Electrical data processing method and system

Abstract

The invention provides an electrical data processing method and system, and relates to a data processing technology, and the method comprises the steps: obtaining the distribution information of a target desktop, generating first-level distribution information according to the target desktop, determining an extension path based on the current target information of the target desktop, and generating second-level distribution information according to the extension path. And according to the first-level distribution information and the second-level distribution information, the double-arm robot is controlled to place the distribution target, the automatic distribution level of the robot can be improved, and intelligentization of the whole distribution process is achieved.

Description

Technical Field

[0001] The present invention relates to data processing technologies, and in particular, to an electrical data processing method and system. Background Art

[0002] With the continuous development of automation technologies, in modern intelligent service venues, automated devices such as intelligent robots are widely used.

[0003] In the prior art, in some application scenarios, although a robot can deliver a delivery target to the vicinity of a corresponding demand desktop, subsequent processes often rely on manual intervention. Specifically, the person corresponding to the demand desktop needs to manually place the delivery target at the corresponding desktop position, and the robot may not be able to automatically deliver the delivery target to the desktop position specified by the user, making it difficult to achieve full automation of the delivery process.

[0004] Therefore, how to improve the automated delivery level of the robot and achieve the intelligence of the entire delivery process has become a problem to be solved. Summary of the Invention

[0005] The present invention provides an electrical data processing method and system, which can improve the automated delivery level of the robot and achieve the intelligence of the entire delivery process.

[0006] According to a first aspect of the present invention, there is provided an electrical data processing method, including: Obtaining allocation information of a target desktop; Generating first-level delivery information based on the target desktop, determining an extension path based on current target information of the target desktop, and generating second-level delivery information according to the extension path; Controlling a two-armed robot to place a delivery target according to the first-level delivery information and the second-level delivery information.

[0007] Optionally, in a possible implementation manner of the first aspect, the obtaining allocation information of the target desktop includes: Parsing a demand list of the target desktop to obtain a plurality of initial targets, and performing screening processing based on attributes of the initial targets to obtain demand targets, where the attributes include high-risk attributes and low-risk attributes; Splitting the demand list according to a preset order of the demand targets to obtain a delivery sub-table; Generating sub-allocation data for multiple time periods based on the delivery sub-table, and generating the allocation information according to the sub-allocation data.

[0008] Optionally, in a possible implementation manner of the first aspect, it is characterized in that the generating sub-allocation data for multiple time periods based on the delivery sub-table includes: Determine the distribution target in the sub-distribution data, retrieve the desktop image, and send the target image corresponding to the distribution target to the distribution end of the target desktop; Receive the positioning information of the distribution target from the distribution end to generate the sub-distribution data.

[0009] Optionally, in a possible implementation manner of the first aspect, it is characterized in that determining the stretching path based on the current target information of the target desktop includes: Determine the first position of the dual-arm robot relative to the target desktop, and obtain the second position of the delivery target on the target desktop; Generate an initial path according to the connection line between the first position and the second position; Obtain the current target information located on the initial path, and update the initial path according to the current target information to generate a stretching path.

[0010] Optionally, in a possible implementation manner of the first aspect, it is characterized in that obtaining the current target information located on the initial path, and updating the initial path according to the current target information to generate a stretching path includes: Obtain the height information of the current target information. When there is current target information corresponding to the height information greater than the preset height, mark the current target information as an adjustment target; Retrieve the interference range of the adjustment target, and generate a tangent set corresponding to the interference range with the second position center as the starting point; Update the initial path according to the tangent set to generate a stretching path.

[0011] Optionally, in a possible implementation manner of the first aspect, it is characterized in that updating the initial path according to the tangent set to generate a stretching path includes: Summarize the tangent set to generate a tangent set, and determine the outermost tangent in the tangent set as the candidate tangent; Update the first position according to the candidate tangent to obtain the initial updated position, and determine the initial updated position within the allowable delivery range of the target desktop as the allowable updated position; Obtain the update distance between the first position and the allowable updated position, and determine the allowable updated position with the smaller update distance as the selected position; Generate a stretching path according to the connection line between the selected position and the second position.

[0012] Optionally, in a possible implementation manner of the first aspect, it is characterized in that the allowable delivery range of the target desktop is determined by the following method, including: Collect the personnel positions on the target desktop, and perform exclusion processing on the initial delivery range of the desktop according to the personnel positions; Determine that the remaining initial delivery range is the permitted delivery range.

[0013] Optionally, in a possible implementation manner of the first aspect, before controlling the dual-arm robot to place the delivery target, it further includes: Obtain the current target information of the target desktop and the personnel action information in real time; When the personnel action information is in contact with any of the current target information, use the current target information as the judgment target; After determining that the judgment target leaves the target desktop, update the second position according to the position of the judgment target, and adjust the stretching path based on the updated second position.

[0014] Optionally, in a possible implementation manner of the first aspect, after determining that the judgment target leaves the target desktop, updating the second position according to the position of the judgment target includes: Compare the distribution ranges of the judgment target and the delivery target, and determine that the judgment target with a distribution range greater than or equal to the delivery target is the first real-time target; Obtain the first real-time target with the smallest distribution range as the second real-time target, and update the second position to the position of the second real-time target.

[0015] According to the first aspect of the present invention, there is provided an electrical data processing system, including: An allocation module for obtaining the allocation information of the target desktop; A path module for generating first-level delivery information according to the target desktop, determining a stretching path based on the current target information of the target desktop, and generating second-level delivery information according to the stretching path; An execution module for controlling the dual-arm robot to place the delivery target according to the first-level delivery information and the second-level delivery information.

[0016] The beneficial effects of the present invention are as follows: 1. The present invention can accurately place the delivery target at the specified position on the target desktop by combining the user-customized allocation information. During the delivery process, the stretching path corresponding to the arms of the dual-arm robot and the placement position of the delivery target can be dynamically adjusted according to the information of the items already placed on the target desktop and the personnel action information obtained in real time, so as to effectively solve the problem of inaccurate placement caused by the traditional delivery method's inability to adapt to environmental changes, and realize an intelligent item delivery service.

[0017] 2. The present invention realizes the efficient arrangement of distribution tasks by generating sub - allocation data for multiple time periods. Specifically, it can determine the priority order, i.e., the preset order, corresponding to each demand target, and group the demand targets with similar priorities together to form a distribution sub - table, so that the distribution tasks can be carried out in a reasonable time sequence, avoiding chaos and delays during the distribution process.

[0018] 3. The present invention can calculate the best movement path, i.e., the first - level distribution information, when moving to the target desktop according to the current position of the dual - arm robot and the target desktop position, which can ensure that the dual - arm robot can move efficiently and safely to the vicinity of the target desktop in a complex environment. When determining the stretching path of the dual - arm robot, i.e., the second - level distribution information, the present invention can obtain the current target information on the target desktop in real time, such as the item position, height and other information. According to the obtained current target information, the dual - arm robot can further plan the stretching path when placing the demand target with the manipulator. And if there are obstacles in the initially generated stretching path, such as a relatively high dish that has been placed, the dual - arm robot can use the placement position of the distribution target on the target desktop, i.e., the second position, as a reference point, and combine with the interference range of the obstacle to re - plan the path to generate a new stretching path, ensuring that the dual - arm robot can accurately place the distribution target at the position specified by the user, thereby realizing the refined control of the whole process of the dual - arm robot from picking up the distribution target to placing the distribution target. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0020] Figure 1 is a schematic flowchart of an electrical data processing method provided by an embodiment of the present invention; Figure 2 is a schematic diagram of determining a candidate tangent provided by an embodiment of the present invention; Figure 3 is a schematic structural diagram of an electrical data processing system provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0021] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part rather than all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0022] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, "a plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0023] It should be understood that in the present invention, "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a system, product or device including a series of units does not necessarily have to be limited to those units clearly listed, but may include other units not clearly listed or inherent to such products or devices.

[0024] It should be understood that in the present invention, "a plurality" means two or more. "Including A, B, and C" means that all of A, B, and C are included, "including A, B, or C" means including any one of A, B, and C, and "including A, B, and / or C" means including any one, any two, or all three of A, B, and C.

[0025] It should be understood that in the present invention, "B corresponding to A", "B corresponding to A relatively", "A corresponding to B relatively", or "B corresponding to A relatively" means that B has a corresponding relationship with the shape or function of A, and B can be determined according to A. Determining B according to A does not mean determining B only according to A, but B can also be determined according to A and / or other information.

[0026] In the description of the present invention, it should be understood that the terms "center", "length", "width", "thickness", "top end", "bottom end", "upper", "lower", "left", "right", "front", "rear", "vertical", "horizontal", "inner", "outer", "axial", "circumferential", etc. indicating the orientation or positional relationship are based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the indicated position or element must have a specific orientation, be constructed and operated in a specific manner, and thus cannot be construed as a limitation to the present invention.

[0027] In the present invention, unless otherwise clearly specified or defined, terms such as "installed", "connected", "linked", "fixed", etc. shall be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or integrated; it may be a mechanical connection, an electrical connection, or communication with each other; it may be directly connected, or indirectly connected through an intermediate medium, which may be the internal connection of two components or the interaction relationship between two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0028] In the present invention, unless otherwise clearly specified or defined, the first feature being "above" or "below" the second feature may include the direct contact between the first and second features, or may include the situation where the first and second features are not in direct contact but in contact through other features therebetween. Moreover, the first feature being "above", "over" and "on top of" the second feature includes that the first feature is directly above and obliquely above the second feature, or simply means that the horizontal height of the first feature is higher than that of the second feature. The first feature being "under", "beneath" and "underneath" the second feature includes that the first feature is directly below and obliquely below the second feature, or simply means that the horizontal height of the first feature is lower than that of the second feature.

[0029] The technical solutions of the present invention will be described in detail below with specific embodiments. The examples of the embodiments are shown in the drawings, in which the same or similar reference numerals are used to denote the same or similar components or components with the same or similar functions throughout. These specific embodiments below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0030] S1. Obtain the allocation information of the target desktop.

[0031] Among them, the target desktop may be the dining table desktop where the user is located, and the allocation information refers to the placement positions customized by the user for the selected dishes with the help of the terminal. Subsequently, when the robot delivers meals, it can place each dish at the position specified by the user in combination with the allocation information.

[0032] In practical applications, in some scenarios where automated devices are introduced, although the manual burden is partially reduced, most of these devices lack intelligent path planning and environmental perception capabilities. For example, simple food delivery robots often travel along fixed routes. Once they encounter complex situations such as messy items on the dining table, they are prone to problems such as collisions and inability to reach the designated location. Moreover, in the placement link of the delivery target, it is difficult for the existing technology to achieve precise and reasonable placement according to the real-time state of the target desktop, such as the position of the placed items and the personnel distribution, resulting in unreasonable utilization of the desktop space and even affecting the customers' dining or the execution of subsequent delivery tasks. This solution can accurately place the delivery target at the designated position on the target desktop by combining the user-customized allocation information. And during the delivery process, according to the information of the items already placed on the target desktop and the personnel movement information obtained in real time, the extension paths corresponding to the arms of the dual-arm robot and the placement position of the delivery target are dynamically adjusted, so as to effectively solve the problem of inaccurate placement caused by the inability of the traditional delivery method to adapt to environmental changes and achieve intelligent item delivery services.

[0033] Specifically, when a user dines in a restaurant, the user can place an order for multiple dishes through a smart terminal, such as the user's own mobile phone. And the user can specify the placement position of each dish on the dining table, that is, the target desktop, according to factors such as the user's dining habits and the distribution of the people at the same table, and obtain the allocation information for the target desktop. For example, the hot dishes can be placed on the side close to the user for easy access, and the soup can be placed in the center of the target desktop where it is not easy to spill.

[0034] In some embodiments, the specific implementation manner of step S1 may be: S11, parse the requirement list of the target desktop to obtain multiple initial targets, and perform screening processing based on the attributes of the initial targets to obtain requirement targets, where the attributes include high-risk attributes and low-risk attributes.

[0035] After receiving the dining order information of the user, deeply analyze the requirement list of the target table. The requirement list contains all the dishes ordered by the user and related information. Each dish is extracted as an initial target, and these initial targets may cover various types of dishes, such as hot dishes, cold dishes, soups, staple foods, etc. For each initial target, screening processing can be performed according to its attributes. The attributes are divided into high-risk attributes and low-risk attributes. High-risk attributes usually represent items that need special attention during the delivery process. For example, soups are prone to spilling and belong to high-risk attributes. Some fragile tableware or dishes with special shapes and easy to damage may also be classified as high-risk attributes. Low-risk attributes represent relatively safe and stable items, such as ordinary cold dishes and staple foods. By judging the attributes of the initial targets, the targets with high-risk attributes are screened out, and their delivery conditions and requirements are further evaluated. For the initial targets with high-risk attributes that do not meet the current delivery conditions, such as the restaurant kitchen lacking specific anti-spill packaging equipment at this time, resulting in some soups being unable to be safely delivered, these targets will be temporarily excluded from the demand targets. For the initial targets with low-risk attributes, as long as there are no other special restrictions, they can be directly included in the scope of demand targets. Through this screening process, it is ensured that the demand targets entering the subsequent delivery process are all items that can be safely and smoothly delivered under the current conditions, improving the feasibility and efficiency of the delivery task.

[0036] Among them, the requirement list refers to the list of all the dishes ordered by the user and related information. The initial target refers to each dish extracted from the requirement list. The attribute refers to the characteristic of each initial target. The demand target refers to the item that will be actually delivered in the subsequent delivery process. The high-risk attribute refers to the characteristic of the item that needs special attention during the delivery process. The low-risk attribute refers to the characteristic of the relatively safe and stable item.

[0037] S12, split the requirement list according to the preset order of the demand targets to obtain a delivery sub-table.

[0038] After obtaining the demand target, further process the demand list, split the demand list according to the preset order of the demand target, and obtain the delivery sub-table. The preset order can be comprehensively determined according to various factors. First, the production time of the dishes is an important factor. For dishes with complex production processes and long production times, such as roasted duck that needs to be roasted, production and delivery should be arranged first to ensure the rationality of the overall dining time. Second, the importance of the dishes also affects the order. For example, the main courses in a set meal are usually more important than the side dishes and will be given priority for delivery. In addition, the order of users' meals is also one of the considerations. For example, appetizers may be delivered before the main course, and desserts are usually served last. According to these factors, determine a priority order for each demand target, that is, the preset order. For example, in an order containing a starter salad, a main course steak, a side dish of fries, and a dessert cake, the production time of the salad is relatively short, and as an appetizer, it should be served first, so the priority is relatively high and the preset order is relatively forward. The steak, as the main course, although it takes a long time to produce, has a high importance level, so the priority is also high and the preset order is relatively forward. The fries, as a side dish, have a relatively low priority. The cake, as a dessert, is usually eaten last and has the lowest priority.

[0039] According to the determined preset order, split the demand list, and combine the demand targets with similar priorities or that can be delivered simultaneously according to the dining process to form a delivery sub-table. For example, in the above order, the salad and the steak can form a delivery sub-table because they both belong to the dishes that need to be delivered in the early stage of the meal. The fries can form a separate delivery sub-table because its production time is relatively short and it can be delivered appropriately after the main course. The cake can form another delivery sub-table and be delivered as the last dish. Through this splitting method, the originally complex and chaotic demand list can be organized into an orderly delivery sub-table, providing a clear structure for generating sub-allocation data in multiple time periods later, making the arrangement of delivery tasks more reasonable and orderly, and helping to improve the delivery efficiency and the customer dining experience.

[0040] Among them, the preset order refers to the priority order of demand targets comprehensively determined according to various factors (such as the production time of dishes, importance level, the order of users' meals, etc.), and the delivery sub-table refers to the list obtained by splitting the demand list according to the determined preset order.

[0041] S13. Generate sub-allocation data in multiple time periods based on the delivery sub-table, and generate the allocation information according to the sub-allocation data.

[0042] After obtaining the delivery sub-table, since the demand targets in each delivery sub-table have different characteristics and there are time requirements in the actual dining process, multi-period sub-allocation data can be generated. For example, for an order containing appetizers, main courses, and desserts, the appetizers need to be delivered as soon as possible after the customer is seated. The main course takes a longer time to prepare and will be delivered later. The dessert comes after the main course. Therefore, according to the characteristics of these demand targets and the dining time requirements, the delivery process is divided into multiple periods, and corresponding sub-allocation data is generated for each period. The generated multi-period sub-allocation data is integrated and further processed to finally generate complete allocation information. During the process of generating the allocation information, relevant detailed information of the target table can be combined, such as the specific layout of the table and the placement positions of user-customized items (such as which area of the table a specific dish is placed). By comprehensively considering these factors, the generated allocation information can better fit the actual delivery scenario, thereby improving the accuracy and efficiency of the dual-arm robot delivery. For example, the allocation information will clearly instruct the dual-arm robot to accurately deliver the items in a specific delivery sub-table to the designated position of the target table at a specific time, and reasonably arrange the order and path planning of the delivery to ensure that the entire delivery process is efficient and accurate, and maximally meet the needs of customers and improve the service quality.

[0043] Among them, the sub-allocation data refers to the specific delivery data for each period generated based on the delivery sub-table.

[0044] In some embodiments, "generating multi-period sub-allocation data based on the delivery sub-table" in step S13 includes the following steps: S131, determine the allocation target in the sub-allocation data, retrieve the desktop image, and send the target image corresponding to the allocation target to the allocation end of the target table.

[0045] For each delivery sub - table, the demand targets therein can be used as allocation targets. For example, in a delivery sub - table containing salad and steak, salad and steak are the allocation targets. These allocation targets are the core objects of subsequent deliveries and need to be accurately identified and processed. Moreover, through devices such as cameras installed in the restaurant, the real - time image corresponding to the target table, that is, the table - top image, can be retrieved. This image can show the current state of the table - top, such as whether there are other items placed, the placement location, and the occupied space, etc. Understanding the actual situation of the table - top is crucial for reasonably arranging the placement locations of the allocation targets. At the same time, the target images corresponding to each allocation target can be obtained. These images can be standard pictures of the dishes, used to be shown to users at the allocation end, enabling users to more intuitively understand the dishes to be delivered. Then, the table - top image and the target images corresponding to the allocation targets can be sent to the allocation end of the target table. The allocation end can be an intelligent terminal installed on the dining table or the user's mobile terminal. Users can see these images at the allocation end, providing a basis for subsequent positioning operations.

[0046] Among them, the allocation target refers to the demand target in the delivery sub - table and is the core object of subsequent deliveries. The table - top image refers to the real - time image corresponding to the target table. The target image refers to the image corresponding to each allocation target, usually a standard picture of the dish, used to be shown to users at the allocation end, enabling users to more intuitively understand the dishes to be delivered. The allocation end refers to the terminal that receives the table - top image and the target images corresponding to the allocation targets.

[0047] S132. Receive the positioning information of the allocation target from the allocation end and generate the sub - allocation data.

[0048] After seeing the table - top image and the target images at the allocation end, users can, according to their own needs and actual situations, position each allocation target. For example, users can specify that the salad should be placed in the upper - left corner of the table - top and the steak should be placed in the position slightly to the right of the middle. This positioning method can fully consider the personalized needs of users, improve the accuracy of delivery and user satisfaction. The allocation end sends the positioning information of the allocation target by the user to the dual - arm robot. After receiving this positioning information and combining with information such as the previously determined delivery time period, etc., sub - allocation data can be generated. The sub - allocation data will contain content such as the positioning information of each allocation target, providing detailed guidance for subsequent delivery work.

[0049] In some embodiments, when generating the sub - allocation data, it further includes: A1. Obtain the allocation range of each of the allocation targets, and determine the allocation targets with an interference relationship according to the allocation range as the judgment set.

[0050] Specifically, each allocation target has its corresponding allocation range, which can be understood as the area where the item is allowed to be placed on the target table (such as a dining table). For example, a large plate of stir-fried dishes may require a relatively large placement space, so its allocation range is relatively large, while a small portion of dessert may only need a small area, and its allocation range is relatively small. The allocation range of each allocation target can be determined based on the positioning information set by the user at the allocation end before and the actual layout of the target table. For example, if the user designates a certain hot dish to be placed in the upper left corner of the dining table, the specific allocation range of this hot dish at this position can be calculated by combining the size and shape of the dish. When the allocation ranges of two or more allocation targets overlap or affect each other, for example, if the allocation ranges of two larger dishes overlap, there will be a conflict when placing them, and they have an interference relationship. The allocation ranges of all allocation targets can be compared and analyzed one by one. By calculating the overlapping area between the allocation ranges, etc., the allocation targets with an interference relationship can be found, and the allocation targets with an interference relationship can be combined together to form a judgment set. This judgment set is an important basis for determining the delivery order later because these targets need to consider their order and mutual relationship during delivery and placement to avoid conflicts and chaos.

[0051] Among them, the allocation range refers to the specific area where each allocation target is allowed to be placed on the target table, the interference relationship refers to the situation where the allocation ranges of two or more allocation targets overlap or affect each other, and the judgment set refers to the set formed by combining the allocation targets with an interference relationship.

[0052] A2. Determine the stacking order of the allocation targets in the judgment set, and sort the stacking order according to the preset order of the allocation targets to generate the delivery order.

[0053] In the judgment set, there is a reasonable placement order for each distribution target, that is, the stacking order. For example, if one dish is a soup and the other is a solid dish, and their distribution ranges overlap, since the soup is prone to spilling, the solid dish may be placed first and then the soup. Therefore, based on these factors, the stacking order of the distribution targets in each judgment set can be determined. When determining the delivery order, the distribution targets in the judgment set can be initially sorted according to the stacking order. Then, this sorting result is combined with the preset order for calibration. For example, if a main course should be placed first in the stacking order, but from the perspective of the preset order, the appetizer should be delivered first, then the final sorting will give priority to the preset order and place the appetizer in the front. Through such calibration, the final delivery order can be generated. It should be noted that when the distribution ranges of the distribution targets overlap, it is necessary to additionally consider whether the previous distribution target has been removed during the delivery process. Because if the previous target has not been removed, the subsequent target may not be able to be placed at the designated position as planned. For example, if the distribution ranges of two dishes overlap and the dish delivered first always occupies the overlapping area, the dish to be delivered later cannot be placed properly. Therefore, when the dual-arm robot performs the delivery task, it will monitor the status of the previous distribution target in real time. Only when the previous target is removed and the overlapping area is vacated will the delivery of the subsequent target be arranged to ensure that each distribution target can be successfully placed in its corresponding distribution range, further guaranteeing the accuracy and efficiency of the delivery.

[0054] Among them, the stacking order refers to a reasonable placement order for each distribution target in the judgment set, and the delivery order refers to the final delivery order generated after calibrating with the preset order after determining the stacking order.

[0055] S2. Generate first-level delivery information according to the target desktop, determine the stretching path based on the current target information of the target desktop, and generate second-level delivery information according to the stretching path.

[0056] Among them, the first-level delivery information refers to the movement path information from the position where the dual-arm robot picks up the required target to the position of the target desktop. The current target information refers to the information corresponding to the required target that the dual-arm robot is currently going to place, such as information like the position and the range occupied on the target desktop. The stretching path refers to the extended path of the mechanical arm of the dual-arm robot when placing the required target. The second-level delivery information refers to the stretching path information of the mechanical arm when the dual-arm robot further plans to place the required target after arriving at the target desktop according to the currently obtained current target information.

[0057] Specifically, the dual-arm robot can be located in the kitchen food pickup area during actual operation to wait for receiving delivery tasks. When the order processing system of the smart restaurant receives a new delivery requirement, it can send the location information of the target table and the dish information included in the order to the dual-arm robot. The dual-arm robot can calculate the best movement path from the kitchen food pickup area to the target table based on its current position (i.e., the position of the target of the pickup requirement) and the position of the target table, using the built-in map navigation algorithm and path planning program. This movement path information is the first-level delivery information, which covers the route planning for the robot to move in the restaurant environment and can include the passages passed, the turning angles, and the estimated travel time, etc., to ensure that the robot can efficiently and safely shuttle through the complex environment in the restaurant and quickly reach near the target table.

[0058] When the dual-arm robot is about to reach the target table, it can obtain the current target information of the target table in real time through the sensors it carries, such as cameras. These information include the positions, heights, etc. of the items already placed on the target table. For example, the camera takes pictures of the target table, and the image processing algorithm analyzes the images to identify the positions and occupied spaces of the existing plates, tableware, beverage cups, etc. on the table to evaluate the possible impact on the robot's placement of dishes. According to the obtained current target information, the dual-arm robot further plans the stretching path when the robotic arm places the target of the requirement. If it detects that the items in a certain area on the target table are relatively high, the robotic arm will automatically avoid this area and find other suitable stretching paths. After determining the stretching path, the dual-arm robot can generate the second-level delivery information based on its own position at the current moment (at this time, the robot has moved near the target table) and the specific position of the target table, combined with the planning details of the stretching path. The second-level delivery information not only includes the specific action instructions during the stretching process of the robot's robotic arm but also involves the fine-tuning movement information of the overall dual-arm robot during the process of placing dishes, to ensure that the robotic arm can accurately place the dishes at the position specified by the user. For example, during the stretching process of the robotic arm, in order to avoid the outstretched arm of the diner, it may be necessary to slightly adjust the stretching speed and angle at a certain moment, and these dynamically adjusted information are all included in the second-level delivery information, so as to achieve the refined control of the whole process of the robot from picking up dishes to placing dishes.

[0059] In some embodiments, the stretching path can be determined by the following method: S21, determine the first position of the dual-arm robot relative to the target table, and obtain the second position of the delivery target on the target table.

[0060] Specifically, the position of the dual-arm robot relative to the target table can be accurately determined through the positioning system carried by the dual-arm robot itself, such as the Global Positioning System (GPS) combined with indoor positioning technologies such as Wi-Fi positioning. This position is the first position, and the placement position of the delivery target, which is the current delivery requirement target of the dual-arm robot, on the target table can be obtained, that is, the second position. For example, when the user specifies on the mobile phone ordering application that a certain hot dish should be placed at the corner position near their right hand on the dining table according to their dining habits and the distribution of people at the same table, after receiving this information, the dual-arm robot can determine this position as the second position of the delivery target on the target table.

[0061] Among them, the first position refers to the position of the dual-arm robot relative to the target table, and the second position refers to the placement position of the delivery target on the target table.

[0062] S22. Generate an initial path according to the connection line between the first position and the second position.

[0063] Specifically, after determining the first position and the second position, using simple geometric principles, connect these two positions to preliminarily plan a path from the position of the dual-arm robot itself to the specified placement position on the target table. This path is the initial path. Among them, the initial path refers to the path preliminarily planned by connecting the first position of the dual-arm robot and the second position of the delivery target, from the position of the robot itself to the specified placement position on the target table.

[0064] S23. Obtain the current target information located on the initial path, and update the initial path according to the current target information to generate an extended path.

[0065] The dual-arm robot can obtain the current target information located on the initial path in real time through sensors configured by itself, such as cameras. Specifically, it can capture an image of the target table area in the direction of the initial path through the camera, and the image processing algorithm analyzes the image to identify the positions and height information of objects such as dishes and plates that have been placed in this area. For example, when the camera captures a dish that has been placed on the initial path, the image recognition algorithm determines its position coordinates and height information to obtain the current target information. According to the obtained current target information, it is judged whether the initial path is feasible. If there are obstacles on the initial path, such as dishes that have been placed, the robot can update the initial path according to the position and height information of the obstacles. For example, if it is detected that there is a relatively high placed dish in a certain area on the initial path, the dual-arm robot can use the placement position of the delivery target on the target table, that is, the second position, as a reference point, and combine the interference range of the obstacle to re-plan the path.

[0066] In some embodiments, the specific implementation manner of step S23 may be: S231. Obtain the height information of the current target information. When there is current target information corresponding to the height information greater than the preset height, mark the current target information as the adjustment target.

[0067] Specifically, the height information can be extracted from the obtained current target information, and the height information is compared with the preset height. Here, the preset height is not a fixed value, but is set according to the arm movement characteristics when the dual-arm robot places the delivery target. Since the robot arm is generally tilted downward when placing an object, the space near the second position corresponding to the delivery target is relatively small. To avoid the manipulator from colliding with obstacles, the preset height here will be set lower. For example, in the area closer to the second position, the preset height may be set to 30 cm, while in the area farther from the second position, since the manipulator has more room for movement, the preset height can be appropriately increased, such as 50 cm. The extracted height information is compared with the preset height at the corresponding position. When it is detected that the height of the object in the current target information is greater than the preset height in the corresponding distance range, the current target information corresponding to the object is marked as the adjustment target. For example, in the area closer to the second position, the camera recognizes that the height of an object is 40 cm, which is greater than the preset height of 30 cm in this area. Then the current target information related to this object will be marked as the adjustment target. The purpose of marking the adjustment target is to be able to focus on dealing with these obstacles that may affect the path subsequently, so as to generate a suitable stretching path.

[0068] Among them, the height information refers to the height data of the placed object extracted from the current target information, the preset height refers to the pre-set reference height value, and the adjustment target refers to the current target information corresponding to the object whose height is greater than the preset height in the corresponding distance range.

[0069] S232. Retrieve the interference range of the adjustment target, and generate a tangent group corresponding to the interference range starting from the center of the second position.

[0070] Among them, the interference range refers to the area range corresponding to the adjustment target on the target desktop, and the tangent group refers to the combination of all tangents corresponding to each adjustment target.

[0071] Specifically, for the adjustment target, the corresponding interference range information can be retrieved. The interference range refers to the area range corresponding to the adjustment target on the target desktop, and this range is determined according to the shape, size, etc. of the adjustment target. Starting from the center of the second position, a tangent group corresponding to the interference range can be generated. Specifically, tangents can be drawn from the center of the second position to the edge of the interference range, and these tangents can represent the possible path directions for the robotic arms of the dual-arm robot to avoid the adjustment target. For example, if the interference range of the adjustment target is a circular area, then multiple tangents can be drawn from the center of the second position to the circumference of the circular interference range to form a tangent group. If the interference range of the adjustment target is a rectangular area, then multiple tangents can be drawn from the center of the second position to the vertices of the rectangular interference range to form a tangent group. Since there may be multiple adjustment targets, there may be multiple groups of tangent groups. These tangents provide a direction reference for determining a new path later, and the stretching path to avoid the adjustment target can be planned based on these tangents.

[0072] S233. Update the initial path according to the tangent group to generate a stretching path.

[0073] Specifically, by analyzing the generated tangent group in detail, the feasibility of each tangent can be evaluated. The factors considered include whether the tangent is within the movement range of the robot and whether new interference will occur with other objects when extending along the tangent. For example, some tangents may cause the robotic arm to extend to a position beyond its movement limit or collide with other objects around the target desktop, and these tangents will be excluded. By screening the tangents, the feasible tangents can be retained, and the initial path can be updated according to the screened tangents to obtain the stretching path.

[0074] In some embodiments, the specific implementation manner of step S233 can be: S2331. Summarize the tangent group to generate a tangent set, and determine the outermost tangent in the tangent set as the candidate tangent.

[0075] Specifically, summarize the generated tangent groups to form a tangent set. This tangent set contains all the tangents corresponding to the interference range of the obstacle. Determine the outermost tangent in the tangent set as the candidate tangent. The outermost tangent helps the robot better avoid interference with the obstacle during movement. For example, when the interference range of the obstacle is a circular area, the outermost tangent in the tangent set may be the tangent that is tangent to the edge of the circular interference range and is farthest from the initial path. And since there may be multiple adjustment targets, there may also be multiple groups of corresponding tangent groups. The determined candidate tangents can belong to different tangent groups. Refer to Figure 2 , which is a schematic diagram for determining candidate tangents provided by an embodiment of the present invention. As shown in Figure 2As shown in [reference], an initial path can be obtained by connecting the first position and the second position on the target desktop. On the initial path, there are two adjustment targets, and two corresponding sets of tangent groups can be obtained. These two sets of tangent groups can be aggregated to obtain a corresponding tangent set. From Figure 2 it can be seen that there are four tangents in this tangent set, which are tangent 1, tangent 4, tangent 2, and tangent 3 from top to bottom. In this tangent set, tangent 1 and tangent 3 are the outer tangents, so tangent 1 and tangent 3 can be determined as candidate tangents. And it can be seen from the figure that tangent 1 and tangent 3 belong to different tangent groups.

[0076] Among them, the tangent set refers to the set obtained by aggregating the obtained tangent groups, and the candidate tangent refers to the outermost tangent in the tangent set.

[0077] S2332. Update the first position according to the candidate tangent to obtain an initial updated position, and determine the initial updated position within the allowable delivery range of the target desktop as the allowable update position.

[0078] Specifically, extend the candidate tangent, and determine the position where the extended tangent intersects the edge of the target desktop. This position is the initial updated position. In this way, a possible new starting position based on the candidate tangent can be determined to re-plan the path to avoid obstacles. After obtaining the initial updated position, it is necessary to determine whether it is within the allowable delivery range of the target desktop. The allowable delivery range is obtained by excluding the initial delivery range of the desktop after considering factors such as the position of the personnel. Only the initial updated position within the allowable delivery range will be determined as the allowable update position. This screening process ensures that the subsequent operations of the robot will not interfere with the personnel and will not place the delivery target in an inappropriate area, improving the rationality when placing the delivery target.

[0079] Among them, the initial updated position refers to the position where the extended tangent intersects the edge of the target desktop after extending the candidate tangent. The allowable delivery range refers to the range that can ensure that the dual-arm robot will not interfere with the personnel when placing the delivery target. The allowable update position refers to the initial updated position within the allowable delivery range.

[0080] In some embodiments, the allowable delivery range of the target desktop can be determined by the following method: S23321. Collect the personnel position of the target desktop, and exclude the initial delivery range of the desktop according to the personnel position.

[0081] Specifically, the robot collects the position information of the personnel on the target desktop through the cameras equipped on itself. The cameras can capture images of the target desktop, and use image recognition technology to identify the positions of the personnel. According to the collected personnel position information, the initial delivery range of the desktop is processed for exclusion. For example, if a person is sitting on the left side of the target desktop, then the area near the left side in the initial delivery range may be marked as an unavailable area and excluded from the initial delivery range. The principle of exclusion is to ensure that the delivery operation of the robot will not collide with or interfere with the personnel, and to ensure the safety and comfort of the personnel.

[0082] Among them, the personnel position refers to the specific sitting position of the personnel corresponding to the target desktop, and the initial delivery range refers to the entire area where the dual-arm robot originally planned to perform delivery operations on the target desktop without considering factors such as personnel positions.

[0083] S23322, determine the remaining initial delivery range as the permitted delivery range.

[0084] After processing the exclusion of the initial delivery range, the remaining part is the permitted delivery range. This permitted delivery range is the area where the dual-arm robot can move safely and perform deliveries during subsequent operations. When the dual-arm robot plans the path and places the delivery target, it will be strictly restricted within this permitted delivery range to ensure the smooth completion of the delivery task.

[0085] S2333, obtain the update distance between the first position and the permitted update positions, and determine the permitted update position with the smaller update distance as the selected position.

[0086] Specifically, the distance between the first position (i.e., the original position of the dual-arm robot relative to the target desktop) and each permitted update position can be calculated. This distance is the update distance. Compare the update distances between each permitted update position and the first position, and select the permitted update position with the smaller update distance as the selected position. Selecting the position with the smaller update distance can reduce the moving distance of the robot, improve the delivery efficiency, and also help to maintain the stability and accuracy of the robot's movement. Among them, the update distance refers to the update distance between the first position and the permitted update position, and the selected position refers to the permitted update position with the smaller update distance.

[0087] S2334, generate an extended path according to the connection line between the selected position and the second position.

[0088] After determining the selected position and the second position, an extended path can be generated according to the connection line between these two positions. This extended path is the new path of the dual-arm robot from the new starting position to the target placement position after avoiding the obstacles with a higher height on the target desktop, and can ensure that the robot safely and accurately places the item at the specified position on the target desktop to complete the delivery task.

[0089] In some embodiments, before the dual-arm robot places the delivery target, it further includes: B1. Obtain the current target information of the target desktop and the personnel movement information in real time.

[0090] Specifically, the dual-arm robot continuously monitors the target desktop through a camera configured on itself. By taking real-time pictures of the target desktop, it uses advanced image processing algorithms to identify information such as the positions and occupied ranges of the items already placed on the target desktop, and obtains the current target information of the target desktop in real time. Moreover, it can monitor the movements of the personnel around the target desktop in real time. The camera captures the limb movement images of the personnel, and analyzes the images through a human pose recognition algorithm to determine whether the personnel have actions such as reaching, grasping, and moving. For example, when a person reaches for a certain dish on the desktop, this action can be recognized and converted into personnel movement information and transmitted to the control system of the robot. At the same time, it can also monitor the change in the distance between the dish taken by the personnel and the target desktop in real time to further assist in judging whether the personnel are performing corresponding moving operations on the dishes already placed on the desktop.

[0091] Among them, the personnel movement information refers to the limb movement information of the personnel around the target desktop.

[0092] B2. When the personnel movement information is in contact with any of the current target information, use the current target information as the judgment target.

[0093] When the control system of the dual-arm robot receives the personnel movement information and determines that the action belongs to contacting an item on the target desktop, it immediately determines the current target information corresponding to the contacted item as the judgment target. For example, when the camera captures that a person reaches out and picks up a plate on the desktop, the current target information related to the plate at this time, including the position, shape, and occupied space of the plate, is marked as the judgment target. This process ensures that the robot can accurately lock the item involved in the personnel operation and provides a clear basis for subsequent adjustment decisions. Among them, the judgment target refers to the required target (i.e., the dish) that has been placed on the target desktop and contacted by the personnel.

[0094] B3. After determining that the judgment target leaves the target desktop, update the second position according to the position of the judgment target, and adjust the stretching path based on the updated second position.

[0095] Specifically, the dual-arm robot can continuously monitor and judge the state of the target through a camera. When it judges that the target has disappeared from the target table, for example, when a person completely picks up the dinner plate and takes it away from the table, the dual-arm robot can determine that the judgment target has left the target table. After determining that the judgment target has left the target table, the robot updates the originally preset second position of the delivery target (i.e., the placement position of the delivery target on the target table) according to the position information when the judgment target leaves. For example, if it was originally planned to place dish D at the corresponding second position on the target table, and during the delivery process, a person takes away dish C that was originally placed nearby, at this time, the dual-arm robot can infer based on the position where dish C left that the user may hope to place dish D at the original position of dish C, so it updates the second position of dish D to the position where dish C left. Based on the updated second position, the dual-arm robot can re-plan the extension path when placing the delivery target with the robotic arm. The robot will comprehensively consider its current position, the updated second position, and the environmental information around the target table, such as the positions of other already placed items and the positions of people, and use a path planning algorithm to generate a new extension path. For example, if there are other obstacles between the new second position and the robot's current position, the robot will recalculate the path to avoid the obstacles to ensure that the robotic arm can safely and accurately place the delivery target at the updated second position, thereby realizing the dynamic adjustment of the delivery process and better adapting to on-site changes.

[0096] In some embodiments, "after determining that the judgment target has left the target table, updating the second position according to the position of the judgment target" in step B3 includes the following steps: B31. Compare the allocation ranges of the judgment target and the delivery target, and determine the judgment target whose allocation range is greater than or equal to that of the delivery target as the first real-time target.

[0097] Specifically, the allocation range information of the judgment target (i.e., the item that is operated by the person and leaves the table) and the delivery target (i.e., the item to be placed, such as dish D) can be obtained. The allocation range can be understood as the range area occupied by the delivery target on the target table. For example, for dish C (judgment target) and dish D (delivery target), their respective allocation ranges can be determined based on information such as the size and shape of the dishes and the placement area that the user may specify when ordering food. Compare the allocation range of the judgment target with the allocation range of the delivery target. If the allocation range of the judgment target is greater than or equal to the allocation range of the delivery target, then the judgment target is determined as the first real-time target. For example, if the allocation range of dish C is greater than or equal to the allocation range of dish D, then dish C is recognized as the first real-time target. The purpose of this step is to screen out those judgment targets that may provide a suitable placement space for the delivery target and prepare for determining a more optimal placement position. Among them, the first real-time target refers to the judgment target whose allocation range is greater than or equal to the allocation range of the delivery target.

[0098] B32. Obtain the first real-time target with the smallest allocation range as the second real-time target, and update the second position to the position of the second real-time target.

[0099] When there are multiple determined first real-time targets, the allocation ranges of these first real-time targets can be further obtained, and the first real-time target with the smallest allocation range can be found from them and determined as the second real-time target. The reason for selecting the target with the smallest allocation range is that a smaller allocation range may mean a more precise placement position and less impact on other areas of the target table. For example, if the allocation ranges of multiple dishes (first real-time targets) are all greater than or equal to the allocation range of the delivery target, the sizes of the allocation ranges of these dishes can be compared, and the first real-time target with the smallest allocation range is selected as the second real-time target. Update the second position of the delivery target to the position of the second real-time target, that is, if it is determined that the position of a certain dish (second real-time target) is the most suitable for placing the delivery target, the dual-arm robot can adjust the originally preset second position for the delivery target to the position when the second real-time target leaves. In this way, the robot can select a relatively optimal position to place the delivery target according to the actual changes on the target table, improving the rationality of the delivery and user satisfaction. Through this series of steps, the dual-arm robot can dynamically adjust the delivery strategy in a complex and changeable delivery environment to achieve a more efficient and accurate delivery service. Among them, the second real-time target refers to the first real-time target with the smallest allocation range.

[0100] Through the above implementation methods, it can be ensured that the dual-arm robot can dynamically adjust the delivery strategy in a complex and changeable delivery environment to achieve a more efficient and accurate delivery service.

[0101] S3. Control the dual-arm robot to place the delivery target according to the first-level delivery information and the second-level delivery information.

[0102] After the control system of the dual-arm robot receives the first-level delivery information and the second-level delivery information, it integrates and analyzes these two sets of information. According to the moving path planned in the first-level delivery information, the robot drives its own mobile chassis and moves smoothly from the meal collection area in the kitchen to near the target table at a preset speed and direction. When it arrives near the target table, it can accurately control the actions of the robotic arm such as stretching and rotating according to the action instructions of the robotic arm in the second-level delivery information. For example, the robotic arm moves the dish smoothly to above the placement position specified by the user according to the determined stretching path.

[0103] During the process of the robotic arm placing the dish at the target position, the robot continuously monitors the state of the target table and the relative relationship between itself and the target position in real time through sensors such as cameras. If it is found that the position of the diner has changed, or the position of the items on the target table has changed due to the actions of the people, the dual-arm robot can adjust the second-level delivery information in real time according to the latest current target information. For example, if the diner suddenly stretches his arm to the originally planned dish placement position, the control system of the robot will immediately react and adjust the stretching path and placement action of the robotic arm. Without disturbing the diner, the dish is placed at an alternative position that generally meets the user's expectations and is safe and reasonable. Through this dynamic adjustment mechanism, it can be ensured that the delivery target can be accurately and safely placed on the target table, providing an intelligent and personalized item delivery service for users.

[0104] Through the above implementation manners, it can be ensured that the delivery target can be accurately and safely placed on the target table.

[0105] See Figure 3 , which is a schematic structural diagram of an electrical data processing system provided by an embodiment of the present invention. The data processing system based on the electrical data processing system includes: An allocation module for obtaining the allocation information of the target table; A path module for generating first-level delivery information according to the target table, determining a stretching path based on the current target information of the target table, and generating second-level delivery information according to the stretching path; An execution module for controlling the dual-arm robot to place the delivery target according to the first-level delivery information and the second-level delivery information.

[0106] Figure 3 The device in the illustrated embodiment can correspondingly be used to execute Figure 1 the steps in the method embodiment shown. The implementation principle and technical effects are similar and will not be elaborated here.

[0107] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than limiting it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An electrical data processing method, characterized in that, Including: Obtain the allocation information of the target desktop; Generate first-level delivery information based on the target desktop, determine the stretching path based on the current target information of the target desktop, and generate second-level delivery information according to the stretching path; According to the first-level delivery information and the second-level delivery information, control the dual-arm robot to place the delivery target.

2. The electrical data processing method according to claim 1, characterized in that, The obtaining the allocation information of the target desktop includes: Parse the requirement list of the target desktop to obtain multiple initial targets, and perform screening processing based on the attributes of the initial targets. The attributes include high-risk attributes and low-risk attributes; Split the requirement list according to the preset order of the requirement targets to obtain a delivery sub-table; Generate sub-allocation data for multiple time periods based on the delivery sub-table, and generate the allocation information according to the sub-allocation data.

3. The electrical data processing method according to claim 2, wherein The generating sub-allocation data for multiple time periods based on the delivery sub-table includes: Determine the allocation targets in the sub-allocation data, retrieve the desktop image, and send the target image corresponding to the allocation target to the allocation end of the target desktop; Receive the positioning information of the allocation target by the allocation end to generate the sub-allocation data.

4. The electrical data processing method according to claim 1, wherein The determining the stretching path based on the current target information of the target desktop includes: Determine the first position of the dual-arm robot relative to the target desktop, and obtain the second position of the delivery target on the target desktop; Generate an initial path according to the connection line between the first position and the second position; Obtain the current target information located on the initial path, and update the initial path according to the current target information to generate a stretching path.

5. The electrical data processing method according to claim 4, characterized in that The obtaining the current target information located on the initial path, and updating the initial path according to the current target information to generate a stretching path includes: Obtain the height information of the current target information. When there is current target information corresponding to the height information greater than the preset height, mark the current target information as an adjustment target; Retrieve the interference range of the adjustment target, and generate a tangent group corresponding to the interference range with the second position as the starting point; Update the initial path according to the tangent group to generate a stretching path.

6. The electrical data processing method according to claim 5, characterized in that, The updating the initial path according to the tangent group to generate a stretching path includes: Summarize the tangent group to generate a tangent set, and determine the outermost tangent in the tangent set as the candidate tangent; Update the first position according to the candidate tangent to obtain an initial updated position, and determine the initial updated position within the allowable delivery range of the target desktop as the allowable updated position; Obtain the update distance between the first position and the allowable updated position, and determine the allowable updated position with the smaller update distance as the selected position; Generate a stretching path according to the connection line between the selected position and the second position.

7. The electrical data processing method according to claim 6, characterized in that Determine the allowable delivery range of the target desktop through the following method, including: Collect the personnel positions on the target desktop, and perform elimination processing on the initial delivery range of the desktop according to the personnel positions; Determine the remaining initial delivery range as the allowable delivery range.

8. The electrical data processing method according to claim 1, characterized in that, Before controlling the dual-arm robot to place the delivery target, it also includes: Obtain the current target information of the target desktop and the personnel movement information in real time; When the personnel movement information is to touch any of the current target information, use the current target information as the judgment target; After determining that the judgment target leaves the target desktop, update the second position according to the position of the judgment target, and adjust the stretching path based on the updated second position.

9. The electrical data processing method according to claim 8, characterized in that, After determining that the judgment target leaves the target desktop, updating the second position according to the position of the judgment target includes: Compare the allocation ranges of the judgment target and the delivery target, and determine the judgment target whose allocation range is greater than or equal to the delivery target as the first real-time target; Obtain the first real-time target with the smallest allocation range as the second real-time target, and update the second position to the position of the second real-time target.

10. An electrical data processing system, characterized in that, Including: An allocation module for obtaining the allocation information of the target desktop; A path module for generating first-level delivery information according to the target desktop, determining a stretching path based on the current target information of the target desktop, and generating second-level delivery information according to the stretching path; An execution module for controlling the dual-arm robot to place the delivery target according to the first-level delivery information and the second-level delivery information.

Images