Method and system for operating a laboratory automation system

Abstract

The present disclosure relates to a method for operating a laboratory automation system (1), the laboratory automation system (1) including a carrier (10) including a receiving location (11) for receiving a sample container (12) configured to hold a sample to be analyzed by a laboratory device (13), a placement device (14) configured to pick and place the sample container (12), an imaging device (15), and a data processing device (16) including at least one processor (17) and a memory (18). The method includes detecting an image of the receiving location (11) by an imaging device (15), determining in a data processing device (16) whether the receiving location (11) is free and configured to receive the sample container (12) by applying a machine learning algorithm for image analysis of the image of the receiving location (11), and if the receiving location (11) is determined to be free and configured to receive the sample container (12), placing the sample container (12) at the receiving location (11) by a placement device (14).Furthermore, a laboratory automation system (1) is disclosed.

Description

[Technical Field]

[0001] The present disclosure refers to a method for operating a laboratory automation system and a system for operating a laboratory automation system. [Background technology]

[0002] Laboratory automation systems are used to determine samples, such as samples of body fluids, in an automated manner. Each sample is typically received in a sample container that is processed through the laboratory automation system.

[0003] A laboratory automation system may include multiple units. A laboratory automation system usually includes multiple laboratory stations, such as pre-analytical, analytical, or post-analytical stations. Typically, sample containers are transported on transport carriers between different stations of the system via a sample distribution system / transport system. Transport carriers, with or without sample containers, can be moved along a line for processing samples. Sample containers can be supplied to the laboratory automation system via trays containing multiple sample containers. A loading device can remove sample containers from the tray and load them into receiving locations on the transport carrier, or vice versa.

[0004] U.S. Patent Application Publication No. 2018 / 0045747 discloses a method for tube slot location using a tray coordinate system and a camera coordinate system. The method includes receiving a series of images from at least one camera of a tray containing tube slots arranged in a matrix of rows and columns. The method includes determining calibration information to provide a mapping of positions from the tray coordinate system to positions from the camera coordinate system, and automatically aligning the tray based on the encoder values ​​and the calibration information.

[0005] The document US Patent No. 10,319,092 describes a method for detecting characteristics of sample tubes, which comprises extracting image patches substantially centered on a tube slot of a tray or on the top of a tube within a slot. For each image patch, the method comprises assigning a first set of locations defining whether the image patch is at the image center, a corner of the image, or a central edge of the image, selecting a trained classifier based on the first set of locations, and determining whether the respective tube slot holds a tube.

[0006] The document U.S. Pat. No. 10,290,090 discloses a method using image-based tube top circle detection, which involves extracting a region of interest patch from one of a series of images of a tube tray, the region of interest having a target tube top circle and a boundary constrained by a two-dimensional projection of the circle centers of different types of tube tops.

[0007] Document US Pat. No. 1,014,0705 relates to a method and system for detecting characteristics of sample tubes in a laboratory environment, including a drawer vision system that can be trained and calibrated.

[0008] Document WO 2019 / 013960 discloses an image-based detection method for sample tube tops for use in automated diagnostic analysis systems, based on a convolutional neural network for pre-processing images of sample tube tops to enhance the edges of the tube top circles while suppressing edge responses from other objects that may appear in the image.

[0009] Document EP 3581935 A1 relates to a method for operating a system for the automatic detection of laboratory work items and their status in the area of ​​target storage locations in a laboratory work area.

[0010] The document US 10274505 relates to an analytical laboratory system and method for processing samples, in which sample containers are transported from an input area to a distribution area by a gripper including means for inspecting the tubes, and images of the sample containers are captured and analyzed to determine the identity of the sample containers.

[0011] Document WO 2019 / 084468 provides a system and method for recognizing various sample containers carried in a rack, where the sample containers in the rack are identified and various characteristics associated with the containers and the rack are detected and evaluated to determine the validity and type of the containers in the rack.

[0012] Document US 9135515 discloses a method for visually inspecting pelleted samples, which produces an inspection image of the bottom of a sample tube holder.

[0013] The system of document EP 2776844 comprises an image acquisition device configured to acquire images of one or more of the sample vessels in the sample vessel holder, and an image analysis device coupled to the image acquisition device.

[0014] In document US 10509047 a method and device for handling sample tubes is presented, in which the position of the sample tube is identified and the sample tube is handled depending thereon.

[0015] Document EP 3330713 A1 relates to a laboratory handling system comprising several racks, each adapted to carry several laboratory sample containers, a rack mounting unit on which the racks are mounted, and a rack detection unit adapted to detect the position and / or type of the rack mounted on the rack mounting unit.

[0016] U.S. Patent Application Publication No. 2017 / 124704 describes a method and system for detecting characteristics of sample tubes in a laboratory environment, including a drawer vision system that can be trained and calibrated. Images of a tube tray captured by at least one camera are analyzed to extract image patches that enable a processor to automatically determine whether a tube slot is occupied, whether a tube has a cap, and whether a tube has a cup at the top of the tube. The processor can be trained using random forest techniques and multiple training image patches. The camera can be calibrated using a three-dimensional calibration target that can be inserted into the drawer. Summary of the Invention

[0017] It is an object of the present disclosure to provide a method for operating a laboratory automation system and a laboratory automation system that provides improved flexibility and safety with regard to the placement of sample containers.

[0018] To solve this problem, there is provided a method for operating a laboratory automation system according to independent claim 1. Furthermore, there is provided a system for operating a laboratory automation system according to independent claim 16. Further embodiments are disclosed in the dependent claims.

[0019] According to one aspect, a method for operating a laboratory automation system is provided, the laboratory automation system including: a carrier including a receiving location for receiving a sample container configured to hold a sample to be analyzed by a laboratory device; a loading device configured to pick and place the sample container; an imaging device; and a data processing device including at least one processor and memory. The method includes detecting an image of the receiving location by the imaging device; determining in the data processing device whether the receiving location is free and configured to receive the sample container by applying a machine learning algorithm for image analysis of the image of the receiving location; and if the receiving location is determined to be free and configured to receive the sample container, loading the sample container into the receiving location by the loading device.

[0020] According to another aspect, there is provided a laboratory automation system including a carrier including a receiving location for receiving a sample container configured to hold a sample to be analyzed by a laboratory device, a loading device for picking and placing the sample container, an imaging device, and a data processing device including at least one processor and a memory, the system being configured to: detect an image of the receiving location by the imaging device; determine in the data processing device whether the receiving location is free and configured to receive the sample container by applying a machine learning algorithm for image analysis of the image of the receiving location; and, if the receiving location is determined to be free and configured to receive the sample container, load the sample container into the receiving location by the loading device.

[0021] As a result, errors in the laboratory automation system due to loading the wrong type of sample container or carrier into the machine, loading in the wrong position, incorrect loading, or not leaving the receiving location free can be handled and / or prevented.

[0022] Within the context of the present disclosure, a carrier may generally refer to a device for receiving a sample vessel or multiple sample vessels. A carrier may also refer to a rack or tray.

[0023] The system may include a laboratory device, which may be configured, for example, to analyze a sample, which may include a bodily fluid.

[0024] The receiving location may include a recess (slot) in the carrier. Additionally or alternatively, the receiving location may include a protrusion on the carrier. The receiving location may have a receiving location bottom surface and a receiving location side surface. The receiving location depth of the receiving location may be the vertical difference between the receiving location bottom surface and the receiving location top edge. The receiving location bottom surface shape and / or the receiving location top surface shape may be any of a disk, a polygon, a rectangle, a square, and an ellipse. The receiving location bottom angle between the receiving location bottom surface and the receiving location side surface may be 90° or more, preferably 90° or more and less than 150°, more preferably 90° or more and less than 100°, and most preferably 90° or more and less than 95°.

[0025] The receiving location, specifically the slot, may have one of a cylindrical shape, a conical shape, a polyhedral shape, a cubic shape, and a rectangular parallelepiped shape. The cylindrical shape may be one of a cylindrical shape, an elliptical cylindrical shape, and a prismatic shape.

[0026] The sample vessel may have a vessel bottom surface, vessel sides, and a vessel top surface. The vessel height of the sample vessel may correspond to the vertical difference between the vessel bottom surface and the vessel top surface.

[0027] The container bottom surface shape and / or the container top surface shape may be one of a disk, a polygon, a rectangle, a square, and an ellipse. The container bottom angle between the container bottom surface and the container side surface may be 90° or more, preferably 90° or more and less than 150°, more preferably 90° or more and less than 100°, and most preferably 90° or more and less than 95°. The angle difference between the receiving location bottom angle and the container bottom angle may be less than 30°, preferably less than 10°. The receiving location bottom angle and the container bottom angle may be the same.

[0028] The sample vessel may have one of a cylindrical shape, a conical shape, a polyhedral shape, a cubic shape, and a rectangular parallelepiped shape. The receiving location and the sample vessel may have the same shape or different shapes. The sample vessel may be a sample tube.

[0029] Determining whether the receiving location is configured to accept a sample container may include determining the type of receiving location from the image using a machine learning algorithm.

[0030] Determining whether a receiving location is configured to receive a sample container may be performed in response to determining whether the receiving location is free to receive a sample container. Specifically, determining whether a receiving location is configured to receive a sample container may be performed in response to determining that the receiving location is free to receive a sample container. In other words, it may be provided that determining whether a receiving location is configured to receive a sample container is performed (only) for receiving locations that are free to receive a sample container.

[0031] It may also be provided that determining whether the receiving location is free to receive the sample container and determining whether the receiving location is configured to receive the sample container are performed simultaneously, in particular by applying a machine learning algorithm for image analysis of an image of the receiving location in a data processing device.

[0032] Determining the type of receiving location from the image may include classifying the type of receiving location with a machine learning algorithm. In this or other embodiments, the machine learning algorithm may include, for example, an artificial neural network. The machine learning algorithm may include a supervised learning algorithm, such as a support vector machine, decision tree learning, or similarity learning. The machine learning algorithm may also include a pattern matching algorithm. The type of receiving location may be associated with a class label, for example.

[0033] The method may further comprise comparing the receiving location type with the container type of the sample container and, if the receiving location type is assigned to the container type, determining a receiving location configured to receive the sample container. In one embodiment, it may be provided that each receiving location type is assigned to at least one, preferably exactly one, container type. If the receiving location type and the container type geometrically match, the receiving location type may be assigned to the container type.

[0034] In another embodiment, the method may further include the receiving location type indicating a receiving location bottom diameter that is smaller than the bottom diameter upper limit and / or larger than the bottom diameter lower limit. The receiving location type may also include a receiving location top diameter that is smaller than the top diameter upper limit and / or larger than the top diameter lower limit. The receiving location bottom diameter may be the diameter of the receiving location bottom surface. The receiving location top diameter may be the diameter of the area enclosed by the top edge of the receiving location.

[0035] The upper limit of the bottom diameter may be 7 mm to 20 mm, preferably 9 mm to 15 mm, more preferably 13 mm (depending on the type of receiving location). The lower limit of the bottom diameter may be 6 mm to 19 mm, preferably 8.5 mm to 14.5 mm, more preferably 12.8 mm. The upper limit of the top diameter may be 7 mm to 20 mm, preferably 9 mm to 15 mm, more preferably 13 mm. The lower limit of the top diameter may be 6 mm to 19 mm, preferably 8.5 mm to 14.5 mm, more preferably 12.8 mm.

[0036] The bottom diameter upper limit may be less than the top diameter upper limit. Alternatively, the bottom diameter upper limit and the top diameter upper limit may be the same. The bottom diameter lower limit may be less than the top diameter lower limit. Alternatively, the bottom diameter lower limit and the top diameter lower limit may be the same. The bottom diameter lower limit may be less than the bottom diameter upper limit. Alternatively, the bottom diameter lower limit and the bottom diameter upper limit may be the same. The top diameter lower limit may be less than the top diameter upper limit. Alternatively, the top diameter lower limit and the top diameter upper limit may be the same.

[0037] A receiving location may also be determined to be configured to receive a sample container if at least a first difference between the receiving location bottom diameter and the container bottom diameter is 0.0% to 5.0% of the receiving location bottom diameter, preferably 0.5% to 2.0% of the receiving location bottom diameter, and more preferably 1.0% of the receiving location bottom diameter. Alternatively, the first difference may be 0% to 5.0% of the container bottom diameter, preferably 0% to 2.0% of the container bottom diameter, and more preferably 0.1% of the container bottom diameter. Still alternatively, the first difference may be 0 mm to 4.0 mm, preferably 0 mm to 2.0 mm, and more preferably 0.1 mm.

[0038] The method may further include the receiving location type indicating a receiving location depth that is less than an upper depth limit and / or greater than a lower depth limit. The upper depth limit may be 50 mm to 210 mm, preferably 80 mm to 180 mm, more preferably 100 mm. The lower depth limit may be 40 mm to 200 mm, preferably 75 mm to 175 mm, more preferably 99 mm. The lower depth limit may be less than the upper depth limit. Alternatively, the lower depth limit and the upper depth limit may be the same.

[0039] A receiving location may also be determined to be configured to receive a sample container if at least a second difference between the receiving location depth and the container height is between 1% and 80% of the receiving location depth, preferably between 5% and 50% of the receiving location depth, and more preferably between 20% of the receiving location depth. The second difference may also be between 1% and 80% of the container height, preferably between 5% and 50% of the container height, and more preferably between 20% of the container height. Further alternatively, the second difference may be between 1.0 mm and 5.0 cm, preferably between 5.0 mm and 2.5 cm, and more preferably 2.0 cm.

[0040] In one embodiment, the method may further include indicating a receiving location bottom angle between the receiving location bottom surface and the receiving location side surface of the receiving location that is less than an upper bottom angle limit and / or greater than a lower bottom angle limit. The upper bottom angle limit may be between 90° and 150°, preferably between 90° and 110°, and more preferably between 90° and 95°. The lower bottom angle limit may be between 89° and 170°, preferably between 90° and 105°, and more preferably between 90° and 92°. The receiving location type may include a receiving location top angle that is less than an upper top angle limit and / or greater than a lower top angle limit.

[0041] The upper limit of the top angle can be 90° to 150°, preferably 90° to 110°, and more preferably 90° to 95°.The lower limit of the top angle can be 89° to 170°, preferably 90° to 105°, and more preferably 90° to 92°.

[0042] The receiving location type may further include at least one of a receiving location bottom surface shape, a receiving location top surface shape, a receiving location side surface shape, and a receiving location notch indicator that indicates that the receiving location has a side notch.

[0043] The method may also include determining at least one of a receiving location bottom surface shape, a receiving location top surface shape, a receiving location bottom diameter, a receiving location top diameter, a receiving location depth, a receiving location bottom angle, a receiving location top angle, and a receiving location notch indicator from the determined receiving location type. Further, the method may include comparing at least one of a receiving location bottom surface shape, a receiving location top surface shape, a receiving location bottom diameter, a receiving location top diameter, a receiving location depth, a receiving location bottom angle, a receiving location top angle, and a receiving location notch indicator from the determined receiving location type with a value for a corresponding container type. From the comparison, it may also be determined that the receiving location is configured to receive a sample container.

[0044] Generally, at least one of the receiving location bottom surface shape, receiving location top surface shape, receiving location bottom diameter, receiving location top diameter, receiving location depth, receiving location bottom angle, receiving location top angle, receiving location notch indicator, lateral alignment, and receiving locations available for receiving sample containers can be determined by applying a machine learning algorithm.

[0045] Receiving locations that are free to receive a sample container may in particular include empty receiving locations, in particular receiving locations that have not received a (further) sample container. Receiving locations that are not free to receive a sample container may in particular include receiving locations that are not empty, in particular receiving locations that have received a (further) sample container.

[0046] The method can include providing container type data in a memory indicative of a container type, wherein the container type data can be indicative of at least one of the following: a container bottom surface shape, a container top surface shape, a container bottom diameter, a container top diameter, a container height, a container bottom angle, a container top angle, and a container notch indicator indicative of the presence of a side notch on the container.

[0047] The method may include scanning a sample container with a scanning device and providing a container type from a database in response to scanning the sample container with the scanning device. The scanning may include scanning a tag on the sample container. The tag may be, for example, a bar code or a QR code.

[0048] The database may be stored in the memory of the data processing device. Alternatively, the database may be stored in an external data processing device, and preferably transmitted to the data processing device from an external data processing device. The database may include assignments of receiving location types to container types and / or assignments of container types to receiving location types.

[0049] Alternatively, the container type may be provided via time scheduling information and / or location information data. For example, sample containers of a particular container type (corresponding to a particular receiving location type) may be provided at a particular time and / or location. The container type may be provided from a database.

[0050] The method may further include detecting a second image of the receiving location by the imaging device and determining the container type from the second image using a machine learning algorithm. Alternatively, the method may further include detecting a second image of the receiving location by a second imaging device different from the imaging device, and providing the container type may include determining the container type from the second image using a machine learning algorithm. The second imaging device may be a camera. The image and / or the second image may be transmitted from the imaging device (respectively, the second imaging device) to a data processing device.

[0051] Placing the sample container at the receiving location may include moving the sample container horizontally and / or vertically with a loading device. The loading device may include a gripping device for mechanically gripping and / or releasing the sample container.

[0052] If it is determined that the receiving location is not available and / or is not configured (suitable) to receive the sample container, an error signal may be generated by the data processing device, in which case the sample container may not be placed in the receiving location.

[0053] The method may further include determining a lateral location of the receiving location from the image, for example, via a machine learning algorithm or a further machine learning algorithm. The lateral location may be, for example, relative to at least one of a carrier, a loading device, a dispensing device including the loading device, and a laboratory automation system. Determining the lateral location of the receiving location may include determining a center point of the receiving location. The receiving location may be determined to be not configured to receive the sample container if the center point of the receiving location is displaced from a reference point by more than a threshold value.

[0054] Detecting the image may include detecting an image of only one receiving location. Alternatively, detecting the image may include detecting images of multiple receiving locations. The image may include a top view of the receiving location. The image may also include a side view, a bottom view, or an oblique view of the receiving location.

[0055] The method may include providing an imaging device attached to the mounting apparatus. Specifically, the imaging device may be configured to move with the mounting apparatus during operation of the mounting apparatus. Alternatively, the imaging device may be (physically) separate from the mounting apparatus. The imaging device may be, for example, a camera.

[0056] The method may further include determining at least one trained pattern via a machine learning algorithm using training images showing the receiving location, specifically showing the type of receiving location. The training may be performed in the data processing device. Alternatively, the training may be performed in a further external data processing device. The trained model may then be transmitted to the data processing device from the further external data processing device.

[0057] Determining the at least one trained pattern may specifically include processing training images illustrating different receiving location types having different receiving location bottom surface shapes, receiving location top surface shapes, receiving location bottom diameters, receiving location top diameters, receiving location depths, receiving location bottom angles, receiving location top angles, and receiving location notch indicators. Further, the training images may illustrate receiving locations that are open or closed to receive sample containers.

[0058] The determined trained pattern / trained model may be provided to a data processing device. Determining whether a receiving location is configured to receive a sample container may include processing at least one trained pattern. Specifically, classifying the type of receiving location may include processing at least one trained pattern.

[0059] Placing the sample container in the receiving location may include verifying an expected container height of the sample container by (e.g., vertical) movement of the mounting device. Preferably, the verification result of the expected container height may be used to determine a further trained pattern via a machine learning algorithm. Alternatively, the verification result of the expected container height may be used to determine at least one further trained pattern via a machine learning algorithm.

[0060] Verifying the expected container height of the sample container may include, for example, recording the vertical distance moved by the mounting device to place the sample container at the receiving location. From the vertical distance, the measured container height of the sample container may be determined, for example, by subtracting an offset value from the vertical distance. The offset value may depend on at least one of the first default vertical orientation of the mounting device, the second default vertical orientation of the carrier, the carrier height, and the vertical gripping position of the mounting device, specifically the vertical gripping position of the mounting device relative to the sample container, when gripping the sample container for loading.

[0061] The expected container height may be determined from a scan of the sample container by a scanning device and / or by determining the container type from the second image.

[0062] It may be provided that if the measured container height is equal to or within a tolerance limit of the expected container height, the verification result is deemed positive. Otherwise, the verification result is deemed negative. The tolerance limit may be, for example, less than 5% of the expected container height, preferably less than 1% of the expected container height.

[0063] The embodiments described above in relation to a method for operating a laboratory automation system may be provided in correspondence with the laboratory automation system.

[0064] Description of Further Embodiments Further embodiments are described below by way of example with reference to the figures. [Brief explanation of the drawings]

[0065] [Figure 1] Schematic diagram of the laboratory automation system. [Figure 2] View of the carrier and sample container from a side view. [Figure 3] 1 is a diagram of a method for operating a laboratory automation system. DETAILED DESCRIPTION OF THE INVENTION

[0066] 1 shows a diagrammatic representation of a laboratory automation system 1. The laboratory automation system 1 includes a carrier 10 including a receiving location 11 for receiving a sample container 12 configured to hold a sample to be analyzed by a laboratory device 13. The laboratory automation system further includes a loading device 14 configured to pick and place the sample container 12, an imaging device 15, such as a camera, attached to the loading device 14, and a data processing device 16 including at least one processor 17 and a memory 18. Additionally, a scanning device 19 (e.g., a barcode scanner) may be provided.

[0067] The placement device 14 includes a gripping device for mechanically gripping the sample container 12 in order to pick and place the sample container 12 .

[0068] 2 shows a diagrammatic representation of a carrier 10 (with receiving location 11) and a sample container 12 from a side view. In the embodiment shown, the receiving location 11 corresponds to a recess (slot) in the carrier 10. The receiving location 11 has a receiving location bottom surface 20, receiving location sides 21, and a receiving location top edge 22. The receiving location depth of the receiving location 11 corresponds to the vertical difference between the receiving location bottom surface 20 and the receiving location top edge 22.

[0069] When the receiving location bottom angle, which is the angle between the receiving location bottom surface 20 and the receiving location side surface 21, is 90°, the receiving location depth is equal to the vertical length of the receiving location side surface 21. The receiving location bottom surface 20 may be a disk. In this case, when the receiving location bottom angle is 90°, the receiving location 11 has a (circular) cylindrical shape. The receiving location bottom width, receiving location bottom length, and receiving location bottom diameter may correspond to the width, length, and diameter of the receiving location bottom surface 20, respectively. The receiving location top width, receiving location top length, and receiving location top diameter may correspond to the width, length, and diameter of the area surrounded by the top edge 22, respectively.

[0070] The receiving location top angle corresponds to the angle between the receiving location side surface 21 and the carrier top surface 26 .

[0071] Correspondingly, the sample container 12 has a container bottom surface 23, a container side surface 24, and a container top surface 25. The container height of the sample container 12 corresponds to the difference in the vertical direction between the container bottom surface 23 and the container top surface 25. The container bottom surface 23 may be a circular plate. In this case, the sample container 12 may have a (circular) cylindrical shape.

[0072] The container bottom width, container bottom length, and container bottom diameter correspond to the width, length, and diameter, respectively, of the container bottom surface 23. The container top width, container top length, and container top diameter correspond to the width, length, and diameter, respectively, of the container top surface 25.

[0073] FIG. 3 shows a graphical representation of a method for operating a laboratory automation system.

[0074] In a first step 31, a trained pattern is determined using a machine learning algorithm, which may include, for example, an artificial neural network. Determining the trained pattern may include, for example, processing training images having different receiving location types, including different receiving location bottom surface shapes, receiving location top surface shapes, receiving location bottom diameters, receiving location top diameters, receiving location depths, receiving location bottom angles, receiving location top angles, and receiving location notch indicators. The trained pattern is provided in the first data processing device 16.

[0075] In a second step 32, an image of the receiving location 11 is detected by the imaging device 15. For this purpose, the imaging device 15, which is attached to the mounting device 14, can be moved into a position above the carrier 10 with the receiving location 11.

[0076] In a third step 33, the data processing device 16 determines whether the receiving location 11 is free to receive the sample container 12 and whether the location type of the receiving location 11 is configured to receive the sample container 12. Here, the image of the receiving location 11 is analyzed using a machine learning algorithm image analysis to determine the type of the receiving location.

[0077] In a fourth step 34, in response to determining that the receiving location 11 is empty and configured to receive the sample container 12, the sample container is placed in the receiving location 11 by the placement device 14.

Claims

1. A method for operating a laboratory automation system (1), said laboratory automation system (1) comprising: a carrier (10) including a receiving location (11) for receiving a sample container (12) configured to hold a sample to be analyzed by a laboratory device (13); a placement device (14) configured to pick and place the sample container (12); An imaging device (15); a data processing device (16) including at least one processor (17) and a memory (18); Including, The method comprises: detecting an image of the receiving location (11) by the imaging device (15); applying in the data processing device (16) a machine learning algorithm for image analysis of the image of the receiving location (11), whether the receiving location (11) is free to receive the sample container (12); and determining whether the receiving location (11) is free to receive a sample container (12) and whether the receiving location (11) is configured to receive a sample container (12), wherein determining whether the receiving location (11) is configured to receive a sample container (12) comprises processing at least one trained pattern to determine a type of the receiving location from the image of the receiving location (11); If it is determined that the receiving location (11) is empty and configured to receive the sample container (12), the sample container (12) is placed on the receiving location (11) by the placement device (14). Including, Placing the sample container (12) at the receiving location (11) includes verifying an expected container height of the sample container (12), the expected container height being determined by scanning the sample container (12) and / or determining a type of the receiving location from the image of the receiving location (11) and providing a container type from the type of receiving location using a database, verifying the expected container height includes determining a measured container height of the sample container (12), and if the measured container height is equal to or within an acceptable limit, a verification result is deemed positive, and the at least one trained pattern is further determined via the machine learning algorithm using the verification result of the expected container height. method.

2. 2. The method of claim 1, wherein determining whether the receiving location (11) is configured to receive the sample container (12) comprises determining a type of receiving location from the image using the machine learning algorithm.

3. The method of claim 2 , wherein determining the type of receiving location from the image includes classifying the type of receiving location with the machine learning algorithm.

4. 3. The method of claim 2, further comprising comparing the type of the receiving location with the container type of the sample container (12), and determining that the receiving location (11) is configured to receive the sample container (12) if the type of the receiving location is assigned to the container type.

5. The method of claim 2 , further comprising the receiving location type indicating a receiving location bottom diameter that is less than an upper bottom diameter limit and / or greater than a lower bottom diameter limit.

6. The method of claim 2 , further comprising the receiving location type indicating a receiving location depth that is less than an upper depth limit and / or greater than a lower depth limit.

7. 3. The method of claim 2, further comprising: the receiving location type indicating a receiving location bottom angle between a receiving location bottom surface and a receiving location side surface of the receiving location that is less than a bottom angle upper limit and / or greater than a bottom angle lower limit.

8. The method of claim 4, further comprising providing container type data in the memory (18) indicative of the container type.

9. scanning the tag of said sample container (12) by a scanning device (19); 9. The method of claim 8, further comprising providing the container type from a database in response to scanning a tag on the sample container with the scanning device.

10. detecting a second image of the receiving location (11) by the imaging device (15); 9. The method of claim 8, further comprising: using the machine learning algorithm to determine the type of the receiving location from the second image and using the database to determine the container type.

11. 2. The method of claim 1, further comprising determining a lateral location of the receiving location (11) from the image.

12. The method of claim 1 , wherein detecting the image comprises detecting the image of a single receiving location (11).

13. The method of claim 1 further comprising providing the imaging device (15) mounted on the mounting device (14).

14. 10. The method of claim 1, further comprising determining a trained pattern via the machine learning algorithm using training images showing a plurality of receiving locations (11).

15. The method of claim 1 , wherein the validation results of the expected container height are used to determine further trained patterns via the machine learning algorithm.

16. A laboratory automation system (1), comprising: a carrier (10) including a receiving location (11) for receiving a sample container (12) configured to hold a sample to be analyzed by a laboratory device (13); a placement device (14) configured to pick and place the sample container (12); An imaging device (15); a data processing device (16) including at least one processor (17) and a memory (18); and wherein the laboratory automation system (1) comprises: detecting an image of the receiving location (11) by the imaging device (15); applying in the data processing device (16) a machine learning algorithm for image analysis of the image of the receiving location (11), whether the receiving location (11) is free to receive the sample container (12); and determining whether a receiving location type of the receiving location (11) is suitable for receiving the sample container (12), wherein determining whether the receiving location (11) is configured to receive the sample container (12) comprises processing at least one trained pattern to determine the receiving location type from the image of the receiving location (11); determining whether the receiving location (11) is free to receive the sample container (12) and whether the receiving location (11) is configured to receive the sample container (12); If the receiving location (11) is determined to be empty and suitable for receiving the sample container (12), the sample container (12) is placed on the receiving location (11) by the placement device (14). configured to run Placing the sample container (12) at the receiving location (11) includes verifying an expected container height of the sample container (12), the expected container height being determined by scanning the sample container (12) and / or determining a type of the receiving location from the image of the receiving location (11) and providing a container type from the type of receiving location using a database, verifying the expected container height includes determining a measured container height of the sample container (12), and if the measured container height is equal to or within an acceptable limit, a verification result is deemed positive, and the at least one trained pattern is further determined via the machine learning algorithm using the verification result of the expected container height. Laboratory automation system (1).

Images