Abstract: A coordinating apparatus selects discrete systems that simulate behavior of an actual environment and outputs an indicator value related to the actual environment, shares internal states related to the actual environments obtained on a basis of the behavior simulated by the discrete systems selected in the selection process, generates a shared internal state, decides such an action that a post-coordination integrated indicator value obtained by integrating a post-coordination indicator value from the discrete systems when the discrete systems are coordinated is optimized, the action being should be taken and being able to be taken by the discrete systems on a basis of the shared internal state in a case where the discrete systems are coordinated, determines whether or not the discrete systems should be coordinated on a basis of the post-coordination indicator values, and the indicator value from each of the discrete systems, and outputs a determination result.

Abstract: A retail agent determines a parameter of an activity proposal model by using data stored in a past record database, and determines parameters of an activity determination model and an activity value evaluation model by further using base activity simulation data. Consequently, it is possible to appropriately determine parameters of a subsystem control method in a complex system which cannot be embodied as a simulator and shows a significant change with respect to past record data.

Abstract: This control system includes: a state calculating unit which calculates the state of a controlled object on the basis of control-system data including an actual measured value output from the controlled object and a predetermined target value; a reward granting unit which grants a reward in accordance with the state of the controlled object; an action selecting unit which selects an action for the state, on the basis of the granted reward; and a control parameter determining unit which, in. accordance with the selected action, determines a control parameter to lie used by a controller that calculates a command value to be input into the controlled object, on the basis of the actual measured. value, the target value, and a control rule.

Abstract: According to one embodiment, a machine control system includes: a selecting unit which acquires a state quantity of a machine converted from data acquired by a sensor provided in the machine to select two or more learning models according to the acquired state quantity; a composing unit which inputs the state quantity acquired by the selecting unit to each of the two or more learning models selected by the selecting unit to calculate a composed value using a command value output from each of the learning models; and a learning unit which outputs a command value with respect to the machine in a range based on the composed value calculated by the composing unit, acquires a state quantity of the machine, searches for a command value of a specific condition from a combination of the output command value and the acquired state quantity, and outputs the searched command value to the machine, thereby creating a new learning model.

Abstract: A learning control system is provided in each of a plurality of subsystems of a system and includes a plurality of agents that performs learning to control of the subsystem using a control model and a learning management agent that manages and controls learning of each of the plurality of agents. The learning management agent is operated with a plurality of experiment systems including the plurality of control model sets of the plurality of agents and determines a plurality of updating control model sets in the plurality of experiment systems of a next generation from an evaluation result of the plurality of experiment systems of the current generation. The agent transmits control model information of a current generation to the learning management agent and receives control model information of the next generation from the learning management agent.

Abstract: A robot system is provided in which various kinds of articles can be treated only with a small number of articles registered in advance, and an unknown article can be further treated as long as the article has a shape close to that of the article registered in advance. A robot system is disclosed which includes: a mechanism unit that manipulates an article to be manipulated; a shape measurement unit that measures a shape of an object; a basic operation storage unit that stores basic operation representing basic operation of the mechanism unit; an operation method calculation unit that deforms the stored basic operation to calculate an operation method on the basis of the shape of the object measured by the shape measurement unit; and a control unit that executes a control of the mechanism unit on the basis of the operation method calculated by the operation method calculation unit.

Abstract: A retail agent determines a parameter of an activity proposal model by using data stored in a past record database, and determines parameters of an activity determination model and an activity value evaluation model by further using base activity simulation data. Consequently, it is possible to appropriately determine parameters of a subsystem control method in a complex system which cannot be embodied as a simulator and shows a significant change with respect to past record data.

Abstract: The control device includes: an observation unit that calculates an amount relating to a state of a control target detected by a sensor; an abnormality predictor detection unit that detects an abnormality predictor of the control target; a reward calculation unit that calculates a reward which is an amount obtained by evaluating pass or fail of an operation of the control target; a basic control amount calculation unit that calculates data relating to the state during an operation and a basic control amount serving as a reference to control the control target; a control amount search unit that searches for a control amount at which the reward satisfies a predetermined condition based on the basic control amount, the data relating to the state during the operation and the reward; and a control unit that generates a command value to the control target.

Abstract: A control device controls a subject to be controlled that obtains a certain state by an action, and is configured to conduct: an obtaining process to obtain the state and the action of the subject to be controlled from the subject to be controlled; a generating process to generate a reward that causes a next action of the subject to be controlled to optimize a next state of the subject to be controlled, based on the state and the action of the subject to be controlled; a selecting process to select a next action of the subjected to be controlled, based on the state and the action of the subject to be controlled, and the reward; and a control process to give a control command value to the subject to be controlled, the control command value corresponding to the next action of the subject to be controlled.

Abstract: An information processing apparatus includes: a path planning unit that generates path data to a destination of a certain object; a filter setting unit that sets a filter representing an acquisition range to map data; and a map data acquisition unit that acquires, from the map data, data in a range set by the filter.

Abstract: The control device includes: an observation unit that calculates an amount relating to a state of a control target detected by a sensor; an abnormality predictor detection unit that detects an abnormality predictor of the control target; a reward calculation unit that calculates a reward which is an amount obtained by evaluating pass or fail of an operation of the control target; a basic control amount calculation unit that calculates data relating to the state during an operation and a basic control amount serving as a reference to control the control target; a control amount search unit that searches for a control amount at which the reward satisfies a predetermined condition based on the basic control amount, the data relating to the state during the operation and the reward; and a control unit that generates a command value to the control target.

Abstract: According to one embodiment, a machine control system includes: a selecting unit which acquires a state quantity of a machine converted from data acquired by a sensor provided in the machine to select two or more learning models according to the acquired state quantity; a composing unit which inputs the state quantity acquired by the selecting unit to each of the two or more learning models selected by the selecting unit to calculate a composed value using a command value output from each of the learning models; and a learning unit which outputs a command value with respect to the machine in a range based on the composed value calculated by the composing unit, acquires a state quantity of the machine, searches for a command value of a specific condition from a combination of the output command value and the acquired state quantity, and outputs the searched command value to the machine, thereby creating a new learning model.

Abstract: A mobile apparatus includes a position detection device, and an autonomous mobile body. The position detection device includes input means for inputting route data, a distance sensor, map data, position identification means, and relative route calculation means for calculating a relative position and a relative angle to a position of the target point from the position data and the route data of the mobile body. The autonomous mobile body includes a controller that controls an autonomous travel of the autonomous mobile body itself by using the relative position and the relative angle received from the position detection device as control signals.

Abstract: A learning control system is provided in each of a plurality of subsystems of a system and includes a plurality of agents that performs learning to control of the subsystem using a control model and a learning management agent that manages and controls learning of each of the plurality of agents. The learning management agent is operated with a plurality of experiment systems including the plurality of control model sets of the plurality of agents and determines a plurality of updating control model sets in the plurality of experiment systems of a next generation from an evaluation result of the plurality of experiment systems of the current generation. The agent transmits control model information of a current generation to the learning management agent and receives control model information of the next generation from the learning management agent.

Abstract: A robot system is provided in which various kinds of articles can be treated only with a small number of articles registered in advance, and an unknown article can be further treated as long as the article has a shape close to that of the article registered in advance. A robot system is disclosed which includes: a mechanism unit that manipulates an article to be manipulated; a shape measurement unit that measures a shape of an object; a basic operation storage unit that stores basic operation representing basic operation of the mechanism unit; an operation method calculation unit that deforms the stored basic operation to calculate an operation method on the basis of the shape of the object measured by the shape measurement unit; and a control unit that executes a control of the mechanism unit on the basis of the operation method calculated by the operation method calculation unit.

Abstract: A control device controls a subject to be controlled that obtains a certain state by an action, and is configured to conduct: an obtaining process to obtain the state and the action of the subject to be controlled from the subject to be controlled; a generating process to generate a reward that causes a next action of the subject to be controlled to optimize a next state of the subject to be controlled, based on the state and the action of the subject to be controlled; a selecting process to select a next action of the subjected to be controlled, based on the state and the action of the subject to be controlled, and the reward; and a control process to give a control command value to the subject to be controlled, the control command value corresponding to the next action of the subject to be controlled.

Abstract: An information processing apparatus includes: a path planning unit that generates path data to a destination of a certain object; a filter setting unit that sets a filter representing an acquisition range to map data; and a map data acquisition unit that acquires, from the map data, data in a range set by the filter.

Abstract: Position identification means (7) for estimating the position of a mobile robot (1) includes a laser distance sensor (6) that measures a distance from the mobile robot (1) to an object, means for recognizing an object from data of the measured distance from the mobile robot (1) to the object and map data, travel area storage means (12) for storing a travel area of the mobile robot (1), specified area storage means (13) for storing a specified area that is separate from the travel area of the mobile robot (1), and object determination means (14) for determining whether an object is present within the travel area of the mobile robot (1) that is stored in the travel area storage means (12).

Abstract: Position identification means (7) for estimating the position of a mobile robot (1) includes a laser distance sensor (6) that measures a distance from the mobile robot (1) to an object, means for recognizing an object from data of the measured distance from the mobile robot (1) to the object and map data, travel area storage means (12) for storing a travel area of the mobile robot (1), specified area storage means (13) for storing a specified area that is separate from the travel area of the mobile robot (1), and object determination means (14) for determining whether an object is present within the travel area of the mobile robot (1) that is stored in the travel area storage means (12).

Abstract: A position detection device includes position identification means (5) for identifying a position and an angle of a mobile body, using a distance sensor (3) and a map (2), and relative position calculation means (7) for calculating a relative position and a relative angle of the mobile body relative to a target position and a target angle of the mobile body, that are set by input means (6), and outputs an identification result of the position identification means (5) and a calculation result of the relative position calculation means (7) is configured to be attached to the mobile body (100).