Toyota Jidosha Kabushiki Kaisha

Hiroaki Daba

Makoto Kobayashi

Issei Nakashima

Nobuhisa Otsuki

Manabu Yamamoto

Masayuki Imaida

Taiga Matsumoto

Yoshiaki Kato

Takuya Iwata

Ai Kurokawa

A learning apparatus, a walking training apparatus, a method, a system, a program, and a trained model for performing walking training at appropriate setting parameters are provided. A learning apparatus according to an embodiment includes: a data acquisition unit configured to acquire rehabilitation data from a walking training apparatus including an actuator configured to assist a walking motion of a trainee and a control unit configured to control the actuator in accordance with a setting parameter; and a data generation unit configured to generate an index indicating a degree of recovery of the trainee and the setting parameter as learning data; and a learning unit configured to generate a learning model that receives the index and outputs a recommended value of the setting parameter by performing machine learning using the learning data.

Learning system, walking training system, system, method, program, and trained model

A walking training apparatus is a motion support system that includes a walking assistance apparatus as an assistance apparatus, a selected assistance level setting unit, a load data acquisition unit, an angle sensor as a displacement sensor, and an overall control unit as a control unit. The assistance apparatus assists a motion of a joint performed by a user. The assistance level setting unit sets an assistance level that is a level of a force exerted by the assistance apparatus. The load data acquisition unit acquires load data related to a load of the assistance apparatus. The displacement sensor detects a displacement of the joint. The control unit determines a recommended assistance level, which is an assistance level to be recommended, based on the assistance level, the load data, and an output of the displacement sensor, and outputs information about the determined recommended assistance level.

Motion support system, action support method, program, learning apparatus, trained model, and learning method

The server is a learning apparatus including a data acquisition unit and a learning unit. The data acquisition unit acquires profile data and a selected assistance level as learning data. The profile data indicates a profile related to a trainee before executing rehabilitation regarding rehabilitation executed using a walking training apparatus as a rehabilitation support system. The selected assistance level is an assistance level selected at the time of executing the rehabilitation. The learning unit learns to determine a recommended assistance level recommended to be selected when the trainee uses the rehabilitation support system based on the learning data. Further, the learning unit generates a trained model that receives the profile data and outputs the recommended assistance level based on the learning.

Learning apparatus, rehabilitation support system, method, program, and trained model

A learning system, a walking training system, a method, a program, and a trained model for performing walking training at appropriate setting parameters are provided. A learning system according to an embodiment includes: a data acquisition unit configured to acquire rehabilitation data from a walking training system including an actuator configured to assist a walking motion of a trainee and a control unit configured to control the actuator in accordance with a setting parameter; a data generation unit configured to generate the rehabilitation data including detection data and the setting parameter as learning data; and a learning unit configured to perform machine learning using the learning data, thereby generating a learning model that receives the detection data and outputs a recommended value of the setting parameter.

Learning system, walking training system, method, program, and trained model

A walking training apparatus includes: a treadmill; a walking assistance apparatus configured to be mounted on a leg part of a user and assist the user's walking; a first pulling means for pulling at least one of the walking assistance apparatus and the leg part of the user upward and frontward; a second pulling means for pulling at least one of the walking assistance apparatus and the leg part of the user upward and rearward; and control means for controlling, while the treadmill is not being operated, pulling forces of the first pulling means and the second pulling means in such a way that the direction of a resultant pulling force, which is a resultant force of the pulling force of the first pulling means and the pulling force of the second pulling means, is changed rearward compared to a case in which the treadmill is being operated.

Growing community of inventors

Nisshin, Japan

Hiroaki Daba