Toyota Jidosha Kabushiki Kaisha

Issei Nakashima

Makoto Kobayashi

Nobuhisa Otsuki

Manabu Yamamoto

Masayuki Imaida

Taiga Matsumoto

Eiichi Saitoh

Satoshi Hirano

Shigeo Tanabe

Toshio Fuwa

Shuhei Manabe

Hiroaki Daba

Akihiro Saito

Hitoshi Konosu

Takuma Nakamura

Hodaka Kito

Takuma Il

Yo Sato

Toru Miyagawa

Hideo Hasegawa

Yusuke Kinoshita

Hiroshi Shimada

Natsuki Yamakami

Hiroki Tanikawa

Yoshiaki Kato

Eisuke Aoki

Keisuke Suga

Yoshikazu Motozono

Tomio Ikeda

Yoshinori Fujikake

Taiki Yoshida

Takuya Iwata

Masayuki Takashima

Yasuhiro Ebihara

Yoshie Nakanishi

Nagisa Tanaka

Takeru Fukagawa

Bing Xue

Takashi Homma

Shotaro Yasuda

Asuka Hirano

Masaki Katoh

Yohei Otaka

Akihito Uno

Ai Kurokawa

Yuta Mori

Takuma Ii

Provided is a traffic facility control system capable of achieving both ensuring of physical safety of a moving person and reduction of a psychological burden on the moving person. The traffic facility control system according to the present disclosure includes: a detection unit configured to detect a moving ability of a person; a determination unit configured to determine a psychological state of the person; and a control unit configured to control a traffic facility installed at at least one of the vicinity of a current position of the person, a position on a route along which the person moves, or a position along the route based on the moving ability of the person and the psychological state of the person.

Traffic facility control system, traffic facility control method, and program

A first exemplary aspect is a health promotion system using a computer, the health promotion system including: a door mechanism configured to be opened by an operation performed by a person; a control unit configured to control the door mechanism; and identification information acquisition unit that acquires identification information for identifying the person who operates the door mechanism. The control unit acquires health condition information indicating a health condition of the person, determines whether or not the health condition satisfies a target value that is predetermined for the person identified by the identification information, and increases an exercise load of the operation for opening the door mechanism when the health condition does not satisfy the target value.

Health promotion system and health promotion method

The learning system includes a data generation unit configured to generate learning data based on rehabilitation data and a learning unit configured to perform machine learning using the learning data. A sensor is provided to detect a plurality of motion amounts in a walking motion of a trainee, and it is evaluated that, when one of the motion amounts matches one of abnormal walking criteria, that the walking motion is an abnormal walking pattern that meets the matched abnormal walking criterion. The data generation unit generates each of the pieces of rehabilitation data before and after a change in the results of evaluation of the abnormal walking pattern as learning data. The learning unit sequentially inputs each of the pieces of rehabilitation data as one data set, thereby performing machine learning.

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

The present disclosure provides an extraction system capable of accurately extracting a region of an image where a leg part of a trainee is included. an extraction system including: an image acquisition unit that acquires an image obtained by capturing the trainee; an extraction unit that sets regions of the image on both left and right sides of the belt of the treadmill to regions of the image where the leg part of the trainee is not present and thereby distinguishes the set regions from the region of the image where the leg part of the trainee is included, and extracts the region of the image where the leg part of the trainee is included; and a mask processing unit that applies a mask to each of the regions of the image where the leg part of the trainee is not present.

Extraction system, walking training system, extraction method, and extraction program

A learning unit of a learning system generates the following learning model. That is, this learning model is a model that inputs rehabilitation data for each predetermined period and predicts a change in index data, the rehabilitation data being data about rehabilitation performed by a trainee using a rehabilitation support system, the index data indicating at least one of a symptom, a physical ability, and a degree of recovery of the trainee. This rehabilitation data includes at least the index data and training data of the trainee, the training data being acquired during the rehabilitation in the rehabilitation support system. Further, the learning unit generates the learning model by using, as teacher data, data obtained in a period until the index data reaches a predetermined target level.

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

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

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

The learning apparatus includes a data generation unit configured to generate learning data based on rehabilitation data and a learning unit configured to perform machine learning using the learning data. A sensor is provided to detect a plurality of motion amounts in a walking motion of a trainee, and it is evaluated that, when one of the motion amounts matches one of abnormal walking criteria, that the walking motion is an abnormal walking pattern that meets the matched abnormal walking criterion. The data generation unit generates each of the pieces of rehabilitation data before and after a change in the results of evaluation of the abnormal walking pattern as learning data. The learning unit sequentially inputs each of the pieces of rehabilitation data as one data set, thereby performing machine learning.

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 motion state monitoring system, a training support system, a motion state monitoring method, and a program capable of suitably managing measurement results according to an attaching direction of a sensor are provided. A motion state monitoring system according to the present disclosure monitors a motion state of a target part of a subject's body. The motion state monitoring system includes an acquisition unit, an attaching direction detection unit, and a control processing unit. The acquisition unit acquires sensing information of a sensor attached to the target part. The attaching direction detection unit detects an attaching direction of the sensor. The control processing unit outputs information related to the sensing information in association with the attaching direction.

Motion state monitoring system, training support system, motion state monitoring method, and program

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.

Appropriate housing equipment according to the physical ability of a trainee who has performed rehabilitation in order to restore or maintain the physical ability is easily presented. A housing equipment presentation apparatus includes a storage unit configured to store definition information defining housing equipment information according to a physical ability, an acquisition unit configured to externally acquire physical ability information of a trainee who has performed training in order to restore or maintain his/her physical ability, a conversion unit configured to convert the acquired physical ability information into the housing equipment information based on the definition information, and an output unit configured to output presentation information including the converted housing equipment information.

Housing equipment presentation apparatus, system, method and program

A state estimation program is for causing a computer to function to determine a state of training in a rehabilitation support system used by a trainee to perform training of a preset motion and includes a threshold setting step and a state estimation step. The threshold setting step is for acquiring a sensor output, the sensor output being an output of a sensor included in the rehabilitation support system in the training performed by the trainee and setting a threshold for determining one of a normal state and an abnormal state of the training based on the sensor output. The state estimation step is for estimating whether the training is performed in the normal state or the abnormal state based on the threshold.

State estimation program, trained model, rehabilitation support system, learning apparatus, and state estimation method

A walking training system according to this embodiment includes a harness, at least three pulling units, and a control unit configured to control the at least three pulling units in such a way that a position of the harness in a horizontal plane becomes a target position. One of the at least three pulling units is a first pulling unit configured to apply a pulling force to the harness from front of the trainee, another one of the at least three pulling units is a second pulling unit configured to apply a pulling force to the harness from rear of the trainee, and another one of the at least three pulling units is a third pulling unit configured to apply a pulling force to the harness from a direction different from the first and second pulling units.

Walking training system and operation method

Growing community of inventors

Toyota, Japan

Issei Nakashima