Product packaging using computer vision and adaptive package selection

Abstract

A system (100) and method for packaging a shipping container (108). The method includes: detecting, by a computing device (132), a presence of a shipping container (108); generating, by the computing device (132), a 3D point cloud comprising a 3D perspective representation of an interior of the shipping container (108) and a surface of at least one item placed in the shipping container (108); analyzing, by the computing device (132), the 3D point cloud to identify a void region within the interior of the shipping container (132) that is empty of the at least one item; selecting, by the computing device (132), a percentage from a plurality of possible percentages based on characteristics of the void region; and causing, by the computing device (132), a protective packaging (120, 124) to be dispensed into the void region such that the selected percentage of the void region is filled with the protective packaging (120, 124).

Description

[0001] Cross-reference to related applications

[0002] This application claims priority and benefit to U.S. Provisional Patent Application No. 63 / 488,023, filed March 2, 2023, the contents of which are incorporated herein by reference in their entirety. Background Technology

[0003] Description of related technologies

[0004] When a product is purchased online, it is packaged and sent to the buyer via parcel delivery. Products are typically sent in flexible mailers or boxes lined / filled with protective packaging. Protective packaging may include, for example, bubble wrap, wrapping paper padding, biodegradable peanut packing, foam, corrugated padding, and / or inflatable mats (or pillows). Individuals place one or more products in the box, obtain the protective packaging, fill the box with the protective packaging, and seal the box for shipment. Known processes utilize human assistance throughout the box filling / sealing process. Summary of the Invention

[0005] This disclosure relates to a method for packaging a shipping container. The method includes: detecting the presence of the shipping container using a computing device; generating a 3D point cloud using the computing device, the 3D point cloud including a 3D perspective representation of the interior of the shipping container and the surface of at least one item placed in the shipping container; analyzing the 3D point cloud using the computing device to identify void regions inside the shipping container, the void regions being empty of the at least one item; selecting a percentage from a plurality of possible percentages based on characteristics of the void regions using the computing device; and assigning protective packaging to the void regions using the computing device, such that the selected percentage of the void regions is filled with protective packaging.

[0006] This disclosure also relates to a system. The system includes: a processor; and a non-transitory computer-readable storage medium including programming instructions configured to cause the processor to implement a method for packaging a shipping container. The programming instructions include instructions to: detect the presence of the shipping container; generate a 3D point cloud including a 3D perspective representation of the interior of the shipping container and the surface of at least one article placed in the shipping container; analyze the 3D point cloud to identify void regions inside the shipping container, the void regions vacating the at least one article; select a percentage from a plurality of possible percentages based on characteristics of the void regions; and cause protective packaging to be allocated to the void regions, such that the selected percentage of the void regions is filled with protective packaging.

[0007] This disclosure also relates to a non-transitory computer-readable medium storing instructions that, when executed by at least one computing device, cause the at least one computing device to perform operations. These operations include: detecting the presence of a shipping container; generating a 3D point cloud including a 3D perspective representation of the interior of the shipping container and the surface of at least one article placed in the shipping container; analyzing the 3D point cloud to identify void regions inside the shipping container, the void regions vacating the at least one article; selecting a percentage from a plurality of possible percentages based on characteristics of the void regions; and causing protective packaging to be allocated to the void regions, such that the selected percentage of the void regions is filled with the protective packaging. Attached Figure Description

[0008] The solution will be described with reference to the following figures, where similar numbers throughout the figures represent similar items.

[0009] Figure 1 A diagram illustrating the system is provided.

[0010] Figures 2-3 Each provided is an illustration of a shipping container that includes a void area that has been divided into void areas.

[0011] Figure 4 A graph is provided showing the non-linear relationship between the cubic volume of the void region and the number of inflatable pads to be used to fill the cubic volume of the void region.

[0012] Figures 5A-5B (Collectively referred to as “Figure 5”) provides a flowchart illustrating the methods for filling, closing and sealing shipping containers.

[0013] Figure 6 A diagram of the computing device is provided. Detailed Implementation

[0014] It will be readily understood that the components of the embodiments described herein and illustrated in the accompanying drawings can be arranged and designed in a wide variety of different configurations. Therefore, as illustrated in the figures, the following more detailed description of various embodiments is not intended to limit the scope of this disclosure, but merely represents various embodiments. Although various aspects of the embodiments are presented in the drawings, the drawings are not necessarily drawn to scale unless specifically indicated otherwise.

[0015] This solution may be embodied in other specific forms without departing from its spirit or essential characteristics. The described embodiments should be considered illustrative rather than restrictive in all respects. Therefore, the scope of this solution is indicated by the appended claims rather than by this specific embodiment. All modifications within the equivalent meaning and scope of the claims are to be included within its scope.

[0016] References to features, advantages, or similar language throughout this specification do not imply that all features and advantages achievable through this solution are or should be present in or should be present in any single embodiment of this solution. Rather, references to features and advantages should be understood as meaning that a particular feature, advantage, or characteristic described in connection with an embodiment is included in at least one embodiment of this solution. Therefore, the discussion of features, advantages, and similar language throughout this specification may (but not necessarily) refer to the same embodiment.

[0017] Furthermore, the features, advantages, and characteristics described in this solution can be combined in any suitable manner in one or more embodiments. Those skilled in the art will recognize, based on the description herein, that this solution can be practiced without one or more specific features or advantages of a particular embodiment. In other instances, additional features and advantages that may not be present in all embodiments of this solution may be recognized in certain embodiments.

[0018] Throughout this specification, references to "an embodiment," "embodiment," or similar language mean that a particular feature, structure, or characteristic described in connection with the indicated embodiment is included in at least one embodiment of this solution. Therefore, the phrases "in an embodiment," "in an embodiment," and similar language throughout this specification may (but not necessarily) refer to the same embodiment.

[0019] As used in this document, unless the context clearly specifies otherwise, the singular forms “a,” “an,” and “the” include plural references. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. As used in this document, the term “comprising” means “including, but not limited to,” “including.”

[0020] As described above, products purchased online are packaged and sent to the buyer via parcel delivery services. Products are typically sent in flexible mailing bags or boxes lined / filled with protective packaging materials. Protective packaging may include cushioning or void fill, such as bubble wrap, packing paper padding, foam, and / or inflatable mats (or pillows). Individuals or robotic robots may pick up (one or more) products and place them into selected boxes or mailing bags. Appropriate protective packaging is then obtained to cover or fill voids in the boxes, occupying space and protecting (one or more) products for shipment. It is known that human assistance is used throughout the picking process prior to the filling / sealing, the selection of boxes or mailing bags, the sorting of products for the order, and the decisions regarding the type of internal packaging and the style of boxes or mailing bags.

[0021] In distribution centers, there is a need for a method to package consumer-purchased products at high speed with limited or no human assistance required. Therefore, traditional solutions are labor-intensive, isolated, and disconnected, resulting in increased human input in protecting products through the use of more or less packaging or incorrect packaging methods. The solution described herein provides an automated or semi-automated method for identifying and packaging items with protective packaging, thereby sending items to their destination on a relatively large scale. Automation or semi-automation reduces costs, the amount of labor required, and the amount of human error.

[0022] One or more products are configured to be placed inside or between packaging containers or articles being shipped or stored to protect the articles, fill empty spaces within the container (such as a packaging container), and / or prevent or inhibit the movement of the articles within the packaging container. While there is overlap between the following categories, example categories of protective packaging items include protective filler items and block-and-brace items.

[0023] Protective padding elements are typically provided individually or as multiple units configured to be placed in void spaces to provide a desired level of packaging. Such units typically have a predetermined size, or may have predetermined dimensions and be configurable in another dimension, such as length. In some examples, the size of the protective padding element may be configurable in several or all of its dimensions. Protective padding elements are typically resilient and flexible to compress and adapt to the corners, edges, and sides of the packaged item, thereby filling or cushioning the space surrounding the item(s) rather than presenting a solid shape corresponding to the space surrounding the item. Protective padding elements include, for example, void fillers and cushioning elements.

[0024] Cavity fillers typically provide minimal cushioning and are relatively soft. These fillers are commonly used to fill the empty spaces within packaging containers to reduce movement of lightweight items that are or may be fragile or susceptible to damage from the box's interior, or to prevent the internal movement of potentially damaging items (such as glass jars) when multiple products are placed in a box. Examples of void fillers include crumpled-paper padding with a fairly light, loft pattern and other easily compressible space fillers.

[0025] Cushioning elements are configured to provide cushioning for packaged items, as well as varying degrees of protection against shocks and impacts that may occur 20-30 times during an average shipping cycle. Examples of cushioning materials include inflatable air pillows and pads, bubble wrap, paper padding with a fluffy structure capable of withstanding moderate shocks and impacts, foam boards, and packaged peanuts. Typically, both gap filler and cushioning elements are provided as multiple units of similar size (often a common, predetermined size), although in some applications, additional protective filler or cushioning elements may be made in custom sizes.

[0026] Multiple gap fillers or cushioning materials used are typically selected by allocating a certain length of material to place inside the container to adequately fill the gap spaces, thereby providing the desired protective function. Some gap fillers or cushioning materials, such as expandable paper or bubble wrap that can be used to wrap items such as bottles, jars, or fragile items, can be used to seal or otherwise surround items.

[0027] Several systems have been used to speed up the packaging process and reduce waste by optimizing the amount of protective packaging (e.g., inflatable cushions) used to fill each shipping container (e.g., box). Traditional systems primarily involve manual determination, which is based on guesswork about what they are packing and the correct boxes, the amount of packaging, and the proper use of the packaging. In some cases, cameras have been used for trial and error and quality improvement as prices have decreased over the years. In this solution, machine learning allows cameras and other sensors to: detect when a shipping container approaches the dispensing system; automatically calculate the size of the detected shipping container; detect when the center of the shipping container aligns with the dispenser using cameras or other sensors; generate a 2D image from the top of the carton to identify portions of the shipping container's contents; identify whether the interior of the shipping container is empty or lacks any objects or items; calculate the volume of the identified empty areas; optionally segment the empty areas; communicate with a timer that will dispense some protective packaging to fill the empty areas or portions of each empty area (e.g., based on the size of the empty area, the size of the empty area portion, and / or the type of product placed in the shipping container); and / or control the dispenser to dispense protective packaging into the shipping container.

[0028] This solution will now be described in conjunction with the packaging of the purchased items. This solution can also be used in other applications when it is necessary to deliver objects from a starting location to a destination.

[0029] Figure 1An illustration is provided of a system 100 typically configured to facilitate the packaging and shipment of articles 110. Articles may include a variety of products and may include perishable items (e.g., food) and / or non-perishable items (e.g., clothing, home appliances, automotive parts, beauty products, personal care items, books, consumer electronics, entertainment tickets, fashion accessories, footwear, office supplies, sports equipment, toys, video games, watches, eyeglasses, and / or jewelry).

[0030] System 100 includes one or more packaging stations 102, one or more sensor systems 106, one or more optional inflation modules 160, one or more dispensers 118, 122, and one or more container closure / sealing devices 126. These components are communicatively coupled to each other and to one or more computing devices 132 via a network 130 (e.g., the Internet or an intranet). Each packaging station 102 includes a conveyor belt 104 controlled by a controller 192. Any known or future known conveyor belts and controllers may be used herein. One or more optional storage bins may be provided at the ends of the conveyor belt 104 for temporary storage of sealed shipping containers and / or transport to sorting / shipping stations.

[0031] like Figure 1 As shown, sensor system 106 is positioned relatively close to packaging station 102, a location suitable for generating sensor data relating to shipping containers 108, 170, 180 moving from conveyor belt 104 toward one or more dispensers 118, 122. Each shipping container 108, 170, 180 has one or more items 110 placed therein, which may or may not be protected from damage by protective packaging dispensed by one or more dispensers 118, 122 during shipment. Shipping containers may include, but are not limited to, shipping boxes, shipping bags, and / or shipping envelopes. Sensor system 106 may include, but is not limited to, one or more monocular cameras, one or more digital cameras, one or more radar sensors, one or more lidar sensors, one or more time-of-flight (ToF) cameras, and / or one or more other sensor devices. More than one sensor type may be combined to generate additional data or confirm point cloud accuracy, especially in the case of opaque or reflective surfaces.

[0032] One or more dispensers 118, 122 can have any suitable configuration to produce the desired type of protective filler. For example, one or more dispensers 118, 122 can be configured to convert supplied material into protective packaging material. In this case, one or more dispensers 118, 122 may include one or more paper padding machines, one or more inflation and sealing devices, and / or one or more foam-in-bag devices. Alternatively, one or more dispensers 118, 122 can simply dispense protective packaging elements from them. In this case, one or more dispensers 118, 122 can store and dispense packaged peanuts, discrete lengths of bubble wrap, discrete lengths of paper padding, and / or other types of protective packaging elements. One or more dispensers 118, 122 may include a cutting mechanism for cutting bubble wrap sheets and / or paper padding sheets from the rolls stored therein. In other scenarios, one or more distributors 118, 122 are coupled to external devices that supply protective packaging to be dispensed by one or more distributors 118, 122. These external devices may include, but are not limited to, one or more inflatable sealing modules.

[0033] One or more inflation modules 160 are configured to inflate inflatable protective packaging, such as mats, pillows, and airbags. The inflated protective packaging is then provided to dispenser 118 for storage and dispensing into shipping containers as they pass beneath it. A single dispenser 118 may be provided in system 100. Alternatively, two or more dispensers 118, 122 may be provided in system 100, configured to dispense the same or different types of protective packaging depending on the required protection. For example, a first dispenser 118 may dispense inflatable mats, while a second dispenser may dispense paper padding. One or more inflation modules 160 and / or one or more dispensers 118, 122 may be manually controlled by an individual 136 or automatically controlled by a computing device 132. This solution will be discussed below in the context of automatic control.

[0034] As the shipping container 108 moves along the upper conveyor belt 104 in direction 114, a proximity sensor 116 detects when the shipping container 108 approaches the sensor system 106. The proximity sensor 116 may include, but is not limited to, a beam brake sensor, a scanner (e.g., a barcode scanner), and / or a camera. The sensor system 106 may generate sensor data continuously or periodically in response to a triggering event. Triggering events may include, but are not limited to, alignment of the center of the shipping container 108 with the axis 150 of the sensor system 106. The shipping container 108... Figure 1The container is shown as including a shipping box. As mentioned above, the shipping container may alternatively include, for example, a shipping bag or a shipping envelope.

[0035] In some scenarios, system 100 performs operations to detect when the center of the shipping container is aligned with axis 150 of sensor system 106. This can be accomplished, for example, using computing device 132 and sensor devices of sensor system 106. A first sensor device generates a depth measurement. Computing device 132 uses the depth measurement to detect the leading edge 140 and trailing edge 142 of the shipping container as it moves on a conveyor belt in direction 114. When the depth measurement is less than a threshold... thr At that time, each leading edge 140 and trailing edge 142 of the shipping container 108 was detected. Threshold thr The selection can be based on the known distance between sensor system 106 and conveyor belt 104 and the known height of the sidewall of the shipping container (where the flange extends in the upward direction, i.e., the flange (or baffle) has not yet bent at the notch (or seam) 152). Additional alternative sensors can be added to identify notches (152) where the baffle folds to close the box, and depth measurement can be achieved by identifying notches that will determine the length of the baffle (flange) or ultimately the depth of the box. These two edge detections are then used to determine the length of shipping container 108. L (Extending in the direction of travel of the conveyor belt 114). Container length. L Edge detection timing and known transmission speed S The time used to identify the alignment of the center of the shipping container with axis 150 t The conveyor belt 104 can be selectively controlled by the controller 192 to (i) continuously move the transport container 108 at a given speed in direction 114, or (ii) temporarily stop the transport container when the center of the transport container 108 is aligned with axis 150. In scenario (i), an encoder can be employed on the moving conveyor to associate gap samples with the axis of the movement.

[0036] In time t At this point, the second sensor device of sensor system 106 is enabled or otherwise activated to generate sensor data containing a 3D point cloud for producing the internal cavity of shipping container 108. The 3D point cloud comprises multiple points plotted on a 3D map to provide a 3D surface map of the inner wall surface of shipping container 108 and / or the exposed surfaces of any articles placed inside the shipping container. Therefore, each point has x, y, and z coordinates.

[0037] Computing device 132 analyzes 3D point cloud and other sensor data to identify one or more regions inside shipping container 108 that (i) are located below baffle seams (or notches) 152, and (ii) are voids or otherwise vacant of any object(s). The identified regions(s) are referred to herein as void regions(s). In some scenarios, the baffles of the shipping container and the filtered contours around the shipping container define the geometry of the shipping container footprint, and through automated depth measurement, computing device 132 is able to determine the volume of the empty space in shipping container 108. Based on the topography of the contents and the volume of the empty shipping container, the remaining space can be calculated as a void. Still images with 3D point clouds allow machine vision to verify the true nature of the contents of shipping container 108, particularly shiny objects, transparent or opaque films, etc.

[0038] In other scenarios, the void area can be determined in another way. The height of the shipping container 108. H When fully packed, it extends vertically from the bottom edge 154 of the box to the baffle seam (or notch) 152. This height... H It can be calculated and / or obtained from data storage 134 in a variety of ways. For example, height. H The depth is calculated based on a depth measurement associated with the leading edge 140 or trailing edge 142 of the shipping container 108. This depth measurement specifies the height of the upper edge of the baffle relative to the top surface of the conveyor belt, sensor equipment, or other reference point. h . H By h Divide by N (Right now, H = h / N) or will h Multiply N To determine, among which N It is any number greater than zero (e.g., 2). h and H The ratio is known. Then the total internal volume of the shipping container 108 (e.g., a box) can be determined using the length... L ,high H and width W To calculate the width. W Determined from 3D point cloud data, and extended laterally to the direction of travel of the conveyor belt 114.

[0039] The dimensions of the boxes may be known, either additionally or alternatively, in a warehouse management system (WMS) or other facility management software. In this case, the box dimensions can be passed to the computing device when an identification code (usually a barcode on the carton) is scanned.

[0040] Then, a cuboid or other 3D shape representing the 3D shipping container with these dimensions can be generated. The cuboid or other 3D shape can then be superimposed on the 3D map such that (i) the center of the cuboid or other 3D shape is aligned with the center of the shipping container 108, and (ii) the bottom face of the cuboid or other 3D shape is aligned with a known position of the top face of the conveyor belt 104. Any points residing outside the cuboid / 3D shape in the 3D point cloud can be discarded or otherwise filtered. The remaining points of the cuboid / 3D shape and the 3D point cloud are then analyzed to identify one or more void regions inside the shipping container 108. The cube product of each identified void region can be calculated using known mathematical algorithms. V .

[0041] After identifying one or more void regions, computing device 132 can store information 160 in data storage 134, which: identifies shipping container 108; identifies each void region detected inside shipping container 108; specifies the location of each void region inside shipping container 108; and specifies the cubic volume of each void region. V ; and / or specify the type of each object placed inside the shipping container 108. The object type can be determined based on known or to be known object type detection techniques that use 3D point clouds, scanner data (e.g., barcode data), machine vision, and / or accessible product data extracted from a database of products with pre-programmed sizes or manually determined dimensions, using 3D scanners for determining product size.

[0042] Then the computing device 132 can determine the cubic volume of each void region. V Is it large enough to be filled with at least a minimum amount of protective packaging (e.g., a minimum length of paper padding or a minimum number of inflatable pads that can be measured in linear footage)? If not, the shipping container 108 may be selectively made to travel toward the downstream shipping container closure / seal device 126 without dispensing any protective packaging into it through one or more dispensers 118, 122.

[0043] If so, the computing device 132 performs other operations to facilitate the filling of the shipping container 108 by one or more distributors 118, 122 with one or more protective packages 120, 124. For each void region, the computing device 132 can perform calculations based on the cubic volume associated with the void region. V And / or the type of object placed in or near the void area in the shipping container 108 (i) select the type of packaging material from multiple packaging material types, and / or (ii) select a percentage between 0% and 100%. For example, when the cube volumeV When the object has a first value and its type is a blanket, the computing device 132 selects paper padding and 60%; and alternatively, when the volume... V When the second value is available and the object type is glassware, the calculation device selects an inflatable cushion (or pillow) and 95%. The percentage indicates the minimum amount that the void area should be filled with protective packaging.

[0044] Cube product of the void region V The relationship between the percentage of void areas that should be filled with protective packaging can be non-linear. Figure 4 The document provides graphs illustrating illustrative nonlinear relationships. These nonlinear relationships can be empirically determined based on collected information and / or best curve fitting algorithms.

[0045] When selecting an inflatable type of protective packaging, the computing device 132 can additionally determine the amount of air the protective packaging should be inflated. For example, the computing device 132 predetermines that an inflatable pad of a given size (e.g., 5x8 inches in its uninflated state) should be used to fill the shipping container 108. The computing device 132 then accesses, for example, a lookup table (LUT) to obtain the inflation amount of the inflatable pad, such that at least 75% of the void area inside the box is filled. The LUT may consist of an identifier for an inflatable pad of a given size, an identifier for the type of object placed in the shipping container, the type of shipping container (e.g., box), and the dimensions of the shipping container (i.e., L , W , H The percentage of air filling in the air pad should be indexed for the area of ​​the air pad and / or the void area. LUTs can identify different inflation volumes for different types of objects, different sizes of pads, different types of shipping containers, different sizes of shipping containers, and / or different fill percentages.

[0046] When selecting packing paper padding, the computing device 132 may additionally determine whether the paper padding should be stacked, folded (e.g., accordion folded), loosely wound, tightly wound, loosely crimped, or tightly crimped. For example, the computing device 132 predetermines that packing container 108 should be filled with paper padding of discrete sizes. The computing device 132 then accesses, for example, a LUT to obtain information indicating whether the paper should be loosely or tightly crimped. The LUT may use identifiers for discrete-sized paper padding, identifiers for the type of object placed in the shipping container, shipping container type (e.g., box), shipping container dimensions (i.e., ... L , W , HThe percentage of paper padding filling should be used to index the area of ​​wrinkles and / or voids. LUTs can identify different types or amounts of wrinkles for different types of objects, different discrete sizes of paper padding, different types of shipping containers, different sizes of shipping containers, and / or different filling percentages.

[0047] Next, computing device 132 provides information to one or more inflation modules 160 and / or one or more dispensers 118, 122 that is useful for filling shipping container 108 with selected parameters. This information may include, but is not limited to: void area identifiers, void area locations within the shipping container (e.g., quadrant identifiers), the type of protective packaging to be used in each void area (e.g., inflatable cushions or paper padding), the number of protective packaging units for each void area (e.g., 10 inflatable cushions or 20 discrete-sized paper padding sheets), the quantity of protective packaging for each void area (e.g., 18 feet of paper padding per cubic foot), the inflation amount, the type of paper or padding fold (e.g., accordion-style), the type of paper or padding roll (e.g., loose or tight), and / or the type of crease (e.g., loose or tight). In some scenarios, large void areas may be divided into two or more void area portions of the same or different sizes. Therefore, this information may also include void area portion identifiers and their locations within the shipping container. The same or different types of protective packaging can be used in the void areas and / or portions of the void areas. For example, a large inflatable pad 172 can be used in the first quadrant void area 174 inside the shipping container 170, and a small inflatable pad 176 can be used in the second quadrant void area 178 inside the shipping container. Alternatively, an inflatable pad can be used in the first quadrant void area 182 inside the shipping container 180, and crepe paper padding can be used in the second quadrant void area 184 inside the shipping container.

[0048] Protective packaging can be inserted into the shipping container manually by individual 136 or automatically by one or more dispensers 118, 122. In the latter case, computing device 132 is configured to control the operation of one or more inflation modules 160 and / or one or more dispensers 118, 122. Any inflation module known or to be known herein for inflating packaging pads, pillows, and / or airbags may be used. Furthermore, any dispenser known or to be known herein may be used. In some scenarios, the dispenser is specifically modified to rotate or move the dispensing head angularly along multiple axes (e.g., x-axis, y-axis, and / or z-axis) such that the shipping material is dispensed into multiple void regions and / or multiple void region portions (e.g., quadrant portions) according to instructions received from computing device 132.

[0049] After the shipping container has been filled with protective packaging, it is closed and sealed at container closure / sealing device 126. Any known or to be known container closure / sealing device may be used herein. In some scenarios, the container closure / sealing device includes one or more articulating arms with grippers at their distal ends and controllable joints along the longer arms of these articulating arms. Thus, articulated arms and controllers are well known. If the shipping container is a box, baffle 130 is bent and coupled together at seam 152 (e.g., via tape, PSA, or cold glue and / or staples). Other devices 190 may be provided downstream of container closure / sealing device 126. These other devices may include, but are not limited to, labeling devices for applying one or more labels to the shipping container 200.

[0050] As mentioned above, in some scenarios, the gap region can be segmented. Figure 2 An illustration of a shipping container 200 is provided, which includes a void region 202 divided into multiple void region portions 204, 206, and 208. Identical or different protective packaging can be allocated to the void region portions 204, 206, and 208. If the same inflatable protective packaging is to be used in the void region portions 204, 206, and 208, the same or different inflation amounts can be used for each void region portion 204, 206, and 208. Other segmentation techniques can also be used. For example, such as those by… Figure 3 As shown in the top view of the shipping container 300 provided, the void area can be divided into four quadrants, resulting in four void area portions 304, 306, 308, and 310.

[0051] Figure 5 illustrates a method for placing (one or more) items (e.g., Figure 1 Item 110) is packaged in a shipping container (e.g., Figure 1 Shipping container 108 Figure 1 170 Figure 1 180 Figure 2 200 or Figure 3 The flowchart of illustrative method 500 in Figure 5 is shown. Method 500 may include more or fewer operations than those shown in Figure 5. Some or all of the operations of method 500 may be performed in the same or different order as shown. Some or all of the operations of method 500 may be performed by a computing device (e.g., Figure 1 Computing device 132 and / or Figure 6 (600) and / or processors (e.g., Figure 6 The central processing unit (606) executes the commands.

[0052] Method 500 begins at 502 and continues to 504, where the proximity sensor (e.g., Figure 1 The proximity sensor 116 detects when the shipping container approaches the sensor system (e.g., Figure 1 The sensor system 106). As used herein, the term "proximity" may refer to the leading edge of the shipping container (e.g., Figure 1 The leading edge 140) and the axis of the sensor system (e.g., Figure 1 The predefined distance between axes 150 in the diagram refers to the location or presence of the shipping container at the packing station. The predefined distance can be selected based on the given application. For example, predefined distances may be 1-10 feet, ≤10 feet, ≤5 feet, ≤2 feet, ≤1 foot, or ≤10 inches.

[0053] Next, in 506, the computing device (e.g., Figure 1 The computing device 132) detects a trigger event. The trigger event may include, but is not limited to, the alignment of the center of the shipping container with the axis of the sensor system. This detection can be performed in various ways. (The above is combined with...) Figure 1 A technique for depth measurement using the leading and trailing edges (e.g., leading edge 140 and trailing edge 142) of a shipping container is discussed. This technique can be used here to determine the time when the center of the shipping container will align with the sensor system axis. t .

[0054] Enable or otherwise activate the sensor system in 508, so that in time... t Generate sensor data. Sensors may include, but are not limited to, ToF cameras, LiDAR sensors, radar sensors, and / or other sensors capable of generating sensor data that can be used to produce 3D point clouds. The ToF camera provides point cloud topography and visible light images. Generate a 3D point cloud for the internal cavity of the shipping container in step 510. The 3D point cloud provides a surface map of the exposed inner wall surfaces of the shipping container and / or the exposed surfaces of any items placed inside the shipping container.

[0055] The computing device analyzes the 3D point cloud in 512 to identify void regions inside the shipping container (e.g., Figure 2 The gap area 202 or Figure 3 (302). In box 514, calculate the cube product for the void region. V If the cube product V If the container is not large enough to be filled with a minimum amount of protective packaging [516: No], then method 500 continues to 518, wherein the shipping container is directed toward the downstream container closure / sealing device (e.g., without any protective packaging being dispensed into it). Figure 1The container closure / sealing device 126) proceeds. Method 500 then continues to what will be discussed below. Figure 5B Box 542.

[0056] If the cube product V If the container is large enough to be filled with a minimum amount of protective packaging [516: Yes], then method 500 proceeds to the operations of optional boxes 520-526. These optional operations 520-526 involve: segmenting the gap area; detecting the type of item placed in the shipping container; targeting the gap area or each segment (e.g., Figure 2 The gap area part 204, Figure 2 206 Figure 2 208 Figure 3 304 Figure 3 306 Figure 3 308 or Figure 3 (310), selecting the type of protective packaging based on its cube volume and / or associated item type; and / or, for empty areas or each segment, selecting the percentage to be filled with protective packaging based on its cube volume and / or associated item type. Any known or to be known object detection technique can be employed in box 522. For example, a machine learning algorithm trained on sensor data including 3D point cloud numbers to detect certain types of objects can be used. The machine learning algorithm can include, but is not limited to, neural networks. Database queries using, for example, scanner data (e.g., barcode data) can also be employed.

[0057] After completing operation 516 or the optional operation, method 500 continues to... Figure 5B 528. (For example) Figure 5B As shown, 528 relates to determining whether the selected protective packaging is inflatable. Inflatable protective packaging may include, but is not limited to, cushions, pillows, and / or airbags. If the selected protective packaging is not inflatable [528: No], then method 500 proceeds to 534, which will be discussed below. Conversely, if the protective packaging is inflatable [528: Yes], then method 500 proceeds to the operations of optional blocks 530, 532. Optional operations involve: selecting the inflation amount based on certain criteria for the void area or each segment thereof; and / or causing the inflation module (e.g., Figure 1 The inflation module 160 inflates the transport material and supplies the same amount to the dispenser (e.g., Figure 1Distributor 118). The criteria for making selections regarding box 520 may include, but are not limited to: (one or more) shipping container characteristics, (one or more) protective packaging characteristics, (one or more) article characteristics, selected percentage values, and / or other criteria. Shipping container characteristics may include, for example, type and / or size. Protective packaging article characteristics may include, for example, type and / or size. Article characteristics may include, but are not limited to, type, size, and / or fragility.

[0058] In decision box 534, the computing device determines whether the selected protective packaging is paper padding. If not [534: NO], method 500 proceeds to 538, which will be discussed below. If yes [534: YES], method 500 proceeds to the operation of optional box 536 or box 538. Box 536 involves, optionally for the void area or each section, selecting whether the paper should be folded or crimped based on certain criteria. These criteria may be the same as or different from the criteria used to make the selection in box 530. Therefore, the criteria used in box 536 may include, but are not limited to, shipping container characteristics, protective packaging characteristics, article characteristics, selected percentage values, and / or other criteria.

[0059] In box 538, the computing device controls one or more distributors (e.g., Figure 1 The automatic operation of one or more distributors 118, 122) to distribute transport material into void areas and / or one or more void area portions. Automatic operation may include, but is not limited to: actuating motors, actuating belts, actuating wheels, enabling air vectoring, opening valves, actuating latches, actuating telescopic shafts, one or more articulated arms, and / or one or more movable joints.

[0060] Air knives or other suitable mechanisms can be used to steer inflatable protective packaging (such as cushions, pillows, and airbags) into the shipping container. Articulated steering blades made of polymer or metal can also be used to steer inflatable protective packaging into the shipping container. A chute can be provided from a dispenser, with a drive belt on each side for inserting the unit of inflatable protective packaging into the appropriate portion of the shipping container. The insertion point of any of the above transport mechanisms can be manipulated to the correct location within the shipping container by moving the insertion funnel, for example, linearly (e.g., up, down, laterally) or at an angle. For containment of the protective packaging unit after insertion, the transport mechanism can use a brush, a set of elastic ropes spanning the top of the shipping container (allowing the inflatable protective packaging to be squeezed through without popping back or drifting out); or a cover plate of the shipping container itself to help contain the shipping material inside the shipping container. In addition to or in place of containment mechanisms, the placement area can be isolated from the environment to avoid airflows that could prevent the inflatable protective packaging from reaching its target area or that could subsequently displace the inflatable protective packaging.

[0061] Paper padding and inflatable protective packaging (such as cushions, pillows, and airbags) can be inserted via various drive mechanisms or guided through chutes with articulated joints. For example, paper padding or inflatable protective packaging can be conveyed via parallel drive belts on the sides of the chutes using flexible drive wheels. The drive wheels can be articulated in a manner that causes the paper padding or inflatable protective packaging to turn laterally. In the case of paper padding, such articulation creates lateral creases in the crease web that allow the paper padding to weave back and forth in the shipping container. The insertion point of the paper padding or inflatable protective packaging can be manipulated to the correct position in the shipping container by moving the insertion funnel linearly (e.g., up, down, sideways) or at an angle. The amount of paper padding or inflatable protective packaging is determined by the void volume, which is subdivided into smaller areas for a precise ratio of padding or inflatable protective packaging to voids.

[0062] In step 540, the shipping container is closed and sealed. Then, step 542 is performed, where step 500 ends or other operations are performed. Typically, at this stage, a shipping label is printed and affixed to the packaging.

[0063] Now for reference Figure 6 A diagram of computing device 600 is provided. Figure 1 Sensor system 106 Figure 1 Computing device 132 and / or Figure 1 The controller 192 is the same as or similar to the computing device 600. Therefore, the discussion of the computing device 600 is sufficient to understand these components of the system 100.

[0064] In some scenarios, this solution is used in a client-server architecture. Therefore, Figure 6 The computing device architecture shown is sufficient to understand the details of client computing devices and servers.

[0065] Computing device 600 may include more than Figure 6 The components shown may be more or fewer than those shown. However, the components shown are sufficient to disclose an exemplary solution for implementing this solution. Figure 6 The hardware architecture represents one implementation of a representative computing device configured to provide an improved item return process, as described herein. Therefore, Figure 6 The computing device 600 implements at least a portion of the methods(one or more) described herein.

[0066] Some or all of the components in computing device 600 may be implemented as hardware, software, and / or a combination of hardware and software. Hardware includes, but is not limited to, one or more electronic circuits. Electronic circuits may include, but are not limited to, passive components (e.g., resistors and capacitors) and / or active components (e.g., amplifiers and / or microprocessors). Passive and / or active components may be adapted, arranged, and / or programmed to perform one or more of the methods, programs, or functions described herein.

[0067] like Figure 6 As shown, computing device 600 includes a user interface 602, a central processing unit (“CPU”) 606, a system bus 610, a memory 612 connected to and accessible by other parts of computing device 600 via the system bus 610, a system interface 660, and a hardware entity 614 connected to the system bus 610. The user interface may include input and output devices that facilitate user-software interaction for controlling the operation of computing device 600. Input devices include, but are not limited to, a physical and / or touch keyboard 650. Input devices may be connected to computing device 600 via a wired (serial or wired LAN) or wireless connection (e.g., Bluetooth® or WiFi connection). Output devices include, but are not limited to, a speaker 652, a display 654, and / or a light-emitting diode 656. System interface 660 is configured to facilitate wired or wireless communication to or from external devices, such as network nodes such as access points.

[0068] At least some of the hardware entities in hardware entity 614 perform actions involving accessing and using memory 612, which may be random access memory (RAM), a disk drive, an optical disc read-only memory (CD-ROM), or remote “cloud”-based processing. Hardware entity 614 may include a disk drive unit 616 that includes a computer-readable storage medium 618 on which one or more sets of instructions 620 (e.g., software code) are stored, configured to implement one or more of the methods, processes, or functions described herein. During execution of the instructions 620 by computing device 600, the instructions may also reside wholly or at least partially within memory 612 and / or CPU 606. Memory 612 and CPU 606 may also constitute machine-readable media. As used herein, the term “machine-readable media” refers to a single or multiple media (e.g., a centralized or distributed database, and / or associated caches and servers) storing the set or multiple sets of instructions 620. As used herein, "machine-readable medium" also means any medium capable of storing, encoding, or carrying a set of instructions 620 for execution by computing device 600, and causing computing device 600 to perform one or more of the methods of this disclosure.

[0069] Although the present solution has been illustrated and described with respect to one or more embodiments, equivalent changes and modifications will occur to those skilled in the art upon reading and understanding this specification and the accompanying drawings. Furthermore, while a particular feature of the present solution may be disclosed with respect to only one embodiment among several embodiments, such features may be combined with one or more other features of other embodiments, which may be desirable and advantageous for any given or particular application. Therefore, the breadth and scope of the present solution should not be limited to any of the embodiments described above. Rather, the scope of the present solution should be defined by the following claims and their equivalents.

[0070] Without excluding other possible embodiments, certain exemplary embodiments are summarized in the following terms: Clause 1: A method for packaging a shipping container, comprising: detecting the presence of the shipping container by means of a computing device; generating a 3D point cloud by means of a computing device, the 3D point cloud including a 3D perspective representation of the interior of the shipping container and the surface of at least one article placed in the shipping container; analyzing the 3D point cloud by means of a computing device to identify a void region inside the shipping container, the void region being vacant of the at least one article; selecting a percentage from a plurality of possible percentages by means of a computing device based on characteristics of the void region; and assigning protective packaging to the void region by means of a computing device, such that the selected percentage of the void region is filled with protective packaging.

[0071] Clause 2: The method of Clause 1, wherein the shipping container includes boxes, bags or envelopes or padded mailing bags / envelopes.

[0072] Clause 3: The method according to any of the preceding method clauses further includes: dividing the void region into void region portions; and selecting different percentages from the plurality of possible percentages for at least two void region portions based on the characteristics of the void region portions.

[0073] Clause 4: The method according to any of the preceding method clauses, wherein the characteristics of the void region portion include at least one of the following: cubic volume, relative position of the void region portions to each other, and relative position of the void region portion to at least one article placed in the shipping container.

[0074] Clause 5: The method according to any of the preceding method clauses, wherein the cubic volume of the void area has a non-linear relationship with the percentage of the void area to be filled with protective packaging.

[0075] Clause 6: The method according to any of the preceding method clauses further includes: detecting the occurrence of a triggering event via a computing device; and activating a sensor in response to the triggering event.

[0076] Clause 7: The method according to any of the preceding method clauses, wherein the triggering event includes the alignment of the center of the shipping container with the axis of the sensor.

[0077] Clause 8: The method according to any of the preceding method clauses, wherein the detection of the triggering event is based on a depth measurement for at least one edge of the shipping container.

[0078] Clause 9: The method according to any of the preceding method clauses also includes calculating the cubic product of the void region.

[0079] Clause 10: The method according to any of the preceding method clauses, wherein the characteristics of the void region include a cubic volume.

[0080] Clause 11: The method according to any of the preceding method clauses further includes, when the cubic volume is not large enough to be filled with a threshold amount of protective packaging, such that the shipping container is closed and sealed without any protective packaging being distributed therein.

[0081] Clause 12: The method according to any of the preceding method clauses, wherein when the cube volume is large enough to be filled with a threshold amount of protective packaging, the execution causes the protective packaging to be allocated to the void region.

[0082] Clause 13: The method according to any of the preceding method clauses further includes selecting a protective packaging type from a plurality of possible protective packaging types based on the cube volume or the type of the at least one article when the cube volume is large enough to be filled with a threshold amount of protective packaging.

[0083] Clause 14: The method according to any of the preceding method clauses, wherein the plurality of protective packaging types include at least inflatable cushions, wrapping paper, or foam in place.

[0084] Clause 15: The method according to any of the preceding method clauses further includes, when the selected protective packaging type includes inflatable protective packaging, selecting an inflation volume from a plurality of possible inflation volumes.

[0085] Clause 16: The method according to any of the preceding method clauses, wherein the inflation amount is selected based on at least one of the characteristics of the shipping container, the characteristics of the protective packaging, the characteristics of the at least one article placed in the shipping container, and the selected percentage.

[0086] Clause 17: The method according to any of the foregoing method clauses further includes causing the inflation module to inflate the shipping material at a selected inflation amount.

[0087] Clause 18: The method according to any of the preceding method clauses also includes, when the selected type of protective packaging includes wrapping paper, selecting whether the shipping material should be wrapped, stacked, folded, rolled or wrinkled.

[0088] Clause 19: The method according to any of the preceding method clauses, wherein the choice regarding whether the shipping material should be wrapped, stacked, folded, rolled or wrinkled is based on at least one of the characteristics of the shipping container, the characteristics of the protective packaging, the characteristics of the at least one article placed in the shipping container and the selected percentage.

[0089] Clause 20: A system comprising: a processor; and a non-transitory computer-readable storage medium including programming instructions configured to cause the processor to implement a method for packaging a shipping container, wherein the programming instructions include instructions to: detect the presence of the shipping container; generate a 3D point cloud including a 3D perspective representation of the interior of the shipping container and the surface of at least one article placed in the shipping container; analyze the 3D point cloud to identify void regions inside the shipping container, the void regions vacating the at least one article; select a percentage from a plurality of possible percentages based on characteristics of the void regions; and cause protective packaging to be allocated to the void regions, such that the selected percentage of the void regions is filled with protective packaging.

[0090] Clause 21: A non-transitory computer-readable medium storing instructions that, when executed by at least one computing device, cause the at least one computing device to perform operations including: detecting the presence of a shipping container; generating a 3D point cloud including a 3D perspective representation of the interior of the shipping container and the surface of at least one article placed in the shipping container; analyzing the 3D point cloud to identify void regions inside the shipping container, the void regions vacating the at least one article; selecting a percentage from a plurality of possible percentages based on characteristics of the void regions; and causing protective packaging to be allocated to the void regions, such that the selected percentage of the void regions is filled with protective packaging.

[0091] The breadth and scope of this disclosure should not be limited to any of the example embodiments described above, but should be defined solely by the following claims and their equivalents.

Claims

1. A method for packaging shipping containers, comprising: The presence of the shipping container is detected by a computing device; A 3D point cloud is generated by a computing device, the 3D point cloud including a 3D perspective representation of the interior of the shipping container and the surface of at least one item placed in the shipping container; The 3D point cloud is analyzed by a computing device to identify one or more empty regions inside the shipping container, wherein the one or more empty regions are empty of at least one item; The void region is divided into at least a first void region into multiple void region portions; Using the computing device, based on the characteristics of the plurality of void region portions, a first percentage is selected from a plurality of possible percentages for a first void region portion of the plurality of void region portions, and a different second percentage is selected from the plurality of possible percentages for a second void region portion of the plurality of void region portions, wherein each of the first percentage and the second percentage represents an amount of void region volume that should be filled with protective packaging, wherein the characteristics of the plurality of void region portions include at least one of cube volume, the relative position of the void region portions with each other, and the relative position of the plurality of void region portions with respect to the at least one article placed in the shipping container; as well as The computing device causes the protective packaging to be distributed into the one or more void regions, such that a selected first percentage of a first void region portion is filled with the protective packaging and a selected second percentage of a second void region portion is filled with the protective packaging.

2. The method of claim 1, wherein the shipping container comprises a box, bag, or envelope or a padded mailing bag / envelope.

3. The method according to claim 1, wherein the first void region portion has a cube product that is different from the cube product of the second void region portion.

4. The method according to claim 1, further comprising: The occurrence of the triggering event is detected by the computing device; as well as The sensor is enabled in response to the triggering event.

5. The method of claim 4, wherein the triggering event includes the alignment of the center of the shipping container with the axis of the sensor.

6. The method of claim 5, wherein the detection of the triggering event is based on a depth measurement of at least one edge of the shipping container.

7. The method of claim 1, further comprising calculating the cube product of each of the one or more void regions.

8. The method of claim 7, further comprising calculating the cube product of each of the plurality of void region portions.

9. The method of claim 7, further comprising closing and sealing the shipping container without any protective packaging being dispensed therein when the volume of the cube is not large enough to be filled with a threshold amount of protective packaging.

10. The method of claim 7, wherein when the cube volume is large enough to be filled with a threshold amount of protective packaging, the protective packaging is distributed into the one or more void regions.

11. The method of claim 7, further comprising selecting a protective packaging type from a plurality of possible protective packaging types based on the cube volume or the type of the at least one article when the cube volume is large enough to be filled with a threshold amount of protective packaging.

12. The method of claim 11, wherein the plurality of protective packaging types include at least inflatable cushions, wrapping paper, or on-site foaming.

13. The method of claim 11, further comprising selecting an inflation volume from a plurality of possible inflation volumes when the selected protective packaging type includes inflatable protective packaging.

14. The method of claim 13, wherein the inflation amount is selected based on at least one of: characteristics of the shipping container, characteristics of the protective packaging, characteristics of the at least one article placed in the shipping container, and at least one of a selected first percentage and a second percentage.

15. The method of claim 13, further comprising causing the inflation module to inflate the transport material at a selected inflation amount.

16. The method of claim 11, further comprising, when the selected protective packaging type includes wrapping paper, selecting whether the shipping material should be wrapped, stacked, folded, rolled, or wrinkled.

17. The method of claim 16, wherein the selection regarding whether the shipping material should be wrapped, stacked, folded, rolled, or wrinkled is based on at least one of the following: characteristics of the shipping container, characteristics of the protective packaging, characteristics of the at least one article placed in the shipping container, and at least one of a selected first percentage and a second percentage.

18. The method of claim 1, wherein each of the first percentage and the second percentage represents a minimum amount of void area volume that should be filled with protective packaging.

19. The method of claim 1, further comprising dispensing the protective packaging into the first void region portion.

20. The method of claim 19, further comprising dispensing the protective packaging into the second void region portion.

21. A system comprising: processor; A non-transitory computer-readable storage medium includes programming instructions configured to cause the processor to implement a method for packaging a shipping container, wherein the programming instructions include instructions for: Detect the presence of the shipping container; Generate a 3D point cloud, the 3D point cloud including a 3D perspective representation of the interior of the shipping container and the surface of at least one item placed in the shipping container; Analyze the 3D point cloud to identify one or more empty regions inside the shipping container, the one or more empty regions being empty of at least one item; Divide at least the first void region of the one or more void regions into multiple void region portions; Based on the characteristics of the plurality of void regions, a first percentage is selected from a plurality of possible percentages for a first void region portion of the plurality of void regions, and a different second percentage is selected from the plurality of possible percentages for a second void region portion of the plurality of void regions, wherein each of the first percentage and the second percentage represents an amount of void region volume that should be filled with protective packaging, wherein the characteristics of the plurality of void regions include at least one of the following: cubic volume, relative position of the void regions to each other, and relative position of the plurality of void regions to the at least one article placed in the shipping container; as well as The protective packaging is distributed into the one or more void regions such that a selected first percentage of a first void region portion is filled with the protective packaging and a different selected second percentage of a second void region portion is filled with the protective packaging.

22. The system of claim 21, further comprising a dispenser configured to dispense the protective packaging into the one or more void regions such that a selected first percentage of a first void region portion is filled with the protective packaging and a selected different second percentage of a second void region portion is filled with the protective packaging.

23. A non-transitory computer-readable medium storing instructions that, when executed by at least one computing device, cause the at least one computing device to perform an operation, the operation comprising: Detect the presence of shipping containers; Generate sensor data, which includes a multidimensional representation of the interior of the shipping container and the surface of at least one item placed in the shipping container; Analyze the sensor data to identify one or more empty areas inside the shipping container, the empty areas being vacant of at least one item; The void region is divided into at least a first void region into multiple void region portions; Based on the characteristics of the plurality of void regions, a first percentage is selected from a plurality of possible percentages for a first void region portion of the plurality of void regions, and a different second percentage is selected from the plurality of possible percentages for a second void region portion of the plurality of void regions, wherein each of the first percentage and the second percentage represents an amount of void region volume that should be filled with protective packaging, wherein the characteristics of the plurality of void regions include at least one of the following: cubic volume, relative position of the void regions to each other, and relative position of the plurality of void regions to the at least one article placed in the shipping container; as well as The protective packaging is distributed into the one or more void regions such that a selected first percentage of a first void region portion is filled with the protective packaging and a selected second percentage of a second void region portion is filled with the protective packaging.

24. The non-transitory computer-readable medium of claim 23, wherein the sensor data comprises 3D point clouds.

Images