Abstract: The present invention achieves a multiple-optical-axis photoelectric sensor which can be assembled with reduced effort. A multiple-optical-axis photoelectric sensor (100) includes a light projector (110) and a light receiver (120) each having an outer shape defined by a housing (1) including: an outer case (10); a light-transmitting plate (15); and a pressing member (20). Supporting parts (11b) are provided at respective inner surfaces of side plates of the outer case. Extending parts (11c) are provided at end parts of the corresponding side plates. The pressing member is configured to press the light-transmitting plate against the supporting parts by being attached to the respective extending parts.
Abstract: This image processing device, by superimposing a defect image 52 on a background image 51, with the original image of an inspection subject as the background image 51, and performing image processing in which the display format of the defect image 52 or the display format of the background image 51 is altered, a plurality of composite images 50 having different ways of seeing the defect image 52 with respect to the background image 51 are generated (step 403), the advisability of detecting the defect image 52 from each of the plurality of composite images 50 is verified (step 404), the detectable range 60 of the defect image 52 is estimated on the basis of the detection advisability verification results (step 405), and the detectable range 60 is displayed (step 406).
Abstract: The disclosure is to constitute, while reducing a cost for collecting training data used in machine learning that makes a control module acquire an ability to control a robot device, the control module operatable in an actual environment by the machine learning. A learning device according to one aspect of the present invention executes machine learning of an extractor by using a first learning data set constituted by a combination of simulation data and first environmental information and a second learning data set constituted by a combination of actual data and second environmental information. Further, a learning device according to one aspect of the present invention executes machine learning of a controller by using a third learning data set constituted by a combination of third environmental information, state information, and a control command.
Abstract: A defect inspecting device including an acquisition unit, an image generating unit, an inspection unit, and a setting unit. The image generating unit generates one or more feature extraction images by applying to an inspection image a learned classifier. The inspection unit identifies a region corresponding to a defect based on one or more determination parameters and a binarized image generated based on the feature extraction image. The setting unit provisionally sets the determination parameters on premise of a post-adjustment from a user when a number of image data for learning corresponding to the features is less than a threshold value in a case where the region corresponding to the defect is identified based on the pre-learned features, and sets the determination parameters according to designation from the user in a case where the region corresponding to the defect is identified based on a feature other than the pre-learned features.
Abstract: Provided are a simulation device, a simulation method, and a computer-readable storage medium, which reduce a computation load required for simulation of movement of an operation subject. This simulation device is provided with: a first setting unit that sets framing conditions for a model representing the operation subject; a second setting unit that sets conditions for external force applied to the operation subject; a first simulation unit that simulates the movement of the operation subject under the framing conditions and the conditions for external force; a generation unit that generates learning data; and a learning unit that, by supervised learning using the learning data, generates a learning model that takes the framing conditions, the conditions for external force, and the initial conditions of the plurality of representative points as input and outputs data representing the movement of the plurality of representative points.
Abstract: A control device includes feature amount generating means for generating a feature amount suitable for detecting an anomaly that occurs in a control target from data that relates to the control target, machine learning means for carrying out machine learning using the feature amount generated by the feature amount generating means, anomaly detecting means for detecting the anomaly, based on the feature amount generated by the feature amount generating means and an anomaly detection parameter determined based on a learning result of the machine learning and used in detection of the anomaly that occurs in the control target, instructing means for instructing the anomaly detecting means to perform detection of the anomaly, and data compressing means for data-compressing the feature amount generated by the feature amount generating means, and providing the data-compressed feature amount to the machine learning means and the anomaly detecting means.
Abstract: This control device is connected to a master device and controls a drive target on the basis of the content of communication with the master device, and includes a communication unit which periodically transmits to and receives from the master device first information, which is information relating to control of the drive target, and second information, which is information relating to safety; a first processing unit which controls the drive target by processing the first information; a second processing unit which, by processing the second information, performs processing to ensure safety of the drive target; and an abnormality determining unit which determines that an abnormality has occurred if both the first information and the second information have not been processed within a prescribed period.
Abstract: A shape estimating apparatus includes an acquiring unit and an estimating unit. The acquiring unit is configured to acquire a two-dimensional image. The estimating unit has artificial intelligence, and is configured to provide the artificial intelligence with the two-dimensional image and cause the artificial intelligence to estimate a three-dimensional shape of a subject of the two-dimensional image. A learning result of machine learning performed using learning data containing supervisor data expressing a three-dimensional shape of a sample subject and a sample two-dimensional image obtained by capturing an image of the three-dimensional shape of the sample subject is set to the artificial intelligence.
Abstract: An instruction device includes: an acquiring unit configured to acquire provided metadata, which is attribute information relating to one or more attributes of sensing data, the provided metadata having one or more hierarchy levels that contain information shared by a plurality of sensors; an acquiring unit configured to acquire usable metadata, which is attribute information relating to one or more attributes of an application; a matching unit configured to perform matching between the provided metadata and the usable metadata for each hierarchy level, calculate, for each hierarchy level, an inter-level matching degree that indicates a degree of matching in the hierarchy level, and extract a sensor capable of providing the sensing data that satisfies a request of the application, based on an overall matching degree; and an instruction unit configured to transmit a data flow control instruction that specifies the application and the extracted sensor.
Abstract: This control device comprises a communication unit, one or more functional units, and communication lines that connect the communication unit and the one or more functional units and are independent of each other. The communication unit is configured to execute a first task of sending out, with a first cycle, a first communication frame for executing transmission of data collected by the functional unit to the communication unit and/or transmission of data held by the communication unit to the functional unit via a first communication line among the communication lines, and a second task of sending out, with a second cycle different from the first cycle, a second communication frame for executing transmission of the data collected by the functional unit to the communication unit and/or transmission of the data held by the communication unit to the functional unit via a second communication line among the communication lines.
Abstract: A data generating apparatus includes a first acquisition unit configured to acquire first virtual sensing data representative of a first determination result with respect to a situation in a surrounding of a physical sensor; a second acquisition unit configured to acquire a first calculation criterion; and a first calculator configured to calculate a reliability of sensing data, based on the acquired first virtual sensing data, by using the acquired first calculation criterion, and to generate first reliability data.
Abstract: A data generating apparatus includes a selector configured to select, from a plurality of criteria determined for situation items which are determination targets, one criterion corresponding to first virtual sensing data representative of a first determination result with respect to a situation in a surrounding of the physical sensor; and a determination unit configured to determine the situation in the surrounding of the physical sensor with respect to each of the situation items, based on physical sensing data, by using the selected criterion, and to generate second virtual sensing data representative of a second determination result with respect to the situation.
Abstract: A cleaner according one or more embodiments may include a reception unit that receives a teaching operation performed by an operator. A cleaner may further include a registration unit that registers, with a storage, an individual traveling route corresponding to the teaching operation, an obtaining unit that obtains, from a plurality of the individual traveling routes registered with the storage, a plurality of individual traveling routes selected by the operator, a setting unit that sets an order of the obtained plurality of individual traveling routes, and a generation unit that generates the traveling route based on the obtained plurality of individual traveling routes and the set order of the plurality of individual traveling routes.
Abstract: An information processing device determines, based on a preset threshold, whether the production index belongs to either a first section or a second section contained in one maintenance cycle of the member, wherein a change in the production index is larger in the second section than in the first section. The information processing device executes at least one of first processing in which the production index determined to belong to the first section is used and second processing in which the production index determined to belong to the second section is used.
Abstract: A driver state determination unit of a drive mode switching control device regularly or irregularly determines whether a driver's state is a state of being able to perform a driving operation in a manual drive mode. The drive mode switching control device determines whether an operation performed by the driver is an emergency override operation or a non-emergency override operation. The drive mode switching control device outputs a switching signal for switching an automatic drive mode to the manual drive mode when a determination result by the driver state determination unit immediately before detection of the emergency override operation is that a driver's state is a state of being able to perform a driving operation in the manual drive mode.
Abstract: A control system, a support device, and a recording medium are provided. This control device includes a storage unit which stores native code generated from a first user program that includes a sequence program, and a calculation processing unit which executes the native code stored in the storage unit. A display device of the present invention includes: a storage unit which stores sequence circuit information that is generated from the first user program and defines a circuit configuration of the sequence program; and a monitor functioning unit which acquires, from the control device, a circuit output state that indicates the execution state of the native code, and visualizes the execution state of the sequence program in the control device on the basis of the acquired circuit output state and the sequence circuit information.
Abstract: An autonomous traveling floor cleaner is disclosed that improves cleaning efficiency. A floor cleaner may include a suction nozzle that suctions suction matter collected by a rotary brush, an extension nozzle that suctions suction matter collected by an extension brush, and a collection box for collecting, through an inlet, the suction matter suctioned by the nozzles. The floor cleaner may have an elongated profile. The extension nozzle may be switchable between a retracted posture and a lateral cleaning posture. The extension nozzle in the lateral cleaning posture may be pivotable rearward. The extension nozzle in the lateral cleaning posture may have a protruding end in the width direction to be aligned with an end of a turning range of the floor cleaner in the width direction.