WO2022135138A1

WO2022135138A1 - Robot task deployment method and system, device, and storage medium

Info

Publication number: WO2022135138A1
Application number: PCT/CN2021/136043
Authority: WO
Inventors: 苏启奖; 黄炎; 王柯; 吴昊; 麦晓明
Original assignee: 南方电网电力科技股份有限公司
Priority date: 2020-12-21
Filing date: 2021-12-07
Publication date: 2022-06-30
Also published as: CN112549034A; CN112549034B

Abstract

A robot task deployment method and system, a device, and a storage medium. The robot task deployment method comprises: forming a walkable path network of a robot in a three-dimensional point cloud model of a scene, controlling, according to an inspection task, a pre-established three-dimensional model of the robot to walk in the walkable path network, so as to obtain deployment information corresponding to the inspection task, and completing task deployment of the robot according to the inspection task and the corresponding deployment information, controlling an actual robot to perform automatic inspection according to the inspection task, so as to obtain an inspection result, and establishing an association relationship between the inspection result and the pre-established three-dimensional point cloud model of the scene. In this way, the inspection result is viewed in the three-dimensional point cloud model of the scene.

Description

A robot task deployment method, system, device and storage medium

This application claims the priority of the Chinese patent application filed on December 21, 2020 with the application number 202011519589.8 and the invention titled "A Robot Task Deployment Method, System, Equipment and Storage Medium", the entire contents of which are approved by Reference is incorporated in this application.

technical field

The present application relates to the technical field of inspection robots, and in particular, to a method, system, device and storage medium for deploying robot tasks.

Background technique

Before the inspection robot of the substation inspects, it is necessary to deploy corresponding inspection tasks at specific locations according to the needs of inspection. In this way, the inspection robot can be controlled to arrive at a specific position point to perform the inspection task of the corresponding position point during the inspection process, and then, according to the deployed task, it will complete the inspection action of the predetermined task, such as metering or infrared detection, etc.

At present, when an inspection robot deploys a task, it needs to drive the robot to the corresponding position point in the inspection site, record the relevant information of the position point (such as coordinates and pose, etc.), and control the execution terminal of the inspection robot to complete the inspection. Actions corresponding to tasks (such as adjusting the corresponding angle or focal length of the gimbal, etc.), so as to complete all the deployment work of a single task. After completing all deployment tasks in sequence, all inspection actions can be completed.

However, the above-mentioned deployment task method has a huge workload, and usually requires on-site control by humans, resulting in extremely low efficiency and inaccurate deployment, which has a negative impact on subsequent task inspections. At the same time, the inspection results cannot be intuitively associated with the inspection tasks and are not easy to view, resulting in poor information interaction between the user and the inspection tasks and corresponding equipment.

SUMMARY OF THE INVENTION

The present application provides a robot task deployment method, system, device and storage medium, which are used to solve the problem that the task deployment workload is extremely large, the efficiency is extremely low, and the deployment is inaccurate. At the same time, the information interaction between users and inspection tasks and corresponding equipment Poor technical issues.

In view of this, a first aspect of the present application provides a method for deploying a robot task, including the following steps:

Determine all walkable paths of the robot based on the pre-established 3D point cloud model of the scene, thereby forming a walkable path network;

The pre-established three-dimensional model of the robot walks in the walkable path network according to the assigned inspection task, thereby obtaining deployment information corresponding to the inspection task;

Complete the task deployment of the robot according to the inspection task and the corresponding deployment information;

Control the robot to perform automatic inspection according to the inspection task to obtain inspection results, and establish an association relationship between the inspection results and the pre-established 3D point cloud model of the scene, so that the pre-established 3D scene View the inspection results in the point cloud model.

Preferably, before the determination of all walkable paths of the robot based on the pre-established three-dimensional point cloud model of the scene includes:

Collect full-scene point cloud data and image data of the actual inspection scene of the robot;

Create a scene 3D point cloud model based on the full scene point cloud data and the image data;

In the scene 3D point cloud model, based on the components of the actual scene equipment, the whole scene point cloud data is clustered and divided, so as to obtain the component 3D point cloud model, and then realize the whole scene point cloud data. There is a one-to-one correspondence with the three-dimensional point cloud model of the scene and the three-dimensional point cloud model of the component.

Preferably, after obtaining the three-dimensional point cloud model of the component, and further realizing that the point cloud data of the whole scene is in a one-to-one correspondence with the three-dimensional point cloud model of the scene and the three-dimensional point cloud model of the component, it includes:

importing corresponding preset component attribute information into the model component in the three-dimensional point cloud model of the component, where the preset component attribute information includes component nameplate information and corresponding inspection history data;

In the three-dimensional point cloud model of the component, an association relationship between the model component and the corresponding preset component attribute information is established, so that the associated preset component attribute information can be viewed through the model component.

Preferably, the component nameplate information includes the actual component name, the actual component material properties, and the actual component setting parameters.

Preferably, the pre-established three-dimensional model of the robot before walking in the walkable path network according to the issued inspection task includes:

Building a three-dimensional model of the robot based on the robot and the execution terminal corresponding to the robot;

Importing preset robot attribute information of the robot and the execution terminal into the three-dimensional model of the robot, where the preset robot attribute information includes actual robot material attributes and execution terminal material attributes.

Preferably, the pre-established three-dimensional model of the robot walks in the walkable path network according to the issued inspection task, so as to obtain deployment information corresponding to the inspection task, specifically:

Establishing a three-dimensional coordinate system on the pre-established three-dimensional point cloud model of the scene;

According to the inspection task, control the pre-established three-dimensional robot model to walk along the preset inspection route on the walkable path network, so as to determine the inspection point corresponding to the inspection task and the model component;

The deployment information of the inspection point corresponding to the robot is obtained according to the three-dimensional coordinate system, and the deployment information includes the coordinate value of the inspection point, the pose of the robot, and the execution of the execution terminal of the robot. angle and execution focal length.

Preferably, the obtaining the deployment information of the inspection point corresponding to the robot according to the three-dimensional coordinate system specifically includes:

Calculate the coordinate value of the inspection point and the model component based on the three-dimensional coordinate system;

Calculate the point distance of the corresponding adjacent inspection points according to the coordinate values of the adjacent inspection points;

Comparing the point distance with the preset point distance, when the point distance is less than the preset point distance, the corresponding adjacent inspection points are regarded as the same inspection point, Therefore, the deployment information of the same inspection point is used as the deployment information of the corresponding adjacent inspection point.

In a second aspect, the present application provides a robot task deployment system, including:

The path determination module is used to determine all the walkable paths of the robot based on the pre-established 3D point cloud model of the scene, thereby forming a walkable path network;

an acquisition module, used for walking in the walkable path network through the pre-established three-dimensional model of the robot according to the issued inspection task, so as to obtain deployment information corresponding to the inspection task;

a deployment module, configured to complete the task deployment of the robot according to the inspection task and the corresponding deployment information;

The first association module is used to control the robot to perform automatic inspection according to the inspection task to obtain inspection results, and establish an association relationship between the inspection results and the pre-established three-dimensional point cloud model of the scene, so as to obtain the inspection results. Check the inspection result in the pre-established three-dimensional point cloud model of the scene.

In a third aspect, the present application provides an electronic device, comprising: a processor and a memory, where the memory is used to store program instructions, and the processor is used to implement the above-mentioned robot task when executing a computer program stored in the memory The steps of the deployment method.

In a fourth aspect, the present application provides a storage medium, which stores a computer program, and when the computer program is executed by a processor, implements the steps of the above-mentioned method for deploying a robot task.

As can be seen from the above technical solutions, the embodiments of the present application have the following advantages:

A robot task deployment method, system, device, and storage medium provided by the embodiments of the present application, by forming a walkable path network of a robot in a three-dimensional point cloud model of a scene, and controlling a pre-established three-dimensional model of a robot to walk in a walkable manner according to an inspection task. Walking in the path network, the deployment information can be obtained according to the inspection task, so that the robot can obtain the deployment information without driving the robot to the corresponding position in the inspection site, which solves the problem that the task deployment workload is extremely large, the efficiency is extremely low, and the deployment is inaccurate. question. At the same time, after the task is deployed, the inspection results can be obtained when the actual robot is controlled according to the inspection task to perform automatic inspection, and the inspection results are associated with the pre-established 3D point cloud model of the scene. It is convenient for users to exchange information with the inspection tasks and corresponding equipment, and improve the information interactivity.

Description of drawings

1 is a flowchart of a method for deploying a robot task provided by a first embodiment of the present application;

2 is a flowchart of a method for deploying a robot task provided by a second embodiment of the present application;

3 is a flowchart of a method for deploying a robot task provided by a third embodiment of the present application;

FIG. 4 is a schematic structural diagram of a robot task deployment system according to an embodiment of the present application.

Detailed ways

In order to make those skilled in the art better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only It is a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

For ease of understanding, please refer to FIG. 1 , a method for deploying a robot task provided by this application includes the following steps:

S1: Determine all walkable paths of the robot based on the pre-established 3D point cloud model of the scene, thereby forming a walkable path network;

S2: The pre-established three-dimensional model of the robot walks in the traversable path network according to the issued inspection task, so as to obtain deployment information corresponding to the inspection task;

S3: Complete the task deployment of the robot according to the inspection task and the corresponding deployment information;

S4: Control the robot to perform automatic inspection according to the inspection task to obtain inspection results, and establish an association relationship between the inspection results and the pre-established 3D point cloud model of the scene, so as to view the inspection results in the pre-established 3D point cloud model of the scene .

In this embodiment, the walkable path network of the robot is formed in the three-dimensional point cloud model of the scene, and the pre-established three-dimensional model of the robot is controlled to walk in the walkable path network according to the inspection task. Since the inspection task has inspection instructions , therefore, the pre-established 3D model of the robot can obtain deployment information according to the inspection task, so that the deployment information can be obtained without driving the robot to the corresponding position in the inspection site, which solves the problem that the task deployment workload is extremely large and the efficiency is extremely low. Deployment inaccurate issues.

At the same time, after the task is deployed, the inspection results can be obtained when the actual robot is controlled according to the inspection task to perform automatic inspection, and the inspection results are associated with the pre-established 3D point cloud model of the scene. The inspection results are viewed in the browser, and the viewing methods are not limited to clicks, etc., so as to facilitate the user to interact with the inspection tasks and the corresponding equipment, and improve the information interactivity.

The above is a detailed description of the first embodiment of a robot task deployment method provided by the present invention, and the following is a detailed description of the second embodiment of a robot task deployment method provided by the present invention.

For easy understanding, please refer to FIG. 2 , a method for deploying a robot task provided by the present application includes the following steps:

S101: Collect full-scene point cloud data and image data of the actual inspection scene of the robot;

It should be noted that the full-scene point cloud data and image data of the actual inspection scene can be obtained through the lidar and the camera respectively.

S102: Establish a three-dimensional point cloud model of the scene based on the point cloud data and image data of the whole scene;

It should be noted that the point cloud data of the whole scene is fused with the image data. During the fusion process, the global optimization of the scene is completed through laser frame matching, attitude error estimation and visual image detection, and a 3D point cloud model of the scene is established.

S103: In the 3D point cloud model of the scene, based on the components of the actual scene equipment, cluster and divide the point cloud data of the whole scene, so as to obtain the 3D point cloud model of the component, and then realize that the point cloud data of the whole scene and the 3D scene are respectively There is a one-to-one correspondence between the point cloud model and the 3D point cloud model of the component.

It should be noted that the 3D point cloud model of the scene includes equipment and sites. Therefore, the equipment and sites need to be divided. The point cloud data of the whole scene is clustered and divided, so as to obtain the 3D model of the component level based on the 3D point cloud model of the scene, so that the point cloud data of the whole scene can be divided with the 3D point cloud model of the scene and the 3D point cloud model of the component one by one. Correspondingly, the simulation of the actual inspection environment is more realistic.

S104: Import corresponding preset component attribute information into the model component in the three-dimensional point cloud model of the component, where the preset component attribute information includes component nameplate information and corresponding inspection history data;

It can be understood that the component nameplate information includes the actual component name, the actual component material properties and the actual component setting parameters; the inspection history data is the previous inspection data, and the data presentation form is not limited to curves, tables, etc.

S105: In the three-dimensional point cloud model of the component, establish an association relationship between the model component and the corresponding preset component attribute information, so as to view the associated preset component attribute information through the model component.

It can be understood that, by establishing an association relationship between a model part and the corresponding preset part attribute information, the associated preset part attribute information can be viewed through the model part. In a general example, click a model part to display the associated preset part attribute information. Set component attribute information to facilitate viewing and improve information interactivity.

S106: Determine all walkable paths of the robot based on the three-dimensional point cloud model of the scene, thereby forming a walkable path network;

S107: Establish a three-dimensional model of the robot based on the robot and the execution terminal corresponding to the robot;

It can be understood that the execution terminal is a device that performs inspection tasks for the robot, such as a camera, a PTZ, and the like.

S108: Import the preset robot attribute information of the robot and the execution terminal into the three-dimensional model of the robot, where the preset robot attribute information includes the actual robot material attribute and the execution terminal material attribute;

It can be understood that, after the robot and the execution terminal corresponding to the robot establish the 3D model of the robot, importing the preset robot attribute information can make the established 3D model of the robot closer to the real situation.

S109: The three-dimensional model of the robot walks in the traversable path network according to the issued inspection task, so as to obtain deployment information corresponding to the inspection task;

S110: Complete the task deployment of the robot according to the inspection task and the corresponding deployment information;

It is understandable that by importing the inspection tasks and the corresponding deployment information into the background management system set by the robot, the rapid and automatic deployment of inspection points can be completed, without the need for the robot to drive to the actual position and manually control the detection end. Deployment process.

S111: Control the robot to perform automatic inspection according to the inspection task to obtain inspection results, and establish an association relationship between the inspection results and the three-dimensional point cloud model of the scene, so as to view the inspection results in the three-dimensional point cloud model of the scene.

It should be noted that after viewing the inspection results, the user can make appropriate adjustments to the deployment information according to the actual execution of the robot, so as to complete the accurate deployment of the task.

In this embodiment, after constructing a three-dimensional point cloud model of the scene by simulating the actual inspection scene, a walkable path network of the robot is formed in the three-dimensional point cloud model of the scene, and a three-dimensional model of the robot is built with the actual robot and the corresponding execution terminal, thereby improving the performance of the robot. Task deployment accuracy.

The 3D model of the robot is controlled to walk in the walkable path network according to the inspection task. Since the inspection task has inspection instructions, the 3D model of the robot can obtain deployment information according to the inspection task, so that the robot does not need to be driven to the inspection site. The deployment information can be obtained from the corresponding location points in the system, which solves the problems of huge task deployment workload, extremely low efficiency and inaccurate deployment.

At the same time, after the task is deployed, the inspection result can be obtained when the actual robot is controlled according to the inspection task to perform automatic inspection, and the inspection result can be associated with the 3D point cloud model of the scene. The viewing method of inspection results is not limited to clicking and other methods, which facilitates information interaction between users and inspection tasks and corresponding equipment, and improves information interactivity.

The above is a detailed description of the second embodiment of a robot task deployment method provided by the present invention, and the following is a detailed description of the third embodiment of a robot task deployment method provided by the present invention.

For ease of understanding, please refer to FIG. 3 , a method for deploying a robot task provided by this application includes the following steps:

S201: Collect full-scene point cloud data and image data of the actual inspection scene of the robot;

S202: Establish a three-dimensional point cloud model of the scene based on the point cloud data and image data of the whole scene;

S203: In the scene 3D point cloud model, based on the components of the actual scene equipment, cluster and divide the whole scene point cloud data, so as to obtain the component 3D point cloud model, and then realize that the whole scene point cloud data and the scene 3D point cloud data are respectively There is a one-to-one correspondence between the point cloud model and the 3D point cloud model of the component.

S204: import corresponding preset component attribute information to the model component in the component three-dimensional point cloud model, and the preset component attribute information includes component nameplate information and corresponding inspection history data;

S205: In the three-dimensional point cloud model of the component, establish an association relationship between the model component and the corresponding preset component attribute information, so as to view the associated preset component attribute information through the model component.

It can be understood that the model component is associated with the corresponding preset component attribute information, so that the associated preset component attribute information can be viewed through the model component. In a general example, click on the model component to display the associated preset component attribute information. Set component attribute information to facilitate viewing and improve information interactivity.

S206: Establish a three-dimensional model of the robot based on the robot and the execution terminal corresponding to the robot;

S207: Import the preset robot attribute information of the robot and the execution terminal into the three-dimensional model of the robot, where the preset robot attribute information includes the actual robot material attribute and the execution terminal material attribute;

S208: Establish a three-dimensional coordinate system in the three-dimensional point cloud model of the scene;

S209: control the three-dimensional model of the robot to walk along the preset inspection route on the traversable path network according to the inspection task, so as to determine the inspection points and model components corresponding to the inspection task;

It can be understood that the inspection task has instruction information, which includes a preset inspection route, and the three-dimensional model of the robot performs inspection work along the inspection route according to the inspection task, and performs inspection at the positions that need to be inspected. The positioning detects the model parts, so as to determine the corresponding inspection points and model parts.

S210: Obtain deployment information of the inspection point corresponding to the robot according to the three-dimensional coordinate system, where the deployment information includes the coordinate value of the inspection point, the pose of the robot, and the execution angle and execution focal length of the execution terminal of the robot.

It should be noted that after determining the inspection points and model parts corresponding to the inspection tasks, since the inspection points and model parts are both in the three-dimensional coordinate system, the inspection can be determined by the coordinates of the known three-dimensional coordinate system. The coordinate value of the point and the coordinate of the model part.

According to the coordinate deviation of the three-dimensional model of the robot relative to the X-axis and the Y-axis of the three-dimensional coordinate system, the pose (orientation) of the robot can be determined.

The execution angle can be determined according to the coordinate deviation of the execution terminal (such as the PTZ) relative to the X-axis, Y-axis and Z-axis of the three-dimensional coordinate system.

The execution focal length of the execution terminal can be obtained according to the internal parameters in the execution terminal (such as a camera) and the distance of the execution terminal relative to the model component.

S211: Complete the task deployment of the robot according to the inspection task and the corresponding deployment information;

S212: Control the robot to perform automatic inspection according to the inspection task to obtain inspection results, and establish an association relationship between the inspection results and the three-dimensional point cloud model of the scene, so as to view the inspection results in the three-dimensional point cloud model of the scene.

Further, obtaining the deployment information of the inspection point corresponding to the robot according to the three-dimensional coordinate system in step S210 specifically includes:

S2101: Calculate the coordinate values of the inspection points and model components based on the three-dimensional coordinate system;

S2102: Calculate the point distance of the corresponding adjacent inspection points according to the coordinate values of the adjacent inspection points;

S2103: Compare the point distance with the preset point distance, and when the point distance is less than the preset point distance, take the corresponding adjacent inspection points as the same inspection point, so that the same inspection point The deployment information of the bit is used as the deployment information of the corresponding adjacent inspection point.

It can be understood that when the adjacent inspection points are dense and less than the preset distance, it can be regarded as one inspection point, so that the visible range of the execution terminal can also be regarded as within the same range. In this way, the task deployment work is simplified and the task deployment efficiency is improved.

The above is a detailed description of the third embodiment of a robot task deployment method provided by the present invention, and the above is a detailed description of an embodiment of a robot task deployment system provided by the present invention.

For easy understanding, please refer to FIG. 4 , a robot task deployment system provided by this application includes:

The path determination module 100 is used to determine all the walkable paths of the robot based on the pre-established three-dimensional point cloud model of the scene, thereby forming a walkable path network;

The obtaining module 101 is used for walking in the walkable path network according to the issued inspection task through the pre-established three-dimensional model of the robot, so as to obtain the deployment information corresponding to the inspection task;

The deployment module 102 is used to complete the task deployment of the robot according to the inspection task and the corresponding deployment information;

The first association module 103 is used to control the robot to perform automatic inspection according to the inspection task to obtain inspection results, and establish an association relationship between the inspection results and the pre-established scene 3D point cloud model, so that the pre-established scene 3D point cloud View inspection results in the model.

Further, the system also includes:

The acquisition module is used to collect the full scene point cloud data and image data of the actual inspection scene of the robot;

The first establishment module is used to establish a three-dimensional point cloud model of the scene based on the point cloud data and the image data of the whole scene;

The second establishment module is used to cluster and divide the point cloud data of the whole scene based on the components of the actual scene equipment in the 3D point cloud model of the scene, so as to obtain the 3D point cloud model of the component, and then realize the point cloud of the whole scene. The data is in one-to-one correspondence with the scene 3D point cloud model and the component 3D point cloud model.

Further, the system also includes:

a first import module, used for importing corresponding preset part attribute information to the model parts in the three-dimensional point cloud model of the part, where the preset part attribute information includes part nameplate information and corresponding inspection history data;

In this embodiment, the component nameplate information includes the actual component name, the actual component material properties, and the actual component setting parameters.

The second association module is used for establishing an association relationship between the model part and the corresponding preset part attribute information in the part three-dimensional point cloud model, so as to view the associated preset part attribute information through the model part.

Further, the system also includes:

The third establishment module is used to establish a three-dimensional model of the robot based on the robot and the execution terminal corresponding to the robot;

The second import module is used to import the preset robot attribute information of the robot and the execution terminal into the three-dimensional model of the robot, where the preset robot attribute information includes the actual robot material attribute and the execution terminal material attribute.

Further, the system also includes:

The fourth establishment module is used to establish a 3D coordinate system in the pre-established 3D point cloud model of the scene;

The determination module is used to control the pre-established three-dimensional model of the robot to walk along the preset inspection route on the traversable path network according to the inspection task, so as to determine the inspection point and model components corresponding to the inspection task;

The obtaining module 101 is further configured to obtain deployment information of the inspection point corresponding to the robot according to the three-dimensional coordinate system. The deployment information includes the coordinate value of the inspection point, the pose of the robot, and the execution angle and execution focal length of the execution terminal of the robot.

Further, the system also includes:

The first calculation module is used to calculate the coordinate value of the inspection point and the model component based on the three-dimensional coordinate system;

The second calculation module calculates the point distance of the corresponding adjacent inspection points according to the coordinate values of the adjacent inspection points;

The comparison module is used to compare the point distance with the preset point distance. When the point distance is less than the preset point distance, the corresponding adjacent inspection points will be regarded as the same inspection point, so that the same inspection point will be compared. The deployment information of the inspection point is used as the deployment information of the corresponding adjacent inspection point.

The present invention also provides an electronic device, comprising: a processor and a memory, the memory is used to store program instructions, and the processor is used to implement the steps of the robot task deployment method in the above embodiment when executing the computer program stored in the memory.

The present invention also provides a storage medium, which stores a computer program, and when the computer program is executed by a processor, implements the steps of the robot task deployment method in the above embodiment.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.

The integrated unit, if implemented in the form of a software functional unit and sold or used as an independent product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application can be embodied in the form of software products in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, and the computer software products are stored in a storage medium , including several instructions for executing all or part of the steps of the methods described in the various embodiments of the present application through a computer device (which may be a personal computer, a server, or a network device, etc.). The aforementioned storage media include: U disk, mobile hard disk, read-only memory (full English name: Read-Only Memory, English abbreviation: ROM), random access memory (English full name: Random Access Memory, English abbreviation: RAM), magnetic Various media that can store program codes, such as discs or optical discs.

As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand: The technical solutions recorded in the embodiments are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions in the embodiments of the present application.

Claims

A method for deploying a robot task, comprising the following steps:

Determine all walkable paths of the robot based on the pre-established 3D point cloud model of the scene, thereby forming a walkable path network;

The pre-established three-dimensional model of the robot walks in the walkable path network according to the assigned inspection task, thereby obtaining deployment information corresponding to the inspection task;

Complete the task deployment of the robot according to the inspection task and the corresponding deployment information;

Control the robot to perform automatic inspection according to the inspection task to obtain inspection results, and establish an association relationship between the inspection results and the pre-established 3D point cloud model of the scene, so that the pre-established 3D scene View the inspection results in the point cloud model.
The method for deploying a robot task according to claim 1, wherein before the determination of all walkable paths of the robot based on the pre-established three-dimensional point cloud model of the scene comprises:

Collect full-scene point cloud data and image data of the actual inspection scene of the robot;

Create a scene 3D point cloud model based on the full scene point cloud data and the image data;

In the scene 3D point cloud model, based on the components of the actual scene equipment, the whole scene point cloud data is clustered and divided, so as to obtain the component 3D point cloud model, and then realize the whole scene point cloud data. There is a one-to-one correspondence with the three-dimensional point cloud model of the scene and the three-dimensional point cloud model of the component.
The robot task deployment method according to claim 2, characterized in that, in the obtaining of the three-dimensional point cloud model of the component, the point cloud data of the whole scene are further combined with the three-dimensional point cloud model of the scene and the three-dimensional point cloud of the component, respectively. After one-to-one correspondence, the cloud models include:

importing corresponding preset component attribute information into the model component in the three-dimensional point cloud model of the component, where the preset component attribute information includes component nameplate information and corresponding inspection history data;

In the three-dimensional point cloud model of the component, an association relationship between the model component and the corresponding preset component attribute information is established, so that the associated preset component attribute information can be viewed through the model component.
The robot task deployment method according to claim 3, wherein the part nameplate information includes an actual part name, an actual part material property, and an actual part setting parameter.
The method for deploying a robot task according to claim 1, wherein the step of using a pre-established three-dimensional model of the robot to walk in the walkable path network according to the issued inspection task includes:

Building a three-dimensional model of the robot based on the robot and the execution terminal corresponding to the robot;

Importing preset robot attribute information of the robot and the execution terminal into the three-dimensional model of the robot, where the preset robot attribute information includes actual robot material attributes and execution terminal material attributes.
The method for deploying a robot task according to claim 3, wherein the robot walks in the traversable path network according to the inspection task issued by the pre-established three-dimensional model of the robot, so as to obtain the inspection task corresponding to the inspection task. The corresponding deployment information specifically includes:

Establishing a three-dimensional coordinate system on the pre-established three-dimensional point cloud model of the scene;

According to the inspection task, control the pre-established three-dimensional robot model to walk along the preset inspection route on the walkable path network, so as to determine the inspection point corresponding to the inspection task and the model component;

The deployment information of the inspection point corresponding to the robot is obtained according to the three-dimensional coordinate system, and the deployment information includes the coordinate value of the inspection point, the pose of the robot, and the execution of the execution terminal of the robot. angle and execution focal length.
The robot task deployment method according to claim 6, wherein the obtaining the deployment information of the inspection point corresponding to the robot according to the three-dimensional coordinate system specifically includes:

Calculate the coordinate value of the inspection point and the model component based on the three-dimensional coordinate system;

Calculate the point distance of the corresponding adjacent inspection points according to the coordinate values of the adjacent inspection points;

Comparing the point distance with the preset point distance, when the point distance is less than the preset point distance, the corresponding adjacent inspection points are regarded as the same inspection point, Therefore, the deployment information of the same inspection point is used as the deployment information of the corresponding adjacent inspection point.
A robot task deployment system, comprising:

The path determination module is used to determine all walkable paths of the robot based on the pre-established 3D point cloud model of the scene, thereby forming a walkable path network;

an acquisition module, configured to walk in the walkable path network according to the issued inspection task through a pre-established three-dimensional model of the robot, so as to obtain deployment information corresponding to the inspection task;

a deployment module, configured to complete the task deployment of the robot according to the inspection task and the corresponding deployment information;

The first association module is used to control the robot to perform automatic inspection according to the inspection task to obtain inspection results, and establish an association relationship between the inspection results and the pre-established three-dimensional point cloud model of the scene, so as to obtain the inspection results. Check the inspection result in the pre-established three-dimensional point cloud model of the scene.
An electronic device, comprising: a processor and a memory, the memory is used for storing program instructions, and the processor is used for implementing any one of claims 1-7 when executing the computer program stored in the memory The steps of the robot task deployment method described in item.
A storage medium, characterized in that it stores a computer program, and when the computer program is executed by a processor, implements the steps of the method for deploying a robot task according to any one of claims 1 to 7 .