Abstract: A multi-agent learning method includes: by an agent, presenting acquired information to a human; and, by the human, correcting a behavior of the agent.

Abstract: A controller for controlling a motion of at least one device subject to constraints on the motion, is disclosed. The controller comprises a processor and a memory, where the controller inputs parameters of the task including the state of the at least one device to a neural network trained to output an estimated motion trajectory for performing the task. Further, the controller extracts at least some of the integer values of a solution to a mixed-integer optimization problem for planning an execution of the task that results in the estimated motion trajectory. Further, the controller solves the mixed-integer optimization problem for the parameters of the task with corresponding integer values fixed to the extracted integer values to produce an optimized motion trajectory subject to the constraint and changes the state of the at least one device to track the optimized motion trajectory.

Abstract: An apparatus control device includes an observed value acquiring unit that acquires, from a sensor that observes an environment in which a control target apparatus is installed, an observed value of the environment, an observation predicted value acquiring unit that gives an observed value acquired to a first learning model and acquires an observation predicted value that is a future observed value from the sensor from the first learning model, and an unobservable value acquiring unit that gives an observed value acquired to a second learning model and acquires an unobservable value that is a value not directly observed by the sensor from the second learning model. In addition, the apparatus control device includes a control value calculating unit that calculates a control value of the control target apparatus using the observed value acquired, the observation predicted value acquired, and the unobservable value acquired.

Abstract: An air conditioning control device includes: an operation pattern acquiring unit to acquire operation patterns indicating an operation target air conditioner in a room; a temperature data acquiring unit to acquire temperature data indicating a temperature measured by a temperature sensor when the air conditioner is in operation: a prediction model generating unit to generate, using a control amount of the air conditioner and temperature data acquired when the air conditioner is in operation as training data, a room-temperature prediction model for predicting the temperature measured by the temperature sensor when the air conditioner are in operation; and an operation pattern selecting unit to provide the control amount of the air conditioner to the room-temperature prediction model to acquire a prediction temperature from each of the room-temperature prediction models, and selects one operation pattern from the operation patterns on the basis of the prediction temperature.

Abstract: A controller for controlling a motion of at least one device subject to constraints on the motion, is disclosed. The controller comprises a processor and a memory, where the controller inputs parameters of the task including the state of the at least one device to a neural network trained to output an estimated motion trajectory for performing the task. Further, the controller extracts at least some of the integer values of a solution to a mixed-integer optimization problem for planning an execution of the task that results in the estimated motion trajectory. Further, the controller solves the mixed-integer optimization problem for the parameters of the task with corresponding integer values fixed to the extracted integer values to produce an optimized motion trajectory subject to the constraint and changes the state of the at least one device to track the optimized motion trajectory.

Abstract: In a thermal load estimation device, a process in which a state estimating unit estimates a state amount indicating a state of a target area at an estimation target time by using measurement data obtained by measuring a state amount of the target area, air conditioner operation data indicating an operation state of an air conditioner disposed in the target area, and a thermal load of the target area estimated by a thermal load estimating unit, and a process in which the thermal load estimating unit estimates the thermal load of the target area by using the measurement data, the air conditioner operation data, and an estimation value of the state amount of the target area estimated by the state estimating unit are alternately performed, so that a thermal load likely to be the thermal load of the target area at the estimation target time is estimated.

Abstract: An imaging unit, a control parameter generation unit, a control unit, and a drive unit are provided. The imaging unit captures an image including two objects. The control parameter generation unit feeds information of the captured image including the two objects into an input layer of a neural network, and outputs a position control amount for controlling the positional relation of between the two objects as an output layer of the neural network. The control unit controls current or voltage to control the positional relation between the two objects by using the outputted position control amount. The drive unit changes a position of one of the two objects by using the current or the voltage. Here, the control parameter generation unit selects the neural network from a plurality of neural networks. Therefore, even if there are differences between objects or errors in the positional relationship between the two objects, alignment can be performed more accurately.

Abstract: An image analysis device includes a person detecting unit for detecting person images from image information from a surveillance camera, and acquiring both pieces of person image information as a result of the detection of person images, and pieces of attribution information about persons corresponding to the pieces of person image information, and a person narrowing down unit for performing narrowing-down of person image information with respect to the pieces of person image information and the pieces of person attribution information which are acquired by the person detecting unit, on the basis of a person narrowing down rule, to acquire person image information after the narrowing-down and attribution information about a person corresponding to the person image information.

Abstract: A control device: includes a data acquiring unit to acquire inference data including moving speed information indicating a moving speed of an autonomous mobile object, relative position information indicating a relative position of a dynamic obstacle with respect to the autonomous mobile object, and relative speed information indicating a relative speed of the dynamic obstacle with respect to the autonomous mobile object; a control amount calculating unit to calculate a control amount for controlling movement of the autonomous mobile object depending on movement of the dynamic obstacle using the inference data or preprocessed inference data corresponding to the inference data, and a control unit to control the movement of the autonomous mobile object using the control amount. The control amount calculating unit uses a learned model by machine learning, and the learned model receives an input of the inference data or the preprocessed inference data and outputs the control amount.

Abstract: An element construction unit compares output values of one or more elements included in an intermediate layer calculated by an output value calculating unit with a threshold value, and the number of elements included in the intermediate layer is maintained when any of the output values out of the output values of the one or more elements included in the intermediate layer is greater than the threshold value, and the number of elements included in the intermediate layer is increased when all of the output values of the one or more elements included in the intermediate layer are equal to or less than the threshold value.

Abstract: In a case of performing operations including alignment and insertion regarding two objects, a path setting unit 806 and an actor unit 804 are provided to learn a control amount. The path setting unit 806 provides the amount of movement for removing an object from its inserted position, and for locating it on and around the path of removing. The actor unit 804 obtains positions of the object and the values of a force sensor 801 there to perform learning by letting the positions of the object be the values for the output layer and letting the values of the force sensor 801 be the values for the input layer. Therefore, learning data can be collected efficiently.

Abstract: An air conditioning control device includes: an acquisition unit that acquires air conditioning data acquired by an air conditioner, and a start time of the air conditioner predicted by inputting the air conditioning data into a machine learning model; an augmentation unit that generates augmented data by referring to the air conditioning data and the start time acquired by the acquisition unit; and an update unit that updates the machine learning model, by referring to the air conditioning data and the start time acquired by the acquisition unit as well as the augmented data generated by the augmentation unit.

Abstract: A training device (100) performs training using a neural network. A training condition acquirer (110) of the training device (100) acquires training conditions that indicate prerequisites of the training. A model selector (150) selects, in accordance with the training conditions, a learning model that serves as a framework of a structure of the neural network. A learning model scale determiner (160) determines, in accordance with the training conditions, a scale of the neural network for the selected learning model. A trainer (170) perform training by inputting training data into the neural network in which the selected learning model is configured to the determined scale.

Abstract: An image analysis device includes a person detecting unit for detecting person images from image information from a surveillance camera, and acquiring both pieces of person image information as a result of the detection of person images, and pieces of attribution information about persons corresponding to the pieces of person image information, and a person narrowing down unit for performing narrowing-down of person image information with respect to the pieces of person image information and the pieces of person attribution information which are acquired by the person detecting unit, on the basis of a person narrowing down rule, to acquire person image information after the narrowing-down and attribution information about a person corresponding to the person image information.

Abstract: An imaging unit, a control parameter generation unit, a control unit, and a drive unit are provided. The imaging unit captures an image including two objects. The control parameter generation unit feeds information of the captured image including the two objects into an input layer of a neural network, and outputs a position control amount for controlling the positional relation of between the two objects as an output layer of the neural network. The control unit controls current or voltage to control the positional relation between the two objects by using the outputted position control amount. The drive unit changes a position of one of the two objects by using the current or the voltage. Here, the control parameter generation unit selects the neural network from a plurality of neural networks. Therefore, even if there are differences between objects or errors in the positional relationship between the two objects, alignment can be performed more accurately.

Abstract: In a case of performing operations including alignment and insertion regarding two objects, a path setting unit 806 and an actor unit 804 are provided to learn a control amount. The path setting unit 806 provides the amount of movement for removing an object from its inserted position, and for locating it on and around the path of removing. The actor unit 804 obtains positions of the object and the values of a force sensor 801 there to perform learning by letting the positions of the object be the values for the output layer and letting the values of the force sensor 801 be the values for the input layer. Therefore, learning data can be collected efficiently.

Abstract: An element construction unit compares output values of one or more elements included in an intermediate layer calculated by an output value calculating unit with a threshold value, and the number of elements included in the intermediate layer is maintained when any of the output values out of the output values of the one or more elements included in the intermediate layer is greater than the threshold value, and the number of elements included in the intermediate layer is increased when all of the output values of the one or more elements included in the intermediate layer are equal to or less than the threshold value.

Abstract: A position measurement portion manages a measurement target area by dividing the area into a plurality of section areas, and also manages, or keeps track of, an intra-area interfering object number which is the number of interfering objects in a given section area, independently for each of the plurality of the section areas. The travel controller determines, independently for each of the plurality of section areas, if the section area is in a congested state in which the intra-area interfering object number is greater than a set upper limit number, and selects a congested area travel mode as the travel mode when the travel controller is about to cause the vehicle to travel in a section area that is determined to be in the congested state.

Abstract: A position measurement portion manages a measurement target area by dividing the area into a plurality of section areas, and also manages, or keeps track of, an intra-area interfering object number which is the number of interfering objects in a given section area, independently for each of the plurality of the section areas. The travel controller determines, independently for each of the plurality of section areas, if the section area is in a congested state in which the intra-area interfering object number is greater than a set upper limit number, and selects a congested area travel mode as the travel mode when the travel controller is about to cause the vehicle to travel in a section area that is determined to be in the congested state.

Abstract: Disclosed is an article transport facility in which interference between an article transport vehicle and an interfering object is prevented. A position detector is provided on the ground side for detecting the position of an interfering object, and an external managing device issues a deceleration command to the article transport vehicle if the distance from the article transport vehicle to the interfering object becomes less than or equal to a predetermined low speed distance, based on position information for the interfering object and travel position information for the article transport vehicle. A vehicle side travel controller changes a target travel speed from a normal travel speed to a reduced travel speed which is lower, or less, than the normal travel speed while the target travel speed is set to the normal travel speed, if the deceleration command is issued from the external managing device.