An explanation generation system based on narratology and an unchiku generation system has been developed previously. Moreover, we developed an animation system that simulates the stage performance structure of a kabuki work, Kyōganoko Musume Dōjōji. Based on this background, this study presents the basic method of unchiku generation using a moving illustration system. In the prototype, we use the legend of Dōjōji and edit the general explanation and unchiku texts of Kyōganoko Musume Dōjōji. Further, the system supplements the unchiku using the corresponding animations. We refer to these animations as moving illustrations. These unchiku and animations are not intended to explain the story, but to provide deep knowledge of the explanations inserted in the story.

View full abstract

Agriculture is one of the most important primary industries, however the agricultural workforce in Japan has been decreasing due to the aging, shortage of successors and their heavy work. Smart agriculture and farms, which aim to automate farm work, have been attracting attention for the future sustainable society. We have been organizing the Tomato-Harvesting-Robot Competitions since 2014 to introduce robotic technology and AI into agriculture and promote agricultural technology. The competition consists of a Junior League for young students and a Senior League for general competitors. In this paper, we report the results of the 6th Tomato-Harvesting-Robot Competition and the regulation changes toward practical applications.

View full abstract

Agricultural picking is a key part of agricultural production activities. In recent years, people are committed to improving picking efficiency and freeing labor, and agricultural picking robots have emerged and are widely used. Daylily, as a crop for daily consumption, can significantly reduce serum cholesterol and has extremely high nutritional value. However, Daylily picking time and picking standards are relatively strict, long-term picking daylily will also damage the health of the work. The daylily picking robot designed in this paper can effectively solve the current picking problems, such as: improving picking efficiency, standardizing picking, and reducing physical hazards to laborers

View full abstract

This paper describes a method of navigating a visually impaired person who walks on a sidewalk and goes through a pedestrian crossing by the use of an ego-camera system named MY VISION. The proposed method finds a walkable region on the sidewalk. Thus, at a pedestrian crossing, it finds a traffic light and judges an appropriate timing to cross the road by analyzing the color and flashing status of the signal. The walkable region is found employing Graph- Based Segmentation (GBS), and once a pedestrian crossing is reached through the use of a GPS signal, a traffic light is detected by use of the HOG feature and Random Forest. The effectiveness of the proposed method was verified by experiments. This implies usefulness of a MY VISION system

View full abstract

This paper describes the relationship between tactile stimulation and human body sway. We previously proposed a tactile stimulation-based body sway stabilization system and revealed that simultaneous stimulation behind both auricles significantly improved human balance function, and unilateral stimulation may induce the deviation of the center of pressure (COP). In this paper, some stimulation patterns were applied to participants and COP distribution before/after stimulation was extracted. The results showed that COP values after stimulation could be inclined to the same of the stimulation site. It indicates that tactile stimuli can control human balance function.

View full abstract

Deep learning technology has made remarkable progress in recent years and has been adopted for a variety of applications such as smartphones and cloud servers. These systems employ dedicated processors to reduce power consumption and process massive amounts of data. In this paper, we propose a field-programmable gate array (FPGA) infrastructure for easy verification of user logic. The infrastructure makes it easy to communicate and control a host PC and user logic. We implemented two example logics, which were simple image processing and a restricted Boltzmann machine, into the infrastructure to confirm these features

View full abstract

Measuring the quality of software design artifacts is difficult due to the limitation of information in the design phase. The class diagram is one of the design artifacts produced during the design phase. The syntactic and semantic information in the class is essential to consider in the measurement process. Smell detection uses class-related information to detect the smell as an indicator of a lack of quality. Several classifiers use all information related to the class to prove how informative it for the smell detection process. The smell types that are a concern in this research are Blob and Feature Envy. The experiment using three classifiers (j48, Multi-Layer Perceptron, and Naïve Bayes) confirms that Blob smell detection utilizes the information successfully. On the other hand, Feature Envy still needs more elaboration. The average true positive rate by the classifiers is about 80.67%.

View full abstract

Robot technologies have been changed dramatically with rapid development of the Internet technology. Having reviewed the relevant literature on advanced robot technologies, it is readily evident that most of typical robot technologies are used in single-cause-oriented products, such as robot vacuum cleaners and Asimo, a humanoid robot invented by Honda, which have played an important role in modern society. For further development, networking robot systems comprised of advanced Internet and artificial intelligence technologies are required to deal with future uncertainties. Different technologies should be combined and linked together for multiple-goal-oriented approaches associated with networking robot systems. For evaluating the validity of the proposed new system, a novel approach referred to as the fragility index is introduced in this research

View full abstract

As the most important case management system in school counseling works, the counseling service system must meet the needs and expectations of the school teacher-counselors (the main users). Semi-structured interviews were used to interview school teacher-counselors who have experience in using the system in Tainan. The data are recorded and semantically analyzed after the interview, and the critical factors that affect the system acceptance of the school teacher-counselors are summarized. The conclusion was to discuss the implications of this research and to suggest several future research issues.

View full abstract

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.

View full abstract

In recent years, increase in the number of jellyfish causes damage in the fishery and tourism industries. Currently, most of the jellyfish removal work is carried out by workers. However, this conventional removal work is required a lot of time and manpower. In this paper, we proposed a method for removal work of jellyfish using an underwater robot. Also, we introduced developed ROV type underwater robot, which is called JENOS (Jellyfish Extermination Nifty-robot for Ocean Sustentation), and its removal motion performance. The ROV was developed in consideration of the attitude control during the removal operation. Because, the attitude, such as surge and pitch, of ROV became unstable when performing jellyfish removal work. To solve this problem, we equipped 8 thrusters to improve attitude stability during the jellyfish removal work. As results, surge acceleration was reduced about 30.0%, and pitch angle velocity was reduced about 25.8%, and the jellyfish sample was chopped within 25 seconds.

View full abstract

In this paper, the consensus problem of general linear discrete-time multi-agent systems with the cooperative-antagonistic interactions and limited communication bandwidth is investigated, and a bipartite consensus con-trol protocol is proposed for each agent, which is given in terms of the state of its dynamic encoder and decod-ers with uniform quantizer. It’s demonstrated that the bipartite consensus can be realized, if the signed undi-rected graph is connected and structurally balanced/unbalanced. Furthermore, the explicit form of the conver-gence rate is given. Numerous simulations are presented to illustrate the feasibility of the control scheme used on this system.

View full abstract

A distributed control algorithm based on artificial potential function, coordinate transformation and complex Laplacian for formation control of second-order rectangular agents is presented in this paper. The system can achieve the desired formation, avoid collision and maintain connectivity between agents. The stability analysis of this algorithm is given. Finally, the effectiveness of the algorithm is illustrated by the simulation results.

View full abstract

Extended Place/transition Net (EPN) is expected to be one of formal software modeling techniques to realize model-driven development. This paper shows a personal on-demand learning technique that helps engineers to acquire skills for using EPN, and then illustrates a prototype tool for it. In the technique, each engineer as a learner tries to construct his/her EPN model so as to satisfy given software requirements. The key ideas of the technique are (i) to construct a learner's EPN model by using given components only, (ii) to convert a learner's EPN model into a VDM++ specification, and (iii) to visualize the behavior of software by using animated graphics. Preliminary discussion and experiments with trial users of the prototype tool have been conducted to evaluate the effectiveness of the technique.

View full abstract

Previous spherical mobile robots were driven by two rollers with a fixed rotational axis, which restricts the angular velocity vector of the sphere to two dimensions. Three-dimensional freedom is expected to improve the rotational diversity of the sphere. This study proposes a spherical mobile robot with a variable roller-rotational axis that allows the movement of three degrees of freedom. Furthermore, the kinetic energy of transporting the sphere by the rollers is minimized by an optimization procedure and it is shown that the kinetic energy of sphere transport is efficient.

View full abstract