shift parameters by estimating a rotational motion from the differences between initial and desired image-plane positions of feature points.
intelligent robots and systems | 2002
Masami Iwatsuki; Norimitsu Okiyama
Image-based visual servoing is a flexible and robust technique to control a robot and guide it to a desired position only by using 2D visual data. However, it is well known that the classical visual servoing based on Cartesian coordinate system has one crucial problem that the camera moves backward at infinity in case that the camera motion from the initial to desired poses is a pure rotation of 180 degrees around the optical axis. This paper proposes a new formulation of visual servoing based on cylindrical coordinate system that can shift the position of the origin. The proposed approach can interpret from a pure rotation around an arbitrary axis to the proper camera rotational motion. It is shown that this formulation contains the classical approach based on Cartesian coordinate system as an extreme case with the origin located at infinity. Furthermore, we propose a decision method of the origin-shift parameters by estimating a rotational motion from the differences between current and desired image-plane positions of feature points.Image-based visual servoing is a flexible and robust technique to control a robot and guide it to a desired position only by using two-dimensional visual data. However, it is well known that the classical visual servoing based on the Cartesian coordinate system has one crucial problem, that the camera moves backward at infinity, in case that the camera motion from the initial to desired poses is a pure rotation of 1800 around the optical axis. This paper proposes a new formulation of visual servoing, based on a cylindrical coordinate system that can shift the position of the origin. The proposed approach can interpret from a pure rotation around an arbitrary axis to the proper camera rotational motion. It is shown that this formulation contains the classical approach based on the Cartesian coordinate system as an extreme case with the origin located at infinity. Furthermore, we propose a decision method of the origin-shift parameters by estimating a rotational motion from the differences between initial and desired image-plane positions of feature points.
frontiers in education conference | 2009
Yuji Tokiwa; Koji Nonobe; Masami Iwatsuki
In distance education, students in a remote classroom tend not to sustain their motivation, mainly because of a lack of intensity due to non-physical presence of a lecturer. To address this issue, two software tools were developed for teachers and students, respectively. The tool for teachers is called eRoster. On the teachers PC, the eRoster can display not only the students name but also the students attributes - id, future career, interest, club, faculty, and entrance time. Then, the teacher by name can call on the appropriate student whose attribute is related to the topics of the lecture. The tool for students is a so-called clicker and enables students to be more completely engaged in the interactivity of active learning. The developed system facilitates individually owned multi-devices of the students like PCs, cell phones, iPod Touches, and other PDAs as data entry systems.
frontiers in education conference | 2005
Akira Yonekawa; Hideki Hirano; Daisuke Yoshizawa; Masami Iwatsuki
State-of-the-art Internet technologies allow us to provide advanced and interactive distance education services. On the other hand, teleoperation systems with robot manipulator or vehicle via Internet have been developed in the field of robotics. By fusing two techniques, we can develop a remote experiment system for engineering educations based on World Wide Web, which allows students to take courses on experiments and exercises through the Internet anytime and anywhere they want. Although such remote experiment systems have been recently proposed by using an inverse pendulum, a coupled tank, heat transfer system and so on, they are inflexible because only their control parameters can be accessed by users. In this paper, we propose an unmanned and full-fledged remote experiment system comparable to regular local experiment systems that can provide flexible and effective practices to students, since the users can upload, compile and execute any source codes they create via Internet. The proposed system allows student users to exercise and practice remotely about principles of stepping motor control, image processing and their application to trajectory control for a robot vehicle. In this system, a student user has to prepare only a PC connected to Internet and installed with a browser and a text editor, because all procedures necessary for the experiments can be executed on the server side. Furthermore, this paper reports the results of a questionnaire survey on the proposed system for student users in our department in order to evaluate its effectiveness
international conference on robotics and automation | 2002
Masami Iwatsuki; Norimitsu Okiyama
Image-based visual servoing is a flexible and robust technique to control a robot and guide it to a desired position only by using 2D visual data. However, it is well-known that the visual servoing has one classical problem that the camera moves backward at infinity in case that the camera motion from the initial to desired poses is a pure rotation of 180 degrees around optical axis. It has been considered so far that the problem can not be essentially solved by the simplest conventional approach. This paper shows that the problem can be solved as simply as the conventional approach by introducing cylindrical coordinates into the formulation of visual servoing. Furthermore, we propose a new hybrid visual servoing that can control properly even in the situation coupling between translational and rotational motions by using a linear combination of velocity screws obtained from the Cartesian and cylindrical approaches with the rate of magnitudes of these translational velocities in z direction as a weight. This hybrid approach is modified to keep all feature points within the field of view by combining with another weight that is defined by a sigmoid function of the shortest distance to the edge of the image plane from the feature point.
Systems and Computers in Japan | 1996
Minoru Kodaira; Teruhiko Ohtomo; Atsushi Tanaka; Masami Iwatsuki; Takao Ohuchi
This paper describes an intelligent travel control algorithm for a mobile robot vehicle using neural networks, and proposes a method that realizes path planning and generation of motion commands simultaneously. Smooth moving trajectories are controlled by the outputs of cascaded identification modules that have learned the dynamic characteristics of a mobile robot vehicle with strong nonlinearities of both driving force and steering angle. A system is adopted that mutually transforms the absolute coordinate and dynamic coordinate. Because a consequence of the coordinate transformation in this system is that the dynamic position values are normally zero, it is possible to reduce greatly the number of training patterns and, at the same time, to be able to construct an environment similar to that in which a human being drives a vehicle. A travel control system, by which a mobile robot vehicle can move on a smooth traveling path and avoid obstacles, is created by introducing a danger function as an expression of static and dynamic obstacles in an unstructured environment. Finally, the validity of the proposed travel control system is confirmed by computer simulations.
cyberworlds | 2012
Masaki Oshita; Reiko Yamanaka; Masami Iwatsuki; Yukiko Nakatsuka; Takeshi Seki
Noh is a genre of Japanese traditional theater, a kind of musical drama. Similar to other dance forms, Noh dance (shimai) can also be divided into small, discrete units of motion (shosa). Therefore, if we have a set of motion clips of motion units (shosa), we can synthesize Noh dance animation by composing them in a sequence based on the Noh dance notation (katatsuke). However, it is difficult for researchers, learners, and teachers of Noh dance to utilize existing animation systems to create such animations of Noh dance. The purpose of this research is to develop an easy-to-use authoring system for Noh dance animation. In this paper, we introduce the design, implementation and evaluation of our system. To solve the problems of existing animation systems, we employ our smart motion synthesis technique to compose motion units automatically. We classify motion units as either pattern or locomotion units. Pattern units are specific forms of motion and can be represented as shot motion clips, whereas locomotion ones denote movement towards a specific position or direction and must be generated on the fly. To deal with locomotion-type motion units, we implemented a module to generate walking motion based on a given path. We created several Noh dance animations using this system, which was evaluated through a series of experiments.
International Journal of Distance Education Technologies | 2007
Masami Iwatsuki; Norio Takeuchi; Hisato Kobayashi; Kazuo Yana; Hiroshi Takeda; Hisashi Yaginuma; Hajime Kiyohara; Akira Tokuyasu
This article describes a new automatic digital content generation system we have developed. Recently some universities, including Hosei University, have been offering students opportunities to take distance interactive classes over the Internet from overseas. When such distance lectures are delivered in English to Japanese students, there is a pressing need to provide materials for review after class, such as video content on a CD-ROM or on a Web site. To meet this need, we have developed a new automatic content generation system, which enables the complete archiving of lectures including video/audio content, synchronized presentation materials, and handwritten traces on virtual whiteboards. The content is generated in real time and is immediately available at the end of the class. In addition, this system incorporates a unique video search algorithm which adopts a phonetic-based search technology. This enables quick review of the video content by typed-in keywords. The system can automatically create a vast amount of digital content and provide students with an efficient learning tool.
international conference on computer graphics and interactive techniques | 2012
Masaki Oshita; Reiko Yamanaka; Masami Iwatsuki; Yukiko Nakatsuka; Takeshi Seki
In this article, we introduce an easy-to-use authoring system for Noh (Japanese traditional) dance animation. This is a joint research between computer animation and Noh research groups.
intelligent robots and systems | 2003
Masami Iwatsuki; Norimitsu Okiyama
This paper proposes preferential direction control for visual servoing based on orthogonal curvilinear coordinate systems. In this paper, we present a generalized formulation of visual servoing based on curvilinear coordinate systems, which guarantees to converge an error between initial and desired positions of image feature points. Simulation results show that the formulation is effective to control the trajectories of feature points in preferred directions by applying to several curvilinear coordinate systems. Furthermore, we demonstrate that the preferential direction control goes well even if a different coordinate system can be adopted for each feature point. The mixed approaches with different coordinate systems can be applied to control a camera to keep image features within the field of view.