Many man-machine interfaces controlled by electromyogram (EMG) signals such as the myoelectric prosthetic hand have been proposed. General classifiers do not cover unintended motions in the training phase and misclassify those inevitably. Since the misclassification can cause dangerous incidents, an interface with high security is required. To solve this problem, this paper proposes a novel control method of man-machine interfaces that can treat unlearned motions. In the experiments, the proposed method was applied to forearm and finger motion classification to evaluate the validity. The outcomes showed that the approach produces higher and more stable classification performance than comparative methods.

When a volcano erupts, the area around the volcano's crater is restricted to off-limits areas according to the eruption warning level, which prevents people from conducting a detailed investigation near the crater. Therefore, our research group has been researching and developing sensor devices transported and deployed in the restricted area. Previous research has used topographic data for the sensor device's safety landing to choose flat terrain with no plant. This method does not consider the visibility to the observation target when the sensor device is an observation camera. To solve these problems, we developed an installation location selection system based on the previous method plus a selection method that considers the prospect to the observation target. The method was implemented and evaluated in the natural environment. In this paper, we explain the proposed method and report field-experimental results.

Generally, wheel odometry accuracy tends to drop significantly in situations such as running on soft ground or when the robot is turning. Visual odometry (VO) is considered a promising alternative for calculating the trajectory of autonomous robots. However, the conventional VO methods have the issues that the accuracy decreases in the environment where in the crowds or have few feature points. In this paper, we propose a real-time and highly accurate VO method that uses a downward-facing monocular camera. The proposed method has advantages in the accuracy and calculation performance by estimating and matching the feature of the ground surface using a lightweight neural network. Besides, the pose of the camera is automatically estimated to prevent the decrease of odometry accuracy due to the error of the camera posture.

Unmanned construction is used to recover from natural disasters in environment expecting secondary disaster. This construction method provides bird's-eye view of multiple viewpoints for operator using a lot of camera images. Therefore, this construction method has problem that increase communication throughput and delay camera images. In this research, we are developing multiple viewpoints of overall bird's-eye view that reduce communication traffic-volume, by superimposing a 3D model of construction machine on an omnidirectional image. In this paper, we describe the result of experiment about generating multiple viewpoints using a construction machine, and show validity of overall bird's-eye view using aerial image in indoor environment.

This research aims to personalize the dynamic tightening control by Active Corset, which is the low back pain prevention tool, to each individual. The standard tightening force control based on the average tendency of subjects was modified based on the height, weight, and age, which is considered to be one of the individual differences in the assisting effect of pelvic tightening. We derived model formula for personalize the tightening force control by a hearing survey that 12 subjects joined. In order to verify the assisting effect of the personalized control law, we conducted a motion measurement experiment on 64 subjects. As a result, we confirmed that the lumbar burden was more reduced by using personalized tightening control in the majority of the subjects as compared with the case of using standard tightening control. In addition, by evaluating the joint stiffness, we confirmed that the lumbar burden can be further reduced by increasing the lumbar joint stiffness in the initial stage of motion.

In distance-based formation control, an approach uses relative target positions of agents to achieve the desired formation shape. The relative target position consists of the desired distances and relative positions of the adjacent agents. This paper proposes leader-follower control laws using the relative target positions for an integrator's multiagent system in the plane. This paper gives a static control law that uses relative target positions and their change rate. Since the proposed control law is sensitive against disturbances, this paper also proposes a dynamic control law using relative target positions. These control laws are available to two-wheels mobile robots that have nonholonomic constraints. Numerical examples illustrate the effectiveness of the proposed formation control laws.

In a policy simulation for the life planning of elderly, the possibility of future asset depletion is analyzed based on clusters generated from specific attributes and segments. However, a room for improvement exists in the detailed understanding of the attributes that branch the simulation re-sults and comparative examination of possible metrics. In this study, we propose a life planning support system that combines the existing method with social simulation log analysis. This system has the following steps: I) Performs simulations based on clusters generated from the feature analy-sis of individual data. II) Grasps the overall pattern of possible results by comprehensive simula-tions based on the individual data and hierarchical classification of the obtained simulation logs. III) Considers the possible measures by comparing the results of I) and II). The main results of this study are as follows: a) Ability to grasp the threshold of the attribute that separates asset depletion and non-depletion. b) Ability to specify countermeasures that can be taken for each cluster along with numerical goals comprehensively and semiautomatically. The proposed system enables de-tailed advice from financial institutions by providing knowledge directly linked to life planning, which leads to an improvement in the effectiveness of industrial applications.