This study aims to develop a system that visualizes pedestrians located in non-line-of-sight (NLOS) regions—such as intersections and shadows cast by buildings—and presents this information to users through VR headsets, thereby reducing collision risk and supporting safe mobility. As the first phase of this research, an image processing system was developed to analyze camera footage and estimate the real-time positions, postures, and movement directions of both pedestrians and users. Specifically, a method was constructed that employs bird’s-eye view transformation for accurate pedestrian localization and utilizes skeleton data derived from pose estimation to recognize postures and movement directions. Evaluation experiments demonstrated high accuracy for basic movements and confirmed the potential for future three-dimensional reconstruction.

This study investigates a navigation method for service robots based not on conventional geometric information, but on natural language–based path generation. First, route planning is performed using OpenStreetMap data, and human-readable instructions such as "turn right at the intersection" are generated from the resulting path. The proposed method is then evaluated in terms of labor and processing time by comparing it with existing GPS- and SLAM-based approaches.

In recent years, development of robots that can run independently in the same space as humans has been progressing. Most of the current navigation methods for autonomous robots use geometric information. While this method is easy to implement, it has some drawbacks, such as the need for accurate self-positioning and vulnerability to errors in sensor information. Humans do not have an exact self-position, but rather, they recognize an approximate location based on surrounding information and envision the path to the goal to reach the destination. Therefore, this study examines a navigation method that plans a route based on an abstract map, such as a hand-drawn map, and then travels independently to the destination.

In this paper, we describe the integrated system for ensuring the safety of forestry workers. It is difficult to accurately acquire GPS information in forests. Therefore, it is necessary to consider a position estimation method that does not use GPS. First, the accuracy of VisualSLAM, IMU, and Beacon alone was verified and evaluated by experiments. We also examined the communication method and self-position estimation system for the integrated system. The results show that the self-positioning of Visual SLAM and IMU requires a large interval for correction, which results in a large error. Therefore, we found that the larger the measurement interval, the larger the error of any sensor system. The future tasks are to improve the accuracy of sensor systems, to optimize the measurement interval, and to integrate the systems.

This paper, we describe a method to detect glass existing in the real environment. One of the characteristics of glass is the semi-mirror surface. Focusing on its characteristics, we investigated a method for detecting glass from itself and its own reflection image. From the results, we were able to detect the glass by the proposed method.

The following topics are dealt with: learning (artificial intelligence); user interfaces; human computer interaction; artificial intelligence; medical signal processing; service robots; image classification; man-machine systems; mobile computing; and feature extraction.

This research discusses a dialogue system for human-robot communication. In order to develop a dialogue system, we conducted prototypes, experiments, and evaluations for each of the following three elements, “voice recognition”, “sentence comprehension”, and “response sentence generation” that are performed when a human talks with another person. Each element could be activated even though it was in the prototype stage.

In this research, in order to clarify robot design elements with high affinity with people, we developed an evaluation system that enables users to evaluate impressions from a highly flexible perspective from augmented reality. Human investigated impression evaluation on robot and identified 5 factors which are the evaluation index.

The purpose of this research is to develop the agricultural support system aimed at light labor and efficiency when doing agricultural work. The support system attempts to achieve the goal by proposing appropriate actions to humans from the state of agricultural land and the growing situation of the crops. To support agricultural work, this system transmits weather data, environmental data of agricultural land to the web server by sensors and scraping. This data is received with the created application. Following the value of the received data, the support system proposes the appropriate actions for the human. The proposed action decided from the four factors of temperature, humidity, illuminance, and soil moisture content, respectively. The experiment is the subject grow crops. In addition, confirm the significant difference between using the support system, not using it. After the experiment, analyze the questionnaire result by T-test to confirm the significant difference. From the results of the experiment, a significant difference in experiments confirmed by the t-test. Therefore, humans grow crops using proposed actions from support systems, It confirmed that light labor and efficiency realized. (183 Words).

In this paper, we considered the localization methods which recognizes landscape. In order to realize localization technique by recognizing landscape like a human, we recognize the landscape from objects arrangement in view. In this paper, we consider landscape recognition by SVM and segmentation method by deep learning. As results of object recognition by SVM and segmentation, the recognition rate was higher in the method by segmentation. In addition, from the experiment of localization by landscape recognition at multiple locations, we clarified the problem when applying this method to localization.

This paper presents a new type of leg-wheeled robot, which is constructed with passive wheels and the idea of reduced degrees of freedom (DOF). Even though there are variety types of mobile robots researched, some of them cannot be used practical purpose because of their high number of DOF, resulting in complex structure and complicated control system. Typical leg-wheeled robots also have a high number of DOF, and because of that, it is very difficult to put them in practical purpose. Thus, we try to develop another type of leg-wheeled robot with reduced DOF, which only have 10 DOF even though they have 6 legs. The motion plan for the robot discussed in previous study was simply moving forward, and those motion plans cannot be applied for moving omnidirectionaly. Therefore, we propose new motion plans, which can be applied for moving in omnidirection, and more details about the motion planning of moving forward by using the new motion plan.

This paper presents another type of robotic cart. In recent years there are a variety of power-assisted machines being researched. From them, robotic carts can help older people carry heavy objects easily and efficiently. Because of the similarity of conventional carts, they can be used in a variety of situations. However, robotic carts have the common mechanism that their wheels are driven directly by actuators. Because of that, energy efficiency is low, and those carts cannot move when battery power is low. As a result, older people are burdened by this disadvantage. To counter this, we tried to develop another type of robotic cart that has passive wheels instead of using regular active wheels. By using passive wheels, the robotic cart has high energy efficiency.

If one of the six legs of a hexapod walking robot is disabled, static walking may be maintained by the remaining five legs. However, to maintain the static stability at maximum, gait study for five legged walking is necessary. Hence, this paper describes a method of gait study for such situation. Since it is very difficult to find out suitable gait by use of analytical method without any model such as insects walking, we employed a high-powered computer. Some devices are applied to reduce the number of computations. As the result, we have got two kinds of gaits which can maintain the gait stability margin at high level.

This paper presents a constructing method for practically used walking machine. For optimal motion, it must have as long a cruising range as possible, and to improve energy cost it should have a powder clutch joint driving system with an engine actuator. We develop applicable leg mechanism with GDA (gravitationally decoupled actuation) to the proposed driving system. Moreover, feasible joint control system for the proposed driving system with powder clutches is designed and implemented by using sliding mode control. From comparison result of this type of driving system with that of a DC motor actuated system, even though power to weight ratio cannot be improved effectively, cruising range is three times longer than DC motor type. Therefore, this type of walking machine can be suitable for personally used walking machine in term of cruising range, cost, and size.

A merit of hexapod walking robots is robustness to recover irregular situations. For example, even if one of the six legs is broken down, the hexapod machine may keep the walking. In this article, we propose a new gait rule named adaptive wave gait. The gait rule corresponds to not only the six legged walking, but also the five legged walking. Meanwhile, we also propose a synchronized motion control which is very important factor for the multiple legged walking. By combining the adaptive wave gait and the synchronized motion control, the gait generation and gait transition can be executed smoothly, and they realize natural walking of hexapod robots.>

This paper describes a new force control method for a hexapod walking robot developed for the purpose of transportation in rough terrain. In unstructured terrain such as soil and gravel, walking robots require the force control to keep its stability. Normally, soft surfaces such as soil has hysteresis characteristics. Thus, general force control, which sometimes shows overshoots is not desired. On this point of view, our new force control uses torque observer and avoids overshoot by a simple strategy. And, we also employed a notion of autonomous distributed control. The distributed controllers placed on each leg decide their own manner with referring information from central controller. We also confirmed the validity of our method by several kinds of numerical simulation.>

This paper discusses dynamical motion control for a quadruped walking machine. A quadruped walking machine requires dynamical control to keep its stability in high speed walking. The authors make the dynamical compensator by using a weight oscillator built in the center of the body. First, the authors calculate the exact oscillator motion that can neutralize the moment, completely. Next, they try to use a harmonic oscillation for the oscillator's motion instead of the accurate motion. Finally, the authors use a notion of autonomous distributed control for motion control and expand it to quasi-dynamical walking.>

Quadruped walking animals have both a static walking manner and a dynamic walking manner. The static walking can keep their stability structurally, but it only appears in slow speed walking. In high speed walking, the dynamic manner is required. Thus, animals change their gaits to be suited for their walking speed. In this paper, the authors propose a new method for transferring the gaits by autonomous distributed control. This control system includes one central rhythm generator and four distributed controllers. The distributed controller receives a phase signal which is a kind of rhythm clock from the central rhythm generator.

This paper describes a synchroniz- ing control for a hexapod walking robot named Hexax-I, which is developed for purpose of trans- portation in unstructured environnient. Hexapod robots are practical machine for such purpose, but they include several unsolved technical problems. While problems of power and mechanisms are ma- jor to be solved, control problems are also serious problenis. One of big control problem is the strat- egy how to syncliroiiise the six legs. 'Open loop control' is a simple approach, but it is not robust against disturbances by ground, thus it disables the good property,'flexible walking'. This paper proposes a simple control strategy to realize syn- chronized motion of six legs.

This paper describes a hexapod walking robot named Hexax-I, which was developed for transportation in unstructured environments. In general, walking robots have poor energy efficiency due to their walking mechanisms. The authors propose a power system which consists of a gasoline engine and computer-controlled electromagnetic clutches and brakes. Gasoline engines have an excellent weight-to-power ratio in comparison with DC-motors. The authors propose a method of circular walking using the interaction between the steering and the propulsion. The driving systems of the propulsion and of the steering are shared. The robot is therefore lightweight because the steering actuators are left out, and so a high power-to-weight ratio is achieved. A simple control method for steering the legs by utilizing this special structure is also proposed.>