Autonomous 3D Data Center Mapping System

Abstract

The present disclosure relates to an autonomous 3D data center mapping system. An automated data center imaging system is provided, comprising an automated guided vehicle having a housing. The system may include an optical imaging system coupled to the housing and comprising a plurality of cameras, each camera being configured to have a respective field of view, the fields of view at least partially non-overlapping with one another. The system may include a laser imaging system coupled to the housing and configured to scan the data center to obtain a plurality of distances between the housing and a plurality of locations within the data center. The system may include an image processor configured to combine a plurality of images acquired by the camera with the plurality of distances acquired by the laser imaging system into a single mosaic, the image processor being configured to position the plurality of images and the plurality of distances relative to a known coordinate system of the data center.

Description

Technical Field

[0001] The present disclosure relates to an autonomous 3D data center mapping system. Background Art

[0002] The interior of a data center is complex, changing, and dynamic. This set of attributes includes the construction, configuration, maintenance, and repair of the data center and the equipment (servers, racks, etc.) within the data center. Often, the actual arrangement and content of these attributes are somewhere between estimates and history. Continuous monitoring and classification of these data center attributes is difficult to achieve to mitigate the gap between theory and practice.

[0003] The status of data center shelf contents is theorized based on various tools and processes, but knowledge of shelf contents is not always completely accurate. Conventional tools may store the status of data center shelf contents using manually entered information based on barcode asset tag information. However, if such shelf contents information is incorrect or only partially accurate, there may be no easy way to correct such inaccuracies. Summary of the invention

[0004] The present disclosure provides an automatic imaging system and method for imaging a physical location, such as a data center, using an automatic guided vehicle (AGV). The AGV can be equipped with a distance detection tool, such as a laser, to detect the distance between the AGV and different surfaces within the physical location. The imaging system includes a plurality of cameras configured to capture a plurality of images from within the physical location. In addition, the imaging system can correlate the distance with the plurality of images, and can generate a map of the physical location using the plurality of images and the distance.

[0005] One aspect of the present disclosure provides an automatic imaging system, comprising: an automatic guided vehicle having a propulsion system configured to move the vehicle and a processor configured to control a motor and a steering system; an optical imaging system comprising a plurality of cameras, each of the cameras being configured to have a corresponding field of view that at least partially does not overlap with one another; a laser imaging system configured to scan a physical area to obtain corresponding distances between the vehicle and a plurality of locations within the physical area; and one or more processors configured to correlate a plurality of images acquired by the cameras with corresponding distances acquired by the laser imaging system.

[0006] According to some examples, the cameras are arranged in an array, and the array is movable in a vertical direction. The cameras in the array may be spaced apart from each other in a circular pattern, the circular pattern extending in a plane parallel to the vertical direction. The plurality of images may include a first set of images and a first set of distances acquired at a first vertical position, and a second set of images and a second set of distances acquired at a second vertical position, the first vertical position and the second vertical position being spaced apart from each other in the vertical direction.

[0007] According to some examples, the one or more processors are further configured to combine the multiple images acquired by the camera with the corresponding distances acquired by the laser imaging system in a map. The wireless communication component can be configured to communicate with a remote computing system. The one or more processors can be configured to navigate the vehicle to a specific location based on the communication from the remote computing system, the specific location corresponding to at least one of the multiple images acquired by the imaging system. The propulsion system may include: a plurality of wheels rotatably mounted to the housing; a drive element configured to rotate the wheels; a steering system configured to pivot the wheels and navigate the housing along a predetermined path; and a processor configured to control the motor and the steering system.

[0008] Another aspect of the present disclosure provides a method for imaging a physical area using an automated guided vehicle. The method may include: moving the automated guided vehicle to a plurality of locations within the physical area by a propulsion system for navigating the vehicle along a predetermined path; acquiring a plurality of images of the physical area by an optical imaging system coupled to the vehicle, the optical imaging system comprising a plurality of cameras, each of the cameras being configured to have a respective field of view, the fields of view at least partially not overlapping one another; scanning the physical area by a laser imaging system coupled to the vehicle to obtain a plurality of distances between the vehicle and a plurality of locations within the physical area; and correlating the plurality of images acquired by the cameras with the plurality of distances acquired by the laser imaging system.

[0009] According to some examples, the method may further include positioning the plurality of images and the plurality of distances relative to a known coordinate system of the physical area.

[0010] The cameras may be arranged in an array, and the array may be movable in a vertical direction perpendicular to the ground of the physical area. The cameras in the array may be spaced apart from each other in a circular pattern extending in a plane parallel to the vertical direction. Acquiring a plurality of images may include acquiring a first set of images and a first set of distances at a first vertical position; moving the array in a vertical direction from the first vertical position to a second vertical position spaced apart from the first vertical position; and acquiring a second set of images and a second set of distances at the second vertical position. The imaging system may include a fixture having a rail and a bracket, the rail extending in a vertical direction, the bracket coupled to the rail and movable in a vertical direction relative to the rail, the camera being fixed to the bracket, and moving the array includes moving the bracket from a first vertical position to a second vertical position along the rail. Moving the bracket along the rail may be driven by a servo motor coupled to the bracket.

[0011] According to some examples, the method can further include wirelessly transmitting the plurality of images and the plurality of distances to an image processor that is part of a computer remote from the automated guided vehicle.Moving the automated guided vehicle to the first target location can include moving the automated guided vehicle in a horizontal direction perpendicular to the vertical direction, and the field of view extends from the plurality of cameras in a depth direction perpendicular to both the horizontal direction and the vertical direction.

[0012] Yet another aspect of the present disclosure provides a method for imaging a physical area using an automated guided vehicle, the method comprising: moving the automated guided vehicle to multiple locations within the physical area by a propulsion system for navigating the vehicle along a predetermined path; acquiring an initial plurality of images of the physical area by an imaging system coupled to the vehicle, the imaging system comprising a plurality of cameras, each of the cameras being configured to have a corresponding field of view, the fields of view at least partially not overlapping with each other, the acquiring of the initial plurality of images comprising acquiring a first set of images at a first vertical position; moving the plurality of cameras in a vertical direction from the first vertical position to a second vertical position spaced apart from the first vertical position; and acquiring a second set of images at the second vertical position; combining the initial plurality of images acquired by the cameras into an initial single mosaicked image using an image processor; and positioning the initial plurality of images relative to a known coordinate system of the physical area.

[0013] The method may further include receiving a selection of a position within the initial single mosaic image to move the automated guided vehicle to one of a plurality of positions and acquire an updated plurality of images; and combining, using an image processor, the updated plurality of images with the initial plurality of images acquired by the camera into an updated single mosaic image. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1Ais a side view of an example automated 360 degree imaging system in accordance with aspects of the present disclosure.

[0015] Figure 1B is a perspective view of an example automated imaging system.

[0016] Figure 1C yes Figure 1A Side view of the automated imaging system.

[0017] Figure 1D yes Figure 1A Front view of the automatic imaging system.

[0018] Figure 1E is a method for illustrating distance detection according to various aspects of the present disclosure Figure 1A Side view of the automated imaging system.

[0019] Figure 2A It can be done by Figure 1B -D An example array of data center images acquired by the automated data center imaging system.

[0020] Figure 2B Is Figure 1A The imaging system acquires or combines Figure 2A A single mosaicked datacenter image is generated from an array of datacenter images.

[0021] Figure 2C is based on Figure 2B A data center map of a single mosaicked data center image.

[0022] Figure 3 Can be used to control Figure 1A A diagrammatic view of the control system of an automated imaging system.

[0023] Figure 4 is used Figure 1A A flow chart of a method for an automated imaging system to determine a status of a data center layout. DETAILED DESCRIPTION

[0024] The present technology generally relates to automated 3D imaging systems and methods for imaging physical locations using automated guided vehicles (AGVs). For example, the physical location may be a data center or other indoor space. For example, the automated imaging system may be configured to acquire multiple high-resolution images of a data center shelf and combine the multiple images into a single mosaic image. The system may parse location and barcode data from the combined mosaic image to provide accurate current location and data information of the contents of the data center in an automated manner. The automated imaging system may also provide real-time inventory location and data of commercial and retail shelves of products that may otherwise not be available in an automated manner.

[0025] refer to Figure 1A , an AGV with an imaging system mounted thereon can navigate through a physical location and be used to collect a 360-degree image of the location. The 360-degree image can then be used to generate a map of the physical location. Figure 1E In some examples described, the AGV can further detect the distance between the AGV and various points within the physical location. The waiting distance can be associated with the collected 360-degree image and used to generate the map. The physical location shown in this example and described in other examples in this article is a data center. However, it should be understood that the physical location can be any of various types of locations, such as a warehouse, a manufacturing plant, etc.

[0026] Figures 1B to 1D Only one example of an automated 3D imaging system 10 that can be used to image a data center rack 1 is described. The automated imaging system 10 can include an AGV 12 having a housing 14 and a propulsion system 16 configured to move the AGV. The housing 14 is shown as being generally in the shape of a rectangular prism, but in other examples, the housing can have any other shape, such as a square prism, a cylinder, etc. In other examples, the housing 14 can be omitted so that the mechanical and / or electrical components of the AGV 12 are exposed.

[0027] The propulsion system 16 may include: a motor and / or another drive element configured to rotate a plurality of wheels 18 rotatably mounted to the AGV 12; a steering system (not shown) configured to pivot the wheels and navigate the AGV 12 along a predetermined path; and a processor or control system 100 (described below with respect to FIG. Figure 3 Description), which is configured to control the motor and steering system.

[0028] The AGV 12 may also include sensors (not shown) for detecting conditions surrounding the AGV. Figures 1B to 1D The example configuration of the AGV 12 shown in is only one possible example of a flexible mobile robot platform. In other examples, there may be many other configurations of components for moving the AGV 12 from one location to another.

[0029] When using the AGV 12, the position of the AGV may be known relative to a known 3D coordinate system of the physical area (e.g., a data center) in which the AGV is navigating. To obtain the position of the AGV 12 within the known coordinate system as it moves, the AGV may read a barcode on the ground that is at a known position within the coordinate system. As the AGV 12 travels, the AGV may synchronize its position relative to the barcode.

[0030] The automated imaging system 10 may also include an imaging system 20 coupled to the AGV 12. The imaging system 20 may include a plurality of cameras 30. The cameras 30 may each be configured to have a respective field of view 32. The fields of view 32 may at least partially not overlap with one another, but in some instances, the fields of view may not overlap with one another at all. The field of view 32 of the camera 30 may extend away from the camera over a depth distance D between an object, such as a data center rack 1, and the camera.

[0031] The automated imaging system 10 may include an image processor (e.g., Figure 3 The processor 111 shown in FIG. 1 is configured to combine multiple images acquired by the camera 30 into a single mosaic image. Figure 2A and 2B Examples of multiple images and a single mosaic image are shown and described. Although the field of view 32 is shown extending toward shelf 1, the camera 30 can be used to record anything in the data center, including the location of corridors, doors, columns, shelves, fans, wire ducts, etc. The image processing can be fully automatic, so that a single mosaic image, a 360-degree image, and / or a map of the physical location can be generated from the acquired images without human intervention.

[0032] The camera 30 may include one or more optical cameras and laser imaging systems, such as one or more LIDAR (laser radar) scanners. Although the camera 30 is shown in an arrangement of several rows stacked vertically, it should be understood that other arrangements are also possible. For example, the camera can be positioned in a 360-degree configuration around a vertical axis or a horizontal axis. As another example, the camera can be arranged in a rose petal shape so that the camera collectively captures every angle around the AGV. In yet other examples, the camera can be a single 360-degree camera.

[0033] The optical camera can obtain images that can be combined to obtain a visual map of the physical location. For example, the acquired images can be combined to generate a map of the entire data center so that individual shelf components can be visually identified.

[0034] Figure 1E An example of using an AGV to detect the distance between the AGV and various points within a physical location is illustrated. For example, a LiDAR scanner can scan in a direction 33 to obtain position data and / or temperature data for the contents of the physical location within a mapping envelope 34. A LiDAR scanner can obtain more accurate position data than an optical camera. A LiDAR scanner can obtain the dimensional position of doors, columns, shelves, fans, and electrical conduits near the ceiling 2 of the physical location.

[0035] The dimensional accuracy of the LiDAR scan can be within approximately + or -10 mm. In some instances, a single LiDAR scanner can be used, where an internal electromechanical mirror system can move a single laser beam around, allowing approximately one thousand distances to be collected when the AGV is in a single position. In other instances, a fixed array of lasers can be used. Although the system 10 is described as including a LiDAR scanner, some instances use only optical images, while other instances combine optical and LiDAR data.

[0036] In the illustrated example, the imaging system 20 may include a fixture 40 fixed to the housing, the fixture having: a rail 42 extending in a vertical direction V perpendicular to the depth direction D; and a bracket 44 extending in a horizontal direction H perpendicular to the vertical direction and the depth direction. The camera 30 may be fixed to the bracket 44. The camera 30 may be arranged in an array extending in the horizontal direction H along the bracket 44. The cameras 30 in the array may be equally spaced apart from each other by a distance D1 in the horizontal direction. The bracket 44 may be coupled to the rail 42 so that the bracket and the array of cameras 30 fixed thereto are movable relative to the rail in the vertical direction V. The imaging system 20 may include a servo motor (not shown) configured to move the bracket 44 in the vertical direction V along the rail 42. It should be understood that in other examples, the imaging system 20 may include other arrangements of the cameras 30, such as by implementing other mounting fixtures or mechanisms.

[0037] Although the cameras 30 are described above as being arranged in an array extending in the horizontal direction H along the bracket 44, in alternative examples, the cameras may be arranged in a ring around a vertical axis and extending in a plane perpendicular to the depth direction D. The ring may be movable in the vertical direction V along the guide rail 42. According to other examples, the cameras may be arranged in a ring extending around the longitudinal axis. In other examples, the cameras may be arranged in a rose petal shape or a sphere, thereby collecting substantially all of the environment around the AGV. In yet other examples, the camera may be a single 360-degree camera.

[0038] The bracket 44 can be moved to any position in the vertical direction V along the guide rail 42. The first, second and Nth vertical positions P1, P2 and PN of the bracket 44 are Figure 1B As shown in FIG. 1 , the vertical positions are spaced apart from each other in the vertical direction V. As can be seen in FIG. Figure 1C As can be seen in FIG. 1 , the cameras 30 can each perform a separate image scan when the carriage 44 is in each position along the vertical direction V. Each camera 30 can perform any number "N" of image scans that, when combined by an image processor, are required to form a complete mosaic image of the features of the data center. As mentioned above, the combination of such images can be fully automated.

[0039] like Figure 1B As shown in , the carriage 44 can start at a first vertical position P1 and can move downward in a vertical direction V, and as the carriage continues to move downward, each camera can record multiple image scans at each vertical position until the carriage reaches the end of its travel range at an Nth vertical position PN. It should be understood that the imaging system 20 is one example of an imaging system, and in other examples, any of various other embodiments of a system that can carry and move the camera 30 to scan images of a data center can be used.

[0040] The LiDAR scanner may be one or more of the cameras 30 and may include a mirror therein to direct the laser beam in any of more than one thousand orientations relative to the scanner. Alternatively, the LiDAR scanner may be an array of laser beams that are fixed relative to the AGV 12, or the scanner may be movable in a vertical direction V along the rail 42.

[0041] Figure 2A An example is illustrated of multiple optical images 50a through 50x (collectively referred to as images 50) acquired by camera 30 during an image scan of a physical location and a single mosaicked image 60 created by an image processor from images 50. Although the example describes the physical location as a data center, it should be understood that the physical location may be any type of location.

[0042] Each of these optical images can be correlated with the dimensional data acquired by the LiDAR scanner. For example, each of the images 50 can overlap with the corresponding LiDAR data at one thousand points, so that when each image is correlated with the corresponding LiDAR data, one thousand locations within each image will be known relative to the location of the AGV 12 within the known coordinate system of the data center.

[0043] In the example shown, the images 50 are arranged in a four by six grid, with six rows of four images each extending in the horizontal direction H. However, it should be understood that the number and arrangement of the images may vary. Figure 2A As shown in Figures 1B to 1DEach of the four cameras 30 shown in the figure performs six image scans, and each group of scans S1 to S6 is represented by a different horizontal row in the figure. Each of the image scans S1 to S6 is acquired at a different vertical position (e.g., P1 to PN, where N=6) along the carriage 44. Therefore, the plurality of images 50 includes: a first group S1 of images acquired at a first vertical position P1, which includes images 50a-50d; a second group S2 of images acquired at a second vertical position P2, which includes images 50e-50h; to an Nth group of images (S6 in this example) acquired at an nth vertical position PN, which includes images 50u-50x. The first vertical position P1, the second vertical position P2, and the Nth vertical position PN of the carriage 44 are spaced apart from each other in the vertical direction V.

[0044] exist Figure 2A and 2B In the example shown in , the multiple images 50 are images of an area of ​​a data center. An image processor can be used to combine the images 50a to 50x acquired by the camera 30 at positions P1 to PN into a single mosaic image 60. For example, the image processor can identify objects within the images, detect boundaries within the images, and stitch the images together so that the objects within the images are properly aligned. Once the single mosaic image 60 is created, the image processor can optionally parse the single mosaic image to extract asset location information and asset tag bar code information. Once the asset location information and asset tag bar code information are extracted, the wireless communication component can send the optical and distance information from the camera 30 to the remote computer.

[0045] In order to produce a complete single mosaic image 60 with no horizontal or vertical gaps, there may be a small amount of overlap between the fields of view in adjacent images recorded in image 50. However, in other instances, there may be no overlap between the fields of view in adjacent images recorded in image 50, as it may not be necessary to fully image the data center to identify specific components or component types and their locations within the data center, or to parse a single mosaic image to extract asset location information and asset tag bar code information. The example image 60 may be a single image from a set of 20, 50, 100, or 500 images of the entire data center. Any number of images 60 may be combined to allow the entire data center to be imaged.

[0046] According to other examples, a single 360-degree camera may be used to generate Figure 2B 360-degree images.

[0047] refer to Figure 2C, the image 60 can be mapped onto a single 3D mosaic data center map 62, which can be a 3D blueprint of all the shelves, corridors, wire ducts, etc. contained in the data center. In some instances, both the optical image 60 and the lidar data can be combined to create a single mosaic data center map 62. Post-processing of mapping the optical data and lidar data together can be performed by an image processor at a location remote from the AGV 12. Such processing can be fully automated, for example, so that the map is generated without user intervention. For example, the image processor can correlate the optical data and the lidar data and also correlate with the location coordinates within the physical location. Using this correlation, the map can be generated. The user can use this map 62 so that when the user clicks on a specific location on the map, the corresponding image in the image 60 can be displayed. In this way, the user can obtain an on-demand optical view of any portion of the map 62 from a viewpoint similar to what the user can see when he is inside the data center.

[0048] Map 62 can also be used to calculate distances between features visible on the map. For example, a user can calculate distances by placing two virtual pins on the map, and the map can display the distance between the pins (to within plus or minus 10 mm). Map 62 can also be used to determine the size of objects within the data center, such as the width of a column or the width of a shelf, to an accuracy of plus or minus 10 mm.

[0049] The map 62 may be updated periodically by collecting new data with the AGV 12. To update the map 62, the user may command the AGV 12 to travel to one or more desired locations within the data center to collect new optical and lidar data, and such data may replace portions of the map that may have become outdated due to relocation of items within the data center. Each set of optical and lidar data may be associated with the date and time the data was collected to help the user understand whether portions of the map 62 are outdated and need to be updated.

[0050] refer to Figure 3 , illustrating an example control system 100. As shown, the control system 100 includes one or more computing devices 110 coupled to various components 120-125, such as an AGV navigation system 120, a positioning system 121, a lighting device 122, a perception system 123, a cleaning component 124, and a power system 125. The computing device 110 further includes one or more processors 111, a memory 112, and other components typically found in a microprocessor, a general-purpose computer, or the like.

[0051] The one or more processors 111 may be any conventional processor, such as a commercially available microprocessor. Alternatively, the one or more processors may be a dedicated device, such as an application specific integrated circuit (ASIC) or other hardware-based processor. In some examples, the one or more processors may include, for example, a graphics processing unit (GPU) and / or a tensor processing unit (TPU) for machine learning-based perception. Although Figure 3 The processor, memory, and other elements of computing device 110 are functionally illustrated as being within the same block, but one of ordinary skill in the art will appreciate that a processor, computing device, or memory may actually include multiple processors, computing devices, or memories that may or may not be stored within the same physical housing. Similarly, the memory may be a hard drive or other storage medium located in a housing different from that of computing device 110. Thus, references to a processor or computing device will be understood to include references to a collection of processors or computing devices or memories that may or may not operate in parallel.

[0052] The memory 112 may store information accessible by the processor 111, including instructions 113 that may be executed by the processor, and data 114, such as asset location information and / or asset tag barcode information. Such instructions 113 may include: detecting camera positioning based on sensor feedback; adjusting the position of the imaging system; acquiring images of data center shelves; and combining images and parsing mosaic images. The memory 112 may be a type of memory for storing information accessible by the processor 111, including a non-transitory computer-readable medium, or other media for storing data that can be read with the aid of an electronic device, such as a hard drive, a memory card, a read-only memory ("ROM"), a random access memory ("RAM"), a digital versatile disc ("DVD") or other optical disc, and other writable memory and read-only memory. The subject matter disclosed herein may include different combinations of the foregoing, whereby different portions of the instructions 113 and data 114 are stored on different types of media.

[0053] Processor 111 can retrieve, store or modify data 114 according to instruction 113. For example, although the present disclosure is not limited to a specific data structure, data 114 can be stored in a computer register, a relational database as a table with multiple different fields and records, an XML document or a flat file. Data 114 can also be formatted in a computer readable format, such as but not limited to binary values, ASCII or Unicode (Unicode). Only by way of further example, data 114 can be stored as a bitmap, which includes pixels stored in compressed or uncompressed or various image formats (e.g., JPEG), vector-based formats (e.g., SVG) or computer instructions for drawing graphics. In addition, data 114 can include information sufficient to identify relevant information, such as numbers, descriptive text, proprietary codes, pointers, references to data stored in other memories (including other network locations) or information used by functions to calculate relevant data.

[0054] In one example, computing device 110 may be an AGV computing system incorporated into control system 100, such as AGV 12 having imaging system 20. The computing device may be capable of communicating with various components of the system autonomously or without continuous input from a human operator. For example, computing device 110 may communicate with various components 120-125 of control system 100 that operate according to instructions 113 of memory 112 in an autonomous mode that does not require or need continuous or periodic input from an operator. Although these systems are shown as being external to computing device 110, in other examples, these systems may also be incorporated into the computing device.

[0055] Instructions 113 may be executed to perform various operations using one or more of components 120-125 or other components not shown. For example, the AGV navigation system 120 may include a GPS or other system that guides the AGV to a target data center shelf 1 for imaging. The positioning system 121 may be directed to respond to feedback provided by a perception system 123, which may include one or more cameras, sensors, etc. For example, the positioning system 121 may include one or more motors, or other devices for controlling the positioning of the AGV 12 and / or camera 30. When the perception system 123 provides data regarding the proximity of a target location within the data center to the camera 30, the positioning system 121 may adjust the position of one or more of the AGV 12 or the carriage 44 to keep the camera in a position close to the target location.

[0056] The lighting system 122 may include one or more LEDs or other lighting devices. When environmental conditions are such that natural light is insufficient, or in any other case, as long as the AGV 12 is within a predetermined distance from the target location, the lighting system 122 may be directed to illuminate the target location to image a portion of the data center. In this regard, the lighting system 122 may also respond to input from the perception system 123, such as feedback from a light or proximity sensor. Similarly, the cleaning component 124 may also respond to feedback from the perception system 123. For example, one or more processors 111 may determine that the target location is dirty based on an image captured by the perception system 123. Since such dirt may block information, such as an asset tag barcode that needs to be read to determine which component is located in a particular data center shelf 1, the cleaning component 124 may be directed to spray air or perform some other operation to remove debris. The power system 125 may include, for example, a battery for powering the control system 100.

[0057] Although components 110-115 and 120-125 are described above with reference to an example of a data center imaging mode, it should be understood that the components may also operate in response to operator input or other instructions. For example, computing device 110 may provide information to a remote computing device, such as an operator control unit, via transmitter / receiver 115. Similarly, computing device 110 may receive instructions from a remote operator control unit. In other examples, control system 100 may operate in an autonomous imaging mode, but still use transmitter / receiver 115 to provide feedback to a remote computing device.

[0058] Figures 1A to 3 The design of the automated data center imaging system 10 shown in is only one example of an automated data center imaging system. Many other configurations of the automated data center imaging system 10 are contemplated, including imaging systems 20 having different numbers of cameras 30, rails 42 and brackets 44 having different widths, heights, and / or arrangements, and AGVs 12 of various designs. In some configurations, the imaging system 20 may have more or less than four cameras 30, such as 2, 3, 5, 6, 8, or 10, etc. In some examples, image scanning may be performed with the bracket 44 at more or less than six different vertical positions (e.g., 2, 3, 4, 5, 8, 10, 15, or 20, etc.).

[0059] The automated data center imaging system 10 may also be used in environments other than data centers. For example, the automated imaging system 10 may be used for manufacturing or retail inventory tracking. For example, the imaging system 20 may scan bar codes of products on shelves in a warehouse in the image 50 and the single mosaic image 60, and such bar codes may be parsed from the single mosaic image by the image processor. In some examples, the imaging system 20 may scan any two-dimensional space, and information may be parsed from the single mosaic image 60 to provide inventory information based on parsing bar codes from the single mosaic image or based on the shape and arrangement of individual inventory items.

[0060] refer to Figure 4 , describing a method 400 for imaging a data center with an AGV. At box 410, the AGV can move to a first location and capture a first set of one or more images. Moving the AGV can be performed, for example, by an AGV navigation system that controls a propulsion system. The AGV navigation system can be controlled by a computing device and / or a human operator remote from the AGV. The first set of one or more images can be captured using an array of cameras with different positions and / or camera angles, or the images can be captured by a single camera, such as a 360 degree camera. According to some examples, the first set of images can be a single 360 ​​degree image.

[0061] According to some examples, the first set of images can be combined into a single mosaic image of the first location. For example, the images can be combined using an image processor that can be located at the AGV or at a remote location. The single mosaic image can provide, for example, an angled view of the physical location, such as a 360-degree view. According to some examples, multiple sets of images can be collected from multiple locations to generate multiple mosaic images at different locations and with different perspectives.

[0062] At box 420, the distance between the AGV and various objects in the physical location is detected. The distance can be detected by, for example, a laser (e.g., a lidar) or other distance detection mechanism. The distance can be related to the acquired image. For example, in some embodiments, the distance can be calculated substantially simultaneously with the acquisition of the image, and the distance corresponding to the point in each image can be stored in association with the image. For example, the distance can be the distance between the camera and the center of the field of view of the acquired image. As another example, the distance can be the distance between a point on the AGV and an object in the acquired image (e.g., a data center shelf or a computing device located on the shelf), or an identifier (e.g., a bar code marking a device on the shelf).

[0063] At block 430, the AGV may move from the first location to the second location, for example, by navigating to a second set of coordinates within the physical location. The camera may acquire a second set of one or more images at the second location.

[0064] At block 440, distances between the AGV and various objects at the second location are detected.

[0065] At block 450, the first and second images and the detected distances may be used to generate a map of the physical location. According to some examples, the known coordinate system of the physical location may be further used to generate the map. The map may be configured so that when a user clicks on a location on the map, a corresponding image in the captured image may be displayed, and the size of the object and the distance between the locations in the map may be provided.

[0066] Using the generated map, the automated imaging system can receive a selection of a location within the data center map, and the AGV can move to the selected location to acquire an updated plurality of images and an updated set of lidar data. The updated plurality of images and the updated set of lidar data can replace the corresponding images and data within the map.

[0067] Unless otherwise stated, the foregoing alternative examples are not mutually exclusive, but may be implemented in various combinations to achieve unique advantages. Since these and other variations and combinations of the features discussed above may be utilized without departing from the subject matter defined by the claims, the foregoing description of the examples should be made by way of illustration rather than by way of limitation of the subject matter defined by the claims. In addition, the examples described herein and clauses expressed in phrases such as "for example," "including," etc. should not be construed as limiting the subject matter of the claims to specific examples; rather, the examples are intended to illustrate only one of many possible examples. In addition, the same reference numerals in different figures may identify the same or similar elements.

Claims

1. An automatic imaging system, comprising: an automated guided vehicle having a propulsion system configured to move the automated guided vehicle and a vehicle processor configured to control a motor and a steering system; an optical imaging system comprising a plurality of cameras, each camera being configured to have a respective field of view, the different fields of view of the plurality of cameras at least partially not overlapping with each other; a laser imaging system configured to scan a physical area to obtain corresponding distances between the automated guided vehicle and a plurality of locations within the physical area; as well as one or more processors configured to correlate the plurality of images acquired by the plurality of cameras with the corresponding distances acquired by the laser imaging system and combine the plurality of images acquired by the plurality of cameras with the corresponding distances acquired by the laser imaging system to generate a map of the physical area such that when a user clicks on a location on the map, a corresponding image in the captured images is displayed and the distances between the locations in the map are provided, Wherein the plurality of cameras are arranged in an array, and the array is movable in a vertical direction while capturing the plurality of images in different vertical positions. 2 . The automated imaging system of claim 1 , wherein the plurality of cameras in the array are spaced apart from one another in a circular pattern extending in a plane parallel to the vertical direction.

3. The automatic imaging system of claim 1 , wherein the plurality of images include a first group of images corresponding to a first group of distances acquired at a first vertical position and a second group of images corresponding to a second group of distances acquired at a second vertical position, the first vertical position and the second vertical position being spaced apart from each other in the vertical direction. 4 . The automated imaging system of claim 1 , further comprising a wireless communication component configured to communicate with a remote computing system.

5. The automated imaging system of claim 4, wherein the one or more processors are configured to navigate the automated guided vehicle to a specific location based on communications from the remote computing system, the specific location corresponding to at least one of the plurality of images acquired by the optical imaging system.

6. The automated imaging system of claim 1, wherein the propulsion system comprises: a plurality of wheels rotatably mounted to the housing; a drive element configured to rotate the plurality of wheels; and the steering system configured to pivot the plurality of wheels and navigate the housing along a predetermined path.

7. A method for imaging a physical area using an automated guided vehicle, the method comprising: moving the automated guided vehicle to a plurality of locations within the physical area via a propulsion system for navigating the automated guided vehicle along a predetermined path; acquiring a plurality of images of the physical area by an optical imaging system coupled to the automated guided vehicle, the optical imaging system comprising a plurality of cameras, each camera being configured to have a respective field of view, the different fields of view of the plurality of cameras at least partially not overlapping one another; scanning the physical area with a laser imaging system coupled to the automated guided vehicle to obtain a plurality of distances between the automated guided vehicle and a plurality of locations within the physical area; as well as correlating the plurality of images acquired by the plurality of cameras with the plurality of distances acquired by the laser imaging system and combining the plurality of images acquired by the plurality of cameras with the corresponding distances acquired by the laser imaging system to generate a map of a physical area such that when a user clicks on a location on the map, a corresponding image in the captured images is displayed and the distances between the locations in the map are provided, Wherein the plurality of cameras are arranged in an array, and the array is movable in a vertical direction perpendicular to a ground surface of the physical area while capturing the plurality of images in different vertical positions.

8. The method of claim 7, further comprising positioning the plurality of images and the plurality of distances relative to a known coordinate system of the physical area.

9. The method of claim 7, wherein the plurality of cameras in the array are spaced apart from one another in a circular pattern extending in a plane parallel to the vertical direction.

10. The method of claim 7, wherein acquiring the plurality of images comprises: acquiring a first set of images and a first set of distances at a first vertical position; moving the array in the vertical direction from the first vertical position to a second vertical position spaced apart from the first vertical position; as well as A second set of images and a second set of distances are acquired at the second vertical position.

11. The method of claim 10, wherein the optical imaging system comprises a fixture having a rail and a bracket, the rail extending in the vertical direction, the bracket coupled to the rail and movable in the vertical direction relative to the rail, the plurality of cameras being fixed to the bracket, and the moving the array comprises moving the bracket from the first vertical position to the second vertical position along the rail.

12. The method of claim 11, wherein said moving said carriage along said rail is driven by a servo motor coupled to said carriage.

13. The method of claim 7, further comprising wirelessly transmitting the plurality of images and the plurality of distances to an image processor that is part of a computer remote from the automated guided vehicle.

14. The method according to claim 7, further comprising: The automated guided vehicle is moved in a horizontal direction perpendicular to the vertical direction to a first target location, and the different fields of view extend from the plurality of cameras in a depth direction perpendicular to both the horizontal direction and the vertical direction.

15. A method of imaging a physical area using an automated guided vehicle, the method comprising: moving the automated guided vehicle to a plurality of locations within the physical area via a propulsion system for navigating the automated guided vehicle along a predetermined path; acquiring an initial plurality of images of the physical area by an imaging system coupled to the automated guided vehicle, the imaging system comprising a plurality of cameras, each camera being configured to have a respective field of view, the different fields of view of the plurality of cameras at least partially not overlapping one another, wherein acquiring the initial plurality of images comprises: acquiring a first set of images at a first vertical position, moving the plurality of cameras in the vertical direction from the first vertical position to a second vertical position spaced apart from the first vertical position, and acquiring a second set of images at the second vertical position; combining the initial plurality of images acquired by the plurality of cameras into an initial single mosaicked image using an image processor; positioning the initial plurality of images relative to a known coordinate system of the physical region; and generating a map based on the known coordinate system so that when a user clicks a location on the map, a corresponding initial single mosaic image is displayed and distances between locations in the map are provided, Wherein the plurality of cameras are arranged in an array, and the method further comprises moving the array in a vertical direction perpendicular to a ground surface of the physical area while capturing the plurality of images in different vertical positions.

16. The method of claim 15, further comprising receiving a selection of a location within the initial single mosaic image to move the automated guided vehicle to one of the plurality of locations and acquire an updated plurality of images; and The updated plurality of images are combined with the initial plurality of images acquired by the plurality of cameras into an updated single mosaicked image using the image processor.

Images