Perception systems and methods for identifying and processing various objects

Abstract

A fall sensing system is disclosed that includes an open housing structure having an interior volume, an open top, and an open bottom, and a plurality of sensing units positioned to capture sensing data at a plurality of locations within the interior volume and between the open top and the open bottom of the open housing.

Description

[0001] This application is a divisional application of PCT international application number PCT / US2016 / 066786, international application date December 15, 2016, Chinese national application number 201680081764.5, and entitled "Perception system and method for identifying and processing various objects."

[0002] priority

[0003] This application claims priority to U.S. Provisional Patent Application Serial No. 62 / 269,640, filed December 18, 2015, the entire disclosure of which is incorporated herein by reference. Background Art

[0004] The present invention relates generally to perception systems and, more particularly, to scanning systems for use with robots and other sorting systems intended for use in dynamic environments requiring the robots or other sorting systems to adapt to handling various types of objects.

[0005] For example, many order fulfillment operations achieve high efficiency by employing a process known as wave picking. In wave picking, order items are picked from warehouse shelves and placed in a specific location (e.g., into a bin) that contains multiple orders to be sorted downstream. During the sorting phase, individual items are identified and multi-item order items are consolidated into, for example, a single bin or shelf location so that they can be packaged and then shipped to the customer. The process of sorting these items has traditionally been done manually. A human sorter picks an item from an inbound bin, locates a barcode on the item, scans the barcode with a handheld barcode scanner, determines the appropriate bin or shelf location for the item based on the scanned barcode, and then places the item in the determined bin or shelf location, where all items for the order are defined as belonging to that bin or shelf location. Automated systems for order fulfillment have also been proposed. See, for example, US Patent Application Publication No. 2014 / 0244026, which discloses the use of a robotic arm in combination with an arched structure that can be moved into the reach of the robotic arm.

[0006] Other ways of identifying items by scanning codes require either manual processing or the need to control or constrain the position of the code so that it can be reliably detected by a fixed code scanner or a robot-held code scanner (e.g., a barcode scanner). Manually operated barcode scanners are typically either fixed or handheld systems. With fixed systems (such as those used at point-of-sale systems), the operator holds the item and positions it in front of the scanner so that the barcode faces the scanning device's sensor, and the scanner continuously scans and decodes any barcodes it can detect. If the item is not immediately detected, the person holding the item typically needs to change the position or orientation of the item in front of the fixed scanner to make the barcode more visible to the scanner. With handheld systems, the person operating the scanner locates the barcode on the item, then holds the scanner so that the item's barcode is visible to the scanner, and then presses a button on the handheld scanner to begin scanning the barcode.

[0007] Similarly, automatic bar code scanners are also fixed or handheld systems and use the same principles. In the case of bar code scanners commonly used in industrial applications, the possible positions of the bar code must be strictly controlled so that the bar code is visible to one or more scanners. For example, one or more bar code scanners can be placed in a fixed position relative to a conveyor so that they can scan an item (usually a box) as it passes by the scanner. See, for example, U.S. Patent No. 5,495,097. In these mounting schemes, the placement range of the bar code is relatively limited because the bar code is located on a label affixed to one of the four sides or the top or bottom (for example, if it is upside down) of the box and can be presented in the orientation most suitable for scanning using simple mechanical devices.

[0008] In all of these cases, the system uses sensors, cameras, or laser reflectivity sensors, along with software, to detect and decode the barcode. These methods have inherent limitations, including the range of distances within which the barcode can be reliably scanned relative to the orientation of the detection system. First, the barcode must be oriented toward the scanner; second, the range to the barcode must be sufficient to reliably distinguish individual elements; and third, the barcode's tilt and skew must be such that individual elements can be reliably distinguished. The type of sensor employed and the robustness of the software detection and decoding schemes determine these performance parameters.

[0009] Therefore, there remains a need for an object recognition system for robotic and other sorting systems that can accommodate the automatic recognition and processing of a variety of objects in a variety of orientations. Summary of the Invention

[0010] According to one embodiment, the present invention provides a fall sensing system comprising an open housing structure having an interior volume, an open top, and an open bottom, and a plurality of sensing units positioned to capture sensing data at a plurality of locations within the interior volume and between the open top and the open bottom of the open housing.

[0011] According to another embodiment, the present invention provides a perception system for assisting in identifying an object, the perception system comprising a plurality of perception units, each perception unit positioned to point to a different portion of an object's path as the object travels through the perception system without the assistance of any mechanical transport system in contact with the object.

[0012] According to yet another embodiment, the present invention provides a fall sensing system for identifying an object, the fall sensing system comprising a plurality of sensing units, each of the sensing units being positioned to point to a different portion of an object's path, the object path being a path the object can take as it falls and passes through the fall sensing system, and each of the sensing units being enabled to provide sensing data about the object.

[0013] According to a further embodiment, the present invention provides a method for sorting objects. The method includes the steps of: dropping an object into a perception system comprising a plurality of perception units, each of the perception units positioned to point toward a different portion of a path the object can take as it falls through the perception units; and activating the perception units to capture perception data associated with the object. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The following description may be further understood with reference to the accompanying drawings, in which:

[0015] Figure 1 An illustrative isometric diagram of a perception system according to one embodiment of the present invention is illustrated;

[0016] Figure 2 Pictured Figure 1 A front-view illustrative diagram of the perception system;

[0017] Figure 3 An illustrative isometric diagram of a perception system according to another embodiment of the present invention is illustrated;

[0018] Figure 4 Shown Figure 3 Illustrative elevated posterior view of the perceptual system;

[0019] Figure 5 Pictured Figure 3 an illustrative front view of the perceptual system taken along line 5-5 thereof;

[0020] Figure 6 Pictured Figure 3 an illustrative side view of the perceptual system of FIG. 1 taken along line 6-6 thereof;

[0021] Figure 7 Shown Figure 3 Illustrative top-down view of the perceptual system;

[0022] Figure 8 Shown Figure 3 Illustrative linear diagram of a portion of the internal perceptual system;

[0023] Figures 9A-9H Pictured Figure 3 An illustrative linear diagram of the internals of a perception system showing the different stages of illumination and perception data capture;

[0024] Figures 10A-10C An illustrative view of a flow chart is shown, showing Figure 3 The operation of the perception system;

[0025] Figure 11 Shown in Figure 3 An illustrative diagram of the lighting system used in the perception system of FIG.

[0026] Figure 12 Shown in Figure 3 An illustrative diagram of an image capture system used in a perception system of FIG.

[0027] Figures 13A-13R Shown by Figure 3 Illustrative view of an image captured by the perception system ( Figure 13A 、 Figure 13C 、 Figure 13E 、 Figure 13G 、 Figure 13I 、 Figure 13K 、 Figure 13M 、 Figure 13O 、 Figure 13Q ) and related processed image data ( Figure 13B 、 Figure 13D 、 Figure 13F 、 Figure 13H 、 Figure 13J 、 Figure 13L 、 Figure 13N 、 Figure 13P 、 Figure 13R );

[0028] Figure 14 Shown include Figure 3 The sensing system and the sorting system of the feeding equipment and sorting equipment;

[0029] Figure 15 Shown include Figure 3 A sensing system and an article position / orientation adjustment device and a sorting system of a sorting device, wherein the article position / orientation adjustment device includes a lower side sensing unit; and

[0030] Figure 16 Shown include Figure 3 The invention provides a sensing system, an item position / orientation adjustment device and a sorting system of a sorting device, wherein the item position / orientation adjustment device includes a fan.

[0031] The drawings are shown for illustration purposes only. DETAILED DESCRIPTION

[0032] According to one embodiment, the present invention provides a novel object sensing system for automatically sorting individual objects in a group. In applications such as order fulfillment, items or goods are collected into groups of different properties (heterogeneous) and need to be sorted. Individual objects need to be identified and then transported to a location specific to that object. The described system reliably and automatically identifies these objects by employing an automated scanner. The scanner looks for various codes, such as markings (e.g., barcodes, RFID tags, stock keeping units (SKUs), universal product codes (UPCs), Digimarc DW Codes, etc.).

[0033] Systems according to various embodiments of the present invention are operated in conjunction with a robotic pick and place system to automate a portion of the sorting process, particularly the step of identifying the picked object. For example, a robotic arm picks items from a bin instead of a person picking objects from a bin. The objects pass in front of multiple barcode scanners and then, after obtaining the object's identification code, are transported to the appropriate bin or shelf location. Because barcode scanners use cameras or lasers to scan 1D or 2D symbols printed on labels attached to the objects, the barcode must be visible to the scanner's sensor in order to be successfully scanned, thereby automatically identifying items in any heterogeneous stream of objects, such as in a jumbled group of objects found in a bin.

[0034] While fixed industrial scanners require an object's barcode to be located where it is visible to the scanner, the robotic arm of the present invention can pick an object from a heterogeneous collection of objects from a location where the barcode is not visible and place it into the perception system of the present invention. In other embodiments, the system can provide a feed conveyor positioned above the perception system for objects to be dropped into, with the objects being individually positioned on the conveyor. The result is an automated barcode scanning system for any object in a heterogeneous stream of objects that can be used to accurately and reliably identify the object.

[0035] Sorting for order fulfillment is one application for automatically identifying objects from a heterogeneous stream. Barcode scanners have a wide range of further uses, including identifying inventory units or tracking packages. The described system can have many applications in the automated identification and sorting of objects.

[0036] Thus, according to various embodiments, the present invention provides a method for determining the identity of an object from a collection of objects, a method for scanning a barcode of an object using one or more scanners, and a sorting system for differentially handling different objects. According to certain embodiments, the present invention also provides a method for determining the placement of a stationary barcode scanner to maximize the probability of successfully scanning an object selected by a robotic end effector, and a method for determining whether multiple objects are simultaneously encountered by a scanner.

[0037] An important aspect is the ability to identify an object by its barcode or other visual markings using a sensing system that the object falls into. If the barcode is not exposed or visible, the automated scanning system will not be able to see the barcode on the object. Figure 1 As shown, a sensing system 10 according to an embodiment of the present invention may include an open housing 12 through which an object may fall. Inside the housing are a plurality of (e.g., eight or twelve) sensing units 14, which are generally pointed into the interior of the housing from a number of different directions. The housing may also include a plurality of lights 16, which are timed to provide bright, scattered light at the moment each sensing unit 14 takes a picture of a falling object 18. For example, each sensing unit 14 may be positioned at the moment the object falls from the housing. Figure 2 One hundred images are taken when the object falls into the direction shown by A in FIG. 1 . The detection unit 14 can be connected to a processing system 20 that examines each image to search for a unique identifier such as a barcode. The perception unit can include a camera (e.g., 2D or 3D) or a scanner (e.g., a laser reflectivity scanner), other types of barcode readers (such as 1D or 2D barcode scanners, or radio frequency ID scanners), and the processing system 20 can include associated software for processing the perception data. As shown, some cameras are oriented horizontally, other cameras are oriented upward, and some cameras are oriented downward. The system 10 can also include an entry detection unit that utilizes a source 22 across the opening and a detector 24 to provide a curtain of, for example, infrared illumination, and the detector 24 is used to detect an interruption in the illumination. Thus, the detection unit provides a signal indicating that an object has entered the drop scanner 10.

[0038] The perception system can, in certain embodiments, be used in combination with a robotic system, where the robotic system can include a robotic arm equipped with sensors and a computing device, and the combination is expected to exhibit the following capabilities: (a) the ability to pick objects from a specific class of objects and separate them from a heterogeneous stream of objects, whether they are mixed in a cargo box or separated on a motorized or gravity conveyor system; (b) the ability to move objects to any location within its workspace; (c) the ability to place objects in an outbound box or shelf location within its workspace; and (d) the ability to generate a map of objects that can be picked up, represented as a set of candidate grasping points in the workcell and a list of polyhedrons in the space that contain the object.

[0039] Permissible objects are determined by the capabilities of the robotic system. Their size, weight, and geometry should enable the robotic system to pick, move, and place them. They can be any kind of ordered goods, packages, parcels, or other items that would benefit from automated sorting. Each object is associated with a stock keeping unit (SKU) that identifies the item.

[0040] Inbound objects can arrive in one of two configurations, for example: (a) they arrive stacked in a bin of heterogeneous objects; or (b) they arrive on a moving conveyor. The collection of objects includes some with exposed barcodes and others without. The robotic system should be able to pick items from the bin or conveyor. The inbound object flow follows the order in which the objects were unloaded from the bin or conveyor.

[0041] Outbound objects are organized so that they are placed in bins, shelf locations, or rooms into which all objects corresponding to a given order are consolidated. These outbound destinations can be arranged in a vertical array, horizontal array, grid, or some other regular or irregular arrangement, but the arrangement is known to the system. The robotic pick and place system should be able to place objects at all outbound destinations and determine the correct outbound destination based on the object's SKU.

[0042] Objects should be marked with a visually unique marking, such as a barcode or radio frequency identification (RFID) tag, at one or more locations on their exterior so that they can be identified by a scanner. The type of marking depends on the type of scanning system used, but may include 1D or 2D barcode symbols. A variety of symbology or labeling methods can be used. The type of scanner used should be compatible with the marking method. Marking, whether by barcode, RFID tag, or other means, represents the encoding of a symbol string, which is typically a string of letters and numbers. The symbol string uniquely associates the object with a SKU.

[0043] The operation of the above system is coordinated by a central control system 20. Based on the symbolic string, the system determines the SKU associated with an object and the object's outbound destination. The central control system consists of one or more workstations or central processing units (CPUs). The central control system maintains the correspondence between SKUs and outbound destinations in a database, called a manifest. The central control system maintains the manifest by communicating with the warehouse management system (WMS).

[0044] During operation, the general workflow is as follows. First, the system loads an inventory, providing an outbound destination for each inbound object. Next, the system waits for the inbound objects to arrive at a bin or conveyor. The robotic system can pick up one item at a time from the input bin and can drop each item into the perception system discussed above. If the perception system successfully recognizes the markings on the object, the object is identified and forwarded to a sorting station or other processing station. If the object is not identified, the robotic system can place the object back onto the input conveyor and try again, or the conveyor can shunt the object to a manual sorting bin for human inspection.

[0045] The sequence of sensing unit positions and orientations is chosen to minimize the average or maximum amount of time required for scanning. Similarly, if an object is not recognized, it can be diverted to a special outbound destination for unrecognized objects or returned to the inbound stream. This entire process loops until all objects in the inbound collection have been processed. Objects in the inbound stream are automatically identified, sorted, and directed to outbound destinations.

[0046] Thus, according to one embodiment, the present invention provides a system for sorting objects arriving in an inbound bin and requiring placement in a shelf in an outbound bin, where the sorting is based on unique identifiers. A key feature of this embodiment is the specific design of the perception system to maximize the probability of a successful scan while minimizing the average scan time. The probability of a successful scan and the average scan time constitute key performance characteristics. These key performance characteristics depend on the configuration and properties of the perception system, as well as the set of objects and how they are labeled.

[0047] These two key performance characteristics can be optimized for a given set of items and barcode labeling methods. Optimization parameters for a barcode system include the number of barcode scanners, their location and orientation, and the sensor resolution and field of view of the scanners used. Optimization can be accomplished through trial and error, or by simulating models of the objects.

[0048] Optimization through simulation uses a barcode scanner performance model. A barcode scanner performance model is the range of positions, orientations, and barcode element sizes (the size of the smallest feature on a barcode) within which a barcode symbol can be detected and decoded by a barcode scanner. These are typically measured as minimum and maximum ranges, maximum skew angle, maximum pitch angle, and minimum and maximum tilt angle.

[0049] Typical performance of camera-based barcode scanners is that they are able to detect barcode symbols at a range of distances as long as the pitch and yaw of the symbol's plane are within plus or minus 45 degrees, while the symbol's tilt can be arbitrary (between 0 and 360 degrees). Barcode scanner performance models predict whether a given barcode symbol in a given position and orientation will be detected.

[0050] The barcode scanner performance model is combined with a model of where barcodes are expected to be positioned and oriented. The barcode symbol pose model is the range of all positions and orientations, in other words, the range of poses, at which the barcode symbol is expected to be found. For the scanner, the barcode symbol pose model is itself a combination of an item grasping model (which predicts how the robotic system will grasp the object) and a barcode item appearance model (which describes the likely positions of the barcode symbol on the object). For the scanner, the barcode symbol pose model is itself a combination of a barcode item appearance model and an inbound object pose model (which models the distribution of poses that inbound items present to the scanner). These models can be constructed empirically, using analytical models, or approximate models can be used that use a simple sphere model of the object and a uniform distribution on the sphere as the barcode item appearance model.

[0051] Figure 3 A sensing system 30 according to another embodiment of the present invention is shown, which includes a structure 32 having an opening 34. The structure 32 includes multiple rows of sources (e.g., illumination sources such as LEDs) 36 and multiple image sensing units (e.g., cameras) 38. The sources 36 are arranged in a row and each is directed toward the center of the opening. The sensing units 38 are also generally directed toward the opening, but unlike Figure 1 and Figure 2 As in the embodiment of FIG, some cameras are oriented horizontally, while other cameras are oriented upwards, and some cameras are oriented downwards. The system 30 also includes an entry source (e.g., an infrared source) 40 and an entry detector (e.g., an infrared detector 42) for detecting when an object enters the detection system 30.

[0052] Thus, the LEDs and camera surround the interior of the structure 32, and the camera is positioned to view the interior through a window that may include a glass or plastic covering, such as 44. The structure 32 may be hung by a hook 46 or placed over an opening and hung by a bracket 48.

[0053] Figure 8 The diagram shows a portion of the interior of the scanner 30, wherein the parts are shown in a linear layout. Each camera 38' includes a camera portion 50 and a tilting mirror 52 that provides the required field of view within the structure 32. Similarly, Figures 9A-9H The interior of the structure 32 within the scanning area is shown schematically and linearly. Once the entry detectors 40, 42 sense that an item has entered the scanning area, the LEDs and cameras follow a series of steps to capture multiple images. Specifically, Figure 9A As shown at 51 in FIG, the first set of LEDs 36 are illuminated and the first set of cameras 38 are enabled to take a plurality of pictures (a first set of images) of the interior of the scanner. Figure 9B As shown at 53 in FIG, the second set of LEDs 36 is illuminated and the second set of cameras 38 (one camera in this case) is enabled to take multiple pictures (a second set of images) of the interior of the scanner. Figure 9C As shown at 54 in FIG, the third set of LEDs 36 is illuminated and the third set of cameras 38 is enabled to take multiple pictures (the third set of images) of the interior of the scanner. Figure 9D As shown at 55 in FIG, the fourth set of LEDs 36 is illuminated and the fourth set of cameras 38 is enabled to take multiple pictures (the fourth set of images) of the interior of the scanner. Figure 9E As shown at 56 in FIG, the fifth set of LEDs 36 is illuminated, and the fifth set of cameras 38 is enabled to take multiple pictures (fifth set of images) of the interior of the scanner. Figure 9F As shown at 57 in FIG, the sixth set of LEDs 36 is illuminated, and the sixth set of cameras 38 is enabled to take multiple pictures (the sixth set of images) of the interior of the scanner. Figure 9G As shown at 58 in FIG, the seventh set of LEDs 36 is illuminated, and the seventh set of cameras 38 is enabled to take multiple pictures (the seventh set of images) of the interior of the scanner. Figure 9H As shown at 59 in the figure, the eighth set of LEDs 36 is illuminated and the eighth set of cameras 38 is enabled to take multiple pictures of the interior of the scanner (the eighth set of images). Again, the opening in the structure through which the camera captures the image may include clear glass or plastic 44. Each row of LEDs 36 may also include a cover of clear glass or plastic that is separated from the glass or plastic 44 of the opening to prevent light from being transmitted through the glass to any detector 38. In addition, the structure may be configured as shown in FIG. Figure 5 A protective film 33 (eg, an amber film) is shown covering the exterior of the structure (except for the top and bottom openings) that filters some wavelengths of the LEDs to protect anyone in the area.

[0054] Further references Figures 10A-10CThe process begins (step 1000) when the entry detectors 40, 42 detect whether an object has entered the scanner (step 1002). Once this occurs, the first set of lights is turned on and the first set of cameras begins capturing images (step 1004). The first set of lights and cameras are then turned off. The first set of captured images is then sent to a processing core for processing (step 1006). The second set of lights is turned on and the second set of cameras begins capturing images (step 1008). The second set of lights and cameras are then turned off. The second set of captured images is then sent to another processing core for processing (step 1010). The third set of lights is turned on and the third set of cameras begins capturing images (step 1012). The third set of lights and cameras are then turned off. The third set of captured images is then sent to another processing core for processing (step 1014). The fourth set of lights is turned on and the fourth set of cameras begins capturing images (step 1016). The fourth set of lights and cameras are then turned off. The fourth set of captured images is then sent to another processing core for processing (step 1018). The fifth set of lights is turned on and the fifth set of cameras begins capturing images (step 1020). The fifth set of lights and cameras are then turned off. The fifth set of captured images is then sent to another processing core for processing (step 1022). The sixth set of lights is turned on and the sixth set of cameras begins capturing images (step 1024). The sixth set of lights and cameras are then turned off. The sixth set of captured images is then sent to another processing core for processing (step 1026). The seventh set of lights is turned on and the seventh set of cameras begins capturing images (step 1028). The seventh set of lights and cameras are then turned off. The seventh set of captured images is then sent to another processing core for processing (step 1030). The eighth set of lights is turned on and the eighth set of cameras begins capturing images (step 1032). The eighth set of lights and cameras are then turned off. The eighth set of captured images is then sent to another processing core for processing (step 1034).

[0055] The above process can be repeated any number (m) of times (e.g., 50 times) (step 1036). After all m iterations are complete, the system confirms that the item has exited the scanner (step 1038). The system then determines whether any codes were found (step 1040). If no codes were found, it reports and errors that no codes were found (step 1046). If a code was found, the system collects all found codes (step 1042) and determines if all codes match each other (step 1044). If not, the system reports that more than one item was placed in the scanner (step 1050). If all found codes match each other, the system determines if more than one item was placed in the scanner by determining if there is too much space between the areas of the items (step 1048). If so, the system reports that more than one item was placed in the scanner (step 1050). If not, the system reports the identity of the found code (step 1052) and activates the sorting path associated with the found code (step 1054). If no code is found (step 1046) or if the system detects more items in the scanner (step 1050), the system can ask the operator if he wishes to try scanning again (or can be programmed to do so) (step 1056). If so, the system returns the item(s) to the input stream before they fell into the scanner (step 1058). If not, the system moves the item(s) to the manual picking location for a person to pick (step 1060).

[0056] Figure 11 The diagram shows the Figure 3 Specifically, a processor 62 is coupled to the structure 32 so that a light controller 66 is directed by the timing unit 60 to provide lighting control signals to a distribution control unit 64 in the structure 32, wherein the distribution control unit 64 provides individual control to each of the plurality of groups of LEDs 36. Figure 11 As shown, the processor 62 also includes a camera controller 74 coupled to the timing unit 60. The camera controller communicates with the camera controllers 70 on the structure 32 via the core processor 72, and each camera controller communicates with the group 68 of cameras 38. The controller 70 controls the triggering of the cameras and receives captured image data for processing by each corresponding core processor 72. The results of the core processors 72 are provided to the output recognition unit 76.

[0057] Figures 13A-13R Shown by Figure 3 The falling scanner captures nine images of two items during movement and the associated processed image data. Specifically, Figure 13A No objects are seen in Figure 13B The related processed image data shown in does not show the signal. Figure 13C , the object appears in the image, and Figure 13D The related processed image data in shows the image of the object. Figure 13E As shown, a second object appears in the field of view, Figure 13F The related processed image data shown in shows a second item. In this image (and Figure 13H and Figure 13J In the processed image data), the system will detect that more than one item has fallen into the scanner because there will be too much area between the two items. Figure 13G As shown, the second object continues to appear in the field of view, and the related processed image data is Figure 13H Similarly, Figure 13I As shown, the second object continues to appear in the field of view but begins to move closer to the first object, and the associated processed image data is Figure 13J As shown in Figure 13K As shown, the second item moves closer to the first item, and the related processed image data is Figure 13L As shown in Figure 13M and Figure 13O As shown, the second object moves very close to the first object, and the related processed image data are respectively Figure 13N and Figure 13P Shown in. Figure 13Q shows that the item is leaving or has left the scanner, and the related processed image data is in Figure 13R Therefore, capturing multiple images is important for identifying whether more than one item is present in the scanner 32 at a time.

[0058] As described above, the output of the processor provides a signal representing the identified code of the item in the scanner, and based thereon, the sorting system can immediately take action consistent with directing the item in a desired direction or processing path. For example, Figure 14 Shows the use of Figure 3 Items may be dropped into the scanner by any means, such as, but not including, a robotic arm 86 (in which item 84 is dropped) or an input conveyor 90 (in which item 88 is dropped). In the case of a robotic arm 86, the end effector may employ a deflection sensor 85 to detect whether item 84 is moving (e.g., wiggling) relative to the robotic arm 86 before dropping the item into the scanner 32 (and if so, wait until the movement stops).

[0059] The scanner 32 is coupled to the processor 62 as described above, and outputs sort control signals 63 that are provided to a sorting system, such as, for example, a controller 96 of a conveyor 94, which directs the item (e.g., 92) to any one of a plurality of cartons, containers, or locations 98, 104, for example, by moving the item in either direction indicated by C. For example, items 100 and 102 have been directed to location 98, and item 106 has been directed to location 104.

[0060] The system may also include an interruption system that interrupts the object from falling through the sensing system. The interruption system may be useful, for example, when the item to be scanned is a plastic bag (opaque or transparent), particularly when the identification code (such as a barcode) is not visible or not easily visible to the sensing unit, for example, if the bag is folded and obscures the barcode. Figure 15 In this case, the interrupter element can flatten the bag via the interrupter plate 120. The interrupter plate 120, as described above, can include: another detection unit 124 below the transparent window in the interrupter element 120 to detect the identifier mark facing the interrupter element; and a light 126 that is illuminated when the detection unit 124 captures an image. The interrupter element 120 can also be disposed on an articulated bracket 122 that allows the interrupter element to be moved into or out of the path of items falling from the scanning unit 32. The interrupter unit 120 can be disposed within or below the scanning unit 32. Similarly, the scanner 32 is coupled to the processor 62 as described above, and outputs sorting control signals that are provided to a sorting system, such as, for example, a controller of the conveyor 94, which directs the item (e.g., 92) to any of a plurality of cartons, containers, or locations 98, 104, for example, by moving the item in any of the directions indicated by C.

[0061] In other embodiments, the system may include an interrupting element that pushes lighter items upward in the opposite direction for a shorter period of time. Figure 16 In this case, the interrupter element can push the lighter bags upward via a fan 144 attached to a motor 142, which provides upward air pressure through the screen 140. The fan 144 can be located inside or below the scanning unit 32. Likewise, the scanner 32 is coupled to the processor 62 as described above, and the output sorting control signal is provided to a sorting system, such as, for example, a controller of the conveyor 94, which directs the article (e.g., 92) to any of a plurality of cartons, containers, or locations 98, 104, for example, by moving the article in any direction indicated by C.

[0062] Those skilled in the art will appreciate that various modifications and variations can be made to the above-disclosed embodiments without departing from the spirit and scope of the invention.

Claims

1. A method for processing an object, comprising: causing one or more objects to fall into a sensing system, wherein the sensing system comprises a housing having an open top and an open bottom, wherein the one or more objects fall into the sensing system through the open top and exit the sensing system through the open bottom; illuminating a path through the sensing system between the open top and the open bottom using a plurality of illumination sources associated with a plurality of sensing units; capturing perception data associated with the one or more objects falling through a path of the illuminated perception system, wherein the perception data is captured by illumination reflected from the one or more objects by the plurality of perception units; identifying, within the captured perception data from the plurality of perception units, tags associated with the one or more objects; evaluating the identified markers by determining whether the markers identified in the captured perception data from the plurality of perception units match to determine whether the one or more objects are one or more objects that fall simultaneously upon the perception system; In response to determining that all of the identified markers match, transporting the one object to a first predetermined location associated with the identified markers; In response to determining that at least two of the identified signatures do not match, the plurality of objects are transported to a second predetermined location.

2. The method according to claim 1, wherein At least one perception unit of the plurality of perception units comprises a camera, and wherein the perception data captured by the camera comprises image data.

3. The method according to claim 1, wherein At least one of the plurality of perception units comprises a scanner, and the perception data captured by the scanner comprises scanner data.

4. The method according to claim 3, wherein The scanner is a radio frequency ID scanner.

5. The method according to claim 3, wherein The scanner is a barcode scanner.

6. The method according to claim 3, wherein The scanner is a laser reflectivity scanner.

7. The method according to claim 1, wherein The plurality of illumination sources are mounted on opposite sides of each sensing unit.

8. The method according to claim 1, wherein The plurality of illumination sources surround each sensing unit.

9. The method according to claim 1, wherein The plurality of illumination sources includes a plurality of light emitting diodes.

10. The method according to claim 1, wherein The second predetermined location to which the plurality of objects are transported is an input location upstream of the perception system.

11. The method according to claim 1, wherein The second predetermined location to which the plurality of objects are transported is a manual picking location.

12. The method according to claim 1, wherein The captured sensory data includes image data, and evaluating the identified landmarks further includes determining that an object or objects are captured in the image data.

13. The method according to claim 12, wherein: Evaluating the identified landmarks further includes comparing relative positions of detected objects in the image data.

14. A method of processing an object, comprising: causing at least a first object to fall toward a sensing system, wherein the sensing system comprises a housing having an open top and an open bottom, wherein the at least first object falls toward the sensing system through the open top and exits the sensing system through the open bottom; illuminating a first portion of a path through the sensing system between the open top and the open bottom using a first plurality of illumination sources associated with a first sensing unit; capturing first perception data associated with at least the first object falling through the first portion of the path, wherein the perception data is captured by the first perception unit of illumination reflected from at least the first object; illuminating a second portion of the path using a second plurality of illumination sources associated with a second sensing unit; capturing second sensory data associated with at least the first object falling through the second portion of the path, wherein the sensory data is captured by illumination reflected from at least the first object by the second sensory unit; illuminating a third portion of the path using a third plurality of illumination sources associated with a third sensing unit; capturing third perception data associated with at least the first object falling through the third portion of the path, wherein the perception data is captured by illumination reflected from at least the first object by the third perception unit; identifying within the captured first, second, and third sensory data a marker associated with at least the first object; determining whether a second object has fallen into the perception system along with the first object by determining whether the signatures in the first, second, and third perception data match; In response to determining that all of the identified markers match, transporting the first object to a first predetermined location associated with the identified markers; In response to determining that at least two of the identified markers do not match, the first object and the second object are transported to a second predetermined location.

15. The method according to claim 14, wherein The first, second and third portions of the path at least substantially overlap one another.

16. The method according to claim 14, wherein Each of the first, second and third perception units comprises a camera, and wherein the perception data captured by the camera comprises image data.

17. The method according to claim 14, wherein Each of the first, second, and third perception units comprises a scanner, and the perception data captured by the scanner comprises scanner data.

18. The method according to claim 17, wherein The scanner is a radio frequency ID scanner.

19. The method according to claim 17, wherein The scanner is a barcode scanner.

20. The method of claim 17, wherein: The scanner is a laser reflectivity scanner.

21. The method of claim 14, wherein: At least one of the first plurality of illumination sources associated with the first sensing unit, the second plurality of illumination sources associated with the second sensing unit, and the third plurality of illumination sources associated with the third sensing unit are mounted on opposite sides of the respective sensing units.

22. The method according to claim 21, wherein At least one of the first plurality of illumination sources associated with the first perception unit, the second plurality of illumination sources associated with the second perception unit, and the third plurality of illumination sources associated with the third perception unit surrounds the corresponding perception unit.

23. The method according to claim 21, wherein The plurality of illumination sources includes a plurality of light emitting diodes.

24. The method of claim 14, wherein: At least one of the first, second, and third perception data includes image data, and wherein determining whether the second object falls to the perception system includes determining whether one object or multiple objects are captured in the image data.

25. The method of claim 24, wherein: Determining whether one object or multiple objects are captured in the image data includes comparing relative positions of objects detected in the image data.

26. The method of claim 14, wherein: If a second object is determined to be present, the second predetermined location is an input location upstream of the perception system.

27. The method of claim 14, wherein: If the second object is determined to be present, then the second predetermined location is a manual picking location.

28. A method of processing an object, comprising: causing at least a first object to fall toward a sensing system, wherein the sensing system comprises a housing having an open top and an open bottom, wherein the at least first object falls into the sensing system through the open top and exits the sensing system through the open bottom; triggering an entry detector in response to the first object entering the perception system and providing entry detector data; illuminating a portion of a path through the perception system using a plurality of illumination sources associated with and surrounding one or more perception units in response to the entry detector data; capturing perception data associated with at least the first object falling through the portion of the path that is illuminated, wherein the perception data is captured by the one or more perception units of illumination reflected from at least the first object, and the perception data includes image data captured by at least one of the one or more perception units; identifying a unique marker associated with the first object in the captured perception data from the one or more perception units; determining whether a second object enters the perception system simultaneously with the first object by detecting the first object and at least one other object spaced apart from the first object in the image data; in response to detecting only the first object in the image data, transporting the first object to a first predetermined location associated with the identified marker; In response to detecting the first object and at least one other object in the image data, the first object and the second object are transported to a second predetermined location.

29. The method of claim 28, wherein At least one of the one or more sensing units includes a scanner, and the sensing data includes scan data.

30. The method of claim 29, wherein: The scanner is a radio frequency ID scanner.

31. The method of claim 29, wherein: The scanner is a barcode scanner.

32. The method of claim 29, wherein: The scanner is a laser reflectivity scanner.

33. A perception system for processing one or more objects, the perception system comprising: A structure comprising an open path extending from top to bottom; a first plurality of sensing units substantially surrounding a first upper portion of the open path; a second plurality of sensing elements substantially surrounding a second lower portion of the open path; a processor for processing perception data from each of the first plurality of perception units and the second plurality of perception units and for determining whether one or more object identification codes are in the perception data from each of the first plurality of perception units and the second plurality of perception units; A conveying system for directing one or more objects to either a return path or a manual picking path if one or more object identification codes are determined in the sensing data from each of the first and second plurality of sensing units.

34. The sensing system according to claim 33, wherein: The structure is provided with an open housing having an open housing top associated with the top of the structure and an open housing bottom associated with the bottom of the structure.

35. The sensing system according to claim 34, wherein: The perception system further includes an input detector for detecting one or more objects entering the top of the open housing.

36. The sensing system according to claim 33, wherein: The sensing system further includes a plurality of illumination sources.

37. The sensing system according to claim 36, wherein: The plurality of illumination sources includes a plurality of LEDs.

38. The sensing system according to claim 36, wherein: Each of the plurality of illumination sources is associated with a sensing unit of the plurality of sensing units.

39. The sensing system according to claim 36, wherein: The plurality of illumination sources comprises a plurality of illumination source sets, each illumination source set being associated with a sensing unit of the plurality of sensing units.

40. The sensing system according to claim 33, wherein: The transport system includes a conveyor.

41. The sensing system according to claim 40, wherein: The conveyor comprises a bidirectional conveyor.

42. The sensing system according to claim 33, wherein: The sensing system further includes an intermediate element between the bottom of the structure and the transport system, the intermediate element for receiving the one or more objects and facilitating identification of the one or more objects.

43. A perception system for processing one or more objects, the perception system comprising: A structure comprising an open path extending between a top portion and a bottom portion; a first plurality of sensing units substantially surrounding a first upper portion of the open path; a second plurality of sensing elements substantially surrounding a second lower portion of the open path; a processor for processing perception data from each of the first plurality of perception units and the second plurality of perception units and for determining whether a no-object identification code is in the perception data from each of the first plurality of perception units and the second plurality of perception units; A conveying system for directing any object received from the bottom or the structure to either a return path or a manual picking path if it is determined that no object identification code is in the sensing data from each of the first plurality of sensing units and the second plurality of sensing units.

44. The sensing system according to claim 43, wherein: The structure is provided with an open housing having an open housing top associated with the top of the structure and an open housing bottom associated with the bottom of the structure.

45. The sensing system according to claim 44, wherein: The perception system further includes an input detector for detecting one or more objects entering the top of the open housing.

46. ​​The sensing system according to claim 43, wherein: The sensing system further includes a plurality of illumination sources.

47. The sensing system according to claim 46, wherein: The plurality of illumination sources includes a plurality of LEDs.

48. The sensing system according to claim 46, wherein: Each of the plurality of illumination sources is associated with a sensing unit of the plurality of sensing units.

49. The sensing system according to claim 46, wherein: The plurality of illumination sources comprises a plurality of illumination source sets, each illumination source set being associated with a sensing unit of the plurality of sensing units.

50. The sensing system according to claim 43, wherein: The transport system includes a conveyor.

51. The sensing system according to claim 50, wherein: The conveyor comprises a bidirectional conveyor.

52. The sensing system according to claim 43, wherein: The sensing system further includes an intermediate element between the bottom of the structure and the transport system, the intermediate element for receiving the one or more objects and facilitating identification of the one or more objects.

53. A method of providing one or more objects, the method comprising: providing a structure including an open path extending between a top portion and a bottom portion; providing a first plurality of sensing units substantially surrounding a first upper portion of the open path; providing a second plurality of sensing units substantially surrounding a second lower portion of the open path; processing sensory data from each of the first plurality of sensory units and the second plurality of sensory units; determining whether one or more object identification codes are in the perception data from each of the first plurality of perception units and the second plurality of perception units; as well as If more than one object identification code is determined to be in the perception data from each of the first plurality of perception units and the second plurality of perception units, the more than one object is conveyed to either a return path or a manual pick path.

54. The method of claim 53, wherein: The structure is provided with an open housing having an open housing top associated with the top of the structure and an open housing bottom associated with the bottom of the structure.

55. The method of claim 54, wherein The method further includes detecting entry of one or more objects into the open housing top.

56. The method of claim 53, wherein: The method further includes providing illumination using a plurality of illumination sources.

57. The method of claim 56, wherein: The plurality of illumination sources includes a plurality of LEDs.

58. The method of claim 56, wherein: Each of the plurality of illumination sources is associated with a sensing unit of the plurality of sensing units.

59. The method of claim 56, wherein The plurality of illumination sources comprises a plurality of illumination source sets, each illumination source set being associated with a sensing unit of the plurality of sensing units.

60. The method of claim 53, wherein Transporting the one or more objects to either the return path or the manual picking path includes using a conveyor.

61. The method of claim 60, wherein: The conveyor comprises a bidirectional conveyor.

62. The method of claim 53, wherein: The method further includes receiving the one or more objects using an intermediate element between the bottom portions of the structure, and conveying the one or more objects to either a return path or a manual picking path.

63. A method of providing one or more objects, the method comprising: providing a structure including an open path extending between a top portion and a bottom portion; providing a first plurality of sensing units substantially surrounding a first upper portion of the open path; providing a second plurality of sensing units substantially surrounding a second lower portion of the open path; allowing one or more to travel along said open path; processing sensory data from each of the first plurality of sensory units and the second plurality of sensory units; determining whether no object identification code is in the perception data from each of the first plurality of perception units and the second plurality of perception units; as well as receiving the one or more objects from a bottom portion of the structure; as well as If it is determined that no object identification code is in the perception data from each of the first and second plurality of perception units, the one or more objects are conveyed to either a return path or a manual pick path.

64. The method of claim 63, wherein: The structure is provided with an open housing having an open housing top associated with the top of the structure and an open housing bottom associated with the bottom of the structure.

65. The method of claim 64, wherein: The method further includes detecting entry of one or more objects into the open housing top.

66. The method of claim 63, wherein The method further includes providing illumination using a plurality of illumination sources.

67. The method of claim 66, wherein The plurality of illumination sources includes a plurality of LEDs.

68. The method of claim 66, wherein: Each of the plurality of illumination sources is associated with a sensing unit of the plurality of sensing units.

69. The method of claim 66, wherein The plurality of illumination sources comprises a plurality of illumination source sets, each illumination source set being associated with a sensing unit of the plurality of sensing units.

70. The method of claim 63, wherein Transporting the one or more objects to either a return path or a manual picking location includes using a conveyor.

71. The method of claim 70, wherein The conveyor comprises a bidirectional conveyor.

72. The method of claim 63, wherein The method further includes receiving the one or more objects using an intermediate element between the bottom portions of the structure, and conveying the one or more objects to either a return path or a manual picking path.

Images