Abstract: 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.

Abstract: An information processing apparatus for determining an evaluator to evaluate a product or service provided by one of providers from among a plurality of evaluators, the information processing apparatus comprises a controller configured to execute: training a user model, with first data about the providers and second data about the plurality of evaluators who have made evaluations of products or services provided by the providers in past as input data, and third data indicating degrees of usefulness of the evaluations made by the plurality of evaluators in the past as output data; and selecting the evaluator suitable for the one of the providers from among the plurality of evaluators by using the user model.

Abstract: An information processing apparatus comprises a controller, the controller comprising at least one processor configured to perform: acquiring position information about a first user, the user having been absent from a predetermined event at an event holding timing, which is a date and time of the predetermined event having been held; acquiring first information that is information at the event holding timing different from the position information about the first user and is information related to the first user at the event holding timing; determining whether a reason for the first user having been absent from the predetermined event is a force majeure reason or not based on the position information and the first information; and selecting the first user as a follow-up target if the absence reason is determined to be a force majeure reason.

Abstract: The present disclosure relates to a demonstration experiment management system for managing a demonstration experiment. The demonstration experiment management system includes processing circuitry. The processing circuitry acquires information on a consent item of which a participant of the demonstration experiment consents to provide data among a request item. The request item is an item of which an executor of the demonstration experiment requests the participant to provide the data. Then, the processing circuitry calculates a contribution degree of the participant to the demonstration experiment based on at least the consent item. Then, the processing circuitry determines an incentive to be paid to the participant by the executor based on at least the contribution degree.

Abstract: An automated order processing for order items registered in advance as commodities targeted for automated order service is performed. In the automated order processing, it is determined whether any container/package for the order items exists in the disposal box, based on internal status data of a disposal box or identification data on the contents of the container/package existing in the disposal box. If it is determined that any container/package for the order items exists in the disposal box, the number of discarded containers/packages for the order items existing in the disposal box is calculated. Then, it is determined whether the number of discarded containers/packages is equal to or larger than an upper threshold set according to a sales mode of the order items. If it is determined that the number of discarded containers/packages is equal to or larger than the upper threshold, ordering data of the order items is generated.

Abstract: 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.

Abstract: 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.

Abstract: A delivery method according to the present disclosure includes a step of delivering packages to designated destinations by mobile bodies traveling autonomously, each of the packages having a delivery priority level. The delivery method further includes a step of, when a number of mobile bodies gathered in a bottleneck section is larger than a number of mobile bodies capable of passing through the bottleneck section at the same time, preferentially causing a mobile body delivering a package of which the delivery priority level is higher than a package delivered by another mobile body to pass through the bottleneck section.

Abstract: A home delivery system delivering objects to a residence comprises a moving body configured to move autonomously or remotely, a plurality of sensors placed in the residence, and the processing apparatus. The processing apparatus is configured to execute observing status of a resident including whether or not the resident is in the residence based on detection information acquired from the plurality of sensors. Then, the processing apparatus is configured to execute instructing the moving body to start a delivery at least condition that the resident is in the residence and instructing the moving body to complete the delivery on condition that the resident is available to response after the moving body arriving at the residence.

Abstract: When an autonomous mobile robot is acquires enters a stuck state in which the autonomous mobile robot cannot autonomosly move, an autonomous mobile apparatus control system according to the present disclosure transmits an autonomous cancel notification for notifying the higher-level management apparatus that the autonomous mobile robot cannot autonomosly move, waits for an operation instruction from the higher-level management apparatus after the transmission of the autonomous cancel notification. The higher-level management apparatus gives an operation instruction to the autonomous mobile robot in response to receiving the autonomous cancel notification based on information acquired from at least one of the plurality of environment cameras. The autonomous mobile robot is configured to resume autonomous driving in response to safety confirmation based on a proximity sensor provided in the autonomous mobile robot after operating in accordance with the operation instruction.

Abstract: 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.

Abstract: 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.

Abstract: The traveling unit main body and the accommodation unit are adapted to be uncoupled and re-coupled. The traveling unit main body includes a first driving unit and a second driving unit configured to perform at least one of operations of taking out or storing the article from or in the accommodation unit and transporting the article taken out from the accommodation unit. The traveling unit main body performs at least one of the operations of taking out, storing, and transporting the article using the first driving unit and the second driving unit in a state in which the traveling unit main body and the accommodation unit are uncoupled.

Abstract: To effectively enhance the operation efficiency of an autonomous mobile robot, an autonomous mobile robot control system includes a processor and a plurality of environmental cameras. The processor estimates a moving route of each of a plurality of moving bodies on the basis of characteristics of each of the plurality of moving bodies and sets a subset of the plurality of moving bodies whose moving routes overlap among the detected moving bodies as avoidance processing target moving bodies. The processor generates an avoidance procedure for the avoidance processing target moving bodies so the motion of the avoidance processing target moving bodies does not interfere with the motion of other avoidance target moving bodies.

Abstract: A logistics system provides a logistics service utilizing a logistics robot that delivers a package by autonomous traveling. The logistics system includes one or more processors configured to execute a delivery route determination process that determines a delivery route along which the logistics robot delivers the package. When there are a plurality of delivery route candidates from a position of the logistics robot to a delivery destination of the package, the one or more processors select the delivery route from the plurality of delivery route candidates based on at least one of a congestion degree of each of the plurality of delivery route candidates, a time of day, a weather condition, and energy consumption of the logistics robot along each of the plurality of delivery route candidates.

Abstract: At least one of a discharging tendency of waste based on a discharge history of discharge of the waste by a user of a service and a discharge prediction about the waste based on the purchase history of a product by the user is calculated. A need prediction about the service is calculated by using a prediction model which uses, as a parameter, at least one of the discharging tendency of the waste and the discharge prediction about the waste. A level of the service is estimated by a simulation which uses, as parameters, the need prediction and a resource employed for the service. A notification is transmitted to the user suggesting a modification of behavior of at least one of discharge of the waste and purchase of a product by the user based on a comparison result between an estimated level and a stipulated level of the service.

Abstract: A service management device manages a service delivered in a predetermined area. The service management device has an operator interface including a display that displays information for an operator and receiving an input from the operator. The service management device communicates with an autonomous robot used for delivering the service in the predetermined area to acquire, from the autonomous robot, service robot information indicating at least a position and a status of the autonomous robot. The service management device displays a map of the predetermined area and the position of the autonomous robot on the display, based on the service robot information. When the autonomous robot displayed on the display is specified by the operator through the operator interface, the service management device displays a status window indicating the status of the autonomous robot specified by the operator on the display, based on the service robot information.

Abstract: 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.

Abstract: 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.

Abstract: 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.