Automatic delivery method and device of robot

Abstract

The invention discloses an automatic delivery method and device for a robot, and the method comprises the steps: obtaining a starting point and a terminal point of a delivery task, so as to plan a target path; controlling the robot to start moving, and calculating a target communication base station and a target computing power base station according to the position of the robot and the target path; requesting a corresponding intelligent model through the target communication base station according to the function demand information of the distribution task; the intelligent model obtains and analyzes environment information and state information of the robot through the target computing power base station and the target communication base station to obtain an analysis result; and according to an analysis result of the artificial intelligence model, controlling the robot to run to the terminal point. According to the technical scheme of the invention, the robot can complete long-distance distribution in a relatively complex path.

Description

Technical Field

[0001] The present application belongs to the field of data communication, and specifically relates to a robot automatic delivery method and device. Background Art

[0002] With the development and progress of the times, the automatic delivery function of robots has become more and more perfect, and the automatic delivery and transportation of robots can be realized. However, when delivering, the automatic machine will be unable to handle the complex situations encountered on the road due to its limited computing power and relatively simple network interface selection. On the other hand, the relatively simple network interface can easily lead to insufficient computing power of the automatic robot, or poor signal, making it impossible for the robot to complete the delivery task well.

[0003] Therefore, how to enable robots to complete long-distance delivery along more complex routes is a technical problem that urgently needs to be solved. Summary of the invention

[0004] The purpose of this application is to enable robots to complete long-distance deliveries with more complex routes.

[0005] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0006] According to one aspect of an embodiment of the present application, a robot automatic delivery method is provided, the method comprising:

[0007] Get the starting and ending points of the delivery task to plan the target path;

[0008] Control the robot to start moving, and determine a target communication base station and a target computing power base station according to the position of the robot and the target path;

[0009] According to the functional requirement information of the delivery task, requesting a corresponding intelligent model through the target communication base station;

[0010] The intelligent model acquires and analyzes the environment information and state information of the robot through the target computing power base station and the target communication base station to obtain an analysis result;

[0011] According to the analysis result of the intelligent model, the robot is controlled to travel until the end point.

[0012] According to one aspect of an embodiment of the present application, determining a target communication base station and a target computing power base station according to the position of the robot and the target path includes:

[0013] According to the position of the robot and the target path, determine the target communication base station of the road section where the robot will travel, and reserve communication resources;

[0014] According to the predicted communication delay between the target communication base station and the robot, the target computing power base station corresponding to the target communication base station is determined, and computing power resources are reserved.

[0015] According to one aspect of an embodiment of the present application, determining a target communication base station of a road section where the robot is to travel according to the position of the robot and the target path includes:

[0016] When the robot senses that the signal of the currently used target communication base station reaches a set threshold, the first position of the robot is obtained;

[0017] Determine a position in the target path that is a first set distance from the first position as a second position;

[0018] Taking the second position as the center, a communication base station within a second set distance range is used as an initial communication base station;

[0019] An initial communication base station with the largest communication resources is selected from the initial communication base stations as a target communication base station.

[0020] According to one aspect of an embodiment of the present application, determining a target computing power base station corresponding to the target communication base station according to the predicted communication delay between the target communication base station and the robot includes:

[0021] According to the parameter information of the computing power base station and the difficulty of the delivery task, the computing delay of the computing power base station is calculated as the first delay;

[0022] According to the distance between each of the target communication base stations and the target planned path, predicting the communication delay between the target communication base station and the robot as the second delay;

[0023] The difference between the standard delay and the first delay and the second delay is taken as the third delay, and the computing power base station whose communication delay with the target communication base station is less than the third delay is taken as the target computing power base station corresponding to the target communication base station.

[0024] According to one aspect of the embodiment of the present application, the method further includes:

[0025] During the driving process of the robot, the signals of the current target communication base station and the next target communication base station are monitored as a first signal and a second signal respectively, and the robot communicates via the current target communication base station;

[0026] When it is detected that the ratio of the first signal to the second signal is less than the set ratio threshold, the next target communication base station is used as the current target communication base station to ensure smooth communication of the robot.

[0027] According to one aspect of an embodiment of the present application, according to the functional requirement information of the delivery task, requesting a corresponding intelligent model through the target communication base station includes:

[0028] Determining the delivery function required to complete the delivery task according to the functional requirement information of the delivery task;

[0029] According to the external functions in the distribution function, request an intelligent model with corresponding external functions through the target communication base station, and transmit it to the target computing power base station;

[0030] According to the built-in functions in the delivery function, when the smart model is requested for the first time through the target communication base station, the smart model with the corresponding built-in function is transmitted to the robot.

[0031] According to one aspect of the embodiment of the present application, the intelligent model obtains and analyzes the environmental information and state information of the robot through the target computing power base station and the target communication base station to obtain analysis results, including:

[0032] Acquire state information and environment information of the robot, and use the built-in function to perform built-in analysis on the state information and environment information to obtain built-in analysis results;

[0033] Sending the state information, environment information and built-in analysis results to the target computing power base station via the target communication base station;

[0034] The intelligent model in the target computing power base station analyzes the driving state information and environmental information to obtain an external analysis result;

[0035] If the external analysis result is the same as the built-in analysis result, the built-in analysis result is used as the analysis result;

[0036] If the external analysis result is different from the built-in analysis result, the external analysis result is used as the analysis result, and the parameters of the intelligent model set in the target computing power node are sent to the robot to update the parameters of the built-in intelligent model of the robot.

[0037] According to one aspect of the embodiment of the present application, the method further includes:

[0038] If the signal of the target communication base station is unstable, the bandwidth allocation of the target communication base station to the delivery task is increased and / or the corresponding communication task is advanced in the task queue.

[0039] According to one aspect of an embodiment of the present application, the communication base station includes: a 3GPP base station and a non-3GPP base station.

[0040] According to one aspect of an embodiment of the present application, the present application provides an automatic delivery device of a robot, comprising:

[0041] The business management module is used to determine the target path of the delivery task according to the starting point and end point of the delivery task, and to determine the target communication base station and the target computing power base station;

[0042] The model management module is used to provide intelligent models corresponding to various distribution functions, and can install the intelligent models on the target computing power base station and robot through the target communication base station;

[0043] A resource scheduling module is provided in the target computing power base station, and is used to calculate the external analysis result according to the state information and environmental information of the robot, and compare the built-in analysis result with the external analysis result; and is also used to balance the communication resources of the target communication base station to ensure that the first delay and the third delay will not increase when the network of the target communication base station is not smooth;

[0044] The data management module sends and receives data between the robot and the target computing power base station, and stores the data.

[0045] In the technical solution provided in the embodiment of the present application, the starting point and end point of the delivery task are first obtained to plan the target path; the robot is controlled to start moving, and the target communication base station and the target computing power base station are calculated according to the position of the robot and the target path; according to the functional requirement information of the delivery task, the corresponding intelligent model is requested through the target communication base station; the intelligent model obtains and analyzes the robot's environmental information and state information through the target computing power base station and the target communication base station to obtain the analysis results; according to the analysis results of the artificial intelligence model, the robot is controlled to travel to the end point. In the present application, multiple target communication base stations are determined through the target path so that the robot can maintain smooth communication and has the ability to travel long distances. By making the target computing power base station peripheral, the computing power that the robot can use is greatly increased, so that it can face various complex road conditions.

[0046] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0047] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0049] Figure 1 A flow chart of an automatic delivery method of a robot according to an embodiment of the present application is shown.

[0050] Figure 2 A flow chart is shown for determining a target communication base station and a target computing power base station based on the position and target path of a robot according to an embodiment of the present application.

[0051] Figure 3 A flow chart is shown for determining a target communication base station for a section of a road on which the robot is to travel based on the robot's position and target path according to one embodiment of the present application.

[0052] Figure 4 A flowchart is shown for determining a target computing power base station corresponding to a target communication base station based on the predicted communication delay between the target communication base station and the robot according to an embodiment of the present application.

[0053] Figure 5 A flowchart of a robot changing a currently used target communication base station according to an embodiment of the present application is shown.

[0054] Figure 6 A flow chart is shown for requesting a corresponding intelligent model through a target communication base station based on functional requirement information of a delivery task according to an embodiment of the present application.

[0055] Figure 7 The figure shows a flowchart in which an intelligent model according to an embodiment of the present application obtains and analyzes the robot's environmental information and status information through a target computing power base station and a target communication base station to obtain analysis results.

[0056] Figure 8 A block diagram of the computer system structure for implementing an automatic delivery method of a robot according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0057] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more comprehensive and complete and fully convey the concept of the example embodiments to those skilled in the art.

[0058] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0059] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0060] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0061] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program with a predetermined function, and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0062] See also Figure 1 , Figure 1 The flowchart of the automatic delivery method of a robot according to an embodiment of the present application is shown. The steps of the automatic delivery method of a robot provided in the embodiment of the present application include:

[0063] Step S110, obtaining the starting point and end point of the delivery task to plan the target path;

[0064] Step S120, controlling the robot to start moving, and determining the target communication base station and the target computing power base station according to the robot's position and target path;

[0065] Step S130, requesting a corresponding intelligent model through a target communication base station according to the functional requirement information of the delivery task;

[0066] Step S140, the artificial intelligence model obtains and analyzes the robot's environmental information and state information through the target computing power base station and the target communication base station to obtain an analysis result;

[0067] Step S150, according to the analysis result of the artificial intelligence model, control the robot to travel to the end point.

[0068] The above five steps are described in detail below.

[0069] In step S110, the starting point and the end point of the delivery task are obtained, and the target path is planned.

[0070] In some embodiments, the shortest path between the start point and the end point of the delivery task is used as the target path.

[0071] In some embodiments, each path between the starting point and the end point of the delivery task is obtained as an alternative path. If there is only one alternative path, the alternative path is directly used as the target path.

[0072] If there are multiple alternative paths, the transit time of each alternative path is predicted, and the alternative path with the shortest time is taken as the target path.

[0073] In step S120, the robot is controlled to start moving, and the target communication base station and the target computing power base station are determined according to the robot's position and target path.

[0074] In the embodiment of the present application, as the robot moves on the target path, the target communication base station is gradually determined. In this way, the robot can continuously obtain support from the target communication base station on the target path, always have a good communication signal, and ensure that the machine can always upload its status information and environmental information and get feedback in time. When encountering a complex environment, it can also get support in time.

[0075] Then, the corresponding target computing power base station is determined according to the target communication base station. The target computing power base station provides computing power support to the robot through the target communication base station, and cooperates with the good target communication signal. This allows the machine to always receive instructions quickly during the driving process of the target path to face different complex environments.

[0076] Through multi-target communication base stations and "computing peripherals", the robot can fully cope with both longer paths and target paths with complex environments.

[0077] In one embodiment of the present application, the communication base station includes: a 3GPP base station and a non-3GPP base station. A base station refers to a base station using the 3GPP plan. A non-3GPP base station refers to a base station that does not use the 3GPP plan. The goal of 3GPP (3rd Generation Partnership Project) is to achieve a smooth transition from 2G networks to 3G networks, ensure backward compatibility of future technologies, support easy network construction, and roaming and compatibility between systems. Its functions: 3GPP is mainly responsible for formulating specifications for the third generation technology based on the GSM core network and UTRA (FDD is W-CDMA technology, TDD is TD-SCDMA technology) as the wireless interface.

[0078] In the embodiment of the present application, 3GPP base stations and non-3GPP base stations can be used simultaneously, so that the robot has more communication access options and further ensures the communication reliability of the robot.

[0079] See also Figure 2 , Figure 2 The flowchart of determining the target communication base station and the target computing power base station according to the position and target path of the robot according to one embodiment of the present application is shown. The embodiment of the present application provides a step S120 of determining the target communication base station and the target computing power base station according to the position and target path of the robot, including

[0080] Step S121, determining the target communication base station of the road section where the robot will travel according to the position of the robot and the target path, and reserving communication resources;

[0081] Step S122, determine the target computing power base station corresponding to the target communication base station according to the predicted communication delay between the target communication base station and the robot, and reserve computing power resources.

[0082] The above two steps are described in detail below.

[0083] In step S121, according to the position of the robot and the target path, the target communication base station of the road section where the robot will travel is determined, and communication resources are reserved.

[0084] In some embodiments, the target road section is evenly divided into several sections, and for each section of the path, the communication base station nearby that can completely cover the section of the path is obtained as the initial communication base station. The initial communication base station with the most communication resources is used as the target communication base station. It should be clear that the communication resources include the allocatable bandwidth of the communication base station. The more allocatable bandwidth, the more communication resources. And the number of tasks in the task queue. The smaller the number of tasks in the task queue, the more communication resources the communication base station has.

[0085] After determining the target communication base station, the time period in which the robot uses each target communication base station is predicted, and communication resources for the time period in which the target communication base station is used are reserved to avoid communication problems due to insufficient communication resources when using the target communication base station.

[0086] See also Figure 3 , Figure 3 A flowchart of determining a target communication base station for a section where the robot is to travel based on the position and target path of the robot according to an embodiment of the present application is shown. The present application embodiment provides a step S121 of determining a target communication base station for a section where the robot is to travel based on the position and target path of the robot, including:

[0087] Step S201, when the robot senses that the signal of the target communication base station currently in use reaches a set threshold, the first position of the robot is obtained;

[0088] Step S202, determining a position in the target path that is a first set distance from the first position as a second position;

[0089] Step S203, taking the second position as the center, taking the communication base station within the second set distance range as the initial communication base station;

[0090] Step S204 , selecting an initial communication base station with the largest communication resources from the initial communication base stations as a target communication base station.

[0091] The above four steps are described in detail below.

[0092] In step S201, when the robot starts to travel, it first determines a target communication base station according to the starting point of the delivery task. Specifically, according to the starting point of the delivery task, several communication base stations that can cover the starting point of the delivery task are determined as initial communication base stations, and one of the initial communication base stations with the most communication resources is determined as the target communication base station currently used.

[0093] Then, when the robot senses that the signal of the currently used target communication base station reaches the set threshold, the first position of the robot is obtained. That is, when the signal of the currently used target communication base station reaches the set threshold, it is necessary to start preparing to determine the next target communication base station.

[0094] In some embodiments, the threshold is set to the peak interval that the robot can reach with the currently used target communication base station. This allows the next target communication base station to be determined in advance when the robot signal is the best, and the target communication base station can be switched in time when the robot signal is not good, without leaving a communication window period.

[0095] In step S202, a position that is a first set distance away from the first position in the target path is determined as the second position. It should be noted that the first set distance can be adjusted according to user needs.

[0096] In step S203, taking the second position as the center, a communication base station within a second set distance range is used as an initial communication base station;

[0097] It should be further clarified that, in some embodiments, the signal coverage range of the initial communication base station should be able to cover the road section between the first location and the second location.

[0098] In step S204, an initial communication base station with the largest communication resources is selected from the initial communication base stations as a target communication base station.

[0099] In some embodiments, the signal strength of the next target communication base station at the first position is less than the product of the set threshold and the set coefficient. The coefficient is set to a decimal between 0 and 1. This is to avoid the next target communication base station being too close to the currently used target communication base station, because if the distance between adjacent target communication base stations is too close, the target communication base stations required for the target path will increase significantly, and communication resources will be occupied too much, which will affect other delivery tasks. It will also cause the robot to frequently switch target communication base stations, which will affect the robot's travel efficiency. Therefore, in this embodiment of the present application, this method is used to determine the next target communication base station.

[0100] In some embodiments, an initial communication base station with the largest communication resources is selected from the initial communication base stations as a target communication base station, and the communication resources of the target communication base station must be greater than a communication resource threshold.

[0101] If there is no initial communication base station with communication resources greater than the communication resource threshold, then the first set distance is reduced according to the preset ratio, and the initial communication base station is re-determined until the next target communication base station is determined. It should be clarified that after the next target communication base station is determined, the first set distance is restored to the value before the first reduction, so as to determine the next target communication base station of the next target communication base station.

[0102] In the embodiment of the present application, it can be ensured that the signal coverage area between the target communication base stations can always cover the robot, and that the communication resources of the target communication base stations are sufficient to complete the communication of the robot.

[0103] In step S122, the target computing power base station corresponding to the target communication base station is determined according to the predicted communication delay between the target communication base station and the robot, and computing power resources are reserved.

[0104] In some embodiments, after determining the target communication base station, taking one of the target communication base stations as an example, the target computing power base station corresponding to the target communication base station can be determined in the following manner. First, the position of the target communication base station is obtained, and the predicted communication delay between the target communication base station and the robot is predicted according to the position of the target communication base station. According to the predicted communication delay, the computing power base station whose communication delay with the target communication base station is less than the set delay is determined as the initial computing power base station, wherein the predicted communication delay is negatively correlated with the set delay, and then the first N initial computing power base stations with more computing power resources are used as the target computing power base stations. N is a positive integer.

[0105] See also Figure 4 , Figure 4 A flowchart of determining a target computing power base station corresponding to a target communication base station according to a predicted communication delay between the target communication base station and the robot according to an embodiment of the present application is shown. The present application embodiment provides a step S122 of determining a target computing power base station corresponding to a target communication base station according to a predicted communication delay between the target communication base station and the robot, including:

[0106] Step S301, calculating the computing delay of the computing power base station according to the parameter information of the computing power base station and the difficulty of the distribution task, as the first delay;

[0107] Step S302, predicting the communication delay between the target communication base station and the robot as the second delay according to the distance between each target communication base station and the target planned path;

[0108] Step S303: Take the difference between the standard delay and the first delay and the second delay as the third delay, and obtain a computing power base station whose communication delay with the target communication base station is less than the third delay as the target computing power base station corresponding to the target communication base station.

[0109] The above three steps are described in detail below.

[0110] First of all, it should be clear that since the robot is always moving, the robot must be able to quickly upload state information and environmental information to the target computing power base station, and the target computing power base station must be able to quickly feed back the analysis results to the robot. In order to meet the control requirements of the robot, the time used in the above process must be less than or equal to the standard delay.

[0111] The standard delay is mainly caused by three parts: the round-trip communication delay between the robot and the target communication base station; the second is the computing delay of the target computing base station to analyze the status information and environmental information; and the third is the round-trip communication delay between the target computing base station and the target communication base station.

[0112] Therefore, in order to meet the above standards, the target computing power base station is determined in the following way.

[0113] In step S301, the calculation delay of the computing power base station is calculated as the first delay according to the parameter information of the computing power base station and the difficulty of the delivery task. It should be clear that the difficulty of the delivery task is determined according to the difficulty of the target path and the number of required functions. The greater the difficulty of the delivery task, the greater the calculation time required for the computing power base station with the same computing power, that is, the longer the calculation delay.

[0114] In step S302, according to the distance between each target communication base station and the target planned path, the communication delay between the target communication base station and the robot is predicted as the second delay. According to the distance from the target communication base station to the target path, the communication delay between the target communication base station and the robot is calculated as the second delay.

[0115] In step S303, the difference between the standard delay and the first delay and the second delay is taken as the third delay, that is, the third delay is obtained by subtracting the first delay and the second delay from the standard delay in sequence, and the computing power base station whose communication delay with the target communication base station is less than the third delay is taken as the target computing power base station corresponding to the target communication base station. It should be clear that each target communication base station corresponds to at least one target computing power base station, and the target computing power base station exchanges data with the robot through the corresponding target communication base station.

[0116] In some implementations, each target communication base station corresponds to three target computing power base stations.

[0117] In some implementations, each target communication base station corresponds to a set number of target computing power base stations. According to the size of the computing power of the target computing power base station, each target computing power base station is provided with a corresponding intelligent model. Exemplarily, in order of computing power from large to small, each target communication base station corresponds to 4 target computing power base stations, namely A, B, C, and D. There are 5 intelligent models corresponding to the delivery task, namely 1, 2, 3, 4, and 5. Intelligent models 1 and 2 need to be set on the target computing power base station A. Intelligent model 3 needs to be set on the target computing power base station B, intelligent model 4 needs to be set on the target computing power base station C, and intelligent model 5 needs to be set on the target computing power base station D. This correspondence applies to each target communication base station and its corresponding target computing power base station.

[0118] In the embodiment of the present application, by setting the intelligent models on different target computing power base stations, the pressure on each target computing power base station is reduced. At the same time, the computing power delay is also shortened, making the target computing power base station respond faster.

[0119] See also Figure 5 , Figure 5 A flowchart of a robot changing a currently used target communication base station according to an embodiment of the present application is shown. The steps of a flowchart of a robot changing a currently used target communication base station are provided in an embodiment of the present application, including:

[0120] Step S401, during the robot's driving process, the signals of the current target communication base station and the next target communication base station are monitored as the first signal and the second signal respectively, and the robot communicates via the current target communication base station;

[0121] Step S402, when it is detected that the ratio of the first signal to the second signal reaches a set ratio threshold, the next target communication base station is used as the current communication base station to ensure smooth communication of the robot.

[0122] The above two steps are described in detail below.

[0123] In step S401, during the driving process of the robot, the signals of the current target communication base station and the next target communication base station are monitored as the first signal and the second signal respectively, and the robot communicates via the current target communication base station.

[0124] In step S402, when it is detected that the ratio of the first signal to the second signal is less than the set ratio threshold, the next target communication base station is used as the current target communication base station to ensure smooth communication of the robot. It should be clear that the ratio threshold is less than 1, that is, when it is detected that the ratio of the first signal to the second signal is less than the set ratio threshold, the signal of the next target communication base station is better. In order to ensure that the robot always has smoother communication, when the next target communication base station can provide a better signal for the machine, the next target communication base station is directly used as the current target communication base station, so that the robot communicates through the new current target communication base station.

[0125] In some embodiments, if the signal of the target communication base station is unstable, the bandwidth allocation of the target communication base station to the delivery task is increased and / or the corresponding communication task is advanced in the task queue.

[0126] In step S130, according to the functional requirement information of the delivery task, the corresponding intelligent model is requested through the target communication base station. It should be clear that different delivery tasks have different functional requirements. For example, during festivals, a blessing function may need to be configured. For example, in the delivery task in "Chongqing", because Chongqing has many steps and slopes, the robot needs to be configured with a corresponding recognition function to specifically identify "slopes" and "steps". Different movement methods are used for different terrains. In order to better "uphill" and "downhill", the corresponding "climbing control function" and "downhill control function" are configured. If the slope is required to calculate the robot's driving power, climbing speed and other parameters.

[0127] In some embodiments, the delivery function includes a visual recognition function, a perceptual recognition function, and an obstacle recognition function.

[0128] In some embodiments, various intelligent models are stored in the model management module. It should be clear that each intelligent model corresponds to at least one delivery function. The robot sends the request information to the model management module through the target communication base station. The model management module matches the intelligent model with the corresponding function according to the request information. The intelligent model is sent to the target computing power base station corresponding to the target communication base station via the target communication base station.

[0129] It should be made clear that in some embodiments, the robot only needs to send a request message to the model management module through the target communication base station. The model management module records the intelligent model required for the delivery task and detects the update of the target communication base station of the delivery task. Whenever a target communication base station is determined, the intelligent model required for the current delivery task is transmitted to the target computing power base station corresponding to the newly discovered target communication base station. The intelligent model is set in the target computing power base station, and uses the computing power resources provided by the target computing power base station to analyze the status information and environmental information uploaded by the robot and provide feedback.

[0130] In other embodiments, all data of the robot during its travel along the target path is collected by the data management module. Each time a new target communication base station is determined, the newly determined target communication base station obtains the intelligent model required for the current delivery task through the data management module, and forms a request message to send to the model management module. The model management module determines the corresponding intelligent model and transmits the intelligent model to the target computing power base station corresponding to the target communication base station that sent the request message.

[0131] See also Figure 6 , Figure 6 The flowchart of requesting a corresponding intelligent model through a target communication base station according to the functional requirement information of a delivery task according to an embodiment of the present application is shown. The embodiment of the present application provides a step S130 of requesting a corresponding intelligent model through a target communication base station according to the functional requirement information of a delivery task, including:

[0132] Step S131, determining the delivery function required to complete the delivery task according to the functional requirement information of the delivery task;

[0133] Step S132, according to the external function in the distribution function, requesting the intelligent model with the corresponding external function through the target communication base station, and transmitting it to the target computing power base station;

[0134] Step S133, according to the built-in functions in the delivery function, when the smart model is requested for the first time through the target communication base station, the smart model with the corresponding built-in function is transmitted to the robot.

[0135] The above three steps are described in detail below.

[0136] In step S131, the delivery function required for the delivery task is determined based on the functional requirement information of the delivery task. In some embodiments, the delivery function is defined by the user. In some embodiments, the delivery function is determined based on the properties of the target path itself. For example, some paths must be equipped with corresponding delivery functions to complete the delivery. The delivery function required to complete the delivery task is determined based on the delivery function required for the target path and the delivery function defined by the user or automatically determined based on the delivery task.

[0137] In step S132, it should be clarified that the delivery functions required to complete the delivery task can be divided into external functions and internal functions. External functions refer to functions provided by the intelligent model installed on the target communication node, such as lane change, route planning, obstacle sensing, obstacle recognition, etc. Internal functions refer to functions provided by the intelligent model installed in the robot, such as self-driving balance.

[0138] According to the external functions in the distribution function, the intelligent model with the corresponding external functions is requested through the target communication base station and transmitted to the target computing power base station. The external functions need to be completed with the help of the target computing power base station, so each time a new target computing power base station is determined, the intelligent model must be obtained again.

[0139] In step S133, according to the built-in function in the delivery function, the smart model with the corresponding built-in function is transmitted to the robot when the smart model is requested for the first time through the target communication base station. Because the robot is always the same, the smart model corresponding to the built-in function only needs to be downloaded when requested for the first time.

[0140] In step S140, the intelligent model obtains and analyzes the robot's environmental information and state information through the target computing power base station and the target communication base station to obtain the analysis results. The robot is equipped with sensors, which can detect its own state parameters, such as endurance, speed, direction, position, horizontal state, weight and other parameters. On the other hand, environmental information such as weather, road friction coefficient, surrounding obstacles, surrounding vehicles, and pedestrians can be obtained. The robot's state information and environmental information are sent to the target computing power base station corresponding to the target communication base station through the target communication base station. The intelligent model in the target computing power base station analyzes the received robot's state information and environmental information to obtain the analysis results, which are also the control instructions for the robot. Such as controlling the robot to accelerate, decelerate, change lanes to overtake, stop, honk, etc.

[0141] See also Figure 7 , Figure 7The flowchart of the intelligent model according to one embodiment of the present application is shown, which obtains and analyzes the environment information and state information of the robot through the target computing power base station and the target communication base station to obtain the analysis result. The embodiment of the present application provides a step S140 in which the intelligent model obtains and analyzes the environment information and state information of the robot through the target computing power base station and the target communication base station to obtain the analysis result, including:

[0142] Step S141, obtaining the state information and environment information of the robot, and using the built-in function to perform built-in analysis on the state information and environment information to obtain a built-in analysis result;

[0143] Step S142, sending the status information, environment information, and built-in analysis results to the target computing power base station via the target communication base station;

[0144] Step S143, the intelligent model in the target computing power base station analyzes the driving state information and the environmental information to obtain an external analysis result;

[0145] Step S144, if the external analysis result is the same as the internal analysis result, the internal analysis result is used as the analysis result;

[0146] Step S145, if the external analysis result is different from the built-in analysis result, the external analysis result is used as the analysis result, and the parameters of the intelligent model set at the target computing power node are sent to the robot to update the parameters of the robot's built-in intelligent model.

[0147] The above five steps are described in detail below.

[0148] In step S141, the robot obtains state information and environmental information of the robot, and uses a built-in function to perform built-in analysis on the state information and environmental information to obtain a built-in analysis result.

[0149] In step S142, the robot uploads the robot's status information, environmental information, and built-in analysis results to the target computing power base station through the target communication base station.

[0150] In step S143, the target base station also performs external analysis based on the robot's state information and environmental information to obtain external analysis results. That is, the intelligent model set inside the robot is partially the same as the intelligent model in the target computing power base station, and the same analysis can be performed on the robot's state information and environmental information to obtain internal analysis results and external analysis results respectively.

[0151] In step S144, if the external analysis result is the same as the internal analysis result, the internal analysis result is used as the analysis result. This is equivalent to the internal analysis result being verified, and the robot can be directly operated according to the internal analysis result.

[0152] In step S145, if the external analysis result is different from the built-in analysis result, the external analysis result is used as the analysis result. Since the external analysis result is calculated using the intelligent model in the target computing power node with more computing power, it is more credible, so the external analysis result is used as the analysis result. This also means that the error of the intelligent model in the robot is large, so when transmitting the external analysis result, the parameters of the intelligent model set in the target computing power node are sent to the robot at the same time to update the parameters of the robot's built-in intelligent model.

[0153] In the embodiment of the present application, the analysis result is verified to make the analysis result more accurate. When it is determined that an error occurs in the intelligent model set in the robot, parameters are sent to the intelligent model set in the robot to repair the intelligent model inside the robot, thereby ensuring that the analysis result is always verified.

[0154] In step S150, the target computing power base station transmits the analysis results to the robot through the target communication base station, and the robot operates according to the analysis results of the artificial intelligence model until it reaches the destination of the delivery task.

[0155] It should be clarified that in some embodiments, the robot sends the robot's status information and the environment information it is in through the target communication base station to the target computing power base station corresponding to the target communication base station at set time intervals to obtain analysis results, and then adjust the robot's driving status.

[0156] In other embodiments, the robot collects its environment information and driving information in real time, but only when the state information and driving information fluctuate outside the set range, such as when the environment information changes, a car is found in front, or an obstacle is found in front. When the state information changes, such as insufficient endurance or blurred lens, the robot's state information and environment information are sent to the target computing power base station through the target communication base station to analyze the fluctuations and obtain the analysis results. The robot continues to drive according to the analysis results.

[0157] In the embodiment of the present application, multiple target communication base stations are determined through the target path so that the robot can maintain smooth communication and enable the robot to have the ability to work over long distances. By making the target computing power base station an external device, the computing power that the robot can use is greatly increased, allowing it to face various complex road conditions. This also allows the robot to complete long-distance delivery tasks with more complex paths.

[0158] A robot automatic delivery device, characterized in that it comprises:

[0159] The business management module is configured to determine the target path of the delivery task according to the starting point and the end point of the delivery task, and determine the target communication base station and the target computing power base station;

[0160] The model management module is configured to provide intelligent models corresponding to various distribution functions, and can install the intelligent models on the target computing power base station and robot through the target communication base station;

[0161] The resource scheduling module is located in the target computing power base station, and is used to calculate the external analysis results according to the robot's state information and environmental information, compare the built-in analysis results with the external analysis results, and provide computing power for the intelligent model; it is also used to balance the communication resources of the target communication base station to ensure that the first delay and the third delay will not increase when the target communication base station network is not smooth;

[0162] The data management module sends and receives data between the robot and the target computing power base station, and stores the data.

[0163] An application scenario description is given for the robot's automatic delivery device. In some embodiments, the business management module obtains the starting point and end point of the delivery task, as well as the delivery requirements; the business management module determines the target path based on the starting point and end point of the delivery task, as well as the delivery requirements.

[0164] When the robot performs a delivery task, the business management module determines the target communication base station and the target computing power base station according to the target path; the business management module requests the model management module for the intelligent model corresponding to the delivery function according to the functional requirements of the delivery task; the model management module sends the intelligent model corresponding to the delivery function to the target computing power base station each time it determines the target computing power base station. The robot then maintains interaction with the target computing power base station so that the robot can complete the delivery task.

[0165] For each interaction between the robot and the target computing power base station, the robot sends the robot's status information, environmental information, and built-in analysis results to the data management module through the target communication network; the data management module sends the above data to the target computing power base station; the target computing power base station analyzes the robot's status information and environmental information to obtain external analysis results; the resource scheduling module set in the target computing power base station compares the external analysis results with the built-in analysis results. If the external analysis results are different from the built-in analysis results, the external analysis results and intelligent model parameters are sent to the data management module; the data management module sends the above data to the robot through the target communication base station. If the external analysis results are the same as the built-in analysis results, the built-in analysis results are sent to the data management module; the data management module sends the above data to the robot through the target communication base station. The robot operates according to the data sent by the target communication base station.

[0166] In some embodiments, the data management module is responsible for saving and transferring transmitted data to prevent data loss. On the other hand, it can also be used to train other intelligent models.

[0167] In some embodiments, the resource scheduling module is further used to balance the communication resources of the target communication base station to ensure that the first delay and the third delay will not increase when the network of the target communication base station is not smooth, and switch the target communication base station according to the order of use to provide communication resources for the robot.

[0168] Figure 8 A block diagram of a computer system structure for implementing an automatic delivery method of a robot according to an embodiment of the present application is shown.

[0169] It should be noted that Figure 8 The computer system 800 shown is only an example and should not affect the functions and usage scope of the embodiments of the present application.

[0170] like Figure 8 As shown, the computer system 800 includes a central processing unit 801 (CPU), which can perform various appropriate actions and processes according to the program stored in the read-only memory 802 (ROM) or the program loaded from the storage part 808 to the random access memory 803 (RAM). Various programs and data required for system operation are also stored in the random access memory 803. The central processing unit 801, the read-only memory 802 and the random access memory 803 are connected to each other through a bus 804. The input / output interface 805 (Input / Output interface, i.e., I / O interface) is also connected to the bus 804.

[0171] The following components are connected to the input / output interface 805: an input section 806 including a keyboard, a mouse, etc.; an output section 807 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a local area network card, a modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the input / output interface 805 as needed. A removable medium 811, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 810 as needed so that a computer program read therefrom is installed into the storage section 808 as needed.

[0172] In particular, according to an embodiment of the present application, the process described in each method flow chart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer readable medium, and the computer program contains a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 809, and / or installed from the removable medium 811. When the computer program is executed by the central processor 801, various functions defined in the system of the present application are executed.

[0173] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by an instruction execution system, device or device or used in combination with it. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0174] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0175] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0176] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation methods of the present application.

[0177] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary technical means in the art that are not disclosed in the present application.

[0178] It should be understood that the present application is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A robot automatic delivery method, characterized in that: The method comprises: Get the starting and ending points of the delivery task to plan the target path; Control the robot to start moving, and determine a target communication base station and a target computing power base station according to the position of the robot and the target path; According to the functional requirement information of the delivery task, requesting a corresponding intelligent model through the target communication base station; The intelligent model acquires and analyzes the environment information and state information of the robot through the target computing power base station and the target communication base station to obtain an analysis result; According to the analysis result of the intelligent model, the robot is controlled to travel until the end point.

2. The method according to claim 1, characterized in that Determining a target communication base station and a target computing power base station according to the position of the robot and the target path includes: According to the position of the robot and the target path, determine the target communication base station of the road section where the robot will travel, and reserve communication resources; According to the predicted communication delay between the target communication base station and the robot, the target computing power base station corresponding to the target communication base station is determined, and computing power resources are reserved.

3. The method according to claim 2, characterized in that Determining a target communication base station of a road section where the robot is to travel according to the position of the robot and the target path includes: When the robot senses that the signal of the currently used target communication base station reaches a set threshold, the first position of the robot is obtained; Determine a position in the target path that is a first set distance from the first position as a second position; Taking the second position as the center, a communication base station within a second set distance range is used as an initial communication base station; An initial communication base station with the largest communication resources is selected from the initial communication base stations as a target communication base station.

4. The method according to claim 3, characterized in that Determining a target computing power base station corresponding to the target communication base station according to the predicted communication delay between the target communication base station and the robot, including: According to the parameter information of the computing power base station and the difficulty of the delivery task, the computing delay of the computing power base station is calculated as the first delay; According to the distance between each of the target communication base stations and the target planned path, predicting the communication delay between the target communication base station and the robot as the second delay; The difference between the standard delay and the first delay and the second delay is taken as the third delay, and the computing power base station whose communication delay with the target communication base station is less than the third delay is taken as the target computing power base station corresponding to the target communication base station.

5. The method according to claim 1, characterized in that The method further comprises: During the driving process of the robot, the signals of the current target communication base station and the next target communication base station are monitored as a first signal and a second signal respectively, and the robot communicates via the current target communication base station; When it is detected that the ratio of the first signal to the second signal is less than a set ratio threshold, the next target communication base station is used as the current target communication base station to ensure smooth communication of the robot.

6. The method according to claim 1, characterized in that According to the functional requirement information of the delivery task, requesting the corresponding intelligent model through the target communication base station includes: Determining the delivery function required to complete the delivery task according to the functional requirement information of the delivery task; According to the external functions in the distribution function, request an intelligent model with corresponding external functions through the target communication base station, and transmit it to the target computing power base station; According to the built-in functions in the delivery function, when the smart model is requested for the first time through the target communication base station, the smart model with the corresponding built-in function is transmitted to the robot.

7. The method according to claim 6, characterized in that The intelligent model acquires and analyzes the environment information and state information of the robot through the target computing power base station and the target communication base station to obtain analysis results, including: Acquire state information and environment information of the robot, and use the built-in function to perform built-in analysis on the state information and environment information to obtain built-in analysis results; Sending the state information, environment information and built-in analysis results to the target computing power base station via the target communication base station; The intelligent model in the target computing power base station analyzes the driving state information and environmental information to obtain an external analysis result; If the external analysis result is the same as the built-in analysis result, the built-in analysis result is used as the analysis result; If the external analysis result is different from the built-in analysis result, the external analysis result is used as the analysis result, and the parameters of the intelligent model set in the target computing power node are sent to the robot to update the parameters of the built-in intelligent model of the robot.

8. The method according to claim 1, characterized in that The method further comprises: If the signal of the target communication base station is unstable, the bandwidth allocation of the target communication base station to the delivery task is increased and / or the corresponding communication task is advanced in the task queue.

9. The method according to claim 1, characterized in that: The communication base stations include: 3GPP base stations and non-3GPP base stations.

10. A robot automatic delivery device, characterized in that: include: The business management module is used to determine the target path of the delivery task according to the starting point and end point of the delivery task, and to determine the target communication base station and target computing power base station; The model management module is used to provide intelligent models corresponding to various distribution functions, and can install the intelligent models on the target computing power base station and robot through the target communication base station; A resource scheduling module is provided in the target computing power base station, and is used to calculate the external analysis result according to the state information and environmental information of the robot, and compare the internal analysis result with the external analysis result; It is also used to balance the communication resources of the target communication base station to ensure that the first delay and the third delay do not increase when the target communication base station network is not smooth; The data management module sends and receives data between the robot and the target computing power base station, and stores the data.

Images