Cooperative control method and system of logistics robot, electronic equipment and product

Abstract

The invention discloses a cooperative control method and system of a logistics robot, electronic equipment and a product, the cooperative control method of the logistics robot provided by the invention controls the robot to walk through a designed blockage avoidance rule and a special area avoidance rule, so that when a plurality of robots are blocked, the robot can be controlled to walk, and the robot can be controlled to walk. The multiple robots are enabled to quickly recover passing; when a plurality of robots walk to special areas such as encountering traffic intersections and channels, barrier-free passing of the current robot can be realized, so that the problem that the robots cannot avoid obstacles when encountering the intersections and the channels in the prior art is solved; meanwhile, the intelligent AI container is adopted for automatic goods taking and placing, on the basis, goods taking and placing operation without manual intervention is achieved, manpower is liberated, and tasks can be executed continuously for 24 hours; therefore, the distribution efficiency and the distribution automation degree are improved, and the method is very suitable for large-scale application and popularization.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent logistics and distribution, and specifically relates to a collaborative control method, system, electronic equipment and product of a logistics robot. Background Art

[0002] With the rapid development of intelligent robots in various fields, intelligent delivery robots are increasingly attracting public attention due to their efficiency, accuracy, cost-effectiveness, safety and other characteristics. At present, the common operation process of intelligent delivery robots is as follows: the operator creates the delivery task through the App on the delivery robot, and then manually puts the items to be delivered into the robot. The intelligent delivery robot delivers the items to the destination along a specific route through special channels such as hotels with relatively small traffic, or restaurant kitchens, and then the robot calls the human to manually enter the password to take out the items, and returns to the original charging pile to wait after the human takes out the items.

[0003] In specific applications, existing intelligent delivery robots have the following deficiencies: (1) When multiple intelligent delivery robots encounter each other and cause a jam, the robots cannot flexibly avoid obstacles. At the same time, they cannot complete obstacle avoidance by themselves, such as avoiding walking in special areas such as intersections and narrow passages. This will reduce the delivery efficiency. (2) The degree of automation is low. The picking up and placing of goods by intelligent delivery robots during delivery are all completed by manual operation. They cannot independently complete the picking up and placing of goods operation process. Therefore, based on the above-mentioned deficiencies, how to provide a collaborative control method for logistics robots with a high degree of automation and strong obstacle avoidance ability has become a problem that needs to be solved urgently. Summary of the invention

[0004] The purpose of the present invention is to provide a collaborative control method, system, electronic equipment and product for a logistics robot, so as to solve the problems of poor obstacle avoidance effect and low degree of automation in the prior art.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] In a first aspect, a collaborative control method of a logistics robot is provided, which is applied to a smart logistics platform, a big data computing platform, an AI smart container, and several logistics robots, wherein the method comprises:

[0007] The big data computing platform receives the delivery tasks pushed by the smart logistics platform, and based on the delivery tasks, selects the optimal logistics robot from a number of logistics robots, and generates logistics task information, wherein the logistics task information includes the optimal delivery path of the optimal logistics robot;

[0008] The big data computing platform sends the logistics task information to the optimal logistics robot;

[0009] The optimal logistics robot receives the logistics task information, walks according to the optimal delivery path in the logistics task information, and uploads its own operation status information to the big data computing platform during the walking process;

[0010] The big data computing platform determines whether the optimal logistics robot is in a blocked state according to the operating state information;

[0011] If so, the big data computing platform determines a number of blocking robots, and controls the operation of each blocking robot according to the blocking avoidance rule, wherein the number of blocking robots includes the optimal logistics robot and the logistics robot that is blocked with the optimal logistics robot, and when any blocking robot is running, the remaining blocking robots among the number of blocking robots are located outside the walking path of any blocking robot and are in a paused state;

[0012] When the optimal logistics robot is unblocked, the big data computing platform determines whether the optimal logistics robot is in a special area based on the latest operating status information of the optimal logistics robot, wherein the special area is a crossroad or a passage area;

[0013] If so, the big data computing platform controls the optimal logistics robot to operate according to the special area avoidance rules, so that the optimal logistics robot can pass through the special area without obstacles;

[0014] When the optimal logistics robot walks to the delivery location according to the optimal delivery route, it pushes the logistics task information to the AI ​​smart container;

[0015] Based on the logistics task information, the AI ​​smart container controls the cargo picking device to place the cargo to the optimal logistics robot, or picks up the cargo from the optimal logistics robot, and after picking up or placing the cargo, feeds back the task execution information to the smart logistics platform, so that the smart logistics platform continues to control the operation of the optimal logistics robot based on the task execution information and the big data computing platform, and in accordance with the blocking avoidance rules and special area avoidance rules until the delivery task is completed.

[0016] Based on the above disclosed content, after obtaining the delivery task, the present invention will select the optimal logistics robot for this delivery from several logistics robots and generate its corresponding optimal delivery path; then, the aforementioned information will be sent to the optimal logistics robot so that the optimal logistics robot can walk along the optimal delivery path; at the same time, during the walking process, the optimal logistics robot will send its own operating status information to the big data computing platform in real time, and the big data computing platform can determine whether the optimal logistics robot is in a blocked state based on the operating status information; if it is in a blocked state, several blocking robots will be determined, and the operation of each blocking robot will be controlled according to the blocking avoidance rules, wherein, when any blocking robot is running, the remaining blocking robots are in their corresponding walking state. outside the path, in this way, any blocking robot can be avoided; based on this, through the aforementioned blocking avoidance rules, the robot can quickly resume passage after being blocked; and after completing the avoidance passage of the blocked robot, the big data computing platform determines whether it is in a special area such as a passage or an intersection based on the latest operating status information of the optimal logistics robot; if so, the big data computing platform controls the operation of the optimal logistics robot according to the special area avoidance rules to enable it to pass through the special area without obstacles; finally, when the optimal logistics robot walks to the delivery location, it can use the cargo picking device on the AI ​​smart container to automatically pick up or put down the goods, and after completing the picking up or putting down the goods, continue to deliver the goods in the aforementioned manner until the delivery task is completed.

[0017] Through the above design, the collaborative control method of the logistics robot provided by the present invention controls the walking of the robot through the designed blocking avoidance rules and special area avoidance rules, so that when multiple robots are blocked, multiple robots can quickly resume passage; and when multiple robots walk to special areas such as traffic intersections and passages where they meet, the current robots can pass through without obstacles, thereby solving the problem in traditional technology that robots cannot avoid obstacles when they meet at intersections and passages; at the same time, the present invention adopts an intelligent AI container to automatically pick up and release goods, based on which, picking up and releasing goods operations without human intervention are realized, manpower is liberated, and tasks can be performed uninterruptedly 24 hours a day; therefore, the present invention improves the distribution efficiency and the degree of automation of distribution, and is therefore very suitable for large-scale application and promotion.

[0018] In a possible design, the big data computing platform controls the operation of each blocking robot according to the blocking avoidance rules, including:

[0019] The big data computing platform obtains the delivery priority of each blocked robot, and sorts each blocked robot in descending order of delivery priority to obtain a sorting sequence;

[0020] For the i-th blocked robot in the sorting sequence, the big data computing platform controls the target robot to walk to the temporary storage area and enter a pause state, wherein the target robot is all blocked robots in the sorting sequence except the i-th blocked robot, and the initial value of i is 1;

[0021] The big data computing platform controls the operation of the i-th blocking robot to release the blocking state, and after the i-th blocking robot leaves the blocking area, the big data computing platform controls the operation of i+1 blocking machines until all blocking robots in the temporary storage area leave the blocking area, wherein the blocking area is the area surrounded by all blocking robots.

[0022] In a possible design, the operation status information includes the location of the optimal logistics robot and the duration of suspended operation, wherein the big data computing platform determines a number of blocked robots, including:

[0023] The big data computing platform determines, based on the position of the optimal logistics robot, a logistics robot from among the plurality of logistics robots that is separated from the optimal logistics robot by a preset distance and has a suspended operation time greater than or equal to a preset time, so as to form a plurality of blocking robots using the optimal logistics robot and the determined logistics robots;

[0024] Accordingly, before controlling each blocking robot to run according to the blocking avoidance rule, the method further includes:

[0025] The big data computing platform determines the individual areas of each blocking robot, wherein the individual area of ​​any blocking robot is a circular area with the blocking robot as the center and a radius of a preset value;

[0026] The big data computing platform labels each individual area to obtain a number of labeled areas, and performs region recognition on each labeled area to obtain the region type corresponding to each labeled area, wherein the region type includes intersections and channel areas;

[0027] The big data computing platform determines the special area according to the area type corresponding to each marked area, so as to control the operation of each blocking robot according to the blocking avoidance rule after determining the special area.

[0028] In a possible design, the big data computing platform controls the operation of the optimal logistics robot according to special area avoidance rules, including:

[0029] The big data computing platform determines whether there is a collision robot in the special area, wherein the collision robot is a logistics robot among the plurality of logistics robots except the optimal logistics robot;

[0030] If so, the big data computing platform determines whether the walking direction of the collision robot is the same as the walking direction of the optimal logistics robot;

[0031] If not, the big data computing platform controls the optimal logistics robot to leave the special area to avoid the collision robot;

[0032] After the collision robot passes through the special area, the big data computing platform controls the optimal logistics robot to operate so as to pass through the special area.

[0033] In a possible design, the cargo picking device includes a primary robotic arm and a secondary robotic arm, wherein the primary robotic arm is provided with a code scanning device, and the logistics task information also includes cargo to be picked up;

[0034] The AI ​​smart container controls the cargo picking device to place the cargo to the optimal logistics robot based on the logistics task information, including:

[0035] The AI ​​smart container determines the cargo location of the to-be-collected goods on the shelf based on the logistics task information, wherein each cargo location on the shelf is provided with a cargo QR code;

[0036] The AI ​​smart container controls the first-level robot arm to extend to the cargo position corresponding to the cargo to be picked up according to the cargo position of the cargo to be picked up on the shelf, and controls the code scanning device to scan the cargo QR code at the cargo position corresponding to the cargo to be picked up to obtain the scanning result;

[0037] The AI ​​smart container determines whether the goods in the target cargo position are the goods to be picked up based on the code scanning result, wherein the target cargo position is the cargo position on the shelf where the goods to be picked up are located;

[0038] If so, the AI ​​smart container controls the secondary robotic arm to take the goods in the target cargo location and put the goods in the target cargo location into the AI ​​smart container.

[0039] In a possible design, any logistics robot is further provided with an obstacle avoidance sensor, wherein the obstacle avoidance sensor includes a laser radar, an ultrasonic radar, and a visual camera, and the method further includes:

[0040] When the optimal logistics robot is in an area outside the special area, the optimal logistics robot obtains the detection data transmitted by the laser radar, the ultrasonic radar and the visual camera, and based on the detection data, performs obstacle avoidance walking on the optimal delivery path.

[0041] In a possible design, before the big data computing platform receives the delivery task pushed by the smart logistics platform, the method further includes:

[0042] The smart logistics platform receives the logistics distribution demand information, and parses and processes the logistics distribution demand information to generate an initial logistics task based on the parsing result;

[0043] The smart logistics platform determines the task execution time based on the initial logistics task;

[0044] The smart logistics platform determines whether the initial logistics task is executed according to the task execution time;

[0045] If so, the smart logistics platform generates the delivery task based on the initial logistics task and pushes the delivery task to the big data computing platform.

[0046] Secondly, a collaborative control system for logistics robots is provided, including: a smart logistics platform, a big data computing platform, an AI smart container, and several logistics robots:

[0047] A big data computing platform, used to receive the delivery tasks pushed by the smart logistics platform, and based on the delivery tasks, select the optimal logistics robot from a number of logistics robots, and generate logistics task information, wherein the logistics task information includes the optimal delivery path of the optimal logistics robot;

[0048] A big data computing platform, used for sending the logistics task information to the optimal logistics robot;

[0049] The optimal logistics robot is used to receive the logistics task information, walk according to the optimal delivery path in the logistics task information, and upload its own operation status information to the big data computing platform during the walking process;

[0050] A big data computing platform, used to determine whether the optimal logistics robot is in a blocked state according to the operating state information;

[0051] If so, the big data computing platform is used to determine a number of blocking robots, and control the operation of each blocking robot according to the blocking avoidance rule, wherein the number of blocking robots includes the optimal logistics robot and the logistics robot that is blocked with the optimal logistics robot, and when any blocking robot is running, the remaining blocking robots among the number of blocking robots are located outside the walking path of any blocking robot and are in a paused state;

[0052] When the optimal logistics robot is unblocked, the big data computing platform is used to determine whether the optimal logistics robot is in a special area based on the latest operating status information of the optimal logistics robot, where the special area is an intersection or a passage area;

[0053] If yes, the big data computing platform is used to control the operation of the optimal logistics robot according to the special area avoidance rules, so that the optimal logistics robot can pass through the special area without obstacles;

[0054] When the optimal logistics robot walks to the delivery location according to the optimal delivery path, it is used to push logistics task information to the AI ​​smart container;

[0055] The AI ​​smart container is used to control the cargo picking equipment to place the cargo to the optimal logistics robot, or to pick up the cargo from the optimal logistics robot based on the logistics task information, and after picking up or placing the cargo, to feedback the task execution information to the smart logistics platform, so that the smart logistics platform can continue to control the operation of the optimal logistics robot based on the task execution information and the big data computing platform, and in accordance with the blocking avoidance rules and special area avoidance rules until the delivery task is completed.

[0056] In the third aspect, a collaborative control device for a logistics robot is provided. Taking the device as an electronic device as an example, the device includes a memory, a processor and a transceiver which are communicatively connected in sequence, wherein the memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the collaborative control method of the logistics robot as in the first aspect or any possible design of the first aspect.

[0057] In a fourth aspect, a storage medium is provided, on which instructions are stored. When the instructions are run on a computer, a collaborative control method of the logistics robot as in the first aspect or any possible design of the first aspect is executed.

[0058] In a fifth aspect, a computer program product comprising instructions is provided, which, when executed on a computer, enables the computer to execute a collaborative control method for a logistics robot as in the first aspect or any possible design of the first aspect.

[0059] Beneficial effects:

[0060] (1) The collaborative control method of the logistics robot provided by the present invention controls the movement of the robots through the designed blocking avoidance rules and special area avoidance rules. In this way, when multiple robots are blocked, the multiple robots can quickly resume passage; and when multiple robots walk to special areas such as traffic intersections and passages where they meet, the current robots can pass through without obstacles, thereby solving the problem of robots in traditional technologies being unable to avoid obstacles when they meet at intersections and passages; at the same time, the present invention adopts intelligent AI containers to automatically pick up and put away goods, based on which, picking up and putting away goods without human intervention is realized, manpower is liberated, and tasks can be performed uninterruptedly 24 hours a day; therefore, the present invention improves the distribution efficiency and the degree of automation of distribution, and is therefore very suitable for large-scale application and promotion.

[0061] (2) The present invention adds a big data algorithm cloud platform, which can reasonably select the optimal robot to perform the task based on the received robot status, equipment and other information and the big data scheduling algorithm model; in this way, transportation traffic conflicts and low efficiency problems can be avoided.

[0062] (3) When multiple robots are blocked, the robots are dispatched according to the delivery priority, that is, the robots except the robot with the highest priority are controlled to walk to the temporary storage area to make way for the passage, and then the robots with the highest priority are controlled to continue to perform the task; then, the robots with the next priority are dispatched, that is, the robots with the next priority are controlled to leave the temporary storage area and walk according to their walking path. In this way, according to the above principle, the robots in the temporary storage area are awakened to perform tasks in an orderly manner until all the robots in the temporary storage area leave the blocked area, so that multiple blocked robots can pass quickly.

[0063] (4) In special areas such as narrow passages and intersections, when the present invention detects that other robots are passing through the special area and their passing direction is opposite to that of the local robot, the local robot will be controlled to wait outside the special area until the other robots have passed and then enter the special area; in this way, the problem of encountering and avoiding obstacles in special areas such as narrow passages and intersections can be solved, thereby improving delivery efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A schematic flow chart of the steps of the collaborative control method of the logistics robot provided by an embodiment of the present invention;

[0065] Figure 2 A schematic diagram of the structure of a collaborative control system for a logistics robot provided by an embodiment of the present invention;

[0066] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0067] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structure of the drawings is only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0068] It should be understood that although the terms first, second, etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another unit. For example, a first unit can be referred to as a second unit, and similarly, a second unit can be referred to as a first unit without departing from the scope of the exemplary embodiments of the present invention.

[0069] It should be understood that the term "and / or" that may appear in this article is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B can represent three situations: A exists alone, B exists alone, and A and B exist at the same time. The term " / and" that may appear in this article describes another type of association object relationship, indicating that two relationships may exist. For example, A / and B can represent two situations: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this article generally indicates that the previous and next associated objects are in an "or" relationship.

[0070] Example:

[0071] See also Figure 2 As shown, a system architecture is provided for the method disclosed in the embodiment of the present application, wherein the system may include but is not limited to: a smart logistics platform, a big data computing platform, an AI smart container and a number of logistics robots (such as setting n); in specific applications, each logistics robot is provided with an AI smart container, and the AI ​​smart container is configured with a cargo picking device; in this way, automatic picking and placing of cargo can be achieved through the aforementioned AI smart container and cargo picking device.

[0072] In this embodiment, the smart logistics management platform is mainly responsible for receiving task data (i.e., the user's logistics distribution demand information), processing and persisting the task data to generate distribution tasks and send them to the big data computing platform; at the same time, it also has the functions of assigning designated robot tasks and monitoring task execution.

[0073] The big data computing platform is mainly used to receive delivery tasks pushed by the smart logistics management platform, and select the best logistics robot and generate the best delivery path to perform the task based on the number, location, status, traffic information and other data of the logistics robots in the delivery area; at the same time, it can also control each logistics robot to operate according to the blockage avoidance rules and special area avoidance rules when the logistics robot cannot rely on itself for avoidance walking (that is, when a blockage occurs or enters a special area (such as a narrow passage or an intersection)), thereby realizing the rapid avoidance passage of the logistics robot to avoid traffic jams.

[0074] At the same time, the logistics robot communicates with the smart logistics management platform and the big data computing platform (such as using a 5G network connection) to receive task data sent by the smart logistics management platform and logistics task information sent by the big data computing platform, and decomposes the task into chassis control data and container control data, and controls the chassis and container to perform corresponding tasks respectively; among them, the robot chassis receives the task data, and under the control of the chassis motion module, it performs the delivery task according to its own avoidance algorithm and along the established route; and the smart AI container, under the control of the container control module, combines the cargo picking equipment to automatically pick up and release goods, thereby achieving a high degree of automation.

[0075] Therefore, through the aforementioned collaborative control system, this embodiment can quickly restore traffic when the robot is blocked, and solve the problem in traditional technology that robots cannot avoid obstacles when meeting at intersections and passages; at the same time, it also realizes the picking and releasing operations without human intervention, freeing up manpower and performing tasks 24 hours a day; thus, the system can improve the distribution efficiency and the degree of automation of distribution, and is very suitable for large-scale application and promotion.

[0076] See also Figure 1 As shown, the collaborative control method of the logistics robot provided in this embodiment can be but is not limited to being run on a smart logistics platform, a big data computing platform, an AI smart container and several logistics robots. It can be understood that the aforementioned execution entity does not constitute a limitation on the embodiments of the present application. Accordingly, the operation steps of this method can be but are not limited to being shown in the following steps S1 to S9.

[0077] S1. The big data computing platform receives the delivery tasks pushed by the smart logistics platform, and based on the delivery tasks, selects the best logistics robot from a number of logistics robots, and generates logistics task information, wherein the logistics task information includes the best delivery path of the best logistics robot; in specific applications, a third-party user sends its logistics delivery demand information (such as goods need to be delivered from place A to place B at xx time) to the smart logistics platform; and after receiving the logistics delivery demand information, the smart logistics platform parses and processes the logistics delivery demand information to generate an initial logistics task (i.e., parse and generate the task) based on the parsing result. Then, the smart logistics platform determines the task execution time based on the initial logistics task; then, according to the task execution time, it determines whether the initial logistics task is executed (that is, whether it needs to be executed immediately, that is, whether the task execution time is the earliest among the current execution tasks); if so, the smart logistics platform generates the distribution task based on the initial logistics task, and pushes the distribution task to the big data computing platform; optionally, the distribution task may include but is not limited to data such as the distribution starting point, distribution end point, distribution goods information (such as goods identification code, type, shelf location number, etc.).

[0078] In this way, after receiving the delivery task, the big data computing platform can determine the optimal logistics robot for this delivery and the optimal delivery path based on this; among which, for example, it can be but not limited to first obtaining the initial operating status information of each logistics robot (for example, the initial operating status information of any logistics robot includes location information and execution task information); then, based on the initial operating status information, the delivery starting point and the delivery end point, the optimal logistics robot is selected from a number of logistics robots and the optimal delivery path is generated; finally, based on the optimal delivery path and the delivery task, the logistics task information is generated; of course, the aforementioned selection of the optimal logistics robot and the optimal delivery path can be implemented using a commonly used scheduling algorithm, which is not specifically limited here.

[0079] After generating the logistics task information, the big data computing platform can push the task, that is, push it to the determined optimal logistics robot so that the optimal logistics robot can perform cargo delivery based on the pushed task; wherein, the task pushing process can be but is not limited to as shown in the following step S2.

[0080] S2. The big data computing platform sends the logistics task information to the optimal logistics robot; in this embodiment, after receiving the logistics task information, the optimal logistics robot can walk according to the optimal delivery path in the logistics task information, and its walking process can be but is not limited to as shown in the following step S3.

[0081] S3. The optimal logistics robot receives the logistics task information to walk according to the optimal delivery path in the logistics task information, and uploads its own operating status information to the big data computing platform during the walking process; in the specific implementation, the operating status information may include but is not limited to the location, power, execution task information and suspension time of the optimal logistics robot; wherein, the suspension time refers to the length of time the optimal logistics robot stays at the same location, which is used to determine whether the optimal logistics robot is in a blocked state; in this way, when the big data computing platform receives the operating status information of the optimal logistics robot, it can determine the operating status and area of ​​the optimal logistics robot based on this, so as to adopt different avoidance methods to walk according to different operating states and different areas; optionally, the control process of the big data computing platform may be but is not limited to the following steps S4 to S7.

[0082] S4. The big data computing platform determines whether the optimal logistics robot is in a blocked state based on the operating status information; in this embodiment, when the suspended operation time in the operating status information is greater than or equal to the stay time threshold, the optimal logistics robot is determined to be in a blocked state; at this time, the walking of the optimal logistics robot and the remaining blocked robots can be controlled according to the blocking avoidance rules to quickly restore the passage of the blocked robots; wherein, the blocking avoidance walking process can be but is not limited to as shown in the following step S5.

[0083] S5. If yes, the big data computing platform is used to determine a number of blocking robots, and control the operation of each blocking robot according to the blocking avoidance rule, wherein the number of blocking robots includes the optimal logistics robot and the logistics robot that is blocked with the optimal logistics robot, and when any blocking robot is running, the remaining blocking robots among the number of blocking robots are located outside the walking path of any blocking robot and are in a paused state; in specific applications, the big data computing platform first determines, based on the position of the optimal logistics robot, a logistics robot that is separated from the optimal logistics robot by a preset distance and has a paused operation time greater than or equal to the preset time from the number of logistics robots, so as to use the optimal logistics robot and the determined logistics robots to form a number of blocking robots; optionally, for example, the preset distance is 0-5m, and the preset time is 5 minutes, so that when the optimal logistics robot stays at the same position for more than the stay time threshold (that is, it is in a blocked state), the logistics robot that is separated from it by less than or equal to 5m and has a paused operation time greater than or equal to 5 minutes can be used as a blocking robot; based on this, area marking can be performed according to the optimal logistics robot and the determined blocking robot, so that after the area marking is completed, the operation of each blocking robot can be controlled according to the blocking avoidance rule.

[0084] The region marking process may be, but is not limited to, steps S51 to S53 as shown below.

[0085] S51. The big data computing platform determines the individual areas of each blocking robot, wherein the individual area of ​​any blocking robot is a circular area with the any blocking robot as the center and a radius of a preset value; in this embodiment, the circular area with the any blocking robot as the center and a radius of 5m can be taken as its corresponding individual area for example but is not limited to; of course, the aforementioned individual area is not limited to a circular area, and the specific area shape can be determined according to actual use, and is not limited to this herein.

[0086] In this way, after determining the individual areas of each blocking robot, the area marking and identification can be performed, and the process can be but not limited to the following step S52.

[0087] S52. The big data computing platform performs labeling processing on each individual area to obtain a number of labeled areas, and performs area identification on each labeled area to obtain the area type corresponding to each labeled area, wherein the area type includes an intersection and a channel area. In this embodiment, the area type to which the labeled area belongs in the distribution area can be determined based on the location of the labeled area, that is, the big data computing platform stores a map of the distribution area, and based on the location of each labeled area, the corresponding area type can be determined in the map, that is, whether it belongs to a channel area or an intersection area. In this way, after the area type of each labeled area is obtained, the special area in the distribution area can be determined, and the process can be but not limited to the following step S53.

[0088] S53. The big data computing platform determines the special area according to the area type corresponding to each marked area, so as to control the operation of each blocking robot according to the blocking avoidance rule after determining the special area.

[0089] Therefore, through the aforementioned steps S51 to S53, the marking of the individual areas corresponding to each blocking robot can be completed. After the marking is completed, the operation of each blocking robot can be controlled according to the blocking avoidance rules. The control process can be but is not limited to the following steps S54 to S56.

[0090] S54. The big data computing platform obtains the delivery priority of each blocked robot, and sorts each blocked robot in order of delivery priority from high to low to obtain a sorting sequence; in this embodiment, the delivery priority of any blocked robot can be obtained by weighted calculation according to the delivery time, the type of delivered goods, and the urgency of the task. Of course, the priorities of different robots can also be set in advance, which is not limited to the above examples; in this way, after obtaining the delivery priority of each blocked robot, each blocked robot can be sorted in order of priority, so that the delivery task can be performed subsequently according to the sorting order; wherein, the execution control process can be but is not limited to the following steps S55 and S56 as shown.

[0091] S55. For the i-th blocking robot in the sorting sequence, the big data computing platform controls the target robot to walk to the temporary storage area and enter a pause state, wherein the target robots are all the blocking robots in the sorting sequence except the i-th blocking robot, and the initial value of i is 1; in this embodiment, it is equivalent to giving priority to the execution of the optimal task, that is, all logistics robots except the robot with the highest priority (i.e., the aforementioned target robot) are uniformly deployed to the temporary storage area in the distribution area to make way for the robot with the highest priority; optionally, multiple temporary storage areas can be set in the distribution area, so that each of the aforementioned target robots can be deployed to the temporary storage area closest to it; of course, the temporary storage areas are all outside the walking path and do not affect the normal passage of the robot.

[0092] In this way, after all logistics robots except the robot with the highest priority are deployed to the temporary storage area, the logistics robot with the highest priority can be controlled to operate, and the process is shown in the following step S56.

[0093] S56. The big data computing platform controls the operation of the i-th blocking robot to release the blocking state, and after the i-th blocking robot leaves the blocking area, the big data computing platform controls the operation of i+1 blocking machines until all the blocking robots in the temporary storage area leave the blocking area, wherein the blocking area is the area surrounded by all the blocking robots; in specific applications, the logistics robot with the highest priority (i.e., the i-th blocking robot) is controlled to move along its corresponding delivery path until it leaves the blocking area formed by all the blocking robots (if there are three blocking robots, then the area surrounded by the three blocking robots is used as the blocking area), at which time, the logistics robot with the next priority can be controlled, that is, the second blocking machine in the sorting sequence is controlled to leave the temporary storage area, and then move along its corresponding delivery path; based on this, according to this principle, the operation of the blocking robots in the temporary storage area is controlled according to priority until all the blocking machines leave the blocking area, and then the avoidance control of each blocking area can be completed.

[0094] In this way, through the aforementioned steps S54 to S56, the robots can be scheduled according to the delivery priority, that is, the robots will execute according to the optimal task first, and then the big data platform will uniformly deploy other robots to nearby reasonable pause areas; then, the big data platform will release them one by one from the temporary storage area according to the execution order (that is, the priority order) until all blocked robots are released; based on this, this embodiment can enable multiple robots to quickly resume passage when multiple robots are blocked, thereby improving delivery efficiency.

[0095] After completing the blocking avoidance of the optimal logistics robot based on the aforementioned step S5 and its sub-steps, monitoring can continue. That is, as mentioned above, the optimal logistics robot will upload its corresponding operating status information in real time; therefore, the big data computing platform can determine the walking area of ​​the optimal logistics robot based on the latest operating status information; in this way, when it enters special areas such as narrow passages and intersections, special area avoidance rules can be used to control the walking of the optimal logistics robot; wherein, the control process of the robot in the special area can be but is not limited to as shown in the following steps S6 and S7.

[0096] S6. When the optimal logistics robot is unblocked, the big data computing platform determines whether the optimal logistics robot is in a special area based on the latest operating status information of the optimal logistics robot, wherein the special area is an intersection or a channel area; in this embodiment, the special areas in the distribution area have been marked as mentioned above, so it can be determined whether the optimal logistics robot is in a special area based on the position in the latest operating status information; wherein, the aforementioned channel area is a narrow channel area for example, and the narrow channel area is a channel that can only accommodate one logistics robot.

[0097] In the specific implementation, if the optimal logistics robot is in the aforementioned special area, it is necessary to control the optimal logistics robot to walk according to the special area avoidance rules, that is, to execute the following step S7.

[0098] S7. If so, the big data computing platform controls the operation of the optimal logistics robot according to the special area avoidance rules, so that the optimal logistics robot can pass through the special area without obstacles; in the specific implementation, the big data computing platform first determines whether there is a collision robot in the special area, wherein the collision robot is a logistics robot other than the optimal logistics robot among the several logistics robots; in this way, it is equivalent to determining whether there are logistics robots other than the optimal logistics robot in the special area; if so, it is necessary to determine whether the walking direction of the collision robot is the same as that of the optimal logistics robot; in this embodiment, if they are different, it means that the two are moving in opposite directions and there is a risk of collision; at this time, the big data computing platform controls the optimal logistics robot to leave the special area to avoid the collision robot; then, after the collision robot passes through the special area, the big data computing platform controls the operation of the optimal logistics robot to pass through the special area.

[0099] Furthermore, when the special area is an intersection, since the intersection is wide, the optimal logistics robot can also be controlled to walk to the boundary of the intersection, so as to achieve the purpose of avoiding collision with the robot.

[0100] At the same time, when the optimal logistics robot is not in a special area or in a blocked state, it can walk autonomously based on the logistics robot's own sensors and in combination with an obstacle avoidance algorithm, that is, in this embodiment, any logistics robot is also provided with an obstacle avoidance sensor (for example, the obstacle avoidance sensor includes a laser radar, an ultrasonic radar, and a visual camera); in this way, when the optimal logistics robot is in an area outside the special area, the optimal logistics robot obtains the detection data transmitted by the laser radar, the ultrasonic radar, and the visual camera, and based on the detection data, performs obstacle avoidance walking on the optimal delivery path; based on this, it is equivalent to autonomously performing obstacle avoidance walking based on the fusion perception of multiple sensors; and when it is in a blocked state or a special area, the obstacle avoidance method disclosed in the aforementioned steps S5 and S7 is used to perform obstacle avoidance walking.

[0101] In addition, the big data computing platform can also provide real-time path adjustments for robots running on site to avoid traffic jams to the greatest extent possible.

[0102] In this way, through the aforementioned steps S4 to S7, the robot can achieve intelligent obstacle avoidance and circumvention in blocked states and special areas, thereby minimizing the blocking time and the encounter problems in narrow passages and intersections; based on this, the delivery efficiency can be greatly improved.

[0103] When the optimal logistics robot is controlled to move according to the above method and when it reaches the delivery location, the AI ​​smart container on the optimal logistics robot can be used to realize automatic picking and placing of goods; wherein, the process of automatic picking and placing of goods can be but is not limited to as shown in the following steps S8 and S9.

[0104] S8. When the optimal logistics robot walks to the delivery location according to the optimal delivery path, it pushes the logistics task information to the AI ​​smart container; in this embodiment, the delivery location usually refers to the delivery starting point, of course, it can also be the delivery end point; among them, when the optimal logistics robot reaches the delivery location, it can automatically pick up or put away the goods, and the process is shown in the following step S9.

[0105] S9. Based on the logistics task information, the AI ​​smart container controls the cargo picking device to place the cargo to the optimal logistics robot, or picks up the cargo from the optimal logistics robot, and after picking up or placing the cargo, feeds back the task execution information to the smart logistics platform, so that the smart logistics platform continues to control the operation of the optimal logistics robot based on the task execution information and the big data computing platform, and in accordance with the blocking avoidance rules and special area avoidance rules until the delivery task is completed.

[0106] In this embodiment, the cargo picking device may include, but is not limited to, a primary robotic arm and a secondary robotic arm, wherein the primary robotic arm is provided with a code scanning device. Therefore, the following steps S91 to S94 may be used to complete the cargo picking process.

[0107] S91. The AI ​​smart container determines the cargo location of the to-be-picked goods on the shelf based on the logistics task information, wherein each cargo location on the shelf is provided with a cargo QR code; in the present embodiment, it has been explained above that the delivery task contains the delivery cargo information (i.e., type, cargo location number, etc.), therefore, the cargo location of the to-be-picked goods can be determined based on the logistics task information, and then, the door of the AI ​​smart container can be controlled to open, and the first-level robotic arm can be extended to the cargo location to perform pickup verification, and the process can be but not limited to as shown in the following steps S92 and S93.

[0108] S92. The AI ​​smart container controls the first-level robotic arm to extend to the storage location corresponding to the goods to be picked up according to the storage location of the goods to be picked up on the shelf, and controls the code scanning device to scan the goods QR code at the storage location corresponding to the goods to be picked up to obtain the code scanning result; in this embodiment, the code scanning device can be, but is not limited to, a camera; in this way, when the first-level robotic arm is extended to the storage location corresponding to the goods to be picked up (that is, the same height as the shelf storage location, and aligned with the goods QR code of the storage location), the camera can be used to perform code scanning processing to obtain the code scanning result; then, based on the code scanning result, it can be determined whether the goods in the storage location are the aforementioned goods to be picked up; wherein, the judgment process can be, but is not limited to, as shown in the following step S93.

[0109] S93. The AI ​​smart container determines whether the goods in the target cargo location are the goods to be picked up based on the scanning result, wherein the target cargo location is the cargo location on the shelf of the goods to be picked up; in this embodiment, the scanning result may include but is not limited to the identification code of the goods, therefore, when the identified identification code is the same as the identification code in the logistics task information, it is determined that the goods in the target cargo location are the goods to be picked up; at this time, the secondary robotic arm can be controlled to grab the goods, and the process is shown in the following step S94.

[0110] S94. If yes, the AI ​​smart container controls the secondary robot arm to take the goods in the target cargo location and put the goods in the target cargo location into the AI ​​smart container.

[0111] In this way, through the aforementioned steps S91 to S94, the automatic picking of goods can be completed; then, after the goods are released, the two robotic arms are retracted, the cabinet door is closed, and the smart logistics platform is notified of the execution of the task at that point. After receiving the task execution reply, the smart logistics platform continues to push the subsequent point B delivery task to the optimal logistics robot to repeat the aforementioned delivery process; of course, the principles of the picking process and the releasing process are the same, and both are completed using robotic arms, so they will not be repeated here.

[0112] In summary, the main working process of the collaborative control method of the logistics robot provided by the present invention is:

[0113] The user uploads the task to the smart logistics management platform, and the general commander smart logistics platform passes the distribution task to the big data computing platform. The big data computing platform selects the best logistics robot to perform the task according to the preset model based on the number, location, status, traffic and other information of the logistics robots in the distribution area; at the same time, after the logistics robot receives the data through the 5G network, it performs the task according to the operation process of the task; in the transportation process, if multiple robots encounter blockages, intersections or special channels, and cannot solve the traffic walking problem according to their own autonomous algorithms, at this time, the operation status data can be reported to the big data computing platform, so that the big data platform can uniformly dispatch multiple robots to perform reasonable traffic control, so that each robot can perform tasks in an orderly manner and avoid traffic jams; then, after the logistics robot arrives at the destination, the AI ​​container on it will perform the corresponding fully automatic pick-up and delivery according to the obtained data. After completion, the data is transmitted back to the smart logistics management platform. After receiving the data feedback from the robot, the platform decides whether the robot will perform subsequent tasks based on the execution of the task.

[0114] Therefore, through the collaborative control method of the logistics robot described in detail in the aforementioned steps S1 to S9, the present invention can quickly restore passage when the robot is blocked, and solve the problem in traditional technology that the robot cannot avoid obstacles when meeting at intersections and passages; at the same time, it also realizes the picking and releasing operations without human intervention, freeing up manpower and performing tasks 24 hours a day; therefore, the system can improve the distribution efficiency and the degree of automation of distribution, and is very suitable for large-scale application and promotion.

[0115] like Figure 2 As shown, the second aspect of this embodiment provides a hardware system for implementing the collaborative control method of the logistics robot described in the first aspect of the embodiment, including: a smart logistics platform, a big data computing platform, an AI smart container, and a plurality of logistics robots;

[0116] The big data computing platform is used to receive the delivery tasks pushed by the smart logistics platform, and based on the delivery tasks, select the optimal logistics robot from a number of logistics robots, and generate logistics task information, wherein the logistics task information includes the optimal delivery path of the optimal logistics robot.

[0117] A big data computing platform is used to send the logistics task information to the optimal logistics robot.

[0118] The optimal logistics robot is used to receive the logistics task information, walk according to the optimal delivery path in the logistics task information, and upload its own operation status information to the big data computing platform during the walking process.

[0119] The big data computing platform is used to determine whether the optimal logistics robot is in a blocked state based on the operating status information.

[0120] If so, the big data computing platform is used to determine several blocking robots and control the operation of each blocking robot according to the blocking avoidance rules, wherein the several blocking robots include the optimal logistics robot and the logistics robot that is blocked with the optimal logistics robot, and when any blocking robot is running, the remaining blocking robots among the several blocking robots are in a paused state.

[0121] When the optimal logistics robot is unblocked, the big data computing platform is used to determine whether the optimal logistics robot is in a special area based on the latest operating status information of the optimal logistics robot, where the special area is an intersection or a passage area.

[0122] If so, the big data computing platform is used to control the operation of the optimal logistics robot according to the special area avoidance rules, so that the optimal logistics robot can pass through the special area without obstacles.

[0123] When the optimal logistics robot walks to the delivery location according to the optimal delivery route, it is used to push logistics task information to the AI ​​smart container.

[0124] The AI ​​smart container is used to control the cargo picking equipment to place the cargo to the optimal logistics robot, or to pick up the cargo from the optimal logistics robot based on the logistics task information, and after picking up or placing the cargo, to feedback the task execution information to the smart logistics platform, so that the smart logistics platform can continue to control the operation of the optimal logistics robot based on the task execution information and the big data computing platform, and in accordance with the blocking avoidance rules and special area avoidance rules until the delivery task is completed.

[0125] The working process, working details and technical effects of the system provided in this embodiment can be found in the first aspect of the embodiment and will not be described in detail here.

[0126] like Figure 3 As shown, the third aspect of this embodiment provides a collaborative control device for a logistics robot. Taking the device as an electronic device as an example, it includes: a memory, a processor and a transceiver that are communicatively connected in sequence, wherein the memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the collaborative control method for the logistics robot as described in the first aspect of the embodiment.

[0127] For example, the memory may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out memory (FIFO) and / or first-in-last-out memory (FILO), etc. Specifically, the processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). At the same time, the processor may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state.

[0128] In some embodiments, the processor may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. For example, the processor may not be limited to a microprocessor of the STM32F105 series, a reduced instruction set computer (RISC) microprocessor, an X86 or other architecture processor, or a processor with an integrated embedded neural network processor (NPU); the transceiver may be, but is not limited to, a wireless fidelity (WIFI) wireless transceiver, a Bluetooth wireless transceiver, a general packet radio service technology (Genera l Packet Rad ioService, GPRS) wireless transceiver, a ZigBee protocol (a low-power LAN protocol based on the IEEE 802.15.4 standard, ZigBee) wireless transceiver, a 3G transceiver, a 4G transceiver and / or a 5G transceiver, etc. In addition, the device may also include, but is not limited to, a power module, a display screen and other necessary components.

[0129] The working process, working details and technical effects of the electronic device provided in this embodiment can be found in the first aspect of the embodiment and will not be described in detail here.

[0130] The fourth aspect of this embodiment provides a storage medium that stores instructions for the collaborative control method of the logistics robot described in the first aspect of the embodiment, that is, the storage medium stores instructions, and when the instructions are run on a computer, the collaborative control method of the logistics robot described in the first aspect of the embodiment is executed.

[0131] The storage medium refers to a carrier for storing data, which may include but is not limited to a floppy disk, a CD, a hard disk, a flash memory, a USB flash drive and / or a memory stick, etc. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0132] The working process, working details and technical effects of the storage medium provided in this embodiment can be found in the first aspect of the embodiment and will not be described in detail here.

[0133] The fifth aspect of this embodiment provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the collaborative control method for the logistics robot as described in the first aspect of the embodiment, wherein the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0134] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A collaborative control method for a logistics robot, characterized in that: Applied to smart logistics platforms, big data computing platforms, AI smart containers and several logistics robots, wherein the method includes: The big data computing platform receives the delivery tasks pushed by the smart logistics platform, and based on the delivery tasks, selects the optimal logistics robot from a number of logistics robots, and generates logistics task information, wherein the logistics task information includes the optimal delivery path of the optimal logistics robot; The big data computing platform sends the logistics task information to the optimal logistics robot; The optimal logistics robot receives the logistics task information, walks according to the optimal delivery path in the logistics task information, and uploads its own operation status information to the big data computing platform during the walking process; The big data computing platform determines whether the optimal logistics robot is in a blocked state according to the operating state information; If so, the big data computing platform determines a number of blocking robots, and controls the operation of each blocking robot according to the blocking avoidance rule, wherein the number of blocking robots includes the optimal logistics robot and the logistics robot that is blocked with the optimal logistics robot, and when any blocking robot is running, the remaining blocking robots among the number of blocking robots are located outside the walking path of any blocking robot and are in a paused state; When the optimal logistics robot is unblocked, the big data computing platform determines whether the optimal logistics robot is in a special area based on the latest operating status information of the optimal logistics robot, wherein the special area is a crossroad or a passage area; If so, the big data computing platform controls the optimal logistics robot to operate according to the special area avoidance rules, so that the optimal logistics robot can pass through the special area without obstacles; When the optimal logistics robot walks to the delivery location according to the optimal delivery route, it pushes the logistics task information to the AI ​​smart container; Based on the logistics task information, the AI ​​smart container controls the cargo picking device to place the cargo to the optimal logistics robot, or picks up the cargo from the optimal logistics robot, and after picking up or placing the cargo, feeds back the task execution information to the smart logistics platform, so that the smart logistics platform continues to control the operation of the optimal logistics robot based on the task execution information and the big data computing platform, and in accordance with the blocking avoidance rules and special area avoidance rules until the delivery task is completed.

2. The method according to claim 1, characterized in that The big data computing platform controls the operation of each blocking robot according to the blocking avoidance rules, including: The big data computing platform obtains the delivery priority of each blocked robot, and sorts each blocked robot in descending order of delivery priority to obtain a sorting sequence; For the i-th blocked robot in the sorting sequence, the big data computing platform controls the target robot to walk to the temporary storage area and enter a pause state, wherein the target robot is all blocked robots in the sorting sequence except the i-th blocked robot, and the initial value of i is 1; The big data computing platform controls the operation of the i-th blocking robot to release the blocking state, and after the i-th blocking robot leaves the blocking area, the big data computing platform controls the operation of i+1 blocking machines until all blocking robots in the temporary storage area leave the blocking area, wherein the blocking area is the area surrounded by all blocking robots.

3. The method according to claim 1, characterized in that The operation status information includes the location of the optimal logistics robot and the duration of suspended operation, wherein the big data computing platform determines a number of blocked robots, including: The big data computing platform determines, based on the position of the optimal logistics robot, a logistics robot from among the plurality of logistics robots that is separated from the optimal logistics robot by a preset distance and has a suspended operation time greater than or equal to a preset time, so as to form a plurality of blocking robots using the optimal logistics robot and the determined logistics robots; Accordingly, before controlling each blocking robot to run according to the blocking avoidance rule, the method further includes: The big data computing platform determines the individual areas of each blocking robot, wherein the individual area of ​​any blocking robot is a circular area with the blocking robot as the center and a radius of a preset value; The big data computing platform labels each individual area to obtain a number of labeled areas, and performs region recognition on each labeled area to obtain the region type corresponding to each labeled area, wherein the region type includes intersections and channel areas; The big data computing platform determines the special area according to the area type corresponding to each marked area, so as to control the operation of each blocking robot according to the blocking avoidance rule after determining the special area.

4. The method according to claim 1, characterized in that The big data computing platform controls the operation of the optimal logistics robot according to the special area avoidance rules, including: The big data computing platform determines whether there is a collision robot in the special area, wherein the collision robot is a logistics robot among the plurality of logistics robots except the optimal logistics robot; If so, the big data computing platform determines whether the walking direction of the collision robot is the same as the walking direction of the optimal logistics robot; If not, the big data computing platform controls the optimal logistics robot to leave the special area to avoid the collision robot; After the collision robot passes through the special area, the big data computing platform controls the optimal logistics robot to operate so as to pass through the special area.

5. The method according to claim 1, characterized in that The cargo picking device includes a primary robotic arm and a secondary robotic arm, wherein the primary robotic arm is provided with a code scanning device, and the logistics task information also includes cargo to be picked up; The AI ​​smart container controls the cargo picking device to place the cargo to the optimal logistics robot based on the logistics task information, including: The AI ​​smart container determines the cargo location of the to-be-collected goods on the shelf based on the logistics task information, wherein each cargo location on the shelf is provided with a cargo QR code; The AI ​​smart container controls the first-level robot arm to extend to the cargo position corresponding to the cargo to be picked up according to the cargo position of the cargo to be picked up on the shelf, and controls the code scanning device to scan the cargo QR code at the cargo position corresponding to the cargo to be picked up to obtain the scanning result; The AI ​​smart container determines whether the goods in the target cargo position are the goods to be picked up based on the code scanning result, wherein the target cargo position is the cargo position on the shelf where the goods to be picked up are located; If so, the AI ​​smart container controls the secondary robotic arm to take the goods in the target cargo location and put the goods in the target cargo location into the AI ​​smart container.

6. The method according to claim 1, characterized in that Any logistics robot is also provided with an obstacle avoidance sensor, wherein the obstacle avoidance sensor includes a laser radar, an ultrasonic radar and a visual camera, and the method further includes: When the optimal logistics robot is in an area outside the special area, the optimal logistics robot obtains the detection data transmitted by the laser radar, the ultrasonic radar and the visual camera, and based on the detection data, performs obstacle avoidance walking on the optimal delivery path.

7. The method according to claim 1, characterized in that Before the big data computing platform receives the delivery task pushed by the smart logistics platform, the method further includes: The smart logistics platform receives the logistics distribution demand information, and parses and processes the logistics distribution demand information to generate an initial logistics task based on the parsing result; The smart logistics platform determines the task execution time based on the initial logistics task; The smart logistics platform determines whether the initial logistics task is executed according to the task execution time; If so, the smart logistics platform generates the delivery task based on the initial logistics task and pushes the delivery task to the big data computing platform.

8. A collaborative control system for a logistics robot, characterized in that: include: Smart logistics platform, big data computing platform, AI smart containers and several logistics robots: A big data computing platform, used to receive the delivery tasks pushed by the smart logistics platform, and based on the delivery tasks, select the optimal logistics robot from a number of logistics robots, and generate logistics task information, wherein the logistics task information includes the optimal delivery path of the optimal logistics robot; A big data computing platform, used for sending the logistics task information to the optimal logistics robot; The optimal logistics robot is used to receive the logistics task information, walk according to the optimal delivery path in the logistics task information, and upload its own operation status information to the big data computing platform during the walking process; A big data computing platform, used to determine whether the optimal logistics robot is in a blocked state according to the operating state information; If so, the big data computing platform is used to determine a number of blocking robots, and control the operation of each blocking robot according to the blocking avoidance rule, wherein the number of blocking robots includes the optimal logistics robot and the logistics robot that is blocked with the optimal logistics robot, and when any blocking robot is running, the remaining blocking robots among the number of blocking robots are located outside the walking path of any blocking robot and are in a paused state; When the optimal logistics robot is unblocked, the big data computing platform is used to determine whether the optimal logistics robot is in a special area based on the latest operating status information of the optimal logistics robot, where the special area is an intersection or a passage area; If yes, the big data computing platform is used to control the operation of the optimal logistics robot according to the special area avoidance rules, so that the optimal logistics robot can pass through the special area without obstacles; When the optimal logistics robot walks to the delivery location according to the optimal delivery path, it is used to push logistics task information to the AI ​​smart container; The AI ​​smart container is used to control the cargo picking equipment to place the cargo to the optimal logistics robot, or to pick up the cargo from the optimal logistics robot based on the logistics task information, and after picking up or placing the cargo, to feedback the task execution information to the smart logistics platform, so that the smart logistics platform can continue to control the operation of the optimal logistics robot based on the task execution information and the big data computing platform, and in accordance with the blocking avoidance rules and special area avoidance rules until the delivery task is completed.

9. An electronic device, characterized in that: include: A memory, a processor and a transceiver which are sequentially connected in communication, wherein the memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the collaborative control method of the logistics robot as described in any one of claims 1 to 7.

10. A computer program product comprising instructions, characterized in that When the instruction is executed on a computer, the computer executes the collaborative control method of the logistics robot as described in any one of claims 1 to 7.

Images