Translating mental health recognition from clinical research into real-world application requires extensive data, yet existing emotion datasets are impoverished in terms of daily mental health monitoring, especially when aiming for self-reported anxiety and depression recognition. We introduce the Japanese Daily Speech Dataset (JDSD), a large in-the-wild daily speech emotion dataset consisting of 20,827 speech samples from 342 speakers and 54 hours of total duration. The data is annotated on the Depression and Anxiety Mood Scale (DAMS) – 9 self-reported emotions to evaluate mood state including "vigorous", "gloomy", "concerned", "happy", "unpleasant", "anxious", "cheerful", "depressed", and "worried". Our dataset possesses emotional states, activity, and time diversity, making it useful for training models to track daily emotional states for healthcare purposes. We partition our corpus and provide a multi-task benchmark across nine emotions, demonstrating that mental health states can be predicted reliably from self-reports with a Concordance Correlation Coefficient value of .547 on average. We hope that JDSD will become a valuable resource to further the development of daily emotional healthcare tracking.

MEL HORSE has been developed for studying quadruped robot and biped robot. The control of zero moment point (ZMP) is indispensable in order for a legged type robot to walk dynamically. By the conventional method, optimization calculation is required in order to calculate the true ZMP, and this is time consuming. Moreover, if it depends on the o(R)-line calculation, then the situation which is not expected when carrying out real-time control of the robot cannot be dealt with. This paper describes the ZMP control using the receding horizon control which is a technique of real-time optimization to cope with the problem mentioned. According to this technique, it is possible to generate an ZMP reference trajectory autonomously in real time.

MEL HORSE has been developed for studying quadruped robots and biped robots. Biped robot "MEL Deinonychus II" is a fore-portion of "MEL HORSE II" developed by the author (1996, 1999). To develop a legged robot, one can not avoid the problem of how to control the robot in real-time. Particularly, the zero moment point (ZMP) control is hard work. In this paper, a new approach to generate ZMP reference trajectory of quadruped robot, biped robot and other type legged robot is proposed. Simulation results are also explained.

A new legged machine named "MEL HORSE II" is developed. MEL HORSE II is a quadruped robot. Different leg-functions are assigned for fore-feet and hind-feet. The fore-feet have the gravity-support function. Unlike the conventional walking robot which has the center of gravity at the center of fuselage, MEL HORSE II has the center of gravity at the front of the fuselage. The hind-feet have the function of generating forward force. Since the center of gravity is distributed at the front part, the hind feet are allowed to reduce the gravity support. We develop these simple mechanism by using a counter balance. Furthermore, an analysis using the proposed vertical/horizontal (V/H) ratio is done. The V/H ratio is a affiliated value from dexterity for measurement of the gravity support function and forwarding function. For leg control, an enhanced passive biped control is proposed. It integrates both biped control and quadruped control.

A new leg-wheel hybrid vehicle named "Roller-Walker" is proposed. The Roller-Walker is a vehicle with special foot mechanism which changes to the sole for walking mode and passive wheels for wheel mode. On rugged terrain the vehicle walks in the leg mode, and on level or comparatively smooth terrain the vehicle makes wheeled locomotion by using the passive wheel in the way of roller-skating. The characteristics of the Roller-Walker are: (1) it has lightweight body and hybrid function; (2) it has potential capability to exhibit high terrain adaptability in the wheeled mode if the control method of the Roller-Walking is fully investigated in the future. The paper makes basic simulation experiments and demonstrates basic relations on the terrain adaptive trajectory control method of the Roller-Walk.