Wholesale market-oriented inspection method and device, medium and equipment

Abstract

The embodiment of the invention discloses a wholesale market oriented inspection method and device, a medium and equipment, and relates to the technical field of path planing.The method comprises the steps that firstly, path planning is conducted according to a market electronic map, a corresponding speed control strategy is formulated, and an inspection path is represented as a node connection form; in the inspection process, once it is detected that an obstacle affects advancing, obstacle avoidance is achieved by planning a temporary path to the nearest node, due to the fact that the data basis of temporary obstacle avoidance is from a real-time picture fed back by the inspection robot, more reasonable planning and deployment can be carried out according to the actual situation, and after temporary obstacle avoidance is completed, the inspection robot can conveniently carry out obstacle avoidance. And the inspection can be continued according to the original plan after returning to the original inspection path, so that the fixed path inspection is changed into the dynamic path planning based on the fixed path, the complex condition of the wholesale market can be better met, the level of the path planning is improved, and the inspection efficiency is improved.

Description

Technical Field

[0001] This application relates to the technical field of path planning, and particularly to an inspection method, device, medium and equipment for wholesale markets. Background Art

[0002] Currently, the monitoring systems in wholesale markets face many difficult problems. Fixed-position cameras have monitoring blind spots. Once special situations occur, it is difficult to conduct real-time tracking, and key information cannot be captured in a timely manner, seriously affecting the response to emergencies. Although drone monitoring has the advantage of mobility, in a complex environment such as a wholesale market with criss-crossing pipelines, vertical and horizontal buildings, and complex lines, it is difficult to fly normally, cannot effectively cover the monitoring area, and there are also potential safety hazards of falling and hurting people. Ground mobile monitoring equipment, such as inspection robots, has stronger adaptability compared to the previous two methods. However, due to the fixed-path mode adopted in the inspection path planning of inspection robots, in the huge traffic flow and pedestrian flow in the wholesale market, the operation of inspection robots is extremely vulnerable to obstacles, and collision accidents are likely to occur or they may get stuck in place for a long time, reducing the level of path planning, and thus affecting the inspection efficiency. Summary of the Invention

[0003] The main purpose of this application is to provide an inspection method, device, medium and equipment for wholesale markets, aiming to solve the problem of low inspection efficiency caused by low path planning level in the prior art.

[0004] To achieve the above object, the technical solutions adopted in the embodiments of this application are as follows: In the first aspect, an embodiment of this application provides an inspection method for a wholesale market, including the following steps: Based on the inspection path and speed control strategy, control the inspection robot to conduct inspections; wherein, the inspection path is composed of node connections on the market electronic map; Respond to the instruction of detecting an obstacle during the inspection process to obtain a target node; wherein, the target node is the node closest to the current position point of the inspection robot along the traveling direction of the inspection path; Generate a temporary obstacle avoidance path and a temporary speed control strategy from the current position point to the target node according to the continuous frame real-time images fed back by the inspection robot; Based on the temporary obstacle avoidance path and the temporary speed control strategy, control the inspection robot to conduct obstacle avoidance inspections until the inspection robot reaches the target node, and then control the inspection robot to continue inspections according to the inspection path and speed control strategy.

[0005] In a possible implementation manner of the first aspect, before controlling the inspection robot to conduct inspections based on the inspection path and speed control strategy, the method further includes: Construct a 3D point cloud map of the market based on the data collected by the lidar; Mark nodes based on the road information on the 3D point cloud map of the market; Overlay the 3D point cloud map of the market with marked nodes and the pedestrian flow heat map to construct an electronic map of the market.

[0006] In a possible implementation manner of the first aspect, before controlling the inspection robot to perform inspections based on the inspection path and the speed control strategy, the method further includes: Extract a number of nodes on the electronic map of the market according to the path planning algorithm; Connect the number of nodes to form an inspection path.

[0007] In a possible implementation manner of the first aspect, before controlling the inspection robot to perform inspections based on the inspection path and the speed control strategy, the method further includes: Obtain a number of node groups according to the inspection path; wherein, a node group is composed of two adjacent nodes in the traveling direction of the inspection path; Determine the interval speed of the inspection robot between the two nodes included in the node group according to the information of the pedestrian flow heat map between the two nodes included in the node group; Generate a speed control strategy according to the interval speed.

[0008] In a possible implementation manner of the first aspect, after marking nodes based on the road information on the 3D point cloud map of the market, the method further includes: Increase the value of the pedestrian flow heat map within the target range centered on the node according to the marked node being located in a special area.

[0009] In a possible implementation manner of the first aspect, generating a temporary obstacle avoidance path and a temporary speed control strategy from the current position point to the target node according to the continuous frame real-time images fed back by the inspection robot, includes: Obtain dynamic pedestrians and static obstacles according to the continuous frame real-time images fed back by the inspection robot; Generate a temporary obstacle avoidance path and a temporary speed control strategy from the current position point to the target node for the purpose of following the dynamic pedestrians and avoiding the static obstacles.

[0010] In a possible implementation manner of the first aspect, after obtaining dynamic pedestrians and static obstacles according to the continuous frame real-time images fed back by the inspection robot, the method further includes: Construct a repulsive force between pedestrians according to the dynamic pedestrians; Construct an environmental obstacle force according to the static obstacles; Superimpose the target driving force, the repulsive force between pedestrians, and the environmental obstacle force to obtain the resultant force on the pedestrian; among them, the target driving force is used to characterize the force that drives the movement of the dynamic crowd flow. Obtain the predicted speed of the dynamic crowd flow according to the resultant force on the pedestrian. For the purpose of following the dynamic crowd flow and avoiding static obstacles, it includes: For the purpose of following the dynamic crowd flow at the predicted speed and avoiding static obstacles.

[0011] In a second aspect, an inspection device for a wholesale market provided by an embodiment of the present application includes: An inspection module for controlling an inspection robot to perform inspections based on an inspection path and a speed control strategy; among them, the inspection path is formed by connecting nodes on the market electronic map. An acquisition module for obtaining a target node in response to an instruction to detect an obstacle during the inspection; where the target node is the node closest to the current position point of the inspection robot along the traveling direction of the inspection path. A generation module for generating a temporary obstacle avoidance path and a temporary speed control strategy from the current position point to the target node according to the continuous frame real-time images fed back by the inspection robot. An obstacle avoidance module for controlling the inspection robot to perform obstacle avoidance inspections based on the temporary obstacle avoidance path and the temporary speed control strategy until the inspection robot reaches the target node, and then controlling the inspection robot to continue the inspection according to the inspection path and the speed control strategy.

[0012] In a third aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which when loaded and executed by a processor, implements the inspection method for a wholesale market provided in any one of the first aspects above.

[0013] In a fourth aspect, an embodiment of the present application provides an electronic device including a processor and a memory, where The memory is used to store a computer program; The processor is used to load and execute the computer program so that the electronic device executes the inspection method for a wholesale market provided in any one of the first aspects above.

[0014] Compared with the prior art, the beneficial effects of the present application are: A patrol inspection method, device, medium and equipment for a wholesale market proposed in an embodiment of the present application. The method includes: controlling a patrol inspection robot to perform patrol inspection based on a patrol inspection path and a speed control strategy; wherein, the patrol inspection path is formed by connecting nodes on a market electronic map; in response to an instruction to detect an obstacle during the patrol inspection, obtaining a target node; wherein, the target node is the node closest to the current position point of the patrol inspection robot in the traveling direction along the patrol inspection path; generating a temporary obstacle avoidance path and a temporary speed control strategy from the current position point to the target node according to the continuous frame real-time images fed back by the patrol inspection robot; based on the temporary obstacle avoidance path and the temporary speed control strategy, controlling the patrol inspection robot to perform obstacle avoidance patrol inspection until the patrol inspection robot reaches the target node, and then controlling the patrol inspection robot to continue patrol inspection according to the patrol inspection path and the speed control strategy. The present application first performs path planning according to the market electronic map and formulates a corresponding speed control strategy, and represents the patrol inspection path in the form of node connection. Once an obstacle affecting the travel is detected during the patrol inspection, obstacle avoidance is achieved by planning a temporary path to the nearest node. Since the data basis for the temporary obstacle avoidance comes from the real-time images fed back by the patrol inspection robot, more reasonable planning and deployment can be carried out according to the actual situation. After completing the temporary obstacle avoidance, returning to the original patrol inspection path, the patrol inspection can continue according to the original plan. In this way, the fixed path patrol inspection is changed to a dynamic path planning based on the fixed path, which can better conform to the complex situation of the wholesale market, improve the level of path planning, and improve the patrol inspection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic structural diagram of an electronic device for the hardware operating environment involved in an embodiment of the present application; Figure 2 It is a schematic flowchart of a patrol inspection method for a wholesale market provided by an embodiment of the present application; Figure 3 It is a schematic module diagram of a patrol inspection device for a wholesale market provided by an embodiment of the present application; Reference numerals in the figure: 101 - processor, 102 - communication bus, 103 - network interface, 104 - user interface, 105 - memory. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0017] Refer to the attached Figure 1 drawing, the attached Figure 1Schematic diagram of the electronic device structure for the hardware operating environment involved in the solution of the embodiment of the present application. The electronic device may include: a processor 101, such as a Central Processing Unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. Among them, the communication bus 102 is used to realize the connection and communication between these components. The user interface 104 may include a display screen (Display) and an input unit such as a keyboard (Keyboard). Optionally, the user interface 104 may also include a standard wired interface and a wireless interface. The network interface 103 may optionally include a standard wired interface and a wireless interface (such as a Wireless-Fidelity (WI-FI) interface). The memory 105 may optionally be a storage device independent of the aforementioned processor 101. The memory 105 may be a high-speed Random Access Memory (RAM) or a stable Non-Volatile Memory (NVM), such as at least one disk memory; the processor 101 may be a general-purpose processor, including a central processor, a network processor, etc., or may also be a digital signal processor, an application-specific integrated circuit, a field programmable gate array, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0018] Those skilled in the art can understand that the structure shown in the appendix Figure 1 does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0019] As shown in the appendix Figure 1 the memory 105, as a storage medium, may include an operating system, a network communication module, a user interface module, and an inspection device for the wholesale market.

[0020] In the electronic device shown in the appendix Figure 1 the network interface 103 is mainly used for data communication with a network server; the user interface 104 is mainly used for data interaction with users; in the present application, the processor 101 and the memory 105 may be arranged in the electronic device. The electronic device calls the inspection device for the wholesale market stored in the memory 105 through the processor 101 and executes the inspection method for the wholesale market provided by the embodiment of the present application.

[0021] Referring to the appendix Figure 2 based on the hardware device of the foregoing embodiment, an embodiment of the present application provides an inspection method for the wholesale market, including the following steps: S10: Control the inspection robot to conduct inspections based on the inspection path and speed control strategy; among them, the inspection path is formed by connecting nodes on the market electronic map.

[0022] In the specific implementation process, the inspection robot conducts inspections for the wholesale market, and collects surrounding environment information during the inspections through the cameras, sensors, etc. carried on it to realize the reporting and management of the market situation. The control of the inspection robot mainly includes two parts. One part is the planning of the inspection path, which can be obtained by manual setting or using a path planning algorithm according to the actual inspection requirements; the other part is the formulation of the speed control strategy, the purpose of which is to control the speed of the inspection robot along the inspection path according to the actual situation. Constructing the inspection path based on the market electronic map and setting nodes on the market electronic map to form the inspection path in the form of nodes can improve the efficiency of path planning.

[0023] In one embodiment, before controlling the inspection robot to conduct inspections based on the inspection path and speed control strategy, the method further includes: Construct a 3D point cloud map of the market based on the data collected by the lidar; Mark nodes based on the road information on the 3D point cloud map of the market; Overlay the 3D point cloud map of the market with marked nodes and the crowd flow heat map to construct the market electronic map.

[0024] In the specific implementation process, due to the characteristics of dense personnel and complex environment in the wholesale market, embedding the crowd flow information in the market electronic map to achieve more reasonable planning. On the one hand, through the fusion of the environmental 3D point cloud data collected by the lidar, a 3D point cloud map of the market is constructed, and then through the learning of the historical crowd flow situation in the market, a crowd flow heat map of the market can be constructed. The crowd flow heat map is also in the form of a map, but the historical crowd flow situation at the corresponding position is characterized by different color depths, that is, it can learn which areas in the market are more crowded with people and which areas have relatively low population density. Overlaying the 3D point cloud map of the market with the crowd flow heat map can not only fully display the market layout, but also characterize the prediction of the population density in different areas.

[0025] In one embodiment, before controlling the inspection robot to conduct inspections based on the inspection path and speed control strategy, the method further includes: Extract several nodes on the market electronic map according to the path planning algorithm; Connect several nodes to form the inspection path.

[0026] In the specific implementation process, existing algorithms such as the A Star algorithm and the ant colony algorithm in path planning algorithms set constraint conditions to make the path planning meet the requirements of patrol inspection, so as to extract the nodes marked on the optimal path, and connect the nodes to quickly form a patrol inspection path.

[0027] In one embodiment, based on the patrol inspection path and the speed control strategy, before controlling the patrol inspection robot to perform patrol inspection, the method further includes: According to the patrol inspection path, obtain a number of node groups; wherein, a node group is composed of two adjacent nodes in the traveling direction of the patrol inspection path; According to the information of the pedestrian flow heat map between the two nodes included in the node group, determine the interval speed of the patrol inspection robot between the two nodes included in the node group; Generate a speed control strategy according to the interval speed.

[0028] In the specific implementation process, since the pedestrian flow information is embedded in the construction of the market electronic map in the foregoing embodiment, in order to achieve a more realistic patrol inspection speed control, the speed is determined according to the interval and the representation of the pedestrian flow heat map. First, all nodes are extracted from the planned patrol inspection path and grouped in the way that two adjacent nodes form a group. The two nodes in the same group correspond to a section of the path on the map. Combining with the personnel density information represented by the pedestrian flow heat map on this section of the path, the patrol inspection speed that conforms to the actual situation is determined. Simply put, a smaller patrol inspection speed is determined in the area with a larger personnel density, and a larger patrol inspection speed is determined in the area with a smaller personnel density, which can improve the safety and efficiency of patrol inspection; by determining the interval speed between each node, a speed control strategy for the entire patrol inspection path is generated.

[0029] In one embodiment, based on the road information on the market 3D point cloud map, after marking the nodes, the method further includes: According to the marked nodes being located in a special area, increase the value of the pedestrian flow heat map within the target range centered on the nodes.

[0030] In the specific implementation process, in order to improve the level of path planning, more features representing the characteristics of the market are introduced, and special areas such as fire channels, market exits, and market entrances are marked on the map. More attention needs to be paid to safety during patrol inspection in these areas. Therefore, if the nodes in the planned path are located in special areas, the patrol inspection speed nearby needs to be controlled slower. Based on the speed determination method in the foregoing embodiment, only a target range needs to be delimited with the nodes as the center, and the value of the corresponding pedestrian flow heat map within the target range on the map is increased, that is, it is represented as an area with a larger personnel density, and a smaller speed value will be assigned in the subsequent speed planning.

[0031] S20: In response to the instruction of detecting an obstacle during the patrol inspection process, obtain the target node; where the target node is the node closest to the current position point of the patrol inspection robot in the traveling direction along the patrol inspection path.

[0032] In the specific implementation process, during the patrol inspection, the patrol inspection robot monitors the environment near the real-time position through the cameras, sensors, etc. carried on it. If it detects that there is an obstacle in front on the planned path, affecting the continuous patrol inspection of the patrol inspection robot, it issues an instruction indicating that an obstacle has been detected. After encountering an obstacle, obstacle avoidance is considered, but the basic principle is to follow the originally planned path. Therefore, the obstacle avoidance strategy is to avoid the obstacle and return to the original path as soon as possible. Record the position of the patrol inspection robot when the instruction of detecting the obstacle is issued as the current position point, and check the nodes included in the patrol inspection path. Assume that continuing the patrol inspection along the original path from the current position point, the first node passed next is the target node, that is, the node closest to the current position point of the patrol inspection robot in the traveling direction along the patrol inspection path.

[0033] S30: Generate a temporary obstacle avoidance path and a temporary speed control strategy from the current position point to the target node according to the continuous frame real-time images fed back by the patrol inspection robot.

[0034] In the specific implementation process, based on the original patrol inspection path, local dynamic obstacle avoidance path planning is carried out on the fixed patrol inspection path. According to the continuous frame real-time images fed back by the camera of the patrol inspection robot, the situation of the surrounding environment at the current position can be obtained, and then local dynamic planning is carried out according to the actual situation to generate a path and a speed control strategy from the current position point to the target node. This path and strategy are used as the temporary obstacle avoidance path and the temporary speed control strategy, which are only used to guide the patrol inspection robot to avoid obstacles and return to the original path.

[0035] In one embodiment, generating a temporary obstacle avoidance path and a temporary speed control strategy from the current position point to the target node according to the continuous frame real-time images fed back by the patrol inspection robot includes: Obtain the dynamic crowd flow and static obstacles according to the continuous frame real-time images fed back by the patrol inspection robot; With the aim of following the dynamic crowd flow and avoiding static obstacles, generate a temporary obstacle avoidance path and a temporary speed control strategy from the current position point to the target node.

[0036] In the specific implementation process, the recognition of obstacles can be completed through continuous-frame real-time images. Objects that are stationary in the continuous-frame real-time images are recognized as obstacles, and those with position movement are recorded as dynamic crowds. This is in line with the actual situation. For example, under normal circumstances, when encountering roadblocks, stationary vehicles, or stalls blocking the way ahead, pedestrians will actively detour from one side. Therefore, the obstacle avoidance strategy of the inspection robot is to segment the obstacles and the moving crowds from the image, and the temporary obstacle avoidance path and the temporary speed control strategy are used to guide the inspection robot to follow the crowd and avoid obstacle blocking.

[0037] In one embodiment, after obtaining the dynamic crowd and static obstacles according to the continuous-frame real-time images fed back by the inspection robot, the method further includes: Constructing the repulsive force between pedestrians according to the dynamic crowd; Constructing the environmental obstacle force according to the static obstacles; Superposing the target driving force, the repulsive force between pedestrians, and the environmental obstacle force to obtain the resultant force received by the pedestrians; wherein, the target driving force is used to represent the force driving the movement of the dynamic crowd; Obtaining the predicted speed of the dynamic crowd according to the resultant force received by the pedestrians.

[0038] In the specific implementation process, during the obstacle avoidance process, the path planning is relatively simple. It can be carried out by selecting a road without obstacles according to the real-time image, and avoiding collisions with the surrounding people through the data fed back by the sensor. Since the personnel density in the wholesale market may be higher than in other scenarios, the difficulty in the obstacle avoidance strategy lies in the speed control. At this time, it mainly depends on the movement of the actual crowd to complete the following. Therefore, how to more accurately predict the speed of the crowd becomes the key. The embodiment of this application considers a crowd modeling method introducing the metaphor of physics mechanics, assuming that the movement of pedestrians is driven by virtual forces, including three parts: the target driving force, the repulsive force between pedestrians, and the environmental obstacle force.

[0039] The repulsive force between pedestrians constructed with the dynamic crowd is:

[0040] Where A is the intensity, B is the action range, d is the distance, here the distance refers to the distance between pedestrians, and e is the base of the natural logarithm, is the unit vector.

[0041] The environmental obstacle force constructed with the static obstacles is:

[0042] Where k is the stiffness coefficient, r is the radius of the obstacle, d is the distance, here the distance refers to the distance between the inspection robot and the obstacle, is a unit vector; the environmental obstacle force is similar to the spring force. Simply put, the farther the distance, the smaller the impact.

[0043] Target driving force The force used to characterize the driving of the dynamic pedestrian flow, which is determined according to the current speed of the pedestrian. The greater the current speed, the greater the target driving force.

[0044] For each pedestrian i, calculate the total force of all its neighbors j and the environment as:

[0045] where represents the target driving force for pedestrian i to move towards the target point, represents the summation of the pedestrian repulsion forces between pedestrian i and pedestrian j, represents the summation of the environmental obstacle forces between pedestrian i and the obstacle obs.

[0046] After obtaining the total resultant force, the instantaneous acceleration can be obtained according to Newton's second law, and the speed magnitude can be obtained by integrating the acceleration. In this way, the predicted speed of the dynamic pedestrian flow is obtained, and the dynamic pedestrian flow can be followed according to this speed.

[0047] Based on the foregoing steps, for the purpose of following the dynamic pedestrian flow and avoiding static obstacles, it includes: For the purpose of following the dynamic pedestrian flow at the predicted speed and avoiding static obstacles.

[0048] S40: Based on the temporary obstacle avoidance path and the temporary speed control strategy, control the inspection robot to perform obstacle avoidance inspection until the inspection robot reaches the target node, and then control the inspection robot to continue the inspection according to the inspection path and the speed control strategy.

[0049] In the specific implementation process, during the implementation of the fixed-path inspection, when encountering an obstacle, trigger temporary obstacle avoidance and perform local dynamic planning. Under the guidance of the temporary obstacle avoidance path and the temporary speed control strategy, control the inspection robot to perform obstacle avoidance inspection. After moving to the target node, complete the obstacle avoidance detour. It should be noted that during the process of moving towards the target node, after approaching the target node, it is necessary to judge whether the target node overlaps with the obstacle. Then, push the target node back one node at this time, and execute the above obstacle avoidance strategy to continue the detour until the obstacle is completely avoided and the target node is reached, and then the inspection can be continued according to the original inspection path and the speed control strategy.

[0050] In this embodiment, first, path planning is performed based on the market electronic map and corresponding speed control strategies are formulated. The inspection path is represented in the form of node connections. During the inspection process, once an obstacle affecting the progress is detected, obstacle avoidance is achieved by planning a temporary path to the nearest node. Since the data basis for temporary obstacle avoidance comes from the real-time images fed back by the inspection robot, more reasonable planning and deployment can be carried out according to the actual situation. After completing the temporary obstacle avoidance, the robot returns to the original inspection path and can continue the inspection according to the original plan. In this way, the fixed-path inspection is changed to a dynamic path planning based on the fixed path, which can better conform to the complex situation of the wholesale market, improve the level of path planning, and enhance the inspection efficiency.

[0051] Refer to the appendix Figure 3 , based on the same inventive concept as in the foregoing embodiment, the embodiment of the present application also provides an inspection device for a wholesale market, including: An inspection module, configured to control an inspection robot to perform inspection based on an inspection path and a speed control strategy; wherein, the inspection path is composed of node connections on the market electronic map; An acquisition module, configured to obtain a target node in response to an instruction to detect an obstacle during the inspection; wherein, the target node is the node closest to the current position point of the inspection robot along the traveling direction of the inspection path; A generation module, configured to generate a temporary obstacle avoidance path and a temporary speed control strategy from the current position point to the target node according to the continuous frame real-time images fed back by the inspection robot; An obstacle avoidance module, configured to control the inspection robot to perform obstacle avoidance inspection based on the temporary obstacle avoidance path and the temporary speed control strategy until the inspection robot reaches the target node, and then control the inspection robot to continue the inspection according to the inspection path and the speed control strategy.

[0052] Those skilled in the art should understand that the division of each module in the embodiment is only a logical function division. In actual applications, all or part of them can be integrated into one or more actual carriers, and these modules can all be implemented in the form of software called by a processing unit, or all in the form of hardware, or in the form of a combination of software and hardware. It should be noted that each module in the inspection device for a wholesale market in this embodiment corresponds one by one to each step in the inspection method for a wholesale market in the foregoing embodiment. Therefore, the specific implementation manner of this embodiment can refer to the implementation manner of the foregoing inspection method for a wholesale market, which will not be elaborated here.

[0053] Based on the same inventive concept as in the foregoing embodiment, the embodiment of the present application also provides a computer-readable storage medium storing a computer program, which when loaded and executed by a processor, implements the inspection method for a wholesale market provided by the embodiment of the present application.

[0054] Based on the same inventive concept as in the foregoing embodiments, an embodiment of the present application further provides an electronic device, including a processor and a memory. Among them, The memory is used to store a computer program; The processor is used to load and execute the computer program so that the electronic device executes the inspection method for the wholesale market provided by the embodiments of the present application.

[0055] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disc, or CD-ROM; it may also be various devices including one or any combination of the foregoing memories. The computer may be various computing devices including smart terminals and servers.

[0056] In some embodiments, the executable instructions may be in the form of a program, software, software module, script, or code, and may be written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including being deployed as an independent program or being deployed as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0057] As an example, the executable instructions may or may not correspond to a file in the file system, and may be stored as part of a file that stores other programs or data. For example, they may be stored in one or more scripts in a Hyper Text Markup Language (HTML) document, stored in a single file dedicated to the program being discussed, or stored in multiple cooperating files (for example, files that store one or more modules, subroutines, or code portions).

[0058] As an example, the executable instructions may be deployed to execute on one computing device, or on multiple computing devices located at one location, or on multiple computing devices distributed at multiple locations and interconnected by a communication network.

[0059] It should be noted that in this article, the terms "include", "comprise", or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or system including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article, or system. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article, or system including that element.

[0060] The serial numbers of the embodiments of the present application above are only for description and do not represent the superiority or inferiority of the embodiments.

[0061] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented through hardware. However, in many cases, the former is a better implementation method. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as a read-only memory / random access memory, magnetic disk, optical disk), and includes several instructions for causing a multimedia terminal device (which can be a mobile phone, a computer, a television receiver, or a network device, etc.) to execute the methods described in the various embodiments of the present application.

[0062] In summary, the present application provides an inspection method, device, medium, and equipment for a wholesale market. The method includes: controlling an inspection robot to perform inspections based on an inspection path and a speed control strategy; wherein the inspection path is formed by connecting nodes on a market electronic map; in response to an instruction to detect an obstacle during the inspection, obtaining a target node; wherein the target node is the node closest to the current position point of the inspection robot along the traveling direction of the inspection path; generating a temporary obstacle avoidance path and a temporary speed control strategy from the current position point to the target node based on the continuous frame real-time images fed back by the inspection robot; and controlling the inspection robot to perform obstacle avoidance inspections based on the temporary obstacle avoidance path and the temporary speed control strategy until the inspection robot reaches the target node, and then controlling the inspection robot to continue the inspection according to the inspection path and the speed control strategy. The present application first performs path planning according to the market electronic map and formulates a corresponding speed control strategy, and represents the inspection path in the form of node connections. During the inspection process, once an obstacle affecting the progress is detected, obstacle avoidance is achieved by planning a temporary path to the nearest node. Since the data basis for the temporary obstacle avoidance comes from the real-time images fed back by the inspection robot, more reasonable planning and deployment can be carried out according to the actual situation. After completing the temporary obstacle avoidance, returning to the original inspection path, the inspection can continue according to the original plan. In this way, the fixed path inspection is changed to a dynamic path planning based on the fixed path, which can better conform to the complex situation of the wholesale market, improve the level of path planning, and improve the inspection efficiency.

[0063] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A wholesale market inspection method, characterized in that: The following steps are involved: Based on the inspection path and speed control strategy, the inspection robot is controlled to perform inspection; wherein the inspection path is formed based on the node connection on the market electronic map; In response to an instruction that an obstacle is detected during the inspection process, a target node is obtained; wherein the target node is the node closest to the current position of the inspection robot in the direction of travel along the inspection path; Generate a temporary obstacle avoidance path and a temporary speed control strategy from the current position point to the target node according to the continuous frame real-time images fed back by the inspection robot; Based on the temporary obstacle avoidance path and the temporary speed control strategy, the inspection robot is controlled to perform obstacle avoidance inspection until the inspection robot reaches the target node, and the inspection robot is controlled to continue inspection according to the inspection path and the speed control strategy.

2. The inspection method for wholesale markets according to claim 1, characterized in that: Before controlling the inspection robot to perform inspection based on the inspection path and speed control strategy, the method further includes: Build a 3D point cloud map of the market based on data collected by LiDAR; Marking the node based on the road information on the market 3D point cloud map; The 3D point cloud map of the market with the nodes marked is superimposed on the heat map of human traffic to construct the electronic map of the market.

3. The inspection method for wholesale markets according to claim 2, characterized in that: Before controlling the inspection robot to perform inspection based on the inspection path and speed control strategy, the method further includes: According to the path planning algorithm, extracting a number of nodes on the market electronic map; A number of the nodes are connected to form the inspection path.

4. The inspection method for wholesale markets according to claim 2, characterized in that: Before controlling the inspection robot to perform inspection based on the inspection path and speed control strategy, the method further includes: According to the inspection path, a plurality of node groups are obtained; wherein the node group is composed of two adjacent nodes in the traveling direction of the inspection path; Determine, according to information of the heat map of human traffic between two nodes included in the node group, a speed of the inspection robot in an inspection interval between two nodes included in the node group; The speed control strategy is generated according to the interval speed.

5. The inspection method for wholesale markets according to claim 4 is characterized in that: After marking the node based on the road information on the market 3D point cloud map, the method further includes: According to the marked node being located in a special area, the value of the heat map of human flow within the target range with the node as the center is increased.

6. The inspection method for wholesale markets according to claim 1, characterized in that: The method of generating a temporary obstacle avoidance path and a temporary speed control strategy from the current position point to the target node according to the continuous frame real-time images fed back by the inspection robot includes: According to the continuous frame real-time images fed back by the inspection robot, dynamic human flow and static obstacles are obtained; With the purpose of following the dynamic flow of people and avoiding the static obstacles, a temporary obstacle avoidance path and a temporary speed control strategy are generated from the current position point to the target node.

7. The inspection method for wholesale markets according to claim 6, characterized in that: After obtaining the dynamic flow of people and static obstacles according to the continuous frame real-time images fed back by the inspection robot, the method further includes: According to the dynamic pedestrian flow, construct a repulsive force between pedestrians; According to the static obstacles, construct environmental obstacle forces; The target driving force, the repulsive force between pedestrians and the environmental obstacle force are superimposed to obtain the resultant force acting on the pedestrians; wherein the target driving force is used to characterize the force driving the dynamic flow of people to move; Obtaining a predicted speed of the dynamic pedestrian flow according to the resultant force exerted on the pedestrian; The purpose of following the dynamic flow of people and avoiding the static obstacles includes: The purpose is to follow the dynamic flow of people at the predicted speed and avoid the static obstacles.

8. A patrol inspection device for wholesale markets, characterized in that: include: An inspection module is used to control the inspection robot to perform inspection based on an inspection path and a speed control strategy; wherein the inspection path is formed based on node connections on an electronic market map; An acquisition module, used to respond to an instruction of an obstacle detected during the inspection process and obtain a target node; wherein the target node is the node closest to the current position point of the inspection robot in the direction of travel along the inspection path; A generation module, used to generate a temporary obstacle avoidance path and a temporary speed control strategy from the current position point to the target node according to the continuous frame real-time images fed back by the inspection robot; The obstacle avoidance module is used to control the inspection robot to perform obstacle avoidance inspection based on the temporary obstacle avoidance path and the temporary speed control strategy until the inspection robot reaches the target node, and controls the inspection robot to continue inspection according to the inspection path and the speed control strategy.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is loaded and executed by the processor, the inspection method for wholesale markets as described in any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: comprising a processor and a memory, wherein: The memory is used to store computer programs; The processor is used to load and execute the computer program so that the electronic device executes the inspection method for wholesale markets as described in any one of claims 1-7.

Images