Abstract: Systems and methods for visuo-tactile object pose estimation are provided. In one embodiment, a method includes receiving image data about an object and receiving depth data about the object. The method also includes generating a visual estimate of the object based on the image data and the depth data. The method further includes receiving tactile data about the object. The method yet further includes generating a tactile estimate of the object based on the tactile data. The method includes estimating a pose of the object based on the visual estimate and the tactile estimate.

Abstract: A remote operation method of a robot includes: a conversion step of converting an operation input to a joint angle command value of the robot when an operator performs an operation; an acquisition step of acquiring actual visual information of a space in which the robot is present; a generation step of generating virtual visual information of an arbitrary viewpoint in the space in which the robot is present for the operator using a three-dimensional representation; and a projection step of projecting the virtual visual information to a screen viewed by the operator when the actual visual information is not newly acquired and projecting a mixed image in which an image based on the newly acquired actual visual information is combined with the virtual visual information when the actual visual information is newly acquired.

Abstract: An autonomous control system includes an acquirer configured to acquire state data of a robot, visual data of the robot, and tactile data of the robot and a processor configured to decide on an action of the robot capable of accomplishing a task given to the robot on the basis of the state data, the visual data, and the tactile data. The processor generates first compressed data having a smaller number of dimensions than data obtained by combining the visual data and the tactile data by fusing and dimensionally compressing the visual data and the tactile data. The processor generates second compressed data having a smaller number of dimensions than the tactile data by dimensionally compressing the tactile data. The processor decides on the action on the basis of combined state data obtained by combining the state data, the first compressed data, and the second compressed data into one.

Abstract: Systems and methods for visuo-tactile object pose estimation are provided. In one embodiment, a method includes receiving image data about an object and receiving depth data about the object. The method also includes generating a visual estimate of the object based on the image data and the depth data. The method further includes receiving tactile data about the object. The method yet further includes generating a tactile estimate of the object based on the tactile data. The method includes estimating a pose of the object based on the visual estimate and the tactile estimate.

Abstract: The present invention provides a method for identifying noise data of laser ranging devices. The measurement data of a plurality of measurement points is acquired by a plurality of laser ranging devices 1A and 1B, which are placed such that the laser beam projection areas thereof overlap with each other. A set of measurement points common to the laser ranging devices 1A and 1B is extracted from the measurement points. Noise data is identified based on the measurement data of each of a plurality of (two) measurement points constituting the set of common measurement points.

Abstract: A robot and its control device capable of improving recognition accuracy of a position and posture of a functional body such as a hand with respect to an object to thereby attain improved stability of the operation involving a change in position/posture of its body are provided. In a case where the magnitude of a deviation ?? of an angle ? made by two reference vectors U1 and U2, representing a manner in which a structure W extends in a camera coordinate system and in a hand coordinate system, respectively, with respect to a reference angle ?0 is greater than a threshold value ?, the probability that the state of interaction between the hand 13 (functional body) and the structure W is divergent from a desired state is high.

Abstract: A second processing unit (40), which receives a first count value N1 transmitted in a predetermined reference cycle ?t1 from the first processing unit (30), has a second counter (41) which outputs a second count value N2 in a cycle ?t2 shorter than the reference cycle ?t1. The second count value N2 is initialized in response to reception of the first count value N1. The second processing unit (40) associates time determined according to the first count value N1 and the second count value N2 with generated or acquired second data (external measurement data).

Abstract: A robot and its control device capable of improving recognition accuracy of a position and posture of a functional body such as a hand with respect to an object to thereby attain improved stability of the operation involving a change in position/posture of its body are provided. In a case where the magnitude of a deviation ?? of an angle ? made by two reference vectors U1 and U2, representing a manner in which a structure W extends in a camera coordinate system and in a hand coordinate system, respectively, with respect to a reference angle ?0 is greater than a threshold value ?, the probability that the state of interaction between the hand 13 (functional body) and the structure W is divergent from a desired state is high.

Abstract: The present invention provides a method for identifying noise data of laser ranging devices. The measurement data of a plurality of measurement points is acquired by a plurality of laser ranging devices 1A and 1B, which are placed such that the laser beam projection areas thereof overlap with each other. A set of measurement points common to the laser ranging devices 1A and 1B is extracted from the measurement points. Noise data is identified based on the measurement data of each of a plurality of (two) measurement points constituting the set of common measurement points.