Abstract: According to one embodiment, a filter includes a first layer and a second layer. The first layer includes a first resin provided with a plurality of holes. The first layer includes a first face. At least a part of the plurality of holes reaches the first face. The second layer includes a second resin. The second resin blocks at least a part of the plurality of holes reaching the first face.

Abstract: A recognition method executed by a processor, includes: acquiring positional relation between a plurality of sensors each of which senses a distance to an object; provisionally classifying an orientation of the object relative to each individual sensor included in the sensors into one of a plurality of classifications based on sensing data acquired by the individual sensor; calculating likelihood of each combination corresponding to the positional relation between the sensors based on a result of provisional classification of the orientation of the object relative to the individual sensor; and classifying the orientation of the object corresponding to each individual sensor in accordance with the calculated likelihood of each combination.

Abstract: A skeleton recognition method for a computer to execute a process includes acquiring distance images from each of a plurality of sensors that sense a subject from a plurality of directions; acquiring joint information that includes joint positions of the subject for each of the plurality of sensors by using a machine learning model that estimates the joint positions from the distance images; generating skeleton information that represents three-dimensional coordinates by integrating the joint information; and outputting the skeleton information of the subject.

Abstract: A control device for controlling a vibrating roller that generates vibration on a front wheel and a rear wheel, includes a front wheel vibration start signal output unit that outputs a front wheel vibration start signal for starting vibration of the front wheel so as to give vibration at a predetermined number of times to a road surface to be constructed per unit length, a calculation unit that calculates the rear wheel vibration start timing based on a time width required from the start of vibration of the rear wheel to the vibration at a frequency that can give vibration to the road surface to be constructed a predetermined number of times, and a rear wheel vibration start signal output unit which outputs a rear wheel vibration start signal which starts the vibration of the rear wheel at the rear wheel vibration start timing.

Abstract: A control device for controlling a vibrating roller that generates vibration on a front wheel and a rear wheel, includes a front wheel vibration start signal output unit that outputs a front wheel vibration start signal for starting vibration of the front wheel so as to give vibration at a predetermined number of times to a road surface to be constructed per unit length, a calculation unit that calculates the rear wheel vibration start timing based on a time width required from the start of vibration of the rear wheel to the vibration at a frequency that can give vibration to the road surface to be constructed a predetermined number of times, and a rear wheel vibration start signal output unit which outputs a rear wheel vibration start signal which starts the vibration of the rear wheel at the rear wheel vibration start timing.

Abstract: A learning device generates a plurality of learning images in which a distance image representing a distance from a reference position to each position of a human body or each position of an object and a part image for identifying each part of the human body or a part of the object are associated with each other. The learning device corrects, based on a distance image and a part image of the learning image, a value of a region corresponding to a part of the object among regions of the distance image. The learning device learns, based on a plurality of learning images including a corrected distance image, an identifier in which characteristics of the distance image and a part of the human body or a part of the object are associated with each other.

Abstract: A depth-image processing device includes: a memory; and a processor coupled to the memory and configured to: generate, cased on a synthetic model in which a three-dimensional model of a human body and a three-dimensional model of an object are combined, a plurality of learning images in which a depth image that indicates a distance from a reference position to respective positions on the human body or to respective positions on the object, and a part image to identify any one of respective parts of the human body and a cart of the object are associated with each other, and learn an identifier in which a feature of the depth image and any one of a part of the human body and a part of the object are associated with each other, based on the learning images.

Abstract: A recognition device a first recognition unit, a second recognition unit, and a third recognition unit. The first recognition unit acquires image information of a target person, and determines, based on a first discriminator and a feature in the image information, a first range corresponding to the image information of the target person. The second recognition unit acquires distance information of the target person, and determines, based on a second discriminator and a feature in the distance information, a second range corresponding to the distance information of the target person. The third recognition unit determines, based on the first range determined by the first recognition unit and the second range determined by the second recognition unit, a direction that a body of the target person is facing, and recognizes, based on the determined direction and a joint position dictionary, a skeleton of the target person.

Abstract: A hydraulic forceps system includes: robotic forceps including: a gripper, first piston coupled to the gripper, first cylinder forming first pressure chamber, filled with a hydraulic fluid, together with the first piston, second piston, second cylinder forming a second pressure chamber, filled with hydraulic fluid, together with the second piston, communication passage through which the chambers communicate, motor that drives the second piston via a linear motion mechanism; control device that controls the motor based on a command position for the first piston; and position sensor used for detecting a position of the second piston. The control device includes: an observer that derives an estimated position of the first piston based on the position of the second detected by the sensor; and a position controller that derives a target rotational speed of the motor based on a deviation between the estimated position of the first piston and the command position.

Abstract: An apparatus includes a memory; a processor coupled to the memory, wherein the processor acquires three-dimensional information of observation points on an object from a sensor, specifies a first area and second areas adjacent to the first area from areas of the object based on the three-dimensional information, and specifies positions of feature points included in the second areas; sets links based on the feature points included in the second areas to estimate positions of skeletons included in the second areas; and uses end points of the skeletons and lengths from the end points of the skeletons to a position of a part included in the first area among parameters used to specify the position of the part, specifies the position of the part included in the first area, and estimates a position of a skeleton included in the first area based on the specified position of the part.

Abstract: A recognition method executed by a processor, includes: acquiring positional relation between a plurality of sensors each of which senses a distance to an object; provisionally classifying an orientation of the object relative to each individual sensor included in the sensors into one of a plurality of classifications based on sensing data acquired by the individual sensor; calculating likelihood of each combination corresponding to the positional relation between the sensors based on a result of provisional classification of the orientation of the object relative to the individual sensor; and classifying the orientation of the object corresponding to each individual sensor in accordance with the calculated likelihood of each combination.

Abstract: A depth-image processing device includes: a memory; and a processor coupled to the memory and configured to: generate, cased on a synthetic model in which a three-dimensional model of a human body and a three-dimensional model of an object are combined, a plurality of learning images in which a depth image that indicates a distance from a reference position to respective positions on the human body or to respective positions on the object, and a part image to identify any one of respective parts of the human body and a cart of the object are associated with each other, and learn an identifier in which a feature of the depth image and any one of a part of the human body and a part of the object are associated with each other, based on the learning images.

Abstract: A learning device generates a plurality of leaning images in which a distance image representing a distance from a reference position to each position of a human body or each position of an object and a part image for identifying each part of the human body or a part of the object are associated with each other. The learning device corrects, based on a distance image and a part image of the learning image, a value of a region corresponding to a part of the object among regions of the distance image. The learning device learns, based on a plurality of learning images including a corrected distance image, an identifier in which characteristics of the distance image and a part of the human body or a part of the object are associated with each other.

Abstract: A recognition device a first recognition unit, a second recognition unit, and a third recognition unit. The first recognition unit acquires image information of a target person, and determines, based on a first discriminator and a feature in the image information, a first range corresponding to the image information of the target person. The second recognition unit acquires distance information of the target person, and determines, based on a second discriminator and a feature in the distance information, a second range corresponding to the distance information of the target person. The third recognition unit determines, based on the first range determined by the first recognition unit and the second range determined by the second recognition unit, a direction that a body of the target person is facing, and recognizes, based on the determined direction and a joint position dictionary, a skeleton of the target person.

Abstract: A hydraulic forceps system includes: robotic forceps including: a gripper, first piston coupled to the gripper, first cylinder forming first pressure chamber, filled with a hydraulic fluid, together with the first piston, second piston, second cylinder forming a second pressure chamber, filled with hydraulic fluid, together with the second piston, communication passage through which the chambers communicate, motor that drives the second piston via a linear motion mechanism; control device that controls the motor based on a command position for the first piston; and position sensor used for detecting a position of the second piston. The control device includes: an observer that derives an estimated position of the first piston based on the position of the second detected by the sensor; and a position controller that derives a target rotational speed of the motor based on a deviation between the estimated position of the first piston and the command position.

Abstract: A measurement apparatus which includes a processor is provided. The processor is configured to calculate, based on a distance image of a measurement target object with at least a joint, a position of a first portion of the measurement target object which corresponds to a non-joint portion or a terminal portion, and a position of a second portion of the measurement target object different from the first portion, and calculate, based on a first line connecting the calculated positions, a joint angle related to a joint of a first measurement target of the measurement target object.

Abstract: A measurement apparatus which includes a processor is provided. The processor is configured to calculate, based on a distance image of a measurement target object with at least a joint, a position of a first portion of the measurement target object which corresponds to a non-joint portion or a terminal portion, and a position of a second portion of the measurement target object different from the first portion, and calculate, based on a first line connecting the calculated positions, a joint angle related to a joint of a first measurement target of the measurement target object.

Abstract: An object to reduce a relief amount at the start of turning. A hydraulic drive system of a construction machine includes: a turning control valve disposed on a first circulation line extending from a first pump; a boom control valve disposed on a second circulation line extending from a second pump; first and second regulators, which change tilting angles of the first and second pumps; and a controller, which controls one or more solenoid proportional valves, which output a secondary pressure to the first and second regulators. While a turning operation is being performed, if a discharge pressure of the first pump is higher than a first setting value and a discharge pressure of the second pump is lower than a second setting value, the controller lowers first and second horsepower control lines that restrict discharge flow rates of the first and second pumps.

Abstract: An apparatus includes a memory; a processor coupled to the memory, wherein the processor acquires three-dimensional information of observation points on an object from a sensor, specifies a first area and second areas adjacent to the first area from areas of the object based on the three-dimensional information, and specifies positions of feature points included in the second areas; sets links based on the feature points included in the second areas to estimate positions of skeletons included in the second areas; and uses end points of the skeletons and lengths from the end points of the skeletons to a position of a part included in the first area among parameters used to specify the position of the part, specifies the position of the part included in the first area, and estimates a position of a skeleton included in the first area based on the specified position of the part.

Abstract: An object to reduce a relief amount at the start of turning. A hydraulic drive system of a construction machine includes: a turning control valve disposed on a first circulation line extending from a first pump; a boom control valve disposed on a second circulation line extending from a second pump; first and second regulators, which change tilting angles of the first and second pumps; and a controller, which controls one or more solenoid proportional valves, which output a secondary pressure to the first and second regulators. While a turning operation is being performed, if a discharge pressure of the first pump is higher than a first setting value and a discharge pressure of the second pump is lower than a second setting value, the controller lowers first and second horsepower control lines that restrict discharge flow rates of the first and second pumps.