Abstract: A forklift which carries a cargo is includes a machine learning apparatus which executes a procedure of: accepting input of learning data of a first category group and evaluation data of a second category group; extracting the learning data of at least one category from the first category group and calculating parameters of the estimation models for controlling the forklift by using the extracted learning data; extracting the evaluation data of at least one category from the second category group and evaluating the estimation models, for which the parameters are calculated, by using the extracted evaluation data; and outputting an estimation model M whose data evaluation result is equal to or larger than a specified threshold value, from among the estimation models for which the parameters are calculated, and a category of the evaluation data used for the evaluation of the estimation model M.

Abstract: A technology capable of dealing with a variation in appropriate recognition parameters due to a change in work environment at a work site at a time of recognizing an article in an image. An article recognition system includes: an input section to which a captured image is input; an output section that presents information to a user; a storage section that stores master data defining features of an object to be recognized; a recognition section that detects the object to be recognized in the image; and a recognition evaluation section that evaluates a recognition content of the recognition section and that presents an alert to the output section on the basis of an evaluation result.

Abstract: An object information registration apparatus that registers information of a first object that is a reference object of object recognition holds a first object image that is an image of the first object and recognition method information related to the first object, selects one or more partial regions included in the first object image, sets a recognition method corresponding to each of the one or more partial regions, acquires feature information of each of the one or more partial regions from the first object image based on the set recognition method, and stores the one or more partial regions, the set recognition method, and the acquired feature information in the recognition method information in association with each other.

Abstract: A carrier system including a plurality of carriers and a control unit, in which each carrier included in the plurality of carriers includes a sensor that detects an object, the control unit stores carrier information indicating a position of a first carrier of the plurality of carriers and transmits an instruction to check existence of a second carrier to the first carrier when identification information and a position of the second carrier of the plurality of carriers are input, the first carrier having received the instruction to check existence performs measurement by the sensor and transmits a result of the performed measurement to the control unit, and the control unit determines whether the input position of the second carrier is correct based on the result of measurement by the sensor received from the first carrier.

Abstract: An object recognition device includes: a data holding unit that stores a reference image of an object of a recognition candidate, each feature point in the reference image, and a feature quantity at each feature point; an image acquisition unit acquires a scene image that is an image of a recognition processing target; a definition calculation unit detects definition indicating the degree of sharpness in each region of the scene image; and a feature acquisition unit and a matching calculation unit that detect a feature point in the scene image to perform a process of matching with the feature point. The matching calculation unit executes, by different methods, an extraction method of feature points in a first region of the scene image where the definition is a first range and in a second region of the scene image where the definition is a second range lower than the first range.

Abstract: A robot system is provided in which various kinds of articles can be treated only with a small number of articles registered in advance, and an unknown article can be further treated as long as the article has a shape close to that of the article registered in advance. A robot system is disclosed which includes: a mechanism unit that manipulates an article to be manipulated; a shape measurement unit that measures a shape of an object; a basic operation storage unit that stores basic operation representing basic operation of the mechanism unit; an operation method calculation unit that deforms the stored basic operation to calculate an operation method on the basis of the shape of the object measured by the shape measurement unit; and a control unit that executes a control of the mechanism unit on the basis of the operation method calculated by the operation method calculation unit.

Abstract: A machine learning system includes a first determination model that determines whether an input image is a second domain image, and a second determination model that determines whether an extracted image obtained by extracting an area where an object is presented from the input image is from the second domain image. Either a pseudo second domain image or the second domain image is selected and input into the first determination model, and either a first extracted image in the pseudo second domain image or a second extracted image in the second domain image is selected and input into an image extracting unit. Learning of the first determination model is performed based on a first determination result, learning of the second determination model is performed based on a second determination result, and learning of a pseudo image generative model is performed based on the first and second determination results.

Abstract: An autonomous system including a plurality of autonomous bodies, each of the autonomous bodies includes a situation grasping unit that grasps situation, an operation determining unit that determines an operation based on the grasped situation, and an operation executing unit that executes the determined operation, the plurality of autonomous bodies included in the autonomous body system includes one or more first autonomous bodies and two or more second autonomous bodies, situation grasped by the situation grasping unit of the first autonomous body includes situation of the second autonomous body, the situation grasped by the situation grasping unit of the second autonomous body includes a result of an operation executed by the operation executing unit of the first autonomous body, and the operation determining unit of the second autonomous body determines an operation based on the result of the operation executed by the operation executing unit of the first autonomous body.

Abstract: A robot system has a manipulator that conveys a conveying object to a conveyance destination having a bottom surface and a wall surface connected to the bottom surface. The system includes: a first process in which the manipulator puts a first conveying object on the bottom surface of the conveyance destination; a second process in which the manipulator conveys a second conveying object to a position that does not come into contact with the first conveying object on the bottom surface of the conveyance destination; and a third process in which the manipulator moves the second conveying object in the direction of the first conveying object from the position that does not come into contact with the first conveying object, and moves the first conveying object by further moving the second conveying object after coming into contact with the first conveying object.

Abstract: A shelf transport system comprising a shelf transport vehicle transporting a shelf having shelf legs, the shelf transport vehicle comprising: a distance sensor measuring a distance to an obstacle; a shelf leg candidate detection module detecting shelf leg candidates, which are candidates for the shelf legs; a shelf arrangement candidate calculation module calculating shelf arrangement candidates, in each of which the shelf is virtually arranged on the shelf leg candidates; an excess/deficiency calculation module calculating, for each of the shelf arrangement candidates, the excessive and the deficient number of shelf leg candidates; a shelf arrangement determination module determining a shelf arrangement from among the shelf arrangement candidates based on the excessive and the deficient number of shelf leg candidates; and a movement destination determination module determining a shelf to which the shelf transport vehicle is to be moved based on the shelf arrangement.

Abstract: An information processing apparatus obtains a plurality of combinations of a position of a work target candidate and a transport machine optimum control parameter which is a control parameter of the transport machine that maximizes performance of the work on a work target when the work target candidate is set as the work target, based on a captured image obtained by capturing an area including a plurality of the work target candidates transported by the transport machine, determines the work target from among the work target candidates based on the combinations, controls the transport machine based on the transport machine optimum control parameter of the determined work target, generates a control plan of the robot based on a position of the determined work target and the transport machine optimum control parameter of the work target and controls the robot according to the generated control plan.

Abstract: A picking robot executes an acquisition process for acquiring the latest recognition result from a storage destination of the latest recognition result of a housed area on the basis of the latest imaged image of the housed area, a modification process for accessing the housed area and modifying a location in the housed area by controlling the robot arm on the basis of the latest recognition result acquired in the acquisition process, an imaging process for imaging the housed area after modification in the housed area by the modification process by controlling the imaging device, a recognition process for recognizing residual articles in the housed area on the basis of an image imaged in the imaging process, and a transmission process for transmitting the recognition result in the recognition process to the storage destination.

Abstract: A robot system is provided in which various kinds of articles can be treated only with a small number of articles registered in advance, and an unknown article can be further treated as long as the article has a shape close to that of the article registered in advance. A robot system is disclosed which includes: a mechanism unit that manipulates an article to be manipulated; a shape measurement unit that measures a shape of an object; a basic operation storage unit that stores basic operation representing basic operation of the mechanism unit; an operation method calculation unit that deforms the stored basic operation to calculate an operation method on the basis of the shape of the object measured by the shape measurement unit; and a control unit that executes a control of the mechanism unit on the basis of the operation method calculated by the operation method calculation unit.

Abstract: A shelf transport system comprising a shelf transport vehicle transporting a shelf having shelf legs, the shelf transport vehicle comprising: a distance sensor measuring a distance to an obstacle; a shelf leg candidate detection module detecting shelf leg candidates, which are candidates for the shelf legs; a shelf arrangement candidate calculation module calculating shelf arrangement candidates, in each of which the shelf is virtually arranged on the shelf leg candidates; an excess/deficiency calculation module calculating, for each of the shelf arrangement candidates, the excessive and the deficient number of shelf leg candidates; a shelf arrangement determination module determining a shelf arrangement from among the shelf arrangement candidates based on the excessive and the deficient number of shelf leg candidates; and a movement destination determination module determining a shelf to which the shelf transport vehicle is to be moved based on the shelf arrangement.

Abstract: A robot is provided. A measurement unit measures an object in a space. An own-position estimation unit calculates an own position of a mobile unit moving through the space by matching measurement data acquired by the measurement unit with map data representing information about the object in the space. A classification unit acquires class-based measurement data obtained by classifying the measurement data into at least two predetermined classes. A class-based own-position estimation unit estimates an own position of the mobile unit for each of the at least two predetermined classes by matching a class-based map having a position of the objects recorded therein for each class with the class-based measurement data. An integration unit configured to integrate the own positions estimated for the respective at least two predetermined classes. A control unit controls the mobile unit based on information from the integration unit.

Abstract: Disclosed is a transfer robot system wherein: a robot has a connecting unit, which removably holds a rack, and which can be electrically connected to the rack, a driving unit, and a control unit; and the control unit moves the robot to the vicinity of a first rack by means of the drive unit, moves the robot and the first rack to the vicinity of a second rack by connecting the robot and the first rack to each other by means of the connecting unit, supplies power to a transfer unit of the first and/or second rack via the connecting unit, operates the transfer unit corresponding to positions where articles to be moved are placed, and moves the articles to predetermined areas on the other rack from the rack having the articles placed thereon.

Abstract: A robot is provided. A measurement unit measures an object in a space. An own-position estimation unit calculates an own position of a mobile unit moving through the space by matching measurement data acquired by the measurement unit with map data representing information about the object in the space. A classification unit acquires class-based measurement data obtained by classifying the measurement data into at least two predetermined classes. A class-based own-position estimation unit estimates an own position of the mobile unit for each of the at least two predetermined classes by matching a class-based map having a position of the objects recorded therein for each class with the class-based measurement data. An integration unit configured to integrate the own positions estimated for the respective at least two predetermined classes. A control unit controls the mobile unit based on information from the integration unit.

Abstract: A system recognizes an arrangement of an object and counts the number of objects, comprising: a sensor for measuring a distance between the sensor and an object; a moving mechanism for moving the sensor; and a computer that is connected with the sensor and includes an object information database, an object arrangement database; a sensor data integrating section; and the sensor an object comparison calculator adapted to create an object model based on the data.

Abstract: A system recognizes an arrangement of an object and counts the number of objects, comprising: a sensor for measuring a distance between the sensor and an object; a moving mechanism for moving the sensor; and a computer that is connected with the sensor and includes an object information database, an object arrangement database; a sensor data integrating section; and the sensor an object comparison calculator adapted to create an object model based on the data.

Abstract: A computer in a transport system includes: a shooting part for shooting a first calibration tray by controlling a camera; a tray position computing part for computing a tray position of the first calibration tray within a captured image which the shooting part shot; a hand position acquisition part for acquiring a hand position indicative of a position of the hand robot of when the hand robot installs onto the first calibration tray a first transported article used for calibration; a calibration part for computing a calibration data based on the tray position and the hand position; and a transported article installing part which, when the mobile robot reached a predetermined arrival area, controls, based on the calibration data, the hand robot so as to install a second transported article onto a second tray, the second tray which the mobile robot being provided with.