In recent years, the utilization of drone for pesticide spraying, load carriage, infrastructure inspection, and remote sensing has been proceeded because it is able to improve the work efficiency and the safety. In particular the utilization of multiple drones in the field of agriculture will enable to reduce the total time of pesticide spraying. On the other hand there are some examples flying multiple drones as the application to art and entertainment. Thus the opportunity of swarm flight control for multiple drones is expected to increase gradually. Therefore, this research aims at the realization of swarm flight control which is useful in the field of agriculture and amusement and so on. The swarm flight control simulation according to human operation using the flocking algorithm Boids well-known for the group behavior simulation of birds and fish was performed in this research. Boids is a kind of computer algorithm expressing swarm flight of birds based on three basic rules. In this research the parameters of three basic rules were tuned by genetic algorithm (GA). Moreover the experiment of evaluation for the operationability was performed after an operator controls one or multiple drones.

To reduce traffic accidents by elderly drivers, we have been developing a robot that reviews their driving with them after returning home. The users put the robot in the car when driving, and reviews their driving with the robot when they get home. In reviewing own driving together with the robot, they may accept the robot’s advice (support acceptability), according to increase attachment to the robot. Naming the robot is considered to be a way to increase the attachment. In this paper, we conducted an experiment focusing on naming the robot. As the result, the correlation between attachment to the robot and support acceptability lowered in the case of naming. It is possible that increased attachment to robots may not lead directly to improved support acceptability.

In this paper, we introduce our study on the cross-modal physiological expression on a robot’s skin using goosebumps, perspiration, and shiver. Human and other living beings show their voluntary and involuntary state via physiological phenomena, and the main visible/tangible phenomena appear on the skin. We especially focused on the expressive strengths and combinations of three involuntary expressions above to affect the nuances of instinctive fear emotions. The evaluation results showed that the fear emotion of the robot, the aliveness, and other impressions of the robot can be transmitted even only by the single use of the involuntary expressions, and that might be caused by ceiling effects of each modality’s strong effectiveness. In addition, some combinations of multiple involuntary expressions, such as increased annoyance in the combination of a small amount of sweating and a large amount of goosebumps expression, showed a unique expressiveness on the factors of the fear extracted in our analyses.

In this paper, we examine the effectiveness of the interpersonal distance between a virtual robot head and humans and the gaze estimation using a display that can be viewed stereoscopically without using any wearable devices. An actual robot with a body which is like human’s body cannot always maintain an appropriate the interpersonal distance, because large movements may harm humans. To solve the problem of actual robots, onscreen agents which are displayed in a flat screen can be used. However, onscreen agents cause the Mona Lisa effect which makes humans feel gazed by agents wherever they stand. In this work, we developed a virtual robot head which is displayed in stereoscopic display. We prepared a scenario of museum tour, and asked 25 participants how far they wanted to move from the virtual museum guide robot head. They were also asked to estimate the point which they felt the virtual robot head was gazing at. As a result, it was found that the interpersonal distance was applied between the virtual robot head and the human by giving a box to the virtual robot head. It was also found that the Mona Lisa effect is reduced by giving a box to the virtual robot head and displaying it in three-dimensionally.

This study focused on the facilitation method using information systems and investigated what factors are related to the facilitation for creative cognition. We experimentally investigated what kind of interfaces and interaction methods are useful in an idea generation task. In Experiment 1, we examined factors related to anthropomorphism and physical reality, and found that suggestions from a robot-based facilitation facilitates better creative cognition than the control with no such facilitations. In Experiment 2, we focused on robot-based facilitation, which was found to be useful in Experiment 1, and examined how interactive modes such as confirmation of participant’s metacognitive activities influences on performance. As a result, we found that the facilitation with confirmation produced better outcomes on performance.

As robots become ever more sophisticated, ubiquitous, and continue to permeate into our everyday life, an important agenda for future studies will be to design and evaluate robots that can adapt its expressions based on user characteristics in real-time and study their effect on perception of the user. To explore the effective expression in human–robot interaction, we intended to endow the humanoid robot Pepper with seven expression patterns showing different combinations of voice and motion traits. The Negative and Anxiety Scale and Big Five Domain Scale were chosen as the phycological indicators, and an online video-based questionnaire was utilized to investigate human perception of robot different expressions. Results have uncovered that robot’s different expressions can elicit individual distinguishing evaluations towards robot. The prominent distinction of personal perceptions among different participants emerges from the data, boosting the idea that the personalized robot with adaptive expression is essential for different individuals and various scenarios. This study provides the first investigations into how to make social robots generate appropriate reactions according to individual inner conditions including personality and attitude towards robots.

In recent years, many Robot Technology (RT) and Information and Communication Technology (ICT) have been introduced into the agricultural field. Many of them are aiming to automate tasks such as harvesting strawberries. However, there are many challenges in fully automating such tasks with robots. For example, simplifying the operation of the robot is challenging, and the high initial cost for introducing RT and ICT technologies becomes a barrier for farmers to install them. In the case of soil cultivation, a worker has to bend forward at the waist and move sideways. A wheelchair to reduce the burden of this work on the body is commercially available. However, this chair has only passive wheels, so the worker must move it on their legs. In this study, we developed an electric wheelchair with an intuitive user interface. The chair is equipped with a pressure sensor on the seat and wheels with a motor. Using the pressure sensor, we calculate the direction in which the passenger wants to move from the weight shift of the passenger, and then the chair assists the passenger in the calculated direction. We used Fuzzy control to assist the movement of the passenger to suit the passenger preference of the assistance. To show the effectiveness of the electric wheelchair, we compared the difference of the surface EMG on the lateral great muscle of both legs during the movement on a flat ground using between the proposed electric wheelchair and a passive wheelchair.

In the field of sports psychology, it is said the presence of cheering spectators has a positive effect on the mental state of athletes. While studies have been conducted to examine the effect of agents as coaches or partners on the motivation of athletes, the effect of cheering from agents has not been studied. In this study, to investigate the effect of cheering by agents, examining the experimental conditions in a preliminary experiment was followed by two surveys which were conducted with the aim of examining the effectiveness of agent cheering on the motivation of the competitors. In the preliminary experiment, we selected suitable timings of the cheering and gestures for agent cheering. In the first survey, we compared the impressions of the agents cheering the competitor in three conditions: “cheering by computer graphics (CG) animation and voice agents,” “cheering by voice agents,” and “no cheering” by Web questionnaires for beginners and experts, respectively. In the second survey, we compared the impressions of the agents cheering for the competitors in two conditions: “cheering by CG animation and voice agents,” and “no cheering” for beginners. From the first survey, it was found that the “cheering by CG animation and voice agents” was effective in motivating the competitors. From the second survey, it was confirmed that “cheering by CG animation and voice agents” increased the motivation and work performance of the competitors.

The functions of intelligent machines and robot manipulators can be extended by attaching special tools or grippers to the end-effector, and they accurately execute various tasks based on operation commands. Here, the robot’s operation is instructed by a skilled robot operator at each step, mainly through controller operation. In order for the robot to learn to motion autonomously, the authors have proposed an algorithm in which the robot learns to imitate the use of unused tools from the information of human work movement [1]. Furthermore, it was shown that tools with relatively high similarity can be learned in a short time based on the use already learned, and executed with high accuracy. In this paper, sweeping movements as a realistic task in human daily life is aimed, and by verifying the combination of a wide variety of broom-shaped tools and objects to be collected, the adaptability of high-speed imitation learning ability by the algorithm was evaluated. The results show that the changes in the cleaning ability of the tools and objects to be handled and their tendencies are clarified. The effect of similarity on the speed of imitation learning are also confirmed. Regarding to the similarity, the validity of the proposed calculation method using multiple tools are verified.

Recently, educational-support robots, which support learning, have been researched and developed. Most previous study focused on the learning effect of the robots teaching learners in learning contents such as mathematics and drawing work. Moreover, the research on the robots which prompt elderly driver to improve their driving behavior is paid attention. In the teaching material of the driving technique, it is often taught using the actual driving image. It is also reported that the learning method using media teaching materials using moving images has high learning effect on learners. However, it has not been verified whether teaching using dangerous driving movie by robot can improve learning effect to learners compared with learning method using media teaching material by dangerous driving movie. Thus, this paper investigates the learning effect given to learners by teaching driving actions to learners by using dangerous driving movie. The degree of mastery in this paper is defined as how much information learned after learning is acquired. In the experiment, the group which received the instruction from the robot using the dangerous driving movie was compared with the group which received the instruction from the learning system using the media teaching material.

A reward function estimated with inverse reinforcement learning has been used to determine a method for controlling a robot. The number of state transitions that can be observed using the action sequence given to inverse reinforcement learning decreases drastically as the complexity of the planning problem increases. Although a reward function can be designed even from partial state transition information, ambiguity in the obtained reward function exists. A reward function that can tolerate ambiguity is required when learning with a reward function that includes ambiguity. In this paper, we propose a method for quantifying the ambiguity of the reward function, which is designed with inverse reinforcement learning using fuzzy reasoning. Experimental results was suggested that proposed method can learn the action sequence while considering the degree of risk and safety.

Interactive design can be dealt as a sort of optimal solution search problems. In optimal solution search, initial value setting plays an important role. In order to solve the initial value setting, our previous study proposed a method using the onomatopoeia thesaurus map that can use arbitrary onomatopoeia. In the experiment of the previous study, we evaluated the proposed method using the brush font design system as an example. The experiment showed that the proposed method can set initial values near the optimum values in the design parameter space. The experiment adopted Euclidean distance between the optimum value and the initial value in the design parameter space. The experiment compared the Euclidean distance between the proposed method and other methods. The relationship between the Euclidean distance and the amount of change of the visual effect for brush fonts is not linear. The amount of change of the visual effect depends on the position in the parameter space. Therefore, the previous study could not show the effectiveness of the proposed method. This paper adopted subjective evaluation to evaluate visual similarity of the brush font between the optimum value and the initial value set by proposed method. We compared the proposed method with the other methods as in the previous research. As the result, the proposed method was most similar to the visual effect generated by the optimum value. In addition, there were statistical significances between the proposed method and the others.

In recent years, the percentage of traffic accidents involving elderly drivers has been increasing, and it is becoming a social problem. To prevent the traffic accidents, it is important for elderly drivers to improve own driving by reviewing it. We have been developing a system that allows to review driving situations at home, in order to improve driving behavior. In this paper, we propose models for estimating the distance between a vehicle and stop lines by using the inclusion-exclusion integral regression model from dashboard camera for the system. First, we extract an image where the markers are placed with known distance to the car in order to build a model. Second, we build six models by varying t-norm of the inclusion-exclusion integral regression model. Then, we compare estimated distances with each obtained model.

There are measurement devices such as magnetic resonance imaging (MRI), which can acquire brain activity. The case of MRI can use to investigate brain function. In addition, other physiological measurement techniques are used as supportive measures in this area of research. Various studies on the learning process have been carried out using these instruments. However, long-term measurement is hard for participants and researchers. The multiple measurements of short periods are consecutive mostly. Concerning this style, the medical risk of these measurements has been pointed out. In this case, one solution is measuring the learning level offline, mean outside MRI. It is considered to reduce the physical and psychological strain on the participants. In this study, we conducted an experiment to observe how to learn about solving puzzles over a long period of time. The obtained learning curve shows the possibility to choose the best period to measure on MRI. Based on these data, we propose a model for predicting the learning level. From these models, we discuss the appropriate timing for biometric measurements in terms of the learning level and validate the curve models.

Recently, as the number of patients with mental illnesses has increased rapidly, more psychotherapists are needed. However, it is still not common to receive appropriate treatment due to high consultation costs and aversion to psychotherapy. This leads to increase of suicides originating in deterioration of mental condition. At the moment, no dialogue system has achieved therapeutic skills close to a human counselor. Therefore, to realize a dialog system capable of recognizing mental problems, we developed three types of methods for extracting trouble sentence and emotional sentence automatically from online Q and A site. Based on these methods, we have developed rule-based extraction system, similarity-based extraction system, and classifier-based extraction system. In the performance evaluation experiments conducted, classifier-based extraction system showed the best F-score of 0.73 when compared to other systems.

An autonomous mobile robot needs to many tasks such as a self-localization, collision detection, and path planning to a target position in an unknown environment. Therefore, it is important for the robot to build environmental maps with different resolutions in each work space. In addition, the robot requires the path planning capability in the unknown environment for applying the robot to various environment such as a disaster site and commercial construction. This research proposes a Growing Neural Gas based topological environmental map building method from a metric map with high resolution map for using the self-localization. Our proposed method enables to build the topological map with occupancy information of the metric map and preserve the geometric feature of the map simultaneously. Next, the path planning method in the unknown environment is proposed by utilizing the occupancy information of the topological map. Finally, we conduct on several experiments for evaluating our proposed method by comparing to other conventional approaches, and discuss the effectiveness of our proposed method.