Tomoki Watanabe has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
Abstract: According to an embodiment, a computing device includes a processing circuitry. The processing circuitry receives an input of tensor data. The processing circuitry sets a window in the tensor data. The processing circuitry compares, for each pair of coordinates in the tensor data within the window, a pixel value at the pair of coordinates with one or more thresholds, and selects a weight value corresponding to a comparison result. The processing circuitry adds the weight values selected for the respective pairs of coordinates to obtain a cumulative value. The processing circuitry derives a value based at least in part on the cumulative value.
Abstract: A variable load calculator calculates a variable load command VL based on AS pressure and a predetermined table. A vehicle deceleration calculator calculates vehicle deceleration ? based on a brake notch command BN and a predetermined table. A required braking force calculator calculates required braking force BL by multiplying a weight indicated by the variable load command VL and the vehicle deceleration ?. An electric braking controller calculates an electric braking pattern in accordance with the required braking force BL and then transmits the electric braking pattern to an inverter controller. The electric braking controller calculates an electric braking force produced by operation of the electric motor and then transmits to a subtractor as feedback BT the electric braking force adjusted in accordance with a speed of the electric motor. The subtractor transmits to a mechanical brake as a mechanical braking command a result obtained by subtracting the feedback BT from the required braking force BL.
Abstract: A location estimating apparatus according to an embodiment includes a degree-of-similarity calculator, a correspondence calculator, and a location calculator. The degree-of-similarity calculator calculates a degree of similarity between the input image and the reference image by an arithmetic operation that varies, in a non-discrete manner, the degree of similarity in accordance with a non-discrete variation of a first parameter. The correspondence calculator calculates correspondence between a pixel of the input image and a pixel of the reference image by an arithmetic operation that varies, in a non-discrete manner, the correspondence in accordance with a non-discrete variation of a second parameter. The location calculator calculates a first location indicating a position and/or an orientation of the first imaging device when the input image is captured by an arithmetic operation that varies, in a non-discrete manner, the first location in accordance with a non-discrete variation of the correspondence.
Abstract: A pseudo-food texture presentation device includes: an enclosure body in which a granular material is enclosed; a measurer configured to measure at least one index among a temperature of an ambient environment of the enclosure body, a humidity of the ambient environment of the enclosure body, a temperature of the enclosure body, and a moisture amount on a surface of the enclosure body; and an enclosure body controller configured to control density of the granular material inside the enclosure body in accordance with the measured index.
July 9, 2019
June 3, 2021
NIPPON TELEGRAPH AND TELEPHONE CORPORATION
Abstract: According to one embodiment, a recognition device includes a hardware processor. The hardware processor is configured to identify presence or absence of composition elements of a target from input observation data, acquire setting information indicative of a relationship between a type and composition elements, and identify a type of the target based on the setting information acquired and the presence or absence of the composition elements.
Abstract: According to an embodiment, an estimation device includes a storage unit and one or more hardware processors, the storage unit storing therein first position information indicating at least a position or a pose of a first landmark in a map. The processors acquire second position information indicating at least a position or a pose of a second landmark around a moving object. The processors estimate third position information and correspondence between the first landmark and the second landmark, based on the first and second position information, where the third position information indicates at least a position or a pose of the moving object in the map. The third position information and the correspondence are estimated such that an observation error of the second landmark in at least the position or the pose specified by the third position information and a matching error are reduced.
Abstract: A robot system according to an embodiment includes one or more processors. The processors acquire first input data predetermined as data affecting an operation of a robot. The processors calculate a calculation cost of inference processing using a machine learning model for inferring control data used for controlling the robot, on the basis of the first input data. The processors infer the control data by the machine learning model set according to the calculation cost. The processors control the robot using the inferred control data.
Abstract: A self position estimation apparatus according to an embodiment includes an acquisition unit configured to acquire map data, and a calculation unit configured to calculate a correspondence weight between observation data on a region around the moving object and the map data, based on a variation amount of depth in a predetermined direction.
Abstract: According to an embodiment, a camera motion estimation device includes a memory and one or more hardware processors configured to function as a first acquisition unit, a second acquisition unit, and an estimation unit. The first acquisition unit is configured to acquire feature point correspondence information indicating correspondence between feature points included in time series images. The second acquisition unit is configured to acquire pixel flow information indicating a locus of a pixel included in the time series image. The estimation unit is configured to estimate a motion of a camera that has captured the time series images, using the pixel flow information and the feature point correspondence information.
Abstract: According to an embodiment, an information processing apparatus includes a memory and processing circuitry. The processing circuitry is configured to acquire three-dimensional position information of a detection point, acquire target surface shape information indicating a shape of a target surface, and calculate state information of an object according to a first distance of the detection point from the target surface on the basis of the three-dimensional position information and the target surface shape information.
Abstract: According to an embodiment, an information processing apparatus includes a position acquiring unit, and an occupancy level calculating unit. The position acquiring unit is configured to acquire position information representing a position where a target exists or no target exists, the position being measured by a sensor. The occupancy level calculating unit is configured to calculate an occupancy level distribution representing a level of occupancy, by the target, of each of a plurality of regions existing along a direction from the position of the sensor to the position indicated by the position information, based on the position information and measurement accuracy of the sensor, the occupancy level distribution being based on a non-measurement probability distribution representing a probability that measurement is not performed by the sensor.
Abstract: The number n of times of chewing is counted by chewing number of times calculation means (13b2) based on a change in the distance l from a photorefiector (50), which is received together with time t by measurement value receiving means (13b1). To vary hardness h of a bag (30) to a stage that can be sensed, according to the number n of times of chewing, a required air pressure is set according to the current number n of times, based on a hardness/air pressure correspondence recording unit (13g) in which stages that have a significant difference therebetween and are stored in association with the number n of times of chewing are recorded. To realize the set air pressure inside the bag (30), the amount of sucking performed using a vacuum pump 20 is controlled by air pressure control means (13b4).
Abstract: It is an object of the present invention to provide a resin composite comprising ultrafine cellulose fibers, in which deterioration of a resin component is suppressed. The present invention relates to a cellulose fiber-containing resin composition comprising cellulose fibers with a fiber width of 1000 nm or less having phosphoric acid groups or phosphoric acid group-derived substituents, and a resin, wherein the counterions of the phosphoric acid groups or phosphoric acid group-derived substituents are organic onium ions, and the conjugate bases of the organic onium ions have a pKb value of 1.0 or more.
Abstract: According to an embodiment, an object detecting apparatus includes a detector and an estimation processing unit. The detector is configured to detect an object candidate area from a captured image. The estimating processing unit is configured to, by performing estimation processing using a part of or a whole of the captured image including at least the object candidate area, output object information including at least information representing a pose of an object in the object candidate area. The estimation processing includes: a first process estimating, from among vertices of a cuboid circumscribing the object and making contact with a road surface, positions of at least two vertices on the captured image that are viewable from a viewpoint of the captured image; and a second process estimating to which one of right-front, left-front, right-rear, or left-rear of the object the vertices having positions estimated by the first process are respectively corresponding.
Abstract: A transformer includes: a base that is a plate-like member and has a first surface and a second surface, a core attached to the first surface of the base, coils wound around the core, coil terminals attached to the second surface of the base, and a cooling unit that is thermally connected to the core and is to release heat transferred from the core. The coil terminals are disposed on the second surface of the base opposite to the first surface of the base to which the core is attached. The cooling unit is disposed on a side of the core opposite to the base.
Abstract: According to an embodiment, an information processing device includes a memory and processing circuitry. The processing circuitry is configured to acquire a peripheral image of a moving object, set a cell in response to a plurality of traveling candidate lines of the moving object in a peripheral area of the moving object, specify a type of an object included in the cell using one or more partitioned areas smaller than the cell included in the peripheral image, and determine whether or not the moving object can progress for the cell based on the type of the object.
August 17, 2017
Date of Patent:
November 3, 2020
Kabushiki Kaisha Toshiba
Kaoru Sugita, Tomoki Watanabe, Satoshi Ito
Abstract: An information processing apparatus according to an embodiment includes one or more processors configured to: acquire an image and three-dimensional point information on a three-dimensional point of acquired surroundings of the image; assign an attribute to each region in the image; set, to the three-dimensional point, the attribute assigned to the corresponding region in the image; and generate an obstacle map based on the three-dimensional point information and the attribute that is set to the three-dimensional point.
Abstract: According to an embodiment, an information processing device includes one or more processors. The one or more processors is configured to acquire a map in which, for each of grids in a particular space, observation information representing object information on an object or the observation information representing non-observation information on non-observation of the object is correlated; and correct, for each of the grids, correlation of the observation information by using a learned model based on the observation information correlated with other peripheral grids.
Abstract: According to one embodiment, a moving object action registration apparatus includes the following units. The acquisition unit acquires at least one reference image including a first reference image including a marker. The landmark detection unit detects, as a landmark, a feature point indicating a characteristic portion in an environment based on the at least one reference image. The marker detection unit detects the marker based on the first reference image. The calculation unit calculates a relative position between the landmark and the marker. The attribute identification unit identifies an attribute of the marker associated with an action. The registration unit registers the relative position and action information being based on the attribute in a database.