Abstract: An information processing device includes: a learning section configured to learn a state transition probability model defined by state transition probability for each action of a state making a state transition due to an action performed by an agent capable of performing action and observation probability of a predetermined observed value being observed from the state, using an action performed by the agent and an observed value observed in the agent when the agent has performed the action.

Abstract: An information processing device includes: a calculating unit configured to calculate a current-state series candidate that is a state series for an agent capable of actions reaching the current state, based on a state transition probability model obtained by performing learning of the state transition probability model stipulated by a state transition probability that a state will be transitioned according to each of actions performed by an agent capable of actions, and an observation probability that a predetermined observation value will be observed from the state, using an action performed by the agent, and an observation value observed at the agent when the agent performs an action; and a determining unit configured to determine an action to be performed next by the agent using the current-state series candidate in accordance with a predetermined strategy.

Abstract: An information processing apparatus includes a storage unit configured to store a node holding dynamics; an input-weight-coefficient adjuster configured to adjust input-weight coefficients on a dimension-by-dimension basis, the input-weight coefficients being weight coefficients for individual dimensions of input data input to input units of the node, the input data being observed time-series data having a plurality of dimensions; and an output-weight-coefficient adjuster configured to adjust output-weight coefficients on a dimension-by-dimension basis, the output-weight coefficients being weight coefficients for individual dimensions of output data having a plurality of dimensions and output from output units of the node.

Abstract: A learning system is provided, which includes network storage means for storing a network including a plurality of nodes, each of which holds a dynamics; and learning means for self-organizationally updating the dynamics of the network on the basis of measured time-series data.

Abstract: A facial expression recognition system that uses a face detection apparatus realizing efficient learning and high-speed detection processing based on ensemble learning when detecting an area representing a detection target and that is robust against shifts of face position included in images and capable of highly accurate expression recognition, and a learning method for the system, are provided. When learning data to be used by the face detection apparatus by Adaboost, processing to select high-performance weak hypotheses from all weak hypotheses, then generate new weak hypotheses from these high-performance weak hypotheses on the basis of statistical characteristics, and select one weak hypothesis having the highest discrimination performance from these weak hypotheses, is repeated to sequentially generate a weak hypothesis, and a final hypothesis is thus acquired.

Abstract: An information processing apparatus includes: model learning means for self-organizing, on the basis of a state transition model having a state and state transition to be learned by using time series data as data in time series, an internal state from an observation signal obtained by a sensor; and controller learning means for performing learning for allocating a controller, which outputs an action, to each of transitions of a state or each of transition destination states in the state transition model indicating the internal state self-organized by the model learning means.

Abstract: A facial expression recognition system that uses a face detection apparatus realizing efficient learning and high-speed detection processing based on ensemble learning when detecting an area representing a detection target and that is robust against shifts of face position included in images and capable of highly accurate expression recognition, and a learning method for the system, are provided. When learning data to be used by the face detection apparatus by Adaboost, processing to select high-performance weak hypotheses from all weak hypotheses, then generate new weak hypotheses from these high-performance weak hypotheses on the basis of statistical characteristics, and select one weak hypothesis having the highest discrimination performance from these weak hypotheses, is repeated to sequentially generate a weak hypothesis, and a final hypothesis is thus acquired.

Abstract: An object detecting device for detecting an object in a given gradation image. A scaling section generates scaled images by scaling down a gradation image input from an image output section. A scanning section sequentially manipulates the scaled images and cutting out window images from them and a discriminator judges if each window image is an object or not. The discriminator includes a plurality of weak discriminators that are learned in a group by boosting and an adder for making a weighted majority decision from the outputs of the weak discriminators. Each of the weak discriminators outputs an estimate of the likelihood of a window image to be an object or not by using the difference of the luminance values between two pixels. The discriminator suspends the operation of computing estimates for a window image that is judged to be a non-object, using a threshold value that is learned in advance.

Abstract: An information processing apparatus includes a target storage means, a control means, a decision means, a prediction means and a generating means, in which the decision means, when determining that the system state makes a transition to a state represented by the target value in accordance with the output of the time series of motor signals generated by the generating means, updates a parameter representing the relationship between input and output, which is used by the control means for controlling the system based on the time series of motor signals generated by the generating means and a time series of sensor signals observed in accordance with the output of the time series of motor signals.

Abstract: A legged mobile robot can calculate the movement amount between a portion of the robot apparatus that had been in contact with a floor up to now and a next portion of the robot apparatus in contact with the floor using kinematics and to switch transformation to a coordinate system serving as an observation reference as a result of the switching between the floor contact portions.

Abstract: A facial expression recognition system that uses a face detection apparatus realizing efficient learning and high-speed detection processing based on ensemble learning when detecting an area representing a detection target and that is robust against shifts of face position included in images and capable of highly accurate expression recognition, and a learning method for the system, are provided. When learning data to be used by the face detection apparatus by Adaboost, processing to select high-performance weak hypotheses from all weak hypotheses, then generate new weak hypotheses from these high-performance weak hypotheses on the basis of statistical characteristics, and select one weak hypothesis having the highest discrimination performance from these weak hypotheses, is repeated to sequentially generate a weak hypothesis, and a final hypothesis is thus acquired.

Abstract: A facial expression recognition system that uses a face detection apparatus realizing efficient learning and high-speed detection processing based on ensemble learning when detecting an area representing a detection target and that is robust against shifts of face position included in images and capable of highly accurate expression recognition, and a learning method for the system, are provided. When learning data to be used by the face detection apparatus by Adaboost, processing to select high-performance weak hypotheses from all weak hypotheses, then generate new weak hypotheses from these high-performance weak hypotheses on the basis of statistical characteristics, and select one weak hypothesis having the highest discrimination performance from these weak hypotheses, is repeated to sequentially generate a weak hypothesis, and a final hypothesis is thus acquired.

Abstract: A gateway object (48) for transmitting and receiving data to and from an object of a robot apparatus (1) is allocated to a radio LAN PC card (41) of the robot apparatus (1), and a gateway object (52) for transmitting and receiving data to and from an object on a personal computer (32) is allocated to a network adapter (31) of a remote system (30). When the radio LAN PC card (41) and the network adapter (31) are connected with each other by radio or wired connection, inter-object communication is carried out between the gateway object (48) of the radio LAN PC card (41) and the gateway object (52) of the network adapter (31), thereby carrying out inter-object communication between the object of the robot apparatus (1) and the object of the personal computer (32). Thus, preparation of a program is facilitated.

Abstract: An obstacle recognition apparatus is provided which can recognize an obstacle by accurately extracting a floor surface. It includes a distance image generator (222) to produce a distance image using a disparity image and homogeneous transform matrix, a plane detector (223) to detect plane parameters on the basis of the distance image from the distance image generator (222), a coordinate transformer (224) to transform the homogeneous transform matrix into a coordinate of a ground-contact plane of a robot apparatus (1), and a floor surface detector (225) to detect a floor surface using the plane parameters from the plane detector (223) and result of coordinate transformation from the coordinate transformer (224) and supply the plane parameters to an obstacle recognition block (226).

Abstract: A facial expression recognition system that uses a face detection apparatus realizing efficient learning and high-speed detection processing based on ensemble learning when detecting an area representing a detection target and that is robust against shifts of face position included in images and capable of highly accurate expression recognition, and a learning method for the system, are provided. When learning data to be used by the face detection apparatus by Adaboost, processing to select high-performance weak hypotheses from all weak hypotheses, then generate new weak hypotheses from these high-performance weak hypotheses on the basis of statistical characteristics, and select one weak hypothesis having the highest discrimination performance from these weak hypotheses, is repeated to sequentially generate a weak hypothesis, and a final hypothesis is thus acquired.

Abstract: A robot includes a face extracting section for extracting features of a face included in an image captured by a CCD camera, and a face recognition section for recognizing the face based on a result of face extraction by the face extracting section. The face extracting section is implemented by Gabor filters that filter images using a plurality of filters that have orientation selectivity and that are associated with different frequency components. The face recognition section is implemented by a support vector machine that maps the result of face recognition to a non-linear space and that obtains a hyperplane that separates in that space to discriminate a face from a non-face. The robot is allowed to recognize a face of a user within a predetermined time under a dynamically changing environment.

Abstract: A robot apparatus includes face includes a face tracking module (M2) for tracking a face in an image photographed by a CCD camera, a face detecting module (M1) for detecting face data of the face in the image photographed by the image pickup device, based on the face tracking information by the face tracking module (M2) and a face identification module (M3) for identifying a specified face based on the face data as detected by the face data detecting module (M1).

Abstract: In a plane detection apparatus, a plane detection unit (3) includes a line fitting block (4) to select a group of distance data points being in one plane from distance data forming an image and extract lines from the distance data point group, and a region growing block (5) to detect one or more planar regions existing in the image from a group of all lines included in the image and extracted by the line fitting block (4). The line fitting block (4) first draws a line D1 connecting end points of the distance data point group, searches a point of interest brk whose distance to the line L1 is largest, segments the data point group by the point of interest brk when the distance is larger than a predetermined threshold, and determines a line L2 by the least-squares method when the distance is smaller than the predetermined threshold.

Abstract: A learning apparatus includes a storage unit configured to store a network formed by a plurality of nodes each holding dynamics; a learning unit configured to learn the dynamics of the network in a self-organizing manner on the basis of observed time-series data; a winner-node determiner configured to determine a winner node, the winner node being a node having dynamics that best match the time-series data; and a weight determiner configured to determine learning weights for the dynamics held by the individual nodes according to distances of the individual nodes from the winner node. The learning unit is configured to learn the dynamics of the network in a self-organizing manner by degrees corresponding to the learning weights.

Abstract: An information processing apparatus includes a storage unit configured to store a node holding dynamics; an input-weight-coefficient adjuster configured to adjust input-weight coefficients on a dimension-by-dimension basis, the input-weight coefficients being weight coefficients for individual dimensions of input data input to input units of the node, the input data being observed time-series data having a plurality of dimensions; and an output-weight-coefficient adjuster configured to adjust output-weight coefficients on a dimension-by-dimension basis, the output-weight coefficients being weight coefficients for individual dimensions of output data having a plurality of dimensions and output from output units of the node.