Work analysis apparatus

Abstract

To improve the accuracy of work analysis.SOLUTION: A work analysis apparatus using machine learning includes: a movement detection unit which detects movement of a worker; a contact detection unit which detects a contact between the worker and an object; and a determination unit which determines whether the worker is working or not, on the basis of a result detected by the movement detection unit and a result detected by the contact detection unit.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present disclosure relates to a work analysis device. [Background technology]

[0002] There are known techniques for analyzing the movements of workers. For example, Patent Document 1 discloses an invention that has a gyro sensor, an acceleration sensor, a direction sensor, and a magnetic sensor, and determines whether the estimation of the direction of movement by the gyro sensor or the direction of movement by the direction sensor is more accurate in estimating the direction of movement in the horizontal direction, depending on the value of magnetic force measured by the magnetic sensor. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2015-169636 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in conventional technology, the analysis does not distinguish between worker movement and whether or not the worker is working. For example, when working on a large object such as a car, the worker repeats walking and carrying within a single process, so even if the worker is performing the same task, an increase or decrease in the number of steps may affect the analysis results.

[0005] In view of the above technical problems, one aspect of the present disclosure aims to improve the accuracy of task analysis. [Means for solving the problem]

[0006] A work analysis device according to one aspect of the present disclosure includes a movement detection unit that detects the movement of a worker, a contact detection unit that detects contact between the worker and an object, and a determination unit that determines whether the worker is working or not based on the detection results by the movement detection unit and the detection results by the contact detection unit. Effect of the Invention

[0007] According to one aspect of the present disclosure, the accuracy of task analysis is improved. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram for explaining an overview of work analysis. [Diagram 2] FIG. 1 is a block diagram showing an example of a work analysis device. [Diagram 3] 1 is a flowchart showing an example of a work analysis method. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. In this specification and the drawings, components having substantially the same functional configurations are denoted by the same reference numerals, and redundant description will be omitted.

[0010] [Embodiment] In recent years, there has been an increasing need to analyze the movements of workers on production lines from the viewpoint of quality assurance or improving production efficiency. For example, workers repeatedly walk and work on large work objects (workpieces) such as automobiles within one process. In conventional technology, work analysis is performed without separating walking and work, so even if the net work is the same, work information fluctuates due to differences in walking distance, which is one of the factors that reduces the accuracy of work analysis. In addition, when a worker moves significantly due to walking, errors in sensor values ​​such as acceleration accumulate, causing a drift phenomenon in which the analyzed position deviates from the actual position.

[0011] One embodiment of the present disclosure is an activity analysis device that analyzes an activity performed by a worker. In this embodiment, the activity analysis device determines whether or not the worker is working based on a detection result of the worker's movement and a detection result of contact between the worker and an object. This makes it possible to separate the worker's movement and activity, improving the accuracy of the activity analysis.

[0012] <Outline of work analysis> FIG. 1 is a diagram for explaining an overview of work analysis. FIG. 1(A) is a diagram showing an example of the relationship between the estimation result of the work procedure and the movement history of the worker. In the conventional work analysis, a predetermined time length (for example, 0.6 seconds) of sensor data is treated as a processing unit, skeletal information at each time is detected from the sensor data, and the work procedure of the worker at each time is estimated based on the change in the skeletal information over time. In addition, in the conventional work analysis, the position of the worker is detected from the sensor data, and the movement history of the worker is calculated based on the change in the position of the worker over time. At this time, since the correct answer label does not include information indicating "movement," it is not possible to distinguish between movement and work.

[0013] In the work analysis of this embodiment, the movement history of the worker is synchronized with the estimated results of the work procedure, making it possible to separate movement from work. This allows work analysis to be performed using only information from the work, and therefore work analysis can be performed without relying on the number of steps taken during movement. In addition, sensor data such as acceleration can be reset for each work, which suppresses the accumulation of errors and avoids the drift phenomenon.

[0014] Figure 1(B) shows a specific example of detailed task analysis. Figure 1(B) shows a worker picking up a part (image a), transporting the part (image b), tightening the part at the destination (image c), completing the tightening (image d), and moving back to the original position (image e).

[0015] In the task analysis of this embodiment, a more detailed division is possible by combining the detection results of the worker's movement and the detection results of the contact between the worker and an object. When the contact between the worker and an object is detected, it becomes possible to divide a simple "movement" from a "transport" in which the worker moves while holding a workpiece. It is also possible to divide a detailed movement, such as picking up a part from a shelf, from a task.

[0016] For example, in image a, it is detected that there is no movement and that an object is in contact with the hand. In this case, it can be determined that the worker is performing the "task" of picking up a part. In image b, it is detected that there is movement and that an object is in contact with the hand. In this case, it can be determined that the worker is "transporting" a part. In image c, it is detected that there is no movement and that an object is in contact with the hand. In this case, it can be determined that the worker is performing the "task" of tightening. In image d, it is detected that there is no movement and that there is no object in the hand. In this case, it can be determined that the worker has completed the "task" of tightening. In image e, it is detected that there is movement and that there is no object in the hand. In this case, it can be determined that the worker is performing simple "movement."

[0017] <Work analysis device> The work analysis device in this embodiment will be described with reference to Fig. 2. Fig. 2 is a block diagram showing an example of the work analysis device.

[0018] The work analysis device 100 in this embodiment is realized by an information processing device such as a computer. The information processing device includes a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), a HDD (Hard Disk Drive), an input device, an output device, an external I / F (Interface), and a communication I / F, each of which is connected to each other via a system bus.

[0019] 2, the work analysis device 100 includes an acquisition unit 101, a position and orientation estimation unit 102, a movement detection unit 103, a contact detection unit 104, a work procedure estimation unit 105, and a determination unit 106. The work analysis device 100 is connected to a sensor C via various wired or wireless interfaces.

[0020] The sensor C is a variety of sensors that observe information related to the worker. The sensor C may be installed at the work site or worn by the worker. The sensor C may be, for example, a process camera, a viewpoint camera, an acceleration sensor, a pressure sensor, or a GPS module. The process camera is a camera that captures an overhead image of the work site. The viewpoint camera is a camera worn by the worker so as to capture an image of the worker's field of vision. The acceleration sensor, pressure sensor, or GPS module is a wearable device worn by the worker.

[0021] The acquisition unit 101 acquires sensor data of an observation of a worker from a sensor C. The acquisition unit 101 acquires the sensor data at predetermined time intervals.

[0022] The position and orientation estimation unit 102 estimates the position and orientation of the worker based on the sensor data acquired by the acquisition unit 101. For example, the position and orientation estimation unit 102 may estimate the position and orientation of the worker by detecting the skeleton of the worker from image information captured by a process camera. The skeleton can be detected using a trained machine learning model. The position of the worker may be estimated using an acceleration sensor or a GPS module.

[0023] The movement detection unit 103 detects the movement of the worker based on the result of the position and orientation estimation by the position and orientation estimation unit 102. For example, the movement detection unit 103 may determine whether or not the worker is moving based on a change in the position of the worker over time.

[0024] The contact detection unit 104 detects contact between the worker and the object based on the sensor data acquired by the acquisition unit 101. For example, the contact detection unit 104 may recognize the worker and the object from image information captured by a process camera, and determine whether the worker's hand and the object overlap. The object may be, for example, a part to be worked on or a tool to be used for the work. The worker and the object can be recognized using a trained object detection model or segmentation model.

[0025] The work procedure estimation unit 105 estimates a work procedure based on the result of the position and orientation estimation by the position and orientation estimation unit 102. For example, the work procedure estimation unit 105 may estimate a work procedure based on a time change in the skeleton of the worker's upper body. The estimation of the work procedure can be performed using a trained machine learning model.

[0026] The determination unit 106 determines whether or not the worker is working, based on the detection result (movement information) by the movement detection unit 103, the detection result (hand tip information) by the contact detection unit 104, and the estimation result (work information) by the work procedure estimation unit 105. For example, the determination unit 106 may separate into movement and work. Also, for example, the determination unit 106 may separate into any of work, movement, and transportation.

[0027] <Work analysis method> The work analysis method executed by the work analysis device 100 in this embodiment will be described with reference to Fig. 3. Fig. 3 is a flowchart showing an example of the work analysis method. The work analysis method is repeatedly executed for each unit of sensor data.

[0028] In step S1, the sensor C observes a worker and generates sensor data. The acquisition unit 101 acquires the sensor data from the sensor C. The acquisition unit 101 sends the acquired sensor data to the position and orientation estimation unit 102 and the contact detection unit 104.

[0029] In step S2, the position and orientation estimation unit 102 estimates the position and orientation of the worker based on the sensor data received from the acquisition unit 101. The position and orientation estimation unit 102 sends the estimated position and orientation to the movement detection unit 103 and the work procedure estimation unit 105.

[0030] In step S3, the movement detection unit 103 receives the position and orientation estimation result from the position and orientation estimation unit 102. The movement detection unit 103 detects the movement of the worker based on the change in the position of the worker over time. The movement detection unit 103 sends movement information indicating the detection result to the determination unit 106.

[0031] In step S4, the contact detection unit 104 recognizes the worker's hand and the object based on the sensor data received from the acquisition unit 101, and detects contact between the worker's hand and the object. The contact detection unit 104 sends hand information indicating the detection result to the determination unit 106.

[0032] In step S5, the work procedure estimation unit 105 estimates a work procedure based on the sensor data received from the acquisition unit 101. The work procedure estimation unit 105 sends work information indicating the estimation result to the determination unit .

[0033] In step S6, the determination unit 106 determines whether or not a first determination condition is satisfied based on the movement information, the hand information, and the work information. The first determination condition is that the movement information indicates no movement, the work information indicates work is being performed, and the hand information indicates contact with an object.

[0034] If the first determination condition is satisfied (YES), the determination unit 106 advances the process to step S7. On the other hand, if the first determination condition is not satisfied (NO), the determination unit 106 advances the process to step S8.

[0035] In step S7, the determination unit 106 determines that the activity is “work.” After that, the determination unit 106 returns the process to step S1.

[0036] In step S8, the determination unit 106 determines whether or not a second determination condition is satisfied based on the movement information, the hand information, and the work information. The second determination condition is that the movement information indicates that there is movement, the work information indicates that there is no work, and the hand information indicates that there is contact with an object.

[0037] If the second determination condition is satisfied (YES), the determination unit 106 advances the process to step S9. On the other hand, if the second determination condition is not satisfied (NO), the determination unit 106 advances the process to step S10.

[0038] In step S9, the determination unit 106 determines the answer to be “transport.” After that, the determination unit 106 returns the process to step S1.

[0039] In step S10, the determination unit 106 determines whether or not a third determination condition is satisfied based on the movement information, the hand information, and the work information. The third determination condition is that the movement information indicates that there is movement, the work information indicates that there is no work, and the hand information indicates that there is no contact with an object.

[0040] If the third determination condition is satisfied (YES), the determination unit 106 advances the process to step S11. On the other hand, if the third determination condition is not satisfied (NO), the determination unit 106 advances the process to step S12.

[0041] In step S11, the determination unit 106 determines the result as "movement." After that, the determination unit 106 returns the process to step S1.

[0042] In step S12, the determination unit 106 of the work analysis device 100 determines that the movement is a "dangerous movement." This is because it is considered that the worker is moving while working. After that, the determination unit 106 returns the process to step S1.

[0043] <Application Examples> This embodiment can be applied to the following processes, for example. First, general work outside the vehicle. Second, a process of removing parts from a shelf and assembling them. Third, a process of transporting a large workpiece using a locker molding or the like and assembling it in a vehicle. Fourth, a process of removing and transporting a workpiece after injection molding. Fifth, detection of multitasking.

[0044] <Effects> The work analysis device in this embodiment determines whether or not a worker is working based on the detection results of the worker's movement and the detection results of the worker's contact with an object. Therefore, according to this embodiment, it is possible to distinguish between movement and work. In one aspect, according to this embodiment, the accuracy of work analysis is improved.

[0045] Although the embodiments of the present invention have been described in detail above, the present invention is not limited to these embodiments, and various modifications and changes are possible within the scope of the gist of the present invention described in the claims. [Explanation of symbols]

[0046] 100: Work analysis device 101: Acquisition unit 102: Position and orientation estimation unit 103: Movement detection unit 104: Contact detection unit 105: Work procedure estimation unit 106: Determination unit

Claims

[Claim 1] A movement detection unit that detects the movement of a worker; a contact detection unit that detects contact between the worker and an object; a determination unit that determines whether the worker is working based on a detection result by the movement detection unit and a detection result by the contact detection unit; A work analysis device comprising:

Images