Abstract: A causal inference model construction method is performed using a computer.

Abstract: A robot controlling device inputs an operation state of a worker from a sensor. The robot controlling device calculates a position vector and a velocity vector of each of the robot and the worker from the operation state of the robot and the operation state of the worker, generates a risk determination area (an area where the robot is stopped, an area where the robot is evacuated, and an area where the robot is decelerated) around each of the robot and the worker, determines a risk based on overlapping between the generated risk determination area of the robot and the generated risk determination area of the worker, generates a collision avoidance trajectory in which collision between the robot and the worker is avoided from a result of the determination, and controls the robot based on the generated collision avoidance trajectory.

Abstract: A work skill supporting device include a storage unit that stores non-standard work model information including a condition of non-standard work, work procedure information including information indicating a work content and information indicating a part to be used in work, and a workplace internal image obtained by photographing an inside of a workplace; a time series skeleton information acquisition unit that acquires time series skeleton information of one or a plurality of workers from the workplace internal image; a non-standard work extraction unit that determines whether or not the time series skeleton information satisfies the condition; a part specification unit that specifies a part serving as a work target using the workplace internal image for the non-standard work determined as satisfying the condition; and a work content specification unit that specifies a work content of the non-standard work with reference to the work procedure information.

Abstract: The software generation method uses a computer, wherein the computer includes a control unit and a storage unit; the storage unit stores manufacturing log data that includes sensor data acquired in one or both of a manufacturing process and an inspection process, and environmental configuration information that relates to a manufacturing device or an inspection device from which the sensor data are acquired for each component or product; and the control unit reads the manufacturing log data from the storage unit, reads the environment configuration information from the storage unit, constructs a causal inference model based on the manufacturing log data, constructs an expanded causal inference model by expanding the causal inference model using the environment configuration information, generates a contracted model by contracting the expanded causal inference model to a causal relation of prescribed target data of interest, and generates prescribed application software by reading the contracted model.

Abstract: A causal relationship model building system includes a computer which processes information for building a causal relationship model relating to a manufacturing flow of an object to be controlled. The computer builds the causal relationship model by using monitor data representing a state of each of a plurality of steps of the manufacturing flow, and quality data as a result of an inspection step, and specifies an allowable range of the monitor data so as to satisfy a target value of the quality data, by using the causal relationship model and the target value, from prediction based on a causal relationship between a plurality of pieces of the monitor data. The computer graphically displays information including the causal relationship model and the allowable range of the monitor data on a display screen.

Abstract: A work skill supporting device include a storage unit that stores non-standard work model information including a condition of non-standard work, work procedure information including information indicating a work content and information indicating a part to be used in work, and a workplace internal image obtained by photographing an inside of a workplace; a time series skeleton information acquisition unit that acquires time series skeleton information of one or a plurality of workers from the workplace internal image; a non-standard work extraction unit that determines whether or not the time series skeleton information satisfies the condition; a part specification unit that specifies a part serving as a work target using the workplace internal image for the non-standard work determined as satisfying the condition; and a work content specification unit that specifies a work content of the non-standard work with reference to the work procedure information.

Abstract: Specifying a suitable manufacturing condition and maintaining product quality is provided when there is a manufacturing state change. A computer in a manufacturing condition specifying system uses manufacturing condition data and quality data at a plurality of time points from a manufacturing flow to build models for each manufacturing state change in each manufacturing process of the flow. The computer uses the model and a quality target value to calculate a predicted value of a manufacturing condition at a next time point as first data based on a first learning model. The computer uses the model as well as the manufacturing condition data and quality data at the current time point to predict quality data at a next time point and calculate a quality error, and uses the first data and the quality error to specify manufacturing condition data at the next time point based on a learning model.

Abstract: A method for work quality control of a worker in work where repetitive operation is performed which includes: a model construction step of statistically constructing, from past path data of the worker, past intermediate quality data on a product to be subjected to the work, and past final quality data on the product to be subjected to the work, a prediction model that receives the path data and the intermediate quality data and outputs the final quality data; a worker position recognition step of recognizing a position of the worker from image data on the work captured; and an unusual worker position determining step of substituting the position of the worker recognized in the worker position recognition step into the model constructed in the model construction step, to determine whether the position of the target worker is a usual one or an unusual one.

Abstract: The software generation method uses a computer, wherein the computer includes a control unit and a storage unit; the storage unit stores manufacturing log data that includes sensor data acquired in one or both of a manufacturing process and an inspection process, and environmental configuration information that relates to a manufacturing device or an inspection device from which the sensor data are acquired for each component or product; and the control unit reads the manufacturing log data from the storage unit, reads the environment configuration information from the storage unit, constructs a causal inference model based on the manufacturing log data, constructs an expanded causal inference model by expanding the causal inference model using the environment configuration information, generates a contracted model by contracting the expanded causal inference model to a causal relation of prescribed target data of interest, and generates prescribed application software by reading the contracted model.

Abstract: A causal inference model construction method is performed using a computer.

Abstract: The monitoring apparatus includes: a processing unit and a data storage unit, in which the data storage unit stores image data of a work situation including a worker and a work object and model data including data indicating that a combination of a positional relationship between an area of the worker and an area of the work object has appeared in the past, and in which the processing unit includes a recognition unit that recognizes the areas of the worker and the work object from the input image, a combination area specification unit that specifies the combination of the positional relationship of the recognized areas of the worker and the work object, a model acquisition unit that acquires the model data from the data storage unit, and an abnormality degree calculation unit that calculates an abnormality degree in the combination of the areas of the worker and the work object.

Abstract: A robot controlling device inputs an operation state of a worker from a sensor. The robot controlling device calculates a position vector and a velocity vector of each of the robot and the worker from the operation state of the robot and the operation state of the worker, generates a risk determination area (an area where the robot is stopped, an area where the robot is evacuated, and an area where the robot is decelerated) around each of the robot and the worker, determines a risk based on overlapping between the generated risk determination area of the robot and the generated risk determination area of the worker, generates a collision avoidance trajectory in which collision between the robot and the worker is avoided from a result of the determination, and controls the robot based on the generated collision avoidance trajectory.

Abstract: A causal relationship model building system includes a computer which processes information for building a causal relationship model relating to a manufacturing flow of an object to be controlled. The computer builds the causal relationship model by using monitor data representing a state of each of a plurality of steps of the manufacturing flow, and quality data as a result of an inspection step, and specifies an allowable range of the monitor data so as to satisfy a target value of the quality data, by using the causal relationship model and the target value, from prediction based on a causal relationship between a plurality of pieces of the monitor data. The computer graphically displays information including the causal relationship model and the allowable range of the monitor data on a display screen.

Abstract: The monitoring apparatus includes: a processing unit and a data storage unit, in which the data storage unit stores image data of a work situation including a worker and a work object and model data including data indicating that a combination of a positional relationship between an area of the worker and an area of the work object has appeared in the past, and in which the processing unit includes a recognition unit that recognizes the areas of the worker and the work object from the input image, a combination area specification unit that specifies the combination of the positional relationship of the recognized areas of the worker and the work object, a model acquisition unit that acquires the model data from the data storage unit, and an abnormality degree calculation unit that calculates an abnormality degree in the combination of the areas of the worker and the work object.

Abstract: Provided is a technology for recovery from an abnormality of an action of a worker. An action instruction apparatus includes: a standard operating procedure storing unit configured to store, for each operation step, output information from a predetermined sensor relating to a standard action of a worker; an operation step identifying unit configured to acquire output information from a sensor and to compare the acquired output information with the standard action to identify an operation step being performed; an operation abnormality detecting unit configured to acquire output information from a sensor relating to an operation step subsequent to the operation step being performed by the worker to detect an operation abnormality when the acquired output information differs from the output information in the operation step subsequent to the operation step being performed; and a recovery action instruction generating unit configured to generate an operation instruction detail for recovery.

Abstract: A system is provided in which a causal relation model acquired according to a manufacturing process data is efficiently used and verification according to domain knowledge is easily performed. There is provided a causal relation model verification method in an information processing device which includes an input device, a display device, a processing device, and a storage device. In the method, a first step is performed in which quality data which is an evaluation result of a resulting product, monitor data which indicates a parameter in a case where the resulting product is generated, and domain knowledge which indicates a mutual relation between the quality data and the monitor data are acquired from the input device or the storage device.

Abstract: Provided is a technology for recovery from an abnormality of an action of a worker. An action instruction apparatus includes: a standard operating procedure storing unit configured to store, for each operation step, output information from a predetermined sensor relating to a standard action of a worker; an operation step identifying unit configured to acquire output information from a sensor and to compare the acquired output information with the standard action to identify an operation step being performed; an operation abnormality detecting unit configured to acquire output information from a sensor relating to an operation step subsequent to the operation step being performed by the worker to detect an operation abnormality when the acquired output information differs from the output information in the operation step subsequent to the operation step being performed; and a recovery action instruction generating unit configured to generate an operation instruction detail for recovery.

Abstract: A method for work quality control of a worker in work where repetitive operation is performed which includes: a model construction step of statistically constructing, from past path data of the worker, past intermediate quality data on a product to be subjected to the work, and past final quality data on the product to be subjected to the work, a prediction model that receives the path data and the intermediate quality data and outputs the final quality data; a worker position recognition step of recognizing a position of the worker from image data on the work captured; and an unusual worker position determining step of substituting the position of the worker recognized in the worker position recognition step into the model constructed in the model construction step, to determine whether the position of the target worker is a usual one or an unusual one.