Substrate transfer robot system and substrate detection method

Abstract

This substrate transfer robot system (100) comprises: a robot (20) that transfers a substrate (101); an irradiation unit (50) that irradiates a main surface (101a) of the substrate (101) held by the robot (20) with detection light (L1) having a predetermined shape; an imaging unit (40) that captures an image of the substrate (101) and thereby captures an image of detection light (L1) reflected at the main surface (101a) of the substrate (101); and a control unit (60) that detects the state of the substrate (101) on the basis of the captured image of the detection light (L1) captured by the imaging unit (40).

Description

Substrate transport robot system and substrate detection method

[0001] The present disclosure relates to a substrate transfer robot system and a substrate detection method.

[0002] Measuring devices for measuring deformation of semiconductor wafers have been disclosed. The measuring device disclosed in Japanese Patent No. 7169994 measures deformation of a semiconductor wafer by analyzing an image of a geometric illumination pattern reflected by the semiconductor wafer. The measuring device described in Japanese Patent No. 7169994 images a semiconductor wafer placed on a turntable in a vacuum chamber while being processed. Because processing in the vacuum chamber is performed while the turntable is rotating, a reflected image of the entire semiconductor wafer can be captured even for large semiconductor wafers. Japanese Patent No. 7169994 also describes an example in which a reflected image of the entire semiconductor wafer is captured by linearly moving the semiconductor wafer using a translation means outside the vacuum chamber.

[0003] Patent No. 7169994

[0004] However, as in the above-mentioned Patent Publication No. 7169994, when imaging a substrate placed on a turntable in a vacuum chamber to detect the state of the substrate, such as deformation of a semiconductor wafer, it is difficult to adjust the position of the substrate to be imaged because the turntable moves only in the rotational direction. Furthermore, even when capturing a reflected image of the entire substrate by linearly moving the substrate using a translation device located outside the vacuum chamber, it is difficult to adjust the position of the substrate to be imaged because the substrate only moves linearly. When it is difficult to adjust the position of the substrate to be imaged, it is difficult to detect the state of the substrate with higher accuracy. Therefore, when detecting the state of a substrate by imaging it, it is desirable to be able to detect the state of the substrate with higher accuracy by adjusting the position of the substrate.

[0005] This disclosure has been made to solve the above-mentioned problems, and one object of this disclosure is to provide a substrate transport robot system and a substrate detection method that are capable of detecting the state of a substrate with greater accuracy.

[0006] A substrate transport robot system according to a first aspect of this disclosure includes a robot that transports a substrate, an irradiation unit that irradiates a main surface of a substrate held by the robot with detection light having a predetermined shape, an imaging unit that images the substrate and thereby captures the detection light reflected from the main surface of the substrate, and a control unit that detects the state of the substrate based on the image of the detection light captured by the imaging unit.

[0007] As described above, the substrate transport robot system according to a first aspect of this disclosure irradiates a main surface of a substrate held by the robot with detection light having a predetermined shape. The state of the substrate is then detected based on an image of the detection light captured by the imaging unit. As a result, because the substrate to be imaged is held by the robot transporting the substrate, the position of the substrate can be easily adjusted by the operation of the robot. Therefore, the substrate can be easily positioned at an appropriate position for detecting the state of the substrate by the operation of the robot, allowing for more accurate detection of the state of the substrate.

[0008] A substrate detection method according to a second aspect of this disclosure captures an image of a substrate held by a robot that transports the substrate, captures detection light having a predetermined shape reflected on a main surface of the substrate, and detects the state of the substrate based on the captured image of the detection light.

[0009] As described above, a substrate detection method according to a second aspect of this disclosure captures an image of a substrate held by a robot, and detects the state of the substrate based on the captured image of the detection light. As a result, because the substrate to be imaged is held by the robot that transports the substrate, the position of the substrate can be easily adjusted by the operation of the robot. Therefore, the substrate can be easily positioned at an appropriate position for detecting the state of the substrate by the operation of the robot, and a substrate detection method can be provided that can detect the state of the substrate with greater accuracy.

[0010] According to the present disclosure, the state of the substrate can be detected with higher accuracy.

[0011] FIG. 1 is a top view showing a substrate processing system in which a substrate transport robot system according to a first embodiment of the present disclosure is arranged. FIG. 2 is a perspective view for explaining the configuration of a substrate. FIG. 3 is a block diagram showing the configuration of the substrate transport robot system according to the first embodiment of the present disclosure. FIG. 4 is a perspective view schematically showing the configuration of the substrate transport robot system. FIG. 5 is a view showing an example of an image of detection light captured by an imaging unit. FIG. 6 is a view showing an example of an image captured by moving a substrate along a plurality of movement directions. FIG. 7 is a view for explaining learning of a trained model. FIG. 8 is a flow chart for explaining a substrate detection method according to the first embodiment. FIG. 9 is a perspective view schematically showing the configuration of a substrate transport robot system according to a second embodiment of the present disclosure. FIG. 10 is a perspective view schematically showing the configuration of a substrate transport robot system according to a third embodiment of the present disclosure.

[0012] First Embodiment A first embodiment of the present disclosure will now be described with reference to the drawings.

[0013] A substrate transport robot system 100 according to a first embodiment will be described with reference to FIGS. 1 to 7. FIG.

[0014] (Substrate Processing System) As shown in FIG. 1 , the substrate transfer robot system 100 is disposed in a substrate processing system 400. The substrate processing system 400 includes a processing device 401 that processes a substrate 101. The processing device 401 includes a robot 402, a load lock unit 403, a plurality of processing module units 404, and a transfer chamber 405. The robot 402 is a horizontal articulated robot that transfers the substrate 101. The load lock unit 403 is a room for loading and unloading the substrate 101. That is, the substrate 101 is placed in the load lock unit 403 for transferring the substrate 101 to the processing device 401. The processing device 401 of the substrate processing system 400 includes two load lock units 403. The load lock units 403 are connected to the substrate transfer robot system 100. In the processing module unit 404, the substrate 101 is subjected to processing such as resist coating and etching. A robot 402 is disposed in the transfer chamber 405. In the transfer chamber 405, the robot 402 transfers the substrate 101 between the load lock unit 403 and the processing module unit 404.

[0015] The substrate transfer robot system 100 transfers the substrate 101 between a FOUP (Front Opening Unify Pod) 110 and a processing device 401 in a substrate processing system 400 in which processing is performed on the substrate 101. The substrate transfer robot system 100 is an EFEM (Equipment Front End Module). The FOUP 110 is a container that stores a plurality of substrates 101. In the FOUP 110, the plurality of substrates 101 are arranged vertically side by side. The FOUP 110 is an example of a substrate storage container.

[0016] 2, the substrate 101 is, for example, a disk-shaped silicon wafer. The substrate 101 has a mirror-finished main surface 101a. The substrate 101 also has a notch 101b that indicates the orientation of the substrate 101. The notch 101b is a V-shaped groove disposed on the outer periphery of the substrate 101 to indicate the direction of the crystal orientation in the substrate 101.

[0017] 3, the substrate transfer robot system 100 includes a transfer chamber 10, a robot 20, an aligner 30, an imaging unit 40, an irradiation unit 50, and a control unit 60. The robot 20 includes a horizontal articulated robot arm 21 and a substrate holding hand 22. The aligner 30 is an example of an adjustment device.

[0018] As shown in FIG. 4 , the transfer chamber 10 is a rectangular parallelepiped housing. The transfer chamber 10 has a front surface 11 on the Y1 direction side and a back surface 12 on the Y2 direction side. The transfer chamber 10 also has a top surface 13 on the vertically upward side, i.e., the Z1 direction side. The transfer chamber 10 transports the substrate 101 within the transfer chamber 10. The transfer chamber 10 houses a robot 20, an aligner 30, an imaging unit 40, an irradiation unit 50, and a control unit 60. Three load port units 11a, to which FOUPs 110 are attached, are arranged horizontally on the front surface 11 on the Y1 direction side of the transfer chamber 10. The load port units 11a each have an opening / closing mechanism. The load port units 11a open and close the doors of the attached FOUPs 110. Two load lock units 403 are connected to the back surface 12 on the Y2 direction side of the transfer chamber 10. An opening / closing mechanism is also arranged between the load lock units 403 and the back surface 12. FIG. 4 shows a state in which a FOUP 110 is attached to one of the three load port sections 11a on the X1 direction side.

[0019] The robot 20 is disposed in the transfer chamber 10 in which the substrate 101 is transferred between the FOUP 110 and the load lock unit 403. The robot 20 performs a transfer operation of the substrate 101 in the transfer chamber 10. Specifically, the robot 20 has a substrate holding hand 22, which is an end effector that holds the substrate 101, disposed at the tip of a robot arm 21. The robot 20 performs a transfer operation of the substrate 101 between the FOUP 110 attached to the load port unit 11a and the load lock unit 403. The robot 20 transfers the substrate 101 while the substrate holding hand 22 holds the substrate 101 along a horizontal plane. The substrate holding hand 22 is a passive type hand that holds the substrate 101 without fixing it.

[0020] The aligner 30 aligns the substrate 101 transported by the robot 20. The aligner 30 adjusts the orientation of the substrate 101 in a predetermined direction. The aligner 30 is disposed in the transport chamber 10, close to the X2 direction, which is one side of the X direction (the left-right direction). The aligner 30 has a substrate mounting portion 30a on which the substrate 101 is mounted. The aligner 30 detects the notch 101b of the substrate 101 from the outer periphery of the substrate 101 by rotating the substrate 101 mounted on the substrate mounting portion 30a along a horizontal plane. Then, based on the position of the notch 101b detected from the outer periphery, the aligner 30 rotates the substrate 101 along a horizontal plane to align the rotational position along the circumferential direction of the main surface 101a of the substrate 101, thereby adjusting the orientation of the substrate 101 in a predetermined direction. The aligner 30 also detects the center position of the substrate 101.

[0021] In the substrate transfer robot system 100, the unprocessed substrate 101 held by the robot 20 is transferred from the FOUP 110 to the aligner 30. Then, the substrate 101 aligned by the aligner 30 is transferred again by the robot 20 to the load lock unit 403. Furthermore, the substrate 101 after being processed in the processing device 401 is transferred by the robot 20 from the load lock unit 403 to the FOUP 110. The transfer operation of the substrate 101 by the robot 20 includes both a carry-out operation for removing the substrate 101 from the FOUP 110 and the load lock unit 403 and a carry-in operation for placing the substrate 101 thereon.

[0022] The imaging unit 40 is, for example, a two-dimensional camera. The imaging unit 40 has an imaging element such as a charge coupled device (CCD) and a complementary metal oxide semiconductor (CMOS). The imaging unit 40 is disposed in a position facing the substrate 101 held by the robot 20. The imaging unit 40 captures an image of the substrate 101 held by the robot 20. In the first embodiment, the imaging unit 40 is disposed above the robot 20 within the transfer chamber 10. The imaging unit 40 is disposed, for example, on the ceiling surface 13 of the transfer chamber 10 within the transfer chamber 10. The imaging unit 40 is disposed in a position where it captures an image of the substrate 101 removed from the FOUP 110. Three imaging units 40 are arranged to correspond to the three load port units 11a to which the FOUPs 110 are attached.

[0023] The irradiation unit 50 irradiates the detection light L1 onto the main surface 101a of the substrate 101, which is being moved relative to the robot 20 in at least one of its position and angle. In the first embodiment, the irradiation unit 50 irradiates the detection light L1 having a predetermined shape onto the main surface 101a of the substrate 101, which is held by the robot 20 and is moving relatively along a predetermined movement direction. The irradiation unit 50 irradiates the detection light L1 in a line shape along a direction intersecting the movement direction when the position of the substrate 101 relative to the irradiation unit 50 is changed. The irradiation unit 50 includes, for example, an LED (Light-Emitting Diode) that irradiates a red line-shaped light as the detection light L1. Note that the term "line-shaped" light here means that when the detection light L1 is irradiated onto a plane such as the main surface 101a of the substrate 101, the detection light L1 has a shape that extends in a line on the irradiated plane. Furthermore, the irradiation unit 50 irradiates the substrate 101 with detection light L1 at the timing when the imaging unit 40 captures an image. The irradiation unit 50 is disposed above the robot 20 within the transfer chamber 10. The irradiation unit 50 is disposed, for example, on the ceiling surface 13 of the transfer chamber 10 within the transfer chamber 10. Similar to the imaging unit 40, three irradiation units 50 are disposed to correspond to the three load port units 11a to which the FOUPs 110 are attached.

[0024] As shown in FIG. 1 , the control unit 60 includes a machine learning unit 61. The control unit 60 controls the operation of each unit of the substrate transport robot system 100. In the first embodiment, the control unit 60 also serves as a robot control unit that controls the operation of the robot 20. That is, the control unit 60 is a robot controller. The control unit 60 also controls the operation of the aligner 30. The control unit 60 also controls the operations of the imaging unit 40 and the irradiation unit 50. The control unit 60 includes, for example, a calculation device such as a CPU (Central Processing Unit). The control unit 60 also includes memories such as a RAM (Random Access Memory) and a ROM (Read Only Memory), and a storage device such as a hard disk. The control unit 60 executes control processing by the calculation device based on programs, parameters, and the like stored in the storage device.

[0025] (Generation of Captured Image) As shown in FIG. 5 , a captured image 71 is acquired by imaging by the imaging unit 40. The captured image 71 captured by the imaging unit 40 is transmitted to the control unit 60. The imaging unit 40 captures the detection light L1 reflected on the main surface 101 a of the substrate 101 by imaging the substrate 101. When the imaging unit 40 captures the detection light L1, the robot 20 changes the position of the substrate 101 relative to the irradiation unit 50. Specifically, when the imaging unit 40 captures the detection light L1, the robot 20 moves the substrate 101 along a predetermined movement direction, thereby moving the substrate 101 relative to the irradiation unit 50. The irradiation unit 50 irradiates the detection light L1 onto the main surface 101 a of the substrate 101, which is moving relatively due to the operation of the robot 20. The imaging unit 40 then captures images of the detection light L1 reflected from the main surface 101 a of the substrate 101 multiple times in accordance with the relative movement of the substrate 101 by the robot 20, which is a change in the position of the substrate 101 relative to the irradiation unit 50. The control unit 60 generates a captured image 71 by capturing the multiple reflected detection light beams L1 through multiple imaging by the imaging unit 40. In detail, the control unit 60 generates one captured image 71 based on the multiple captured images 70 acquired through multiple imaging by the imaging unit 40, so that the detection light L1 reflected across the entire substrate 101 is combined.

[0026] For example, the robot 20 operates to remove the substrate 101 from the FOUP 110 before processing by the processing device 401, and then moves the substrate 101 along the Y2 direction as indicated by the dotted arrow in FIG. 5 . The irradiation unit 50 continuously irradiates the main surface 101a of the substrate 101 being moved by the robot 20 with linear detection light L1 extending along the X direction perpendicular to the Y2 direction, which is the direction of movement, multiple times at the time the substrate 101 is removed from the FOUP 110. The imaging unit 40 continuously captures the detection light L1 reflected by the main surface 101a of the substrate 101 multiple times as the robot 20 moves the substrate 101 in the Y2 direction. The control unit 60 generates one captured image 71 by combining captured images 70 continuously captured by the imaging unit 40 during movement in the Y2 direction, which is one movement direction. For example, to generate a single captured image 71, the control unit 60 moves the substrate 101 using the robot 20 at a constant speed and combines captured images 70 captured multiple times consecutively by the imaging unit 40 at regular time intervals. The combined captured images 70 are superimposed on each other while being shifted in the Y direction to correspond to the movement of the substrate 101. That is, the single captured image 71 is generated so as to represent an image in which multiple detection light beams L1 are reflected across the entire main surface 101a of the substrate 101 along the movement direction of the substrate 101. The interior of the transfer chamber 10 is relatively dark because no light source other than the irradiation unit 50 is installed. Therefore, each of the multiple captured images 70 is captured so as to represent an image in which only the detection light beam L1 reflected on the main surface 101a of the substrate 101 is extracted. In other words, the captured image 71 is an image in which the detection light beam L1 reflected in a manner corresponding to the shape of the substrate 101 is extracted and captured.

[0027] 6 , the control unit 60 generates a captured image 72 by capturing an image of the substrate 101 with the imaging unit 40 while moving the substrate 101 along a movement direction different from that used to generate the captured image 71. That is, in the first embodiment, when the imaging unit 40 captures the detection light L1, the robot 20 moves the substrate 101 along multiple movement directions different from each other. The control unit 60 then generates captured images 71 and 72 in which the detection light L1 is captured by the imaging unit 40 during each of the movement of the substrate 101 along the multiple movement directions of the robot 20. For example, the control unit 60 generates two captured images 71 and 72 by moving the substrate 101 along two movement directions: the Y2 direction, which is a first movement direction of the substrate 101 for generating the captured image 71, and a second movement direction different from the Y2 direction for generating the captured image 72. Note that the captured image 72, like the captured image 71, is generated by combining multiple captured images 70 that have been captured consecutively.

[0028] (Control Process for Detection of Substrate State) As shown in FIG. 7 , in the first embodiment, the control unit 60 uses a trained model 62 generated by machine learning to detect the state of the substrate 101 based on captured images 71 and 72 of the detection light L1 captured by the imaging unit 40 in the transfer chamber 10. The control unit 60 detects the state of the substrate 101, including the position and orientation of the substrate 101, based on the captured images 71 and 72. The state of the substrate 101 detected by the control unit 60 also includes abnormalities of the substrate 101, such as warpage, deformation, chipping, cracks, and scratches. The trained model 62 is generated by machine learning to output an identification result 75 that identifies the state of the substrate 101 based on the reflected images of the detection light L1 in the captured images 71 and 72. The trained model 62 is generated in advance by the machine learning unit 61 of the control unit 60 and stored in a storage device of the control unit 60.

[0029] <Generation of Trained Model> The control unit 60 generates a trained model 62 through machine learning in the machine learning unit 61 based on the teacher image 80, which is input training data. The trained model 62 is generated by machine learning using a data set in which the teacher image 80 is input and the output teacher data 85 is output. For example, the trained model 62 is trained to input each of the captured image 71 and the captured image 72 and output, as the identification result 75, coordinates representing the position of the substrate 101 and the orientation of the substrate 101 indicated by the position of the notch 101b. Furthermore, if an abnormality such as warping occurs in the substrate 101, the shape of the detection light L1 in each of the captured images 71 and 72 will be different from that in a normal case. In the first embodiment, the trained model 62 is generated by machine learning so that an abnormality in the substrate 101 can be identified based on the reflected image of the detection light L1 in the captured image 71 and the captured image 72. The trained model 62 is trained to take the captured image 71 and the captured image 72 as inputs and output an identification result 75 including a likelihood that indicates the probability of whether or not the substrate 101 contains an abnormality.

[0030] The teacher image 80 includes captured images 71 and 72 obtained by capturing the detection light L1 reflected from each of the main surfaces 101a of multiple types of substrates 101, which differ in their states, such as their positions, orientations, or the presence or absence of abnormalities. That is, captured images 71 and 72 are obtained as multiple types of teacher images 80, capturing multiple types of substrates 101, including substrates 101 that are known to be normal and have no abnormalities, and substrates 101 that are known to have abnormalities, while the substrates 101 are arranged in multiple positions and orientations. Furthermore, output teacher data 85 indicating the state of the substrate 101 in each of the multiple types of teacher images 80 is acquired, and each of the multiple types of teacher images 80 and the corresponding output teacher data 85 are stored in the storage device of the control unit 60 in an associated state. The output teacher data 85 includes information indicating the position of the substrate 101, information indicating the orientation of the substrate 101, and information indicating whether an abnormality has occurred in the substrate 101, as information indicating the state of the substrate 101.

[0031] The machine learning unit 61 then performs machine learning to generate a trained model 62 using the plurality of teacher images 80 as input teacher data and the plurality of output teacher data 85 associated with the plurality of teacher images 80 as output teacher data. The machine learning unit 61 generates the trained model 62 through machine learning using deep learning. The machine learning unit 61 generates the trained model 62 through machine learning based on a fully convolution network (FCN), for example.

[0032] The control unit 60 uses the trained model 62 generated by machine learning as described above to obtain an identification result 75 from each of the captured image 71 and the captured image 72. The control unit 60 detects the state of the substrate 101, for example, by calculating the average of the identification result 75 obtained based on the captured image 71 and the identification result 75 obtained based on the captured image 72.

[0033] <Correction of Positional Misalignment> In the first embodiment, the control unit 60 detects a positional misalignment of the substrate 101 relative to the substrate holding hand 22 based on the detected state of the substrate 101. For example, the detection light L1 in each of the captured images 71 and 72 is captured at a timing when the substrate holding hand 22 is at a predetermined position based on the control amount of the robot 20. Therefore, by detecting information indicating the position of the substrate 101 as the state of the substrate 101 based on each of the captured images 71 and 72, the magnitude and direction of the positional misalignment of the position where the substrate 101 is held relative to the position of the substrate holding hand 22 of the robot 20 is detected. The control unit 60 obtains the average of the magnitude and direction of the positional misalignment detected based on the captured image 71 and the magnitude and direction of the positional misalignment detected based on the captured image 72 as the detected magnitude and direction of the positional misalignment, and corrects the transport operation of the robot 20 to correct the positional misalignment of the substrate 101 based on the obtained magnitude and direction of the positional misalignment.

[0034] As an example, captured images 71 and 72 are obtained by capturing an image of substrate 101 taken out of FOUP 110, and if it is detected based on captured images 71 and 72 that substrate 101 is shifted in position relative to substrate holding hand 22 by +2 cm in the X direction and −1 cm in the Y direction, control unit 60 corrects the transport operation of substrate 101 so that substrate 101 is placed at a position shifted by −2 cm in the X direction and +1 cm in the Y direction from the taught position set as the position of substrate placement unit 30a of aligner 30. Specifically, control unit 60 corrects the transport operation of robot 20 by correcting a drive signal output to a drive unit such as a servo motor that serves as a drive source for driving robot arm 21 and substrate holding hand 22.

[0035] <Assistance of Aligner> In the first embodiment, the control unit 60 controls the operation of the aligner 30 using the state of the substrate 101 detected based on the captured images 71 and 72. Specifically, the control unit 60 detects the orientation of the substrate 101 held by the substrate holding hand 22 based on the detected state of the substrate 101. The control unit 60 detects the notch 101b in the substrate 101 based on the identification result 75 from the trained model 62 acquired as the state of the substrate 101 detected based on each of the captured images 71 and 72. For example, the control unit 60 acquires the average position of the position of the notch 101b detected based on the captured image 71 and the position of the notch 101b detected based on the captured image 72 as the position of the detected notch 101b. The control unit 60 then performs an operation to adjust the orientation of the substrate 101 using the aligner 30. Based on the position of the notch 101b of the substrate 101 detected using the captured images 71 and 72, the control unit 60 rotates the substrate 101 along the horizontal plane so that the detection range is not the entire circumference of the outer peripheral edge of the substrate 101, but a portion of the outer peripheral edge of the substrate 101 that includes the position of the detected notch 101b. That is, the control unit 60 roughly detects the orientation of the substrate 101 by detecting the state of the substrate 101 based on the captured images 71 and 72, and then the control unit 60 detects the orientation of the substrate 101 in detail using the aligner 30. In other words, the control unit 60 detects the state of the substrate 101 in advance based on the captured images 71 and 72 so as to assist the operation of the aligner 30.

[0036] <Detection of Abnormality in Substrate> In the first embodiment, the control unit 60 detects an abnormality in the substrate 101 removed from the FOUP 110 during the transport operation of the robot 20, based on the captured images 71 and 72 of the detection light L1 captured at the timing when the substrate 101 is removed from the FOUP 110. The control unit 60 determines that an abnormality has been detected in the substrate 101 when the likelihood indicating the probability of whether or not an abnormality is included in the identification result 75 output as the inference result by the trained model 62 is greater than a predetermined threshold. For example, when the likelihood included in the identification result 75 is a value between 0 and 1, the detection of an abnormality in the substrate 101 is determined using 0.8 as a predetermined threshold. For example, the control unit 60 determines that an abnormality has been detected in the substrate 101 based on the average value of the likelihood included in the identification result 75 acquired based on the captured image 71 and the likelihood included in the identification result 75 acquired based on the captured image 72.

[0037] When an abnormality in the substrate 101 is detected, the control unit 60 outputs abnormality detection information indicating that an abnormality in the substrate 101 has been detected to the outside. For example, the control unit 60 outputs the abnormality detection information to a host control device that controls the entire substrate processing system 400. As an example, when an abnormality in the substrate 101 is detected, the control unit 60 causes the robot 20 to place the substrate 101 in which the abnormality has been detected back into the FOUP 110 based on a signal from the host control device. When the control unit 60 does not receive a signal from the host control device instructing the control unit 60 to place the substrate 101 back into the FOUP 110, the control unit 60 stops the transport operation of the substrate 101 and waits for processing. Note that the detection of an abnormality in the substrate 101 may be notified by displaying information indicating that the abnormality detection information has been obtained on a display device. For example, when a plurality of substrates 101 stored in a FOUP 110 are sequentially transported to a processing device 401 to be processed in the processing device 401, the control unit 60 controls the transport operation of the robot 20 to transport the substrates 101 one by one to the load lock unit 403 via the aligner 30. During the transport of each of the plurality of substrates 101, the control unit 60 acquires captured images 71 and 72 and detects an abnormality in the substrate 101 based on the acquired captured images 71 and 72 using a trained model 62 that has been generated and stored in advance. If an abnormality is detected in one of the plurality of substrates 101, the control unit 60 outputs abnormality detection information and, based on a signal from a higher-level control device, returns the substrate 101 in which the abnormality was detected to its original position in the FOUP 110, thereby storing the substrate 101 again. Then, the control unit 60 transports the next substrate 101 after the substrate 101 for which an abnormality was detected to the load lock unit 403 while similarly checking for an abnormality.

[0038] (Substrate Detection Method) Next, a control process of a substrate detection method by the substrate transport robot system 100 of the first embodiment will be described with reference to Fig. 8. The control process of the substrate detection method of the first embodiment is executed by the control unit 60 of the substrate transport robot system 100.

[0039] First, in step S1, a trained model 62 is generated. Specifically, a teacher image 80 and output teacher data 85 are acquired. Then, using the teacher image 80 and the output teacher data 85 as a data set, the trained model 62 is generated by machine learning so that the state of the substrate 101 can be detected based on the captured images 71 and 72. The generated trained model 62 is stored in the storage device of the control unit 60.

[0040] Next, in step S2, the operation of transporting the substrate 101 is started. Specifically, the operation of the robot 20 is controlled so that the substrate 101 placed in the FOUP 110 is held by the substrate holding hand 22 of the robot 20.

[0041] Next, in step S3, the substrate 101 is removed from the FOUP 110. With the substrate 101 held by the substrate holding hand 22, one substrate 101 before processing is transferred from the FOUP 110 into the transfer chamber 10.

[0042] Next, in step S4, the imaging unit 40 images the substrate 101, which is held by the robot 20 and moving relatively along a predetermined movement direction, thereby obtaining captured images 71 and 72 of the detection light L1 reflected from the main surface 101 a of the substrate 101. Specifically, the irradiation unit 50 irradiates the main surface 101 a of the substrate 101 with the detection light L1, and the imaging unit 40 images the detection light L1 reflected from the main surface 101 a, thereby obtaining each of the captured images 71 and 72 of the detection light L1.

[0043] Next, in step S5, the trained model 62 generated by machine learning is used to detect the state of the substrate 101 based on each of the captured images 71 and 72 of the captured detection light L1. For example, the state of the substrate 101, including the position of the substrate 101 relative to the substrate holding hand 22, the orientation of the substrate 101, and whether or not an abnormality has occurred in the substrate 101, is detected.

[0044] Then, in step S6, it is determined whether or not an abnormality has been detected in the substrate 101 based on the detected state of the substrate 101. If it is determined that an abnormality has been detected in the substrate 101, the process proceeds to step S7. If it is not determined that an abnormality has been detected in the substrate 101, the process proceeds to step S8.

[0045] In step S7, it is determined that an abnormality has been detected in substrate 101, and abnormality detection information indicating that an abnormality has been detected in substrate 101 is output. For example, if a signal is acquired instructing that substrate 101 in which an abnormality has been detected be stored again in FOUP 110, the operation of robot 20 is controlled so that substrate 101 in which an abnormality has been detected be stored again in FOUP 110 without being processed by processing device 401. Then, the control process of the substrate detection method is terminated.

[0046] In step S8, the positional deviation of the substrate 101 in the substrate holding hand 22 is corrected. Specifically, assuming that no abnormality is detected in the substrate 101, the transport operation of the substrate 101 continues, and based on the position of the substrate 101 detected as the state of the substrate 101 in step S5, the positional deviation of the substrate 101 with respect to the substrate holding hand 22 is detected. Then, based on the detected positional deviation of the substrate 101, the transport operation of the substrate 101 by the robot 20 with respect to the aligner 30 is corrected.

[0047] Then, in step S9, the orientation of the substrate 101 is adjusted to a predetermined direction by the aligner 30. Specifically, the position of the notch 101b on the outer peripheral edge of the substrate 101 is detected based on the state of the substrate 101 detected in step S5. Then, based on the detected position of the notch 101b, a detection range for detecting the orientation of the substrate 101 by the aligner 30 is set. Then, from within the set detection range, the aligner 30 detects the notch 101b without using the captured images 71 and 72, and adjusts the rotational position of the substrate 101 so that the substrate 101 faces in a predetermined direction.

[0048] Then, in step S10, the robot 20 transfers the substrate 101 from the aligner 30 to the load lock unit 403 for processing by the processing device 401. Then, the control process of the substrate detection method is completed.

[0049] When the control process of the substrate detection method is executed consecutively for a plurality of substrates 101, the generation of the trained model 62 in step S1 is executed only once, and the control process from step S2 to step S10 is executed repeatedly for each substrate 101. In addition, any one of the control processes in steps S6 to S8 may be executed first.

[0050] Effect of First Embodiment As described above, the substrate transport robot system 100 irradiates the main surface 101a of the substrate 101 held by the robot 20 with detection light L1 having a predetermined shape. Then, the state of the substrate 101 is detected based on the captured images 71 and 72 of the detection light L1 captured by the imaging unit 40. As a result, the substrate 101 to be imaged is held by the robot 20 that transports the substrate 101, and therefore the position of the substrate 101 can be easily adjusted by the operation of the robot 20. Therefore, the substrate 101 can be easily positioned at an appropriate position for detecting the state of the substrate 101 by the operation of the robot 20, and the state of the substrate 101 can be detected with greater accuracy.

[0051] Furthermore, in the first embodiment, an image of the substrate 101 held by the robot 20 is taken to detect the state of the substrate 101 while the robot 20 is transporting the substrate 101, and therefore, unlike a case in which the substrate 101 is placed on a mount section dedicated to image capture that is arranged separately from the robot 20 to image the substrate 101, or a case in which the substrate 101 is moved by a movement mechanism such as a translation means that is arranged separately from the robot 20, it is possible to prevent the device configuration from becoming complicated in order to more accurately detect the state of the substrate 101. Furthermore, because an image of the substrate 101 is taken to detect the state of the substrate 101 while the transport operation of the substrate 101 is being performed, the workload can be reduced compared to a case in which the state of the substrate 101 is detected separately from the transport of the substrate 101.

[0052] Furthermore, in the first embodiment, the irradiation unit 50 irradiates the detection light L1 onto the main surface 101a of the substrate 101, the position and / or angle of which are changed relative to the irradiation unit 50. The imaging unit 40 captures images of the detection light L1 reflected from the main surface 101a of the substrate 101 multiple times as the position and / or angle of the substrate 101 relative to the irradiation unit 50 are changed. The control unit 60 detects the state of the substrate 101 based on each of the captured images 71 and 72 generated by capturing the reflected detection light L1 multiple times by the imaging unit 40. As a result, even when the detection light L1 is irradiated onto only a portion of the main surface 101a of the substrate 101, a reflected image of the detection light L1 reflected across the entire main surface 101a of the substrate 101 can be captured by capturing images multiple times as the position and / or angle of the substrate 101 are changed relative to the substrate 101. Therefore, even when the detection light L1 is irradiated onto only a part of the main surface 101a of the substrate 101, the overall state of the substrate 101 can be detected with high accuracy.

[0053] Furthermore, in the first embodiment, when the imaging unit 40 captures the detection light L1, the robot 20 changes at least one of the position and angle of the substrate 101 relatively with respect to the irradiation unit 50. This allows the imaging unit 40 to capture an image of the substrate 101 while accurately adjusting at least one of the position and angle of the substrate 101 with respect to the imaging unit 40 by using the robot 20 to relatively change the position and at least one of the angle of the substrate 101 with respect to the imaging unit 40. As a result, the state of the substrate 101 can be detected with even greater accuracy.

[0054] Furthermore, in the first embodiment, the irradiation unit 50 irradiates the substrate 101 with linear detection light L1 along a direction intersecting the movement direction when the position of the substrate 101 relative to the irradiation unit 50 is changed. This allows the linear detection light L1 to be reflected by the main surface 101 a of the substrate 101, so that the state of the substrate 101 in a continuous region from one end to the other end of the substrate 101 can be acquired based on a reflected image of the linear detection light L1. Therefore, the state of the substrate 101 can be detected with even greater accuracy based on the captured images 71 and 72 captured using the detection light L1 reflected by the main surface 101 a of the substrate 101.

[0055] Furthermore, in the first embodiment, when the imaging unit 40 captures the detection light L1, the robot 20 moves the substrate 101 along a plurality of different movement directions. The control unit 60 detects the state of the substrate 101 based on the captured images 71 and 72 captured for each movement of the substrate 101 along the plurality of movement directions of the robot 20. As a result, by acquiring the captured images 71 and 72 for each movement of the substrate 101 along each of the plurality of different movement directions, it is possible to acquire a plurality of captured images 71 and 72 in which the substrate 101 moves in different directions during imaging. Therefore, the state of the substrate 101 can be detected based on each of the plurality of types of captured images 71 and 72 in which the substrate 101 moves in different directions, thereby enabling the state of the substrate 101 to be detected with even greater accuracy.

[0056] Furthermore, in the first embodiment, the control unit 60 detects the state of the substrate 101, including at least one of the shape, position, and orientation of the substrate 101, and an abnormality occurring in the substrate 101, based on the captured images 71 and 72. This allows the state of the substrate 101, including at least one of the shape, position, and orientation of the substrate 101, and an abnormality occurring in the substrate 101, to be detected with higher accuracy based on the captured images 71 and 72.

[0057] Furthermore, in the first embodiment, the control unit 60 detects the state of the substrate 101 based on each of the captured images 71 and 72, thereby detecting the notch 101b or the orientation flat, which indicates the orientation of the substrate 101. This allows the notch 101b or the orientation flat to be detected based on each of the captured images 71 and 72, making it possible to easily detect the orientation of the substrate 101 based on each of the captured images 71 and 72.

[0058] Furthermore, in the first embodiment, the control unit 60 detects the state of the substrate 101 based on the captured images 71 and 72 by the imaging unit 40 using a trained model 62 generated by machine learning. Here, machine learning can train the trained model 62 to detect states of the substrate 101 that are different from the learned state of the substrate 101 by learning the states of multiple types of substrates 101. For example, when detecting abnormalities in warpage of the substrate 101 using the trained model 62 generated by machine learning, by using the trained model 62 that has learned that warpage at multiple positions and in multiple directions is abnormal, warpage at positions or directions different from the learned warpage can be accurately detected. Therefore, by detecting the state of the substrate 101 based on each of the captured images 71 and 72 using the trained model 62 generated by machine learning, the states of multiple types of substrates 101 can be detected more accurately.

[0059] In the first embodiment, the robot 20 is disposed in the transfer chamber 10 in which the substrate 101 is transferred to a FOUP 110, which serves as a substrate storage container for storing the substrate 101. The irradiation unit 50 is disposed above the robot 20 in the transfer chamber 10 and irradiates the main surface 101a of the substrate 101 with detection light L1. The imaging unit 40 is disposed above the robot 20 in the transfer chamber 10 and captures the detection light L1 reflected by the main surface 101a of the substrate 101. The control unit 60 detects the state of the substrate 101 based on captured images 71 and 72 captured in the transfer chamber 10. This allows the state of the substrate 101 to be detected based on the captured images 71 and 72 while the robot 20 is transferring the substrate 101 to the FOUP 110. Therefore, an increase in the operation time required to detect the state of the substrate 101 can be suppressed compared to when the transfer of the substrate 101 to the FOUP 110 and the detection of the state of the substrate 101 are performed separately.

[0060] Furthermore, in the first embodiment, the substrate transfer robot system 100 includes an aligner 30 as an adjustment device that adjusts the orientation of the substrate 101 in a predetermined direction. The control unit 60 controls the operation of the aligner 30 using the state of the substrate 101 detected based on the captured images 71 and 72. This allows the state of the substrate 101 to be detected in advance based on the captured images 71 and 72, so that the aligner 30 can adjust the orientation of the substrate 101 with the approximate orientation of the substrate 101 detected in advance. This reduces the time required for the aligner 30 to adjust the orientation of the substrate 101.

[0061] Moreover, in the first embodiment, the robot 20 includes a substrate holding hand 22 that holds the substrate 101. The control unit 60 also serves as a robot control unit that controls the transport operation of the robot 20. The control unit 60 detects a deviation in at least one of the position and orientation of the substrate 101 relative to the substrate holding hand 22 based on the detected state of the substrate 101, and corrects the detected deviation in at least one of the position and orientation of the substrate 101 during the transport operation of the robot 20. In this way, the transport operation of the robot 20 can be corrected by detecting the state of the substrate 101 based on each of the captured images 71 and 72, thereby enabling the transport operation by the robot 20 to be performed with greater accuracy.

[0062] Second Embodiment Next, the configuration of a substrate transport robot system 200 according to a second embodiment will be described with reference to Fig. 9. In the second embodiment, the substrate transport robot system 200 is provided with an irradiation unit 250 that irradiates two detection lights L11 and L12, unlike the substrate transport robot system 100 of the first embodiment that is provided with an irradiation unit 50 that irradiates one detection light L1. Note that components similar to those in the first embodiment are denoted by the same reference numerals, and descriptions thereof will be omitted.

[0063] 9 , the substrate transfer robot system 200 according to the second embodiment includes an irradiation unit 250 and a control unit 260. The irradiation unit 250 irradiates the main surface 101a of the substrate 101 with detection light L11 and detection light L12, which are different from each other in line shape. The irradiation unit 250 irradiates the main surface 101a of the substrate 101 with, for example, two detection lights L11 and L12 that extend in directions parallel to each other and have a common shape, such as color and thickness. The detection light L11 and detection light L12 are examples of a "first detection light" and a "second detection light," respectively.

[0064] As with the imaging of the detection light L1 in the first embodiment, the imaging unit 40 captures images of the detection light L11 and the detection light L12 reflected from the main surface 101 a of the substrate 101 multiple times as the robot 20 moves the substrate 101. The control unit 260 captures a single captured image, similar to the captured images 71 and 72 in the first embodiment, by capturing a plurality of reflected detection lights L11 and a plurality of reflected detection lights L12 through multiple imaging by the imaging unit 40. That is, the captured image in the second embodiment includes both the detection light L11 and the detection light L12. Then, as with the captured images 71 and 72 in the first embodiment, the control unit 260 detects the state of the substrate 101 based on the captured image.

[0065] For example, in the second embodiment, the control unit 260 sets the movement speed of the robot 20 when image capturing is performed by the image capturing unit 40 to twice the movement speed of the robot 20 in the first embodiment. The control unit 260 captures both the detection light L11 and the detection light L12 in one captured image. That is, even when the movement speed of the robot 20 is doubled, the control unit 260 irradiates both the detection light L11 and the detection light L12 onto the main surface 101a of one substrate 101 and captures both the detection light L11 and the detection light L12 reflected by one image capturing unit 40, thereby making the total number of the detection light L11 and the detection light L12 included in one captured image the same as the number of the detection light L1 in the first embodiment. The other configurations of the second embodiment are similar to those of the first embodiment.

[0066] Effect of Second Embodiment In the substrate transfer robot system 200 according to the second embodiment, as described above, the irradiation unit 250 irradiates detection light including the detection light L11 as the first detection light and the detection light L12 as the second detection light, which are different from each other in line shape. The control unit 260 detects the state of the substrate 101 based on a single captured image including the detection light L11 and the detection light L12 generated by multiple captures by the imaging unit 40. This allows two line-shaped detection lights, the detection light L11 and the detection light L12, reflected from the main surface 101a of the substrate 101 to be captured in a single capture. This reduces the number of captures required to capture the line-shaped detection light L11 and L12 reflected across the entire main surface 101a of the substrate 101 compared to when a single line-shaped detection light is reflected. This reduces the time required to detect the state of the substrate 101. Note that other effects of the second embodiment are similar to those of the first embodiment.

[0067] Third Embodiment Next, the configuration of a substrate transfer robot system 300 according to a third embodiment will be described with reference to Fig. 10. In the substrate transfer robot system 300 according to the third embodiment, a robot 320 moves the substrate 101 it holds so as to change its angle with respect to the horizontal plane. Note that components similar to those in the first embodiment are denoted by the same reference numerals, and descriptions thereof will be omitted.

[0068] As shown in FIG. 10 , a substrate transfer robot system 300 according to the third embodiment includes a robot 320, an irradiation unit 350, and a control unit 360. The robot 320 includes a robot arm 321 and a substrate holding hand 322. The irradiation unit 350 irradiates the substrate 101 with linear detection light L21 along the YZ plane. That is, the irradiation unit 350 irradiates the main surface 101a of the substrate 101 with linear detection light L21 extending along the Y direction. In the third embodiment, the irradiation unit 350 irradiates the main surface 101a of the substrate 101 with the detection light L21, the angle of which is changed relative to the main surface 101a. The robot 320 changes the angle of the substrate 101 relative to the irradiation unit 350 when the imaging unit 40 captures the detection light L21. The robot 320 has a rotational drive mechanism that rotates the substrate holding hand 322 in the θ direction, with the direction from the base end to the tip of the substrate holding hand 322 as the rotational axis. For example, a rotational drive mechanism such as a servo motor that rotates the substrate holding hand 322, which serves as an end effector, is disposed at the tip of the horizontally articulated robot arm 321. The irradiation unit 350 emits linear detection light L21 along the rotational axis direction of the rotational movement when changing the angle of the substrate 101 relative to the irradiation unit 350. "Along the rotational axis direction" includes a direction parallel to the rotational axis and a direction tilted from the direction parallel to the rotational axis. In other words, the irradiation unit 350 emits linear detection light L21 that extends in a direction not perpendicular to the rotational axis of the substrate holding hand 322. Specifically, the detection light L21 extends in a direction parallel to the rotational axis direction of the rotational movement of the substrate holding hand 322 on the main surface 101a of the substrate 101. In the third embodiment, similarly to the first embodiment, the state of the substrate 101 is detected based on an image captured by the detection light L21 reflected by the main surface 101 a of the substrate 101. When the image capturing unit 40 captures the detection light L21, the robot 320 moves the substrate 101 along a predetermined movement direction so as to change the angle of the substrate 101 held by the substrate holding hand 322 with respect to the horizontal plane. That is, in the third embodiment, the θ direction is an example of the predetermined movement direction.

[0069] To detect the state of the substrate 101, the control unit 360 causes the robot 320 to transport the substrate 101 to a predetermined position where it will be imaged by the imaging unit 40. The control unit 360 then rotates the substrate 101 by tilting the substrate 101 along the θ direction to change its angle with respect to the horizontal plane without changing the position of the substrate 101 in the XY plane. As an example, the control unit 360 rotates the substrate 101 along the θ direction within a range from −5 degrees to +5 degrees, based on a state in which the main surface 101a of the substrate 101 is aligned with the horizontal plane. The imaging unit 40 captures images of the detection light L21 reflected by the main surface 101a of the substrate 101 multiple times as the substrate 101 moves along the θ direction, which is a change in the relative angle of the substrate 101 with respect to the irradiation unit 350. As in the first embodiment, the control unit 360 detects the state of the substrate 101 based on a single captured image generated by capturing multiple images of reflected detection light L21 using the imaging unit 40 multiple times. Detection of the state of the substrate 101 based on the captured image of the detection light L21 is similar to detection of the state of the substrate 101 based on the captured images 71 and 72 in the first embodiment. Other configurations of the third embodiment are similar to those of the first embodiment. For example, the control unit 360 generates multiple captured images by changing the orientation of the substrate holding hand 322 to change the orientation of the rotation axis. Then, the control unit 360 detects the state of the substrate 101 based on the multiple captured images with different orientations of the rotation axis.

[0070] Effect of Third Embodiment As described above, in the third embodiment, the irradiation unit 350 irradiates the substrate 101 with linear detection light L21 along the rotation axis direction of the rotational movement when the relative angle of the substrate 101 with respect to the irradiation unit 350 is changed. This allows the linear detection light L21 to be reflected by the main surface 101 a of the substrate 101, so that the state of the substrate 101 in a continuous region from one end to the other end of the substrate 101 can be obtained based on a reflected image of the linear detection light L21. Therefore, the state of the substrate 101 can be detected with even greater accuracy based on an image captured of the detection light L21 reflected by the main surface 101 a of the substrate 101.

[0071] Furthermore, in the third embodiment, as described above, the robot 320 changes the angle of the substrate 101 with respect to the horizontal plane when the imaging unit 40 captures the detection light L21. This allows the robot 320 to change the angle of the substrate 101 with respect to the horizontal plane, thereby allowing the irradiation angle of the detection light L21 irradiated onto the substrate 101 to be changed three-dimensionally. As a result, the detection light L21 from a wider variety of irradiation directions can be reflected by the main surface 101a of the substrate 101, and the state of the substrate 101 can be detected based on an image captured of the reflected detection light L21, thereby enabling even more accurate detection of the state of the substrate 101. Note that other effects of the third embodiment are similar to those of the first embodiment.

[0072] [Modifications] The embodiments disclosed herein should be considered to be illustrative and not restrictive in all respects. The scope of the present disclosure is defined by the claims, not by the description of the above-mentioned embodiments, and includes all modifications (modifications) within the meaning and scope of the claims.

[0073] For example, in the first, second, and third embodiments, the state of the substrate 101 is detected based on a single captured image generated by capturing multiple line-shaped detection light beams L1, L11, L12, and L21 reflected by the imaging unit 40 multiple times. However, the present disclosure is not limited to this. In the present disclosure, the state of the substrate may be detected based on a captured image of the detection light captured in a single capture. For example, if the detection light beam is a plurality of point light sources in a grid pattern rather than a line pattern, the state of the substrate may be detected by capturing the detection light beam reflected across the entire main surface of the substrate in a single capture. The shape of the detection light irradiated onto the main surface of the substrate is not limited to a line pattern or a grid pattern, and may have a predetermined geometric shape, such as a concentric circle pattern. Furthermore, the irradiation unit may be configured to irradiate detection light having a predetermined color and shape using a projector device that projects an image. Furthermore, the imaging unit may capture multiple images to obtain a single moving image, and the state of the substrate may be detected based on the moving image.

[0074] Furthermore, in the second embodiment described above, an example was shown in which the state of the substrate 101 is detected by the irradiation unit 250 based on a single captured image including the detection light L11 as the first detection light and the detection light L12 as the second detection light, which are parallel to each other and have the same shape. However, the present disclosure is not limited to this. In the present disclosure, when irradiating the substrate 101 with the first detection light and the second detection light, which are two different detection lights, the first detection light and the second detection light may have different shapes or different colors. Furthermore, when the first detection light and the second detection light are both linear, the first detection light and the second detection light may be irradiated so as to intersect with each other. Furthermore, three or more different linear detection lights may be irradiated. Furthermore, when irradiating multiple detection lights, multiple irradiation units may be separately arranged.

[0075] Furthermore, in the first, second, and third embodiments, examples have been described in which the position, orientation, and abnormality of the substrate 101 are detected as the state of the substrate 101 based on the captured images of the detection lights L1, L11, L12, and L21 by using the trained model 62. However, the present disclosure is not limited to this. In the present disclosure, the state of the substrate detected based on the captured images may be at least one of the shape, position, orientation, and abnormality of the substrate. That is, the shape of the substrate may be detected as the state of the substrate. For example, the shape of the substrate's outline may be detected based on the captured images, and the coordinates of the center position of the substrate and a notch or orientation flat may be detected based on the detected shape of the substrate, thereby detecting the position and orientation of the substrate. Furthermore, the abnormality of the substrate detected as the state of the substrate may be one or more of warpage, deformation, chipping, cracks, and scratches on the substrate. For example, only warpage of the substrate may be detected as an abnormality. Furthermore, the state of the substrate may be detected without using a trained model. For example, the state of the substrate may be detected by detecting a linear structure from the captured image using a predetermined algorithm other than the trained model based on captured images of line-shaped detection light captured multiple times as the substrate moves. In this case, the line-shaped detection light may be detected by extracting the center position in the width direction of the line-shaped detection light included in the captured image.

[0076] Furthermore, in the above-described first, second, and third embodiments, an example was described in which an abnormality in the substrate 101 is detected as the state of the substrate 101 based on the captured images 71 and 72 captured at the time the substrate 101 is removed from the FOUP 110 serving as a substrate storage container as the robot 20, 320 moves the substrate 101, and the substrate 101 for which an abnormality is detected is stored back into the FOUP 110. However, the present disclosure is not limited to this. In the present disclosure, the state of the substrate may be detected based on captured images of the substrate that is not being moved by the robot and is in a stationary state. For example, the irradiation unit may be operated to change at least one of the irradiation direction or position of the irradiation unit, thereby moving the substrate held by the robot relative to the irradiation unit. A predetermined detection position may be set in advance, and an abnormality in the substrate may be detected based on captured images of the substrate moved to the predetermined detection position by the robot. Furthermore, when capturing an image by the imaging unit, at least one of the relative position and angle of the substrate with respect to the irradiation unit may not be changed. For example, while the substrate is held by the robot, the imaging unit may capture detection light irradiated from a stationary irradiation unit and reflected by the stationary substrate. The imaging unit may also be movable. The state of the substrate may be detected based on an image captured at the timing when the substrate is stored in a substrate storage container after processing by the processing device. A substrate for which an abnormality has been detected does not need to be returned to the substrate storage container. For example, the substrate for which an abnormality has been detected may be placed in a container or placement position different from the substrate storage container from which the substrate was removed. When an abnormality is detected in a substrate, the imaging unit may capture an image again, thereby again detecting the state of the substrate using the trained model. When capturing an image again, the position, orientation, or movement direction of the substrate may be changed from that of the first image. A signal indicating the detected state of the substrate may be output to a processing device or the like.In addition, by arranging an alarm unit such as a display device on the front side of the transport chamber, information indicating the detected state of the substrate can be notified by displaying text information and outputting audio information, etc.

[0077] Furthermore, in the first and second embodiments, an example was described in which captured image 71 was acquired while the substrate 101 was moving along a predetermined movement direction, and captured image 72 was acquired while the substrate 101 was moving along a different movement direction different from the predetermined movement direction in which captured image 71 was acquired. However, the present disclosure is not limited to this. In the present disclosure, the state of the substrate may be detected based on a single captured image acquired while the substrate is moving along one movement direction, or captured images may be acquired in each of three or more different movement directions. Furthermore, even when multiple captured images are acquired, the multiple captured images may be acquired while the substrate is moving in a common movement direction. Furthermore, images may be acquired while the relative angle between the substrate and the irradiation unit is changed.

[0078] Furthermore, in the third embodiment, an example was described in which the state of the substrate 101 is detected based on captured images of the detection light L21 captured multiple times while the substrate 101 is rotated along the θ direction to change its angle relative to the horizontal plane without changing its position in the XY plane. However, the present disclosure is not limited to this. In the present disclosure, multiple captured images of the substrate at different angles may be obtained by moving the substrate along the horizontal plane while the angles relative to the horizontal plane are different from each other. In this case, the movement direction of the substrate along the horizontal plane may be different from each other. That is, both the relative position and angle of the substrate with respect to the irradiation unit may be changed. In this case, both the relative position and angle of the substrate with respect to the irradiation unit may be changed by a robot. The detection light emitted by the irradiation unit may be a linear detection light extending along a direction intersecting the movement direction when the relative position of the substrate with respect to the irradiation unit is changed, and a linear detection light extending along the rotation axis direction when the relative angle of the substrate with respect to the irradiation unit is changed.

[0079] In the first, second, and third embodiments, examples have been described in which the notch 101b indicating the orientation of the substrate 101 is detected by detecting the state of the substrate 101, but the present disclosure is not limited to this. In the present disclosure, an orientation flat disposed on the substrate may be detected by detecting the state of the substrate.

[0080] Furthermore, in the above-described first, second, and third embodiments, examples have been described in which the transport operation of the robot 20, 320 is corrected to correct at least one of the position and orientation deviations of the substrate 101 detected based on the detected state of the substrate 101, and the operation of the aligner 30 serving as an adjustment device is controlled based on the detected state of the substrate 101. However, the present disclosure is not limited to this. In the present disclosure, the transport operation of the robot may be corrected to correct at least one of the position and orientation deviations of the substrate based on the detected state of the substrate. That is, the transport operation of the robot may be corrected to correct the orientation deviation of the substrate based on the detected state of the substrate. For example, if the orientation of the substrate held by the substrate holding hand differs from a predetermined orientation based on the detected state of the substrate, the operation of the robot may be corrected so that the substrate is transported in the predetermined orientation. Furthermore, when the operation of the aligner serving as an adjustment device is controlled based on the detected state of the substrate, the adjustment device may only adjust the position of the substrate in the rotational direction without detecting the orientation of the substrate. Furthermore, when controlling the operation of an aligner as an adjustment device based on the detected state of the substrate, a notch or orientation flat indicating the orientation of the substrate may be detected as the state of the substrate based on an image captured with the detection light, and the rotation direction of the substrate in the aligner may be set according to the position of the detected notch or orientation flat. In this case, the aligner can rotate the placed substrate in a direction closer to the notch or orientation flat, thereby reducing the time required for the operation of detecting the orientation of the substrate in the aligner.

[0081] Furthermore, in the first, second, and third embodiments, examples have been described in which the robots 20, 320 have horizontally articulated robot arms 21, 321, respectively. However, the present disclosure is not limited to this. In the present disclosure, the robot arm may have a vertically articulated robot arm instead of a horizontally articulated robot arm. The robot may also have a linear movement mechanism such as a slide mechanism. The substrate holding hand may be an active type hand that fixes and holds the substrate using a vacuum or a chuck. Furthermore, the substrate may be rotated and tilted relative to a horizontal plane while the substrate is fixed, thereby capturing images of the detection light reflected from each of the main surfaces on both sides of the substrate.

[0082] Furthermore, in the above-described first, second, and third embodiments, the substrate transport robot system 100 according to the present disclosure is an EFEM that transports the substrate 101 to the processing device 401. However, the present disclosure is not limited to this. In the present disclosure, the substrate transport robot system may be a system other than an EFEM. For example, the substrate transport robot system may be a stocker or sorter that transports substrates from one substrate storage container to another. Furthermore, the substrate transport robot system may transport substrates transported by a belt conveyor or the like to a substrate storage container or a substrate placement unit, rather than a substrate storage container. Furthermore, substrate state detection according to the present disclosure may be applied to a system that transports substrates on the processing device side. That is, when a substrate is transported between a load lock unit and a processing module unit, the substrate state may be detected using the substrate detection method according to the present disclosure.

[0083] Furthermore, in the first, second, and third embodiments, examples have been described in which the control unit 60, 260, or 360 of the substrate transport robot system 100 generates the trained model 62, detects abnormalities in the substrate 101 based on the captured images 71 and 72, and controls the operation of the robot 20 or 320. However, the present disclosure is not limited to this. In the present disclosure, at least one of generating the trained model and controlling the operation of the robot may be performed by a control device different from the control unit that detects abnormalities in the substrate based on the captured images. For example, the trained model may be generated by a control device located separately from the robot. That is, the trained model may be generated by machine learning performed by a control device located separately from the substrate transport robot system, such as an EFEM. Furthermore, the control unit that detects the state of the substrate based on the captured images may be located separately from the robot control unit that controls the operation of the robot.

[0084] Furthermore, in the first, second, and third embodiments, examples have been described in which the imaging unit 40 and the irradiation units 50, 250, and 350 are disposed inside the transfer chamber 10, but the present disclosure is not limited to this. In the present disclosure, any of the marking member, imaging unit, and irradiation unit may be disposed outside the transfer chamber in which the substrate is transported. For example, when detecting abnormalities in a substrate in a transfer chamber of a processing device that processes the substrate, the ceiling of the transfer chamber of the processing device may be made of a transparent material such as glass, and the marking member, imaging unit, and irradiation unit may be disposed above and outside the transfer chamber.

[0085] Furthermore, in the first, second, and third embodiments, examples have been described in which the irradiation units 50, 250, and 350 irradiate the detection lights L1, L11, L12, and L21 at the timing when the imaging unit 40 captures an image. However, the present disclosure is not limited to this. In the present disclosure, the irradiation of illumination light by the irradiation units may be continuously performed. Furthermore, the irradiation of illumination light may be controlled by a control process performed by the control unit based on the captured image. For example, control may be performed to change the light intensity, wavelength, etc. of the illumination light based on the luminance value, etc., of the captured image. Furthermore, when an abnormality in the substrate is detected, the illumination light may be controlled to change the light intensity, wavelength, etc. of the illumination light, and then the captured image may be captured again, thereby detecting the abnormality in the substrate again using the trained model. Furthermore, an illumination unit that irradiates illumination light may be arranged in the transfer chamber separately from the irradiation unit.

[0086] Furthermore, in the above-described first, second, and third embodiments, examples have been described in which the irradiation units 50, 250, and 350 include LEDs that emit red light as the detection light L1, L11, and L12, L21, but the present disclosure is not limited to this. In the present disclosure, the irradiation units may include light source devices other than LEDs. Furthermore, the illumination light emitted by the irradiation units may have a wavelength of a predetermined color other than red. Furthermore, the illumination light may be light with a wavelength other than visible light, such as infrared light. Furthermore, the number of irradiation units may be one or three or more.

[0087] Furthermore, in the above-described first, second, and third embodiments, an example was shown in which three FOUPs 110 serving as substrate storage containers were attached to the transfer chamber 10 of the substrate transfer robot systems 100, 200, and 300, and three imaging units 40 and three irradiation units 50, 250, and 350 were arranged corresponding to the FOUPs 110, respectively. However, the present disclosure is not limited to this. In the present disclosure, the number of substrate storage containers attached to the transfer chamber may be two or less, or four or more. Furthermore, one imaging unit and one irradiation unit may be arranged for multiple substrate storage containers. In this case, a common imaging unit captures images of substrates being transferred to the multiple substrate storage containers. Furthermore, the number of imaging units and the number of irradiation units may be different from each other.

[0088] Furthermore, in the above first, second, and third embodiments, an example has been described in which the trained model 62 is generated by machine learning of deep learning using a full-layer convolutional network, but the present disclosure is not limited to this. In the present disclosure, the machine learning for generating the trained model does not have to be deep learning. Furthermore, the machine learning for generating the trained model may be machine learning using a convolutional neural network other than a full-layer convolutional network. Furthermore, the machine learning for generating the trained model may be machine learning other than a convolutional neural network.

[0089] Furthermore, in the first, second, and third embodiments, an example was shown in which the substrate 101 whose state is to be detected is a disk-shaped silicon wafer, but the present disclosure is not limited to this. In the present disclosure, the substrate 101 may be a material other than silicon. Furthermore, the state of a rectangular substrate on which electronic components are mounted may be detected instead of a disk-shaped substrate. In this case, the state of the substrate, including its orientation and position, may be detected by detecting the sides of the rectangle.

[0090] Furthermore, in the above first, second, and third embodiments, an example has been shown in which an abnormality in the substrate 101 is detected by using the trained model 62 that receives as input the captured images of the detection lights L1, L11, L12, and L21 captured by the imaging unit 40 and outputs the identification result 75, but the present disclosure is not limited to this. In the present disclosure, image processing such as noise removal, edge enhancement, and contrast change may be performed in advance on the captured images to be input to the trained model for detecting abnormalities in the substrate before inputting them to the trained model.

[0091] The functions of the elements disclosed herein can be performed using circuits or processing circuits, including general-purpose processors, special-purpose processors, integrated circuits, ASICs (Application Specific Integrated Circuits), conventional circuits, and / or combinations thereof, configured or programmed to perform the disclosed functions. A processor is considered a processing circuit or circuit because it includes transistors and other circuitry. In this disclosure, a circuit, unit, or means is hardware that performs the recited functions or hardware that is programmed to perform the recited functions. The hardware may be hardware disclosed herein or other known hardware that is programmed or configured to perform the recited functions. Where the hardware is a processor, which is considered a type of circuit, the circuit, means, or unit is a combination of hardware and software, and the software is used to configure the hardware and / or processor.

[0092] Aspects It will be appreciated by those skilled in the art that the exemplary embodiments described above are examples of the following aspects.

[0093] (Aspect 1) A substrate transport robot system comprising: a robot that transports a substrate; an irradiation unit that irradiates a main surface of the substrate held by the robot with detection light having a predetermined shape; an imaging unit that images the substrate to capture the detection light reflected by the main surface of the substrate; and a control unit that detects a state of the substrate based on the captured image of the detection light captured by the imaging unit.

[0094] (Aspect 2) A substrate transport robot system according to Aspect 1, wherein the irradiation unit irradiates the detection light onto the main surface of the substrate, the main surface being changed in at least one of its position and angle relative to the irradiation unit; the imaging unit captures images of the detection light reflected from the main surface of the substrate multiple times as the position and angle of the substrate relative to the irradiation unit changes; and the control unit detects the state of the substrate based on one of the captured images generated by capturing the multiple reflected detection light beams through multiple imaging by the imaging unit.

[0095] (Aspect 3) The substrate transport robot system according to aspect 2, wherein the robot changes at least one of the position and angle of the substrate relative to the irradiation unit when the imaging unit captures the detection light.

[0096] (Aspect 4) A substrate transport robot system according to Aspect 2 or Aspect 3, wherein the irradiation unit irradiates at least one of the detection light in a line shape along a direction intersecting the movement direction when the relative position of the substrate with respect to the irradiation unit is changed, and the detection light in a line shape along the rotation axis direction of the rotational movement when the relative angle of the substrate with respect to the irradiation unit is changed.

[0097] (Aspect 5) A substrate transport robot system as described in Aspect 3, wherein the robot moves the substrate along a plurality of different movement directions when the imaging unit captures the detection light, and the control unit detects the state of the substrate based on the captured images during each of the movements of the substrate along the plurality of movement directions of the robot.

[0098] (Aspect 6) The substrate transport robot system according to aspect 3, wherein the robot changes an angle of the substrate with respect to a horizontal plane when the imaging unit captures the detection light.

[0099] (Aspect 7) A substrate transport robot system according to any one of Aspects 1 to 6, wherein the control unit detects the state of the substrate, including at least one of the shape, position, and orientation of the substrate, and an abnormality occurring in the substrate, based on the captured image.

[0100] (Aspect 8) The substrate transfer robot system according to aspect 7, wherein the control unit detects a notch or an orientation flat indicating an orientation of the substrate by detecting a state of the substrate based on the captured image.

[0101] (Aspect 9) The substrate transport robot system according to any one of Aspects 1 to 8, wherein the control unit detects a state of the substrate based on the image captured by the imaging unit using a trained model generated by machine learning.

[0102] (Aspect 10) A substrate transport robot system according to any one of Aspects 2 to 6, wherein the irradiation unit irradiates the detection light including first and second detection lights that are different from each other in a line shape, and the control unit detects the state of the substrate based on the one captured image including the first and second detection lights that is generated by capturing images multiple times by the imaging unit.

[0103] (Aspect 11) A substrate transport robot system according to any one of Aspects 1 to 10, wherein the robot is disposed in a transport chamber in which the substrate is transported to a substrate storage container in which the substrate is stored, the irradiation unit is disposed above the robot within the transport chamber and irradiates the detection light onto the main surface of the substrate, the imaging unit is disposed above the robot within the transport chamber and images the detection light reflected by the main surface of the substrate, and the control unit detects a state of the substrate based on the image captured within the transport chamber.

[0104] (Aspect 12) The substrate transport robot system according to any one of Aspects 1 to 11, further comprising an adjustment device that adjusts the orientation of the substrate in a predetermined direction, wherein the control unit controls the operation of the adjustment device using a state of the substrate detected based on the captured image.

[0105] (Aspect 13) A substrate transport robot system according to any one of Aspects 1 to 12, wherein the robot includes a substrate holding hand that holds the substrate, and the control unit also serves as a robot control unit that controls the transport operation of the robot, and detects a deviation in at least one of the position and orientation of the substrate relative to the substrate holding hand based on the detected state of the substrate, and corrects the detected deviation in at least one of the position and orientation of the substrate during the transport operation of the robot.

[0106] (Aspect 14) A substrate detection method comprising: imaging a substrate held by a robot that transports the substrate, capturing detection light having a predetermined shape reflected on a main surface of the substrate; and detecting a state of the substrate based on the captured image of the detection light.

Claims

1. A substrate transport robot system comprising: a robot that transports a substrate; an irradiation unit that irradiates a main surface of the substrate held by the robot with detection light having a predetermined shape; an imaging unit that images the substrate, thereby capturing an image of the detection light reflected by the main surface of the substrate; and a control unit that detects a state of the substrate based on an image of the detection light captured by the imaging unit.

2. A substrate transport robot system as described in claim 1, wherein the irradiation unit irradiates the detection light onto the main surface of the substrate, the position and / or angle of which is changed relative to the irradiation unit; the imaging unit captures images of the detection light reflected from the main surface of the substrate multiple times as the position and / or angle of the substrate changes relative to the irradiation unit; and the control unit detects the state of the substrate based on one of the captured images generated by capturing the multiple reflected detection light beams through multiple imaging by the imaging unit.

3. A substrate transport robot system as described in claim 2, wherein the robot changes at least one of the position and angle of the substrate relative to the irradiation unit when the imaging unit captures the detection light.

4. A substrate transport robot system as described in claim 2, wherein the irradiation unit irradiates at least one of the detection light in a line shape along a direction intersecting the movement direction when the relative position of the substrate to the irradiation unit is changed, and the detection light in a line shape along the rotation axis direction of the rotational movement when the relative angle of the substrate to the irradiation unit is changed.

5. A substrate transport robot system as described in claim 3, wherein the robot moves the substrate along a plurality of different movement directions when the imaging unit captures the detection light, and the control unit detects a state of the substrate based on the captured images during each of the movements of the substrate along the plurality of movement directions of the robot.

6. The substrate transport robot system according to claim 3, wherein the robot changes an angle of the substrate with respect to a horizontal plane when the imaging unit captures the detection light.

7. A substrate transport robot system as described in claim 1, wherein the control unit detects the condition of the substrate, including at least one of the shape, position, orientation, and abnormality occurring in the substrate, based on the captured image.

8. A substrate transport robot system as described in claim 7, wherein the control unit detects a notch or an orientation flat indicating an orientation of the substrate by detecting a state of the substrate based on the captured image.

9. A substrate transport robot system as described in claim 1, wherein the control unit detects the state of the substrate based on the image captured by the imaging unit using a trained model generated by machine learning.

10. A substrate transport robot system as described in claim 2, wherein the irradiation unit irradiates the detection light including first detection light and second detection light that are different from each other in a line shape, and the control unit detects the state of the substrate based on the one captured image including the first detection light and the second detection light generated by multiple imaging by the imaging unit.

11. A substrate transport robot system as described in claim 1, wherein the robot is disposed in a transport chamber in which the substrate is transported to a substrate storage container in which the substrate is stored, the irradiation unit is disposed above the robot within the transport chamber and irradiates the detection light onto the main surface of the substrate, the imaging unit is disposed above the robot within the transport chamber and images the detection light reflected by the main surface of the substrate, and the control unit detects a state of the substrate based on the image captured within the transport chamber.

12. A substrate transport robot system as described in claim 1, further comprising an adjustment device that adjusts the orientation of the substrate to a predetermined direction, wherein the control unit controls the operation of the adjustment device using the state of the substrate detected based on the captured image.

13. A substrate transport robot system as described in claim 1, wherein the robot includes a substrate holding hand that holds the substrate, and the control unit also serves as a robot control unit that controls a transport operation of the robot, and detects a deviation in at least one of the position and orientation of the substrate relative to the substrate holding hand based on the detected state of the substrate, and corrects the detected deviation in at least one of the position and orientation of the substrate during the transport operation of the robot.

14. A substrate detection method, comprising: imaging a substrate held by a robot that transports the substrate, capturing an image of detection light having a predetermined shape reflected by a main surface of the substrate; and detecting a state of the substrate based on the captured image of the detection light.

Images