Abstract: An information processing device generates a prediction output corresponding to input data. The information processing device includes input-node specification processor circuitry, based on the input data, configured to specify input nodes corresponding to the input data and each located on a corresponding one of layers from beginning to end of the learning tree structured, reliability-index acquisition processor circuitry configured to acquire a reliability index obtained through the predetermined learning processing and indicating prediction accuracy, output-node specification processor circuitry, based on the reliability index acquired by the reliability-index acquisition processor circuitry configured to specify, from the input nodes corresponding to the input data, an output node that is the basis of the generation of a prediction output, and prediction-output generation processor circuitry configured to generate a prediction output.

Abstract: An autonomous mobile robot includes a first arithmetic unit configured to calculate a course direction based on an own position, a moving-object position, and a moving-object velocity vector, the course direction being a direction in which the autonomous mobile robot should travel, a second arithmetic unit configured to input the own position, the moving-object position, the moving-object velocity vector, and the course direction into a trained model and thereby calculate an estimated position, the trained model being a model that has been trained, the estimated position being a position at which the autonomous mobile robot is estimated to arrive a predetermined time later without colliding with the moving object, a generating unit configured to generate a remaining route from the estimated position to a destination, and a movement control unit configured to control a movement to the destination based on the course direction and the remaining route.

Abstract: A charged particle emission device includes a pre-emission state detector configured to detect a pre-emission charged state which is a charged state of the charged object before charged particles are emitted, an emission time generator configured to generate an emission time based on a past emission time of charged particles and a charged state of the charged object after the emission, emission processor circuitry configured to emit charged particles to the charged object which is in the pre-emission charged state based on the generated emission time, a post-emission state detector configured to detect a post-emission charged state which is a charged state of the charged object after the charged particles are emitted, machine learning processor circuitry configured to cause a machine learning model to learn a correspondence among the pre-emission charged state, the post-emission charged state, and the emission time generated by the emission time generator.

Abstract: A charged particle emission device includes a pre-emission state detector configured to detect a pre-emission charged state which is a charged state of a charged object before the charged particles are emitted, a learned model configured to receive a charged state of a charged object and a control parameter related to a control amount used for control of the charged particles to be emitted to the charged object to generate an estimated charged state which is a charged state of the charged object after the charged particles are controlled under the control parameter and emitted, an estimated charged state generator configured to input the pre-emission charged state and a plurality of control parameters to the learned model to generate a plurality of estimated charged states corresponding to the pre-emission charged state and the plurality of control parameters.

Abstract: An autonomous mobile robot includes a first arithmetic unit configured to calculate a course direction based on an own position, a moving-object position, and a moving-object velocity vector, the course direction being a direction in which the autonomous mobile robot should travel, a second arithmetic unit configured to input the own position, the moving-object position, the moving-object velocity vector, and the course direction into a trained model and thereby calculate an estimated position, the trained model being a model that has been trained, the estimated position being a position at which the autonomous mobile robot is estimated to arrive a predetermined time later without colliding with the moving object, a generating unit configured to generate a remaining route from the estimated position to a destination, and a movement control unit configured to control a movement to the destination based on the course direction and the remaining route.

Abstract: There is provided an information processing device that generates a prediction output corresponding to input data, the information processing device, including: an input-node specification unit that, based on the input data, specifies input nodes corresponding to the input data and each located on a corresponding one of layers from beginning to end of the learning tree structure; a reliability-index acquisition unit that acquires a reliability index obtained through the predetermined learning processing and indicating prediction accuracy; an output-node specification unit that, based on the reliability index acquired by the reliability-index acquisition unit, specifies, from the input nodes corresponding to the input data, an output node that is the basis of the generation of a prediction output; and a prediction-output generation unit that generates a prediction output, based on the to-be-learned data included in the state space corresponding to the output node specified by the output-node specification unit

Abstract: A data amount compressing method for compressing a data amount corresponding to a learned model obtained by letting the learning model learn a predetermined data group, the learning model having a tree structure in which multiple nodes associated with respective hierarchically divided state spaces are hierarchically arranged, wherein each node in the learned model is associated with an error amount that is generated in the process of the learning and corresponds to prediction accuracy, and the data amount compressing method includes: a reading step of reading the error amount associated with each node; and a node deleting step of deleting a part of the nodes of the learned model according to the error amount read in the reading step, thereby compressing the data amount corresponding to the learned model.

Abstract: A learned model integration method for integrating multiple different learned models obtained by letting a learning model learn a predetermined data group, the learning model having a tree structure in which multiple nodes associated with respective hierarchically divided state spaces are hierarchically arranged, the method includes: a data reading step of reading data related to the multiple different learned models from a predetermined memory unit; and an integrating step in which, for each node constituting a tree structure related to the multiple different learned models, when a node exists in only one learned model, the node is duplicated, and when nodes exist in corresponding positions in the multiple learned models, the corresponding nodes are integrated, thereby integrating the multiple different learned models into a single learned model.

Abstract: A path planning system for bringing state of an object into a target state includes a search tree production unit for producing in advance, in a state space with said target state defined as a root, a search tree having a branch at each one of a plurality of sections of the state space, said state space being divided into the plurality of sections in advance. The system also includes a search tree memory unit for storing the search tree, and a path generation unit for determining, a route on the search tree from the branch corresponding to the current state to the root. The path planning/control system further includes a path control unit for controlling the path of the object to bring the state of the object into the target state in accordance with the route on the search tree determined by the path planning system.

Abstract: A trajectory planning method according to the present invention is one for obtaining a trajectory for controlling a state of an object toward a goal state by a trajectory planning system. The method includes the steps of dividing, by a cell generating section for dividing a state space of the object into cells, the state space into cells in such a way that approximation error due to discretization is minimized for a predetermined number of cells; generating, by a search tree generating section, a search tree which corresponds to state transition of the object in such a way that each cell does not contain more than one of nodes of branches of the search tree; and determining, by a trajectory generating section, a path from the current state to the goal state of the object using the search tree.

Abstract: A trajectory planning system obtains a trajectory for controlling a state of an object toward a goal state. The system includes a search tree generating section which registers a state of the object as a root of a search tree in a state space, registers a next state of the object after a lapse of a predetermined time interval obtained through dynamical relationships during the time interval as a branch of the search tree in the state space.

Abstract: A learning control system according to the present invention is one which performs learning of action values of actions in an apparatus which identifies its state as one of predetermined states, and selects an action based on the obtained action values and the identified state. The learning control system includes n action value learning devices including the first to the n th learning devices which perform learning of n action values from Q1 to Qn, assuming that n is a positive integer and an action value determining device which determines the total action value of an action Q of each state based on outputs of the n action value learning devices.

Abstract: A trajectory planning method according to the present invention is one for obtaining a trajectory for controlling a state of an object toward a goal state by a trajectory planning system. The method includes the steps of dividing, by a cell generating section for dividing a state space of the object into cells, the state space into cells in such a way that approximation error due to discretization is minimized for a predetermined number of cells; generating, by a search tree generating section, a search tree which corresponds to state transition of the object in such a way that each cell does not contain more than one of nodes of branches of the search tree; and determining, by a trajectory generating section, a path from the current state to the goal state of the object using the search tree.

Abstract: A path planning system for bringing state of an object into a target state includes a search tree production unit for producing in advance, in a state space with said target state defined as a root, a search tree having a branch at each one of a plurality of sections of the state space, said state space being divided into the plurality of sections in advance. The system also includes a search tree memory unit for storing the search tree, and a path generation unit for determining, a route on the search tree from the branch corresponding to the current state to the root. The path planning/control system further includes a path control unit for controlling the path of the object to bring the state of the object into the target state in accordance with the route on the search tree determined by the path planning system.

Abstract: A trajectory planning system obtains a trajectory for controlling a state of an object toward a goal state. The system includes a search tree generating section which registers a state of the object as a root of a search tree in a state space, registers a next state of the object after a lapse of a predetermined time interval obtained through dynamical relationships during the time interval as a branch of the search tree in the state space.

Abstract: A learning control system according to the present invention is one which performs learning of action values of actions in an apparatus which identifies its state as one of predetermined states, and selects an action based on the obtained action values and the identified state. The learning control system includes n action value learning devices including the first to the n th learning devices which perform learning of n action values from Q1 to Qn, assuming that n is a positive integer and an action value determining device which determines the total action value of an action Q of each state based on outputs of the n action value learning devices.