Distribution task optimization method, distribution robot, vending system and program product

Abstract

The invention is suitable for the technical field of robots, and provides a distribution task optimization method, a distribution robot, a vending system and a program product. The distribution task optimization method comprises the steps that a received distribution task is responded, the distribution task is in butt joint with a conveying belt of an automatic vending machine, and the conveying belt is used for conveying target goods in the automatic vending machine into a cargo hold of a distribution robot; in response to a received shipped message of the vending machine, sensing the interior of the cargo hold to obtain a cargo sensing result; if the goods sensing result is that the target goods do not exist, error correction operation is executed; and if the goods sensing result is that the target goods exist, carrying out distribution operation. According to the embodiment of the invention, the situation of void delivery can be avoided.

Description

Technical Field

[0001] The present application belongs to the field of robotics technology, and in particular relates to a method for optimizing a delivery task, a delivery robot, a vending system, and a program product. Background Art

[0002] In today's fast-paced world, consumers are increasingly demanding more efficient shopping. The integration of delivery robots and vending machines can meet consumers' demands for instant purchases and timely delivery. However, current delivery solutions can cause the vending machine to become stuck during delivery, or for goods to roll off the conveyor belt and fall to the ground. In these cases, the goods are not delivered to the delivery robot's cabin, and the robot mistakenly believes they have received the goods and proceeds with delivery. This ultimately results in empty cabins, reducing the user experience. Summary of the Invention

[0003] The embodiments of the present application provide a delivery task optimization method, a delivery robot, a vending system, and a program product, which can avoid the problem of empty cabin delivery.

[0004] A first aspect of an embodiment of the present application provides a method for optimizing a delivery task, which is applied to a delivery robot. The method for optimizing a delivery task includes: in response to receiving a delivery task, docking with a conveyor belt of a vending machine, the conveyor belt being used to transport target goods in the vending machine to a cargo hold of the delivery robot; in response to receiving a shipped message from the vending machine, sensing the interior of the cargo hold to obtain a goods sensing result; if the goods sensing result is that the target goods do not exist, performing an error correction operation; if the goods sensing result is that the target goods exist, performing a delivery operation.

[0005] In some embodiments of the first aspect, the performing of the error correction operation includes: searching for the target cargo within the field of view of the delivery robot; if the target cargo is found, controlling the robotic arm to place the target cargo into the cargo hold and performing the delivery operation; if the target cargo is not found, outputting a prompt message.

[0006] In some embodiments of the first aspect, searching for the target goods within the field of view of the delivery robot includes: controlling the delivery robot to rotate and collecting search images in various directions during the rotation; and performing target detection on the search images in various directions respectively to search for the target goods.

[0007] In some embodiments of the first aspect, the performing target detection on the search images in each orientation to search for the target goods includes: performing target detection on the search images in each orientation to obtain the goods type of the goods appearing in each search image; if goods of the same type as the target goods appear only in a single search image, the goods appearing in the single search image are used as the target goods; if goods of the same type as the target goods appear in multiple search images, order classification is performed on the goods appearing in each search image, and the goods belonging to the order of the delivery task are used as the target goods.

[0008] In some embodiments of the first aspect, the order classification of the goods appearing in each search image includes: aligning and splicing the search images to determine the same goods appearing in different search images; if the goods appearing in the search images are the same goods, determining that the goods appearing in each of the search images belong to the order of the delivery task; if the goods appearing in the search images are different goods, obtaining the goods attributes of each of the different goods, and classifying the orders of the different goods according to the goods attributes.

[0009] In some embodiments of the first aspect, the optimization method of the delivery task also includes: if the shipped message of the vending machine is not received within a preset time period, sensing the inside of the cargo hold to obtain a cargo sensing result; if the cargo sensing result is that the target cargo exists, performing a delivery operation, and when the shipped message of the delivery task is received again, filtering the shipped message; if the cargo sensing result is that the target cargo does not exist, performing an error correction operation.

[0010] In some embodiments of the first aspect, the sensing of the interior of the cargo hold to obtain cargo sensing results includes: obtaining product images in the delivery order of the delivery task; taking cargo images of the cargo inside the cargo hold; and comparing the cargo images with the product images to obtain the cargo sensing results.

[0011] A second aspect of an embodiment of the present application provides an optimization device for delivery tasks, including: a docking unit, configured to dock with a conveyor belt of a vending machine in response to receiving a delivery task, the conveyor belt being configured to transport target goods in the vending machine to a cargo compartment of the delivery robot; a perception unit, configured to perceive the interior of the cargo compartment in response to receiving a shipped message from the vending machine to obtain a goods perception result; an error correction unit, configured to perform an error correction operation if the goods perception result is that the target goods do not exist; and a delivery unit, configured to perform a delivery operation if the goods perception result is that the target goods exist.

[0012] A third aspect of an embodiment of the present application provides a delivery robot, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned delivery task optimization method when executing the computer program.

[0013] A fourth aspect of an embodiment of the present application provides a vending system, comprising the delivery robot and vending machine provided in the third aspect.

[0014] A fifth aspect of an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the above-mentioned delivery task optimization method.

[0015] A sixth aspect of an embodiment of the present application provides a computer program product, which, when the computer program is run, enables the above-mentioned method for optimizing the delivery task to be executed.

[0016] In an embodiment of the present application, the delivery robot responds to receiving a delivery task, docks with the conveyor belt of the vending machine, and after receiving the shipment message from the vending machine, senses the inside of the cargo hold to obtain the cargo perception result. If the cargo perception result is that the target cargo does not exist, an error correction operation is performed; if the cargo perception result is that the target cargo exists, a delivery operation is performed. The vending machine message and the cargo hold condition can be used as a reference to avoid empty hold delivery. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] Figure 1 This is a schematic diagram of the implementation process of a delivery task optimization method provided in an embodiment of the present application;

[0019] Figure 2 This is a schematic diagram of a specific implementation process of sensing the interior of a cargo hold provided by an embodiment of the present application;

[0020] Figure 3 This is a schematic diagram of a specific implementation flow of performing an error correction operation provided in an embodiment of the present application;

[0021] Figure 4 is a schematic diagram of the rotation of the delivery robot provided in an embodiment of the present application;

[0022] Figure 5This is a schematic diagram of a specific implementation flow of a delivery task optimization method provided in an embodiment of the present application;

[0023] Figure 6 This is a schematic diagram of the structure of a delivery task optimization device provided in an embodiment of the present application;

[0024] Figure 7 Schematic diagram of the structure of the delivery robot provided in the embodiment of the present application;

[0025] Figure 8 It is a structural diagram of the vending system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of this application more clear, the present application is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without making any creative work are protected by this application.

[0027] In today's fast-paced world, consumers are increasingly demanding more efficient shopping. The integration of delivery robots and vending machines can meet consumers' demands for instant purchases and timely delivery. However, current delivery solutions can cause the vending machine to become stuck during delivery, or for goods to roll off the conveyor belt and fall to the ground. In these cases, the goods are not delivered to the delivery robot's cabin, and the robot mistakenly believes they have received the goods and proceeds with delivery. This ultimately results in empty cabins, reducing the user experience.

[0028] In view of this, the present application proposes a method for optimizing delivery tasks, which can use the information from the vending machine and the cargo hold conditions as a reference to avoid empty cargo hold delivery.

[0029] In order to illustrate the technical solution of the present application, specific embodiments are provided below.

[0030] Figure 1 The following is a schematic diagram of a method for optimizing a delivery task according to an embodiment of the present invention, which can be applied to a delivery robot. The delivery robot is an intelligent device with autonomous mobility and capable of completing delivery tasks.

[0031] Specifically, the above-mentioned method for optimizing the delivery task may include the following steps S101 to S104.

[0032] Step S101: In response to receiving a delivery task, docking with the conveyor belt of the vending machine.

[0033] In the embodiments of this application, a delivery task refers to a delivery task performed by the aforementioned delivery robot. A user can trigger an order through a mini-program or application on their user terminal device. The dispatching device generates a delivery task based on the delivery order corresponding to the order and issues it to the corresponding delivery robot. In response to receiving the delivery task, the delivery robot can open its cargo hold and dock with the vending machine's conveyor belt.

[0034] The vending machine stores the target goods specified in the delivery order of the delivery task, and the conveyor belt can be used to transport the target goods in the vending machine to the cargo compartment of the delivery robot.

[0035] Step S102: in response to receiving the shipment message from the vending machine, sensing the interior of the cargo hold to obtain a cargo sensing result.

[0036] In an embodiment of the present application, a vending machine can deliver target goods from a delivery port via a conveyor belt to a delivery robot's cargo hold, generating a shipped message after delivery. This shipped message indicates that the vending machine has completed the delivery operation of the target goods. To avoid empty cargo holds, the delivery robot can sense the interior of the cargo hold and obtain cargo sensing results.

[0037] Specifically, the delivery robot can collect sensor information in the cabin through perception components such as image sensors, lidar, and weight sensors, and perceive the interior of the cargo hold based on the sensor information to determine whether the target cargo is in the cargo hold and obtain cargo perception results.

[0038] Step S103: If the cargo sensing result is that the target cargo does not exist, an error correction operation is performed.

[0039] If the cargo sensing result indicates that the target cargo is not present, it means that the vending machine has become stuck during delivery, or the cargo has rolled off the conveyor and fallen to the ground, resulting in the target cargo not entering the cargo hold. In this case, a correction operation is required. The correction operation is used to re-enter the cargo hold.

[0040] Step S104: If the cargo sensing result indicates that the target cargo exists, a delivery operation is performed.

[0041] If the cargo sensing result indicates that the target cargo exists, the delivery robot can perform a delivery operation to transport the target cargo to the destination of the delivery task.

[0042] In an embodiment of the present application, the delivery robot responds to receiving a delivery task, docks with the conveyor belt of the vending machine, and after receiving the shipment message from the vending machine, senses the inside of the cargo hold to obtain the cargo perception result. If the cargo perception result is that the target cargo does not exist, an error correction operation is performed; if the cargo perception result is that the target cargo exists, a delivery operation is performed. The vending machine message and the cargo hold condition can be used as a reference to avoid empty hold delivery.

[0043] Specifically, in some embodiments of the present application, after the delivery robot docks with the conveyor belt of the vending machine, the delivery robot may start timing.

[0044] At this time, the optimization method of the delivery task may also include: if no delivery message is received from the vending machine within a preset time period, sensing the interior of the cargo hold to obtain a cargo sensing result.

[0045] If the cargo sensing result indicates that the target cargo exists, the delivery operation is executed, and when the shipped message of the delivery task is received again, the shipped message is filtered;

[0046] If the cargo sensing result is that the target cargo does not exist, an error correction operation is performed.

[0047] That is to say, in an embodiment of the present application, after the delivery robot docks with the conveyor belt of the vending machine, the delivery robot can wait until it receives a shipped message, or until the time for not receiving a shipped message reaches a preset time, and then choose to perform a delivery operation or an error correction operation based on the goods perception result.

[0048] If the duration of not receiving a shipped message reaches a preset value, if the cargo sensing result indicates the presence of the target cargo, the delivery task can be marked while executing the delivery operation. When the shipped message for the delivery task is received again, the shipped message will be filtered. This way, even if the vending machine has already shipped and the delivery robot has received the target cargo due to network or other issues, but the delivery robot has not received the shipped message, the delivery robot can still execute the delivery operation in a timely manner, avoiding the delivery robot mistakenly believing that the cargo has not been received and causing a delivery timeout. By filtering the shipped message, the delivery robot can avoid responding to the same delivery task repeatedly.

[0049] In some embodiments of the present application, sensing the interior of the cargo hold and obtaining cargo sensing results may include: obtaining pictures of goods in the delivery order of the delivery task; taking pictures of the goods inside the cargo hold; and comparing the cargo pictures with the product pictures to obtain cargo sensing results.

[0050] Specifically, the products sold in the vending machine can be set with corresponding product images in advance. When receiving a delivery task, the delivery robot can receive the product images of each product in the delivery order of the delivery task. Please refer to Figure 2 By comparing cargo images taken from the cargo hold with product images and determining the similarity between the two images, cargo perception results can be obtained. If the similarity between the cargo image and the product image is greater than or equal to the similarity threshold, the target cargo is present in the cargo hold. If the similarity between the cargo image and the product image is less than the similarity threshold, the target cargo is not present in the cargo hold.

[0051] In some embodiments of the present application, the delivery task optimization method may further include: if the target cargo is detected to be in a normal position within the cargo hold, executing the delivery operation; if the target cargo is detected to be in an abnormal position within the cargo hold, controlling the robotic arm to adjust the position of the target cargo within the cargo hold and executing the delivery operation. This ensures that the target cargo is properly positioned within the cargo hold, preventing the target cargo from falling out of the cargo hold during delivery, or preventing the cargo from becoming stuck and preventing the user from accessing it.

[0052] In the case where the target goods do not exist, the delivery robot needs to perform error correction operations.

[0053] Specifically, in some embodiments of the present application, Figure 3 As shown, performing the error correction operation may include: step S301 to step S303.

[0054] Step S301: Search for target goods within the field of view of the delivery robot.

[0055] The delivery robot's field of view refers to the range captured by its image sensor. By capturing search images within the field of view and performing target detection on the search images, the robot can detect whether the target goods are within the field of view.

[0056] In order to increase the search range, in some embodiments of the present application, searching for the target goods within the field of view of the delivery robot may include: controlling the delivery robot to rotate and collecting search images in various directions during the rotation process; performing target detection on the search images in various directions respectively to search for the target goods.

[0057] For example, Figure 4As shown, the delivery robot can be controlled to rotate 180° at the current position and collect search images in multiple directions. Target detection is performed on the search images in each direction to search for the target goods. In this way, a search can be performed near the vending machine to find the target goods that have rolled off the conveyor belt and fallen to the ground.

[0058] It should be noted that target detection can be achieved through neural network models, threshold segmentation algorithms, etc., and this application does not impose any restrictions on this.

[0059] Specifically, target detection is performed on each search image in each orientation to search for target goods. This includes performing target detection on each search image in each orientation to determine the type of goods appearing in each search image. If goods of the same type as the target goods appear in only a single search image, the goods appearing in that single search image are considered the target goods. If goods of the same type as the target goods appear in multiple search images, the goods appearing in each search image are classified into order categories, and goods belonging to orders for delivery tasks are considered the target goods.

[0060] That is, by performing object detection on the search image in each orientation, it is possible to determine whether goods appear in the search image in each orientation, as well as the type of goods that appear. The type of goods can represent the classification result of the goods.

[0061] If goods of the same type as the target goods appear in only a single search image, it means that there is only a single goods within the field of view and is located in the direction corresponding to the single search image. In this case, the goods appearing in the single search image can be regarded as the target goods.

[0062] If goods of the same type as the target goods appear in multiple search images, it means that there may be multiple goods within the field of view. In this case, it is necessary to classify the goods appearing in each search image into orders, and use the goods belonging to the orders of the delivery task as the target goods to avoid incorrect delivery of goods for other orders.

[0063] Specifically, in some embodiments of the present application, order classification of goods appearing in each search image may include aligning and splicing the search images to identify identical goods appearing in different search images. It is understood that the same goods may appear simultaneously in search images from several adjacent orientations. By aligning and splicing the search images, a panoramic image can be obtained. In the panoramic image, identical goods appearing in different search images are merged into a single item.

[0064] If the goods appearing in each search image are the same, then it is determined that the goods appearing in each search image belong to the order of the delivery task. In other words, if only a single item exists in the panoramic image, it means that only a single item exists within the field of view, and the item can be regarded as the target item.

[0065] If different goods appear in each search image, the robot obtains the attributes of each of the different goods and categorizes them into orders based on these attributes. These attributes can include product identifiers (such as serial codes) and order identifiers. If multiple goods appear in the panoramic image, the delivery robot uses components such as radio frequency scanners and image sensors to obtain the attributes of each item, categorize the different goods into orders, and select the goods that belong to the delivery order for the delivery task as the target goods.

[0066] Step S302: If the target cargo is found, the robot arm is controlled to place the target cargo into the cargo hold and perform the delivery operation.

[0067] If the target cargo is found, the delivery machine can place the target cargo into the cargo hold through the robotic arm to perform the delivery operation with the target cargo and deliver the target cargo to the destination.

[0068] Step S303: If the target goods are not found, a prompt message is output.

[0069] If the delivery robot fails to find the target goods, it can output a prompt message to remind the staff that a failure occurred during the delivery process.

[0070] Please refer to Figure 5 , Figure 5 The specific flow chart of the delivery task optimization method provided by the present application is shown. After receiving the delivery task, the delivery robot can go to the vending machine, open the hatch and dock with the conveyor belt, wait for the delivery message from the vending machine or wait for the preset time to detect the goods. If the target goods are detected in the cargo hold and the position is normal, the hatch is closed and the delivery operation is performed. If the target goods are detected in the cargo hold and the position of the target goods is abnormal, the robotic arm can be controlled to adjust the position of the target goods in the cargo hold, and the hatch is closed to perform the delivery operation. If the target goods are not in the cargo hold, a search can be performed within the field of view. If the target goods are found, the robotic arm is controlled to place the target goods into the cargo hold, and the hatch is closed to perform the delivery operation. After the delivery is completed, the delivery robot can return to the charging station. If the target goods are not found, a prompt message can be output and the robot returns to the charging station. In this way, the situation of empty cabin delivery can be avoided, the success rate of delivery tasks can be improved, and the user experience can be enhanced.

[0071] It should be noted that, for the sake of simplicity of description, the aforementioned method embodiments are all expressed as a series of action combinations. However, those skilled in the art should be aware that this application is not limited to the described order of actions, because according to this application, certain steps can be performed in other orders.

[0072] like Figure 6 Shown is a structural schematic diagram of a delivery task optimization device 600 provided in an embodiment of the present application, wherein the delivery task optimization device 600 is configured on a delivery robot.

[0073] Specifically, the delivery task optimization device 600 may include:

[0074] The docking unit 601 is configured to dock with a conveyor belt of a vending machine in response to receiving a delivery task, wherein the conveyor belt is configured to transport target goods in the vending machine to a cargo compartment of the delivery robot;

[0075] a sensing unit 602 configured to sense the interior of the cargo hold in response to receiving a shipment message from the vending machine, and obtain a cargo sensing result;

[0076] The error correction unit 603 is configured to perform an error correction operation if the cargo sensing result indicates that the target cargo does not exist;

[0077] The delivery unit 604 is configured to execute a delivery operation if the cargo sensing result indicates that the target cargo exists.

[0078] In some embodiments of the present application, the error correction unit 603 can be used to: search for the target cargo within the field of view of the delivery robot; if the target cargo is found, control the robotic arm to place the target cargo into the cargo hold and perform the delivery operation; if the target cargo is not found, output a prompt message.

[0079] In some embodiments of the present application, the error correction unit 603 may be used to: control the delivery robot to rotate, and collect search images in various directions during the rotation process; and perform target detection on the search images in various directions respectively to search for the target goods.

[0080] In some embodiments of the present application, the error correction unit 603 can be used to: perform target detection on the search images of each orientation respectively to obtain the cargo type of the cargo appearing in each search image; if cargo of the same type as the target cargo appears only in a single search image, the cargo appearing in the single search image is used as the target cargo; if cargo of the same type as the target cargo appears in multiple search images, order classification is performed on the cargo appearing in each search image, and the cargo belonging to the order of the delivery task is used as the target cargo.

[0081] In some embodiments of the present application, the error correction unit 603 can be used to: align and splice each search image to determine the same goods appearing in different search images; if the goods appearing in each search image are the same goods, determine that the goods appearing in each of the search images belong to the order of the delivery task; if there are different goods appearing in each search image, obtain the goods attributes of each of the different goods, and classify the orders of the different goods according to the goods attributes.

[0082] In some embodiments of the present application, the perception unit 602 can be used to: if no shipped message is received from the vending machine within a preset time period, then perceive the inside of the cargo hold to obtain a cargo perception result; the error correction unit 603 can be used to: if the cargo perception result is that the target cargo does not exist, then perform an error correction operation; the delivery unit 604 can be used to: if the cargo perception result is that the target cargo exists, then perform a delivery operation, and when the shipped message of the delivery task is received again, filter the shipped message.

[0083] In some embodiments of the present application, the perception unit 602 may be used to: obtain product images in the delivery order of the delivery task; take pictures of the goods inside the cargo hold; and compare the goods pictures with the product pictures to obtain the goods perception results.

[0084] It should be noted that for the convenience and simplicity of description, the specific working process of the above-mentioned delivery task optimization device 600 can be referred to Figures 1 to 5 The corresponding process of the method will not be described in detail here.

[0085] like Figure 7 FIG. 7 is a schematic diagram of a delivery robot provided in an embodiment of the present application. Specifically, the delivery robot 7 may include: a processor 70, a memory 71, and a computer program 72 stored in the memory 71 and executable on the processor 70, such as a delivery task optimization program. When the processor 70 executes the computer program 72, the steps of the above-mentioned optimization method embodiments of each delivery task are implemented, such as Figure 1 Alternatively, when the processor 70 executes the computer program 72, the functions of the modules / units in the above-mentioned device embodiments are realized, for example, Figure 6 The functions of the docking unit 601, the sensing unit 602, the error correction unit 603 and the distribution unit 604 are shown.

[0086] The computer program may be divided into one or more modules / units, which are stored in the memory 71 and executed by the processor 70 to implement the present application. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in the delivery robot.

[0087] For example, the computer program can be divided into: a docking unit, a perception unit, an error correction unit, and a delivery unit. The specific functions of each unit are as follows: the docking unit is used to, in response to receiving a delivery task, dock with the conveyor belt of the vending machine, and the conveyor belt is used to transport the target goods in the vending machine to the cargo compartment of the delivery robot; the perception unit is used to, in response to receiving a delivery message from the vending machine, perceive the interior of the cargo compartment and obtain a cargo perception result; the error correction unit is used to perform an error correction operation if the cargo perception result indicates that the target goods do not exist; the delivery unit is used to perform a delivery operation if the cargo perception result indicates that the target goods exist.

[0088] The delivery robot may include, but is not limited to, a processor 70 and a memory 71. Those skilled in the art will appreciate that Figure 7 It is only an example of a delivery robot and does not constitute a limitation of the delivery robot. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the delivery robot may also include input and output devices, network access devices, buses, etc.

[0089] The processor 70 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0090] The memory 71 may be an internal storage unit of the delivery robot, such as a hard disk or memory of the delivery robot. The memory 71 may also be an external storage device of the delivery robot, such as a plug-in hard disk, a smart memory card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the delivery robot. Furthermore, the memory 71 may also include both an internal storage unit and an external storage device of the delivery robot. The memory 71 is used to store the computer program and other programs and data required by the delivery robot. The memory 71 may also be used to temporarily store data that has been output or is to be output.

[0091] It should be noted that, for the convenience and brevity of description, the structure of the above-mentioned delivery robot can also refer to the specific description of the structure in the method embodiment, which will not be repeated here.

[0092] like Figure 8 As shown, the present application also provides a vending system, including a delivery robot and a vending machine.

[0093] The vending machine may include a container and a conveyor belt, wherein the container can be used to store goods, and the conveyor belt can be used to transport the target goods in the vending machine to the cargo compartment of the robot.

[0094] Delivery robots can be used to perform Figures 1 to 5 The corresponding process of the method will not be described in detail here.

[0095] In some embodiments of the present application, the delivery robot may specifically include: a communication module configured to obtain delivery tasks via network communication and to interact with the vending machine; a sensing unit configured to sense target cargo within the cargo hold; and a service module including, but not limited to, the aforementioned docking unit, error correction unit, and delivery unit. The error correction unit may include a robotic arm.

[0096] In some embodiments of the present application, the vending system may further include a scheduling unit for interacting with a user terminal device and issuing delivery tasks to the delivery robot.

[0097] It is understood that the vending system may also include Figure 8 More or fewer components than those shown, for example, the vending system may also include a charging station for charging the delivery robot.

[0098] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0099] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0100] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0101] In the embodiments provided in the present application, it should be understood that the disclosed device / delivery robot and method can be implemented in other ways. For example, the device / delivery robot embodiments described above are merely schematic. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0102] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0103] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0104] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0105] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for optimizing a delivery task, characterized in that: Applied to a delivery robot, the delivery task optimization method includes: In response to receiving a delivery task, docking with a conveyor belt of a vending machine, wherein the conveyor belt is used to transport target goods in the vending machine to a cargo compartment of the delivery robot; In response to receiving a delivery message from the vending machine, sensing the interior of the cargo hold to obtain a cargo sensing result; If the cargo sensing result is that the target cargo does not exist, performing an error correction operation; If the cargo sensing result indicates that the target cargo exists, a delivery operation is performed.

2. The method for optimizing a delivery task according to claim 1, wherein: The performing of the error correction operation includes: Searching for the target goods within the field of view of the delivery robot; If the target cargo is found, the robot arm is controlled to place the target cargo into the cargo hold and perform a delivery operation; If the target goods are not found, a prompt message is output.

3. The method for optimizing the delivery task according to claim 2, wherein: The searching for the target goods within the field of view of the delivery robot includes: Controlling the delivery robot to rotate and collecting search images in various directions during the rotation process; Target detection is performed on the search images in each direction to search for the target goods.

4. The method for optimizing the delivery task according to claim 3, wherein: The performing target detection on the search images in each orientation to search for the target goods includes: Performing target detection on the search images in each of the directions to obtain the type of goods appearing in each search image; If goods of the same type as the target goods appear only in a single search image, the goods appearing in the single search image are regarded as the target goods; If goods of the same type as the target goods appear in multiple search images, order classification is performed on the goods appearing in each search image, and the goods belonging to the order of the delivery task are used as the target goods.

5. The method for optimizing the delivery task according to claim 4, wherein: The order classification of the goods appearing in each search image includes: Align and stitch each search image to identify the same goods appearing in different search images; If the goods appearing in each search image are the same goods, determining that the goods appearing in each search image all belong to the order of the delivery task; If the goods appearing in each search image are different goods, then the goods attribute of each of the different goods is obtained, and the orders of the different goods are classified according to the goods attributes.

6. The method for optimizing a delivery task according to any one of claims 1 to 5, wherein: The optimization method of the delivery task also includes: If no delivery message is received from the vending machine within a preset time, the interior of the cargo hold is sensed to obtain a cargo sensing result; If the cargo sensing result indicates that the target cargo exists, the delivery operation is performed, and when a shipped message of the delivery task is received again, the shipped message is filtered; If the cargo sensing result is that the target cargo does not exist, an error correction operation is performed.

7. The method for optimizing a delivery task according to any one of claims 1 to 5, wherein: The sensing of the interior of the cargo hold to obtain cargo sensing results includes: Obtain product images from the delivery order for the delivery task; Taking pictures of the cargo inside the cargo hold; The goods picture is compared with the product picture to obtain the goods perception result.

8. A delivery robot comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method for optimizing the delivery task according to any one of claims 1 to 7 are implemented.

9. A vending system, characterized in that: include: The delivery robot according to claim 8; and Vending machines.

10. A computer program product, characterized in that The invention comprises a computer program, which enables the method for optimizing the delivery task according to any one of claims 1 to 7 to be executed when the computer program is executed.

Images