Robot path planning method, system and equipment based on industrial Internet of Things

Abstract

The invention discloses a robot path planning method, system and device based on the industrial Internet of Things, and relates to the technical field of the industrial Internet of Things, and the method comprises the steps: obtaining a current carrying task of a robot, and determining to-be-carried information corresponding to a to-be-carried object according to the current carrying task; determining whether the contents are fluid or not according to the to-be-carried information, and if yes, determining a first safety gradient according to the container information and the content information; acquiring placement part information corresponding to a placement part of the robot, and determining a second safety gradient according to the placement part information, the container information and the content information; and acquiring a grid map, determining a grid slope value corresponding to each non-edge grid according to the grid map, and generating a carrying path according to the grid slope value, the first safety slope and the second safety slope. The method has the effect of improving the intelligent level of robot carrying.

Description

Technical Field

[0001] The present application relates to the technical field of industrial Internet of Things, and in particular to a robot path planning method, system, and device based on the industrial Internet of Things. Background Art

[0002] In the current industrial environment, robotic handling technology has been widely used in many fields such as manufacturing, logistics and warehousing. With the accelerated development of automation and informatization, robotic systems are gradually being used to carry a variety of items, including packaging boxes, pallets, parts and finished products. These robots not only excel in improving efficiency and reducing labor costs, but also improve production flexibility through precise control and continuous operation. Many modern robotic devices combine advanced sensors, machine vision and artificial intelligence algorithms to enable them to adaptively cope with various complex working environments. Through real-time data processing and path planning, robots can effectively identify obstacles, optimize handling routes, and achieve autonomous handling.

[0003] Although certain achievements have been made in algorithms and technologies in recent years, the overall level of intelligence in robot handling is still relatively low. Existing systems often lack the ability to respond flexibly when dealing with complex and dynamic environments and different types of objects to be handled. They usually rely on preset rules and paths, making it difficult to make intelligent decisions and effectively adapt. This means that robots still require manual intervention and monitoring when handling a variety of objects, which limits their potential for application in efficient automated production and complex logistics systems. Therefore, improving the level of intelligence in robot handling remains an important direction for future development. Summary of the invention

[0004] In order to improve the intelligence level of robot handling, the present application provides a robot path planning method, system, and device based on the industrial Internet of Things.

[0005] In the first aspect, the present application provides a robot path planning method based on the industrial Internet of Things, which adopts the following technical solutions:

[0006] A robot path planning method based on industrial Internet of Things is applied to an industrial Internet of Things system, wherein the industrial Internet of Things system includes a management platform, a sensor network platform and an object platform which are sequentially connected in communication. The method is executed by the management platform and includes:

[0007] Acquire the current handling task of the robot, and determine the to-be-handled information corresponding to the to-be-handled object according to the current handling task; the to-be-handled object includes a container and the contents in the container;

[0008] Determine whether the content is a fluid according to the information to be transported, and if so, obtain container information corresponding to the container and content information corresponding to the content, and determine a first safety slope according to the container information and the content information;

[0009] Acquire placement part information corresponding to the placement part of the robot, and determine a second safety slope according to the placement part information, the container information and the content information;

[0010] A grid map is obtained, and grid slope values ​​corresponding to each non-edge grid are determined according to the grid map, and a transport path is generated according to the grid slope values, the first safety slope, and the second safety slope.

[0011] By adopting the above technical solution, the current handling task of the robot is first obtained, and the to-be-handled information corresponding to the to-be-handled object is determined according to the current handling task, the to-be-handled object includes a container and the contents in the container, and then whether the contents are fluids is determined according to the to-be-handled information. If the contents are fluids, the container information corresponding to the container and the contents information corresponding to the contents are obtained, and a first safety slope is determined according to the container information and the contents information, and then the placement part information corresponding to the placement part of the robot is obtained, and a second safety slope is determined according to the placement part information, the container information and the contents information, and then the grid map is obtained, and the grid slope value corresponding to each non-edge grid is determined according to the grid map, and a handling path is generated according to the grid slope value, the first safety slope and the second safety slope; through the above method, when the object to be handled is a container and the contents in the container, it is possible to effectively avoid overflow of the contents and avoid sliding of the container, thereby rationally planning the handling path, improving the safety of the handling process, and improving the intelligence level of robot handling.

[0012] Optionally, the step of determining a first safety slope according to the container information and the content information includes:

[0013] Acquire a container type and a container height corresponding to the container according to the container information, and acquire a content volume and a content type corresponding to the content according to the content information;

[0014] Acquire historical fluid filling data corresponding to the container according to the container type, the historical fluid filling data including historical fluid volume data and historical fluid height data, and generate a fluid height calculation model according to the historical fluid filling data;

[0015] Inputting the content volume into the fluid height calculation model to obtain the content height in the container;

[0016] A first safety slope is determined according to the type of the container, the type of the contents, the height of the container, and the height of the contents.

[0017] By adopting the above technical scheme, in order to determine the first safety slope, first, the container type and container height corresponding to the container are obtained according to the container information, and the content volume and content type corresponding to the content are obtained according to the content information, and then the historical fluid filling data corresponding to the container is obtained according to the container type, and the historical fluid filling data includes historical fluid volume data and historical fluid height data, and a fluid height calculation model is generated according to the historical fluid filling data, and then the content volume is input into the fluid height calculation model to obtain the content height in the container, and finally the first safety slope is determined according to the container type, content type, container height and content height.

[0018] Optionally, the step of determining the first safety slope according to the type of the container, the type of the contents, the height of the container and the height of the contents includes:

[0019] Determine a corresponding height difference according to the height of the container and the height of the contents;

[0020] Matching the container type and the content type in a preset table to obtain a target safety slope calculation model; the first preset table includes different container types, different content types and safety slope calculation models, and the first preset table is used to represent the mapping relationship between the different container types, the different content types and the safety slope calculation model;

[0021] The height difference is input into the target safety slope calculation model to obtain a first safety slope.

[0022] By adopting the above technical solution, in order to determine the first safety slope, the corresponding height difference is first determined according to the container height and the content height, and then the container type and the content type are matched in a preset table to obtain a target safety slope calculation model. The first preset table includes different types of containers, different types of contents and a safety slope calculation model. The first preset table is used to represent the mapping relationship between different types of containers, different types of contents and the safety slope calculation model, and then the height difference is input into the target safety slope calculation model to obtain the first safety slope.

[0023] Optionally, the step of generating a fluid height calculation model according to the historical fluid filling data includes:

[0024] Cleaning the historical fluid filling data according to the historical fluid filling data to obtain corresponding cleaned data;

[0025] Performing feature engineering processing on the cleaned data according to the cleaned data to obtain corresponding model feature data;

[0026] Based on a K-fold cross-validation method, the model feature data is randomly divided into K data portions, where K is a positive integer, and a pre-selected neural network model is trained according to the K data portions to obtain K trained neural network models;

[0027] The model evaluation indicators corresponding to the K trained neural network models are obtained, wherein the model evaluation indicators include a model complexity indicator, a model interpretability indicator, a training set performance indicator, and a validation set performance indicator, and a target model is selected from the K trained neural network models according to the model evaluation indicators, and the target model is used as a fluid height calculation model.

[0028] By adopting the above technical scheme, in order to generate a fluid height calculation model, the historical fluid filling data is cleaned according to the historical fluid filling data to obtain the corresponding cleaned data, and then the cleaned data is feature engineered according to the cleaned data to obtain the corresponding model feature data, and then the model feature data is randomly divided into K portions of data based on the K-fold cross-validation method, K is a positive integer, and a pre-selected neural network model is trained according to the K portions of data to obtain K trained neural network models, and then the model evaluation indicators corresponding to the K trained neural network models are obtained, and the target model is selected from the K trained neural network models according to the model evaluation indicators, and the target model is used as the fluid height calculation model.

[0029] Optionally, the step of determining the second safety slope according to the placement portion information, the container information and the content information includes:

[0030] Acquire a first material type corresponding to the placement portion according to the placement portion information, acquire a second material type and a container weight corresponding to the container according to the container information, and acquire a content density corresponding to the content according to the content information;

[0031] determining a friction coefficient between an upper surface of the placement portion and a lower surface of the container according to the first material type and the second material type, and determining a content weight corresponding to the content according to the density of the content and the volume of the content;

[0032] A second safety slope is determined according to the friction coefficient and the weight of the contents.

[0033] By adopting the above technical solution, in order to determine the second safety slope, the first material type corresponding to the placement part is first obtained according to the placement part information, and the second material type and container weight corresponding to the container are obtained according to the container information, and the content density corresponding to the content is obtained according to the content information, and then the friction coefficient between the upper surface of the placement part and the lower surface of the container is determined according to the first material type and the second material type, and the content weight corresponding to the content is determined according to the content density and the content volume, and finally the second safety slope is determined according to the friction coefficient and the content weight.

[0034] Optionally, the step of determining the grid slope value corresponding to each non-edge grid according to the grid map includes:

[0035] For each non-edge grid in the grid map, coordinate data of a target grid and elevation data corresponding to the target grid are obtained; the target grid includes the non-edge grid and an adjacent grid, and the adjacent grid is a grid adjacent to the non-edge grid;

[0036] The elevation change value of the non-edge grid is determined according to a preset formula, the coordinate data and the elevation data; the adjacent grid includes an edge adjacent grid and a corner adjacent grid, and the preset formula is: d=w1*(|Z[i-1][j-1]-Z[i][j]|)+w2*(|Z[i-1][j]-Z[i][j]|)+w1

[0037] *(|Z[i-1][j+1]-Z[i][j]|)+w1*(|Z[i][j+1]-Z[i][j]|)+w2

[0038] *(|Z[i+1][j-1]-Z[i][j]|)+w2*(|Z[i+1][j+1]-Z[i][j]|)

[0039] Wherein, (i, j) is the coordinate of the non-edge grid, d represents the elevation change value of the non-edge grid, Z represents the elevation of the grid, w1 represents the first weight corresponding to the corner adjacent grid, and w2 represents the second weight corresponding to the edge adjacent grid;

[0040] The spatial resolution of the grid is obtained, and the grid slope value corresponding to the non-edge grid is determined according to the spatial resolution and the elevation change value.

[0041] By adopting the above technical scheme, in order to determine the grid slope value corresponding to each non-edge grid, for each non-edge grid in the grid map, the coordinate data of the target grid and the elevation data corresponding to the target grid are obtained, the target grid includes the non-edge grid and the adjacent grid, the adjacent grid is the grid adjacent to the non-edge grid, and then the elevation change value of the non-edge grid is determined according to the preset formula, coordinate data and elevation data, the adjacent grid includes the edge adjacent grid and the corner adjacent grid, and then the spatial resolution of the grid is obtained, and the grid slope value corresponding to the non-edge grid is determined according to the spatial resolution and the elevation change value.

[0042] Optionally, the step of generating a transport path according to the grid slope value, the first safety slope and the second safety slope includes:

[0043] Determine a minimum value between the first safety slope and the second safety slope according to the first safety slope and the second safety slope, and use the minimum value as a final safety slope;

[0044] Determine a grid safety representative value corresponding to each non-edge grid according to the grid slope value and the final safety slope;

[0045] Based on a preset path planning algorithm, a transport path is generated according to the grid safety representative value.

[0046] By adopting the above technical solution, in order to generate a transport path, the minimum value of the first safety slope and the second safety slope is first determined based on the first safety slope and the second safety slope, and the minimum value is used as the final safety slope. Then, the grid safety representative value corresponding to each non-edge grid is determined based on the grid slope value and the final safety slope. Finally, based on a pre-set path planning algorithm, a transport path is generated according to the grid safety representative value.

[0047] In the second aspect, the present application also provides a robot path planning system based on the industrial Internet of Things, which adopts the following technical solutions:

[0048] A robot path planning system based on the industrial Internet of Things includes a management platform, a sensor network platform and an object platform that are sequentially connected in communication, wherein the management platform is configured with:

[0049] The module for acquiring information about objects to be transported is used to acquire the current transport task of the robot and determine the information about objects to be transported corresponding to the objects to be transported according to the current transport task; the objects to be transported include containers and the contents in the containers;

[0050] A first safety slope determination module, used to determine whether the content is a fluid according to the to-be-carried information, and if so, obtain container information corresponding to the container and content information corresponding to the content, and determine a first safety slope according to the container information and the content information;

[0051] a second safety slope determination module, configured to obtain placement part information corresponding to the placement part of the robot, and determine a second safety slope according to the placement part information, the container information and the content information;

[0052] The transport path generation module is used to obtain a grid map, determine the grid slope value corresponding to each non-edge grid according to the grid map, and generate a transport path according to the grid slope value, the first safety slope and the second safety slope.

[0053] The transport path generation module comprises:

[0054] The elevation data acquisition submodule is used to acquire the coordinate data of the target grid and the elevation data corresponding to the target grid for each non-edge grid in the grid map; the target grid includes the non-edge grid and an adjacent grid, and the adjacent grid is a grid adjacent to the non-edge grid;

[0055] The elevation change value generating submodule is used to determine the elevation change value of the non-edge grid according to a preset formula, the coordinate data and the elevation data; the adjacent grid includes an edge adjacent grid and a corner adjacent grid, and the preset formula is:

[0056] d=w1*(|Z[i-1][j-1]-Z[i][j]|)+w2*(|Z[i-1][j]-Z[i][j]|)+w1

[0057] *(|Z[i-1][j+1]-Z[i][j]|)+w1*(|Z[i][j+1]-Z[i][j]|)+w2

[0058] *(|Z[i+1][j-1]-Z[i][j]|)+w2*(|Z[i+1][j+1]-Z[i][j]|)

[0059] Wherein, (i, j) is the coordinate of the non-edge grid, d represents the elevation change value of the non-edge grid, Z represents the elevation of the grid, w1 represents the first weight corresponding to the corner adjacent grid, and w2 represents the second weight corresponding to the edge adjacent grid;

[0060] The elevation change value generating submodule is used to obtain the spatial resolution of the grid, and determine the grid slope value corresponding to the non-edge grid according to the spatial resolution and the elevation change value.

[0061] In a third aspect, the present application also provides a computer device, which adopts the following technical solution:

[0062] A computer device comprises a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor implements the method described in the first aspect when executing the computer program.

[0063] In summary, the present application includes at least the following beneficial technical effects: first, the current handling task of the robot is obtained, and the to-be-handled information corresponding to the object to be handled is determined according to the current handling task, the object to be handled includes a container and the contents in the container, and then, according to the to-be-handled information, whether the contents are fluid is determined, if the contents are fluid, the container information corresponding to the container and the contents information corresponding to the contents are obtained, and a first safety slope is determined according to the container information and the contents information, and then the placement part information corresponding to the placement part of the robot is obtained, and a second safety slope is determined according to the placement part information, the container information and the contents information, and then a grid map is obtained, and the grid slope value corresponding to each non-edge grid is determined according to the grid map, and a handling path is generated according to the grid slope value, the first safety slope and the second safety slope; through the above method, when the object to be handled is a container and the contents in the container, it can effectively avoid overflow of the contents and avoid sliding of the container, thereby rationally planning the handling path, improving the safety of the handling process, and improving the intelligence level of robot handling. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is a schematic diagram of the overall process of an embodiment of the present application.

[0065] Figure 2 It is a structural diagram of one application scenario of the system of an embodiment of the present application.

[0066] Figure 3 It is a structural diagram of another application scenario of the system of an embodiment of the present application.

[0067] Figure 4 It is a structural block diagram of the computer device of the present application. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solutions and advantages of this application more clear, the following Figure 1-4 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.

[0069] The embodiment of the present application discloses a robot path planning method based on industrial Internet of Things.

[0070] Reference Figure 1 A robot path planning method based on industrial Internet of Things is applied to an industrial Internet of Things system. The industrial Internet of Things system includes a management platform, a sensor network platform and an object platform that are sequentially connected in communication. The method is executed by the management platform and includes:

[0071] Step S11, obtaining the current transport task of the robot, and determining the to-be-transported information corresponding to the to-be-transported object according to the current transport task.

[0072] The objects to be transported include containers and the contents in the containers.

[0073] Step S12, determining whether the contents are fluids according to the information to be transported, and if so, obtaining container information corresponding to the container and content information corresponding to the contents, and determining a first safety slope according to the container information and the content information.

[0074] Specifically, determine whether the contents are fluid based on the information to be transported. If the contents are fluid, obtain container information corresponding to the container and content information corresponding to the contents, and determine the first safety slope based on the container information and content information. If the contents are not fluid, set the first safety slope to 90 degrees.

[0075] It is understandable that during the transportation process, the type of the transported object may be solid or fluid (such as liquid). Since the transportation process is carried out within the factory and in order to improve the subsequent processing efficiency of the transported object, the container will not be sealed during the transportation process; in addition, some solid particles with flow properties can also be regarded as fluids.

[0076] Step S13, obtaining placement part information corresponding to the placement part of the robot, and determining a second safety slope according to the placement part information, container information and content information.

[0077] Step S14, obtaining a grid map, and determining the grid slope value corresponding to each non-edge grid according to the grid map, and generating a transport path according to the grid slope value, the first safety slope and the second safety slope.

[0078] In the above embodiment, the current handling task of the robot is first obtained, and the to-be-handled information corresponding to the to-be-handled object is determined according to the current handling task, the to-be-handled object includes a container and the contents in the container, and then it is determined whether the contents are fluids according to the to-be-handled information. If the contents are fluids, the container information corresponding to the container and the contents information corresponding to the contents are obtained, and a first safety slope is determined according to the container information and the contents information, and then the placement part information corresponding to the placement part of the robot is obtained, and a second safety slope is determined according to the placement part information, the container information and the contents information, and then the grid map is obtained, and the grid slope value corresponding to each non-edge grid is determined according to the grid map, and a handling path is generated according to the grid slope value, the first safety slope and the second safety slope; through the above method, when the object to be handled is a container and the contents in the container, it is possible to effectively avoid overflow of the contents and avoid sliding of the container, thereby rationally planning the handling path, improving the safety of the handling process, and improving the intelligence level of robot handling.

[0079] As a further implementation of the path planning system, the step of determining the first safety slope according to the container information and the content information includes:

[0080] Step S21, obtaining the container type and container height corresponding to the container according to the container information, and obtaining the content volume and content type corresponding to the content according to the content information.

[0081] Step S22, obtaining historical fluid filling data corresponding to the container according to the container type, the historical fluid filling data including historical fluid volume data and historical fluid height data, and generating a fluid height calculation model according to the historical fluid filling data.

[0082] Step S23, inputting the content volume into the fluid height calculation model to obtain the content height in the container.

[0083] Step S24, determining a first safety slope according to the type of container, the type of contents, the height of the container and the height of the contents.

[0084] In the above embodiment, in order to determine the first safety slope, the container type and container height corresponding to the container are first obtained based on the container information, and the content volume and content type corresponding to the content are obtained based on the content information. Then, the historical fluid filling data corresponding to the container is obtained based on the container type, and the historical fluid filling data includes historical fluid volume data and historical fluid height data. A fluid height calculation model is generated based on the historical fluid filling data, and then the content volume is input into the fluid height calculation model to obtain the content height in the container. Finally, the first safety slope is determined based on the container type, content type, container height and content height.

[0085] As a further implementation of the path planning system, the step of determining the first safety slope according to the type of container, the type of contents, the height of the container and the height of the contents includes:

[0086] Step S31, determining the corresponding height difference according to the container height and the content height.

[0087] Step S32, matching the container type and the content type in a preset table to obtain a target safety slope calculation model.

[0088] Among them, the first preset table includes different types of containers, different types of contents and safety slope calculation models, and the first preset table is used to represent the mapping relationship between different types of containers, different types of contents and safety slope calculation models.

[0089] Step S33, inputting the height difference into a target safety slope calculation model to obtain a first safety slope.

[0090] In the above embodiment, in order to determine the first safety slope, the corresponding height difference is first determined according to the container height and the content height, and then the container type and the content type are matched in a preset table to obtain a target safety slope calculation model. The first preset table includes different types of containers, different types of contents and a safety slope calculation model. The first preset table is used to represent the mapping relationship between different types of containers, different types of contents and the safety slope calculation model, and then the height difference is input into the target safety slope calculation model to obtain the first safety slope.

[0091] As a further implementation of the path planning system, the step of generating a fluid height calculation model according to historical fluid filling data includes:

[0092] Step S41, cleaning the historical fluid filling data according to the historical fluid filling data to obtain corresponding cleaning data.

[0093] Step S42, performing feature engineering processing on the cleaned data according to the cleaned data to obtain corresponding model feature data.

[0094] Step S43, based on the K-fold cross-validation method, the model feature data is randomly divided into K data portions, K is a positive integer, and the pre-selected neural network model is trained according to the K data portions to obtain K trained neural network models.

[0095] Step S44, obtaining model evaluation indicators corresponding to the K trained neural network models, the model evaluation indicators including model complexity indicators, model explanatory indicators, training set performance indicators and validation set performance indicators, and selecting a target model from the K trained neural network models according to the model evaluation indicators, and using the target model as the fluid height calculation model.

[0096] In the above embodiment, in order to generate a fluid height calculation model, the historical fluid filling data is cleaned according to the historical fluid filling data to obtain the corresponding cleaned data, and then the cleaned data is feature engineered according to the cleaned data to obtain the corresponding model feature data, and then the model feature data is randomly divided into K portions of data based on the K-fold cross-validation method, K is a positive integer, and a pre-selected neural network model is trained according to the K portions of data to obtain K trained neural network models, and then the model evaluation indicators corresponding to the K trained neural network models are obtained, and the target model is selected from the K trained neural network models according to the model evaluation indicators, and the target model is used as the fluid height calculation model.

[0097] As a further implementation of the path planning system, the step of determining the second safety slope according to the placement unit information, the container information and the content information includes:

[0098] Step S51, obtaining a first material type corresponding to the placement portion according to the placement portion information, obtaining a second material type and a container weight corresponding to the container according to the container information, and obtaining a content density corresponding to the content according to the content information.

[0099] Step S52, determining the friction coefficient between the upper surface of the placement portion and the lower surface of the container according to the first material type and the second material type, and determining the content weight corresponding to the content according to the content density and the content volume.

[0100] It should be noted that the chemical composition of the material determines the size of its friction coefficient. Different types of materials have different surface microstructures and compositions, so the friction process and wear will also be different, resulting in differences in the friction coefficient. In this embodiment, the upper surface of the placement portion and the lower surface of the container are both roughened, so the friction coefficient is closely related to the type of material. If the upper surface of the placement portion and the lower surface of the container are roughened, then in step S51, the roughness corresponding to the upper surface of the placement portion and the lower surface of the container also needs to be considered.

[0101] Step S53, determining a second safety slope according to the friction coefficient and the weight of the contents.

[0102] It can be understood that if the friction coefficient is μ, then the second safety slope is arctan(μ).

[0103] In the above embodiment, in order to determine the second safety slope, the first material type corresponding to the placement portion is first obtained according to the placement portion information, and the second material type and container weight corresponding to the container are obtained according to the container information, and the content density corresponding to the content is obtained according to the content information, and then the friction coefficient between the upper surface of the placement portion and the lower surface of the container is determined according to the first material type and the second material type, and the content weight corresponding to the content is determined according to the content density and the content volume, and finally the second safety slope is determined according to the friction coefficient and the content weight.

[0104] As a further implementation of the path planning system, the step of determining the grid slope value corresponding to each non-edge grid according to the grid map includes:

[0105] Step S61: for each non-edge grid in the grid map, obtain the coordinate data of the target grid and the elevation data corresponding to the target grid.

[0106] The target grid includes a non-edge grid and an adjacent grid, and the adjacent grid is a grid adjacent to the non-edge grid.

[0107] Step S62, determining the elevation change value of the non-edge grid according to a preset formula, coordinate data and elevation data.

[0108] Among them, the adjacent grid includes the edge adjacent grid and the corner adjacent grid, and the preset formula is:

[0109] d=w1*(|Z[i-1][j-1]-Z[i][j]|)+w2*(|Z[i-1][j]-Z[i][j]|)+w1

[0110] *(|Z[i-1][j+1]-Z[i][j]|)+w1*(|Z[i][j+1]-Z[i][j]|)+w2

[0111] *(|Z[i+1][j-1]-Z[i][j]|)+w2*(|Z[i+1][j+1]-Z[i][j]|)

[0112] (i, j) is the coordinate of the non-edge grid, d represents the elevation change value of the non-edge grid, Z represents the elevation of the grid, w1 represents the first weight corresponding to the corner adjacent grid, and w2 represents the second weight corresponding to the edge adjacent grid;

[0113] Step S63, obtaining the spatial resolution of the grid, and determining the grid slope value corresponding to the non-edge grid according to the spatial resolution and the elevation change value.

[0114] It should be noted that the grid resolution (also called spatial resolution) is a parameter used to describe the actual physical distance represented by each grid cell in the grid dataset in the geographic space; if the spatial resolution of the grid is x*y, the calculation formula for the grid slope value can be:

[0115]

[0116] Where S represents the slope.

[0117] In the above embodiment, in order to determine the grid slope value corresponding to each non-edge grid, for each non-edge grid in the grid map, the coordinate data of the target grid and the elevation data corresponding to the target grid are obtained, the target grid includes the non-edge grid and the adjacent grid, the adjacent grid is the grid adjacent to the non-edge grid, and then the elevation change value of the non-edge grid is determined according to the preset formula, coordinate data and elevation data, the adjacent grid includes the edge adjacent grid and the corner adjacent grid, and then the spatial resolution of the grid is obtained, and the grid slope value corresponding to the non-edge grid is determined according to the spatial resolution and the elevation change value.

[0118] As a further implementation of the path planning system, the step of generating a transport path according to the grid slope value, the first safety slope and the second safety slope includes:

[0119] Step S71, determining the minimum value of the first safety slope and the second safety slope according to the first safety slope and the second safety slope, and taking the minimum value as the final safety slope.

[0120] Step S72, determining the grid safety representative value corresponding to each non-edge grid according to the grid slope value and the final safety slope.

[0121] Step S73, based on a preset path planning algorithm and according to the grid safety representative value, a transport path is generated.

[0122] It is understandable that the path planning algorithm is an algorithm used to calculate the best path from the starting point to the end point. It is often used in robots, self-driving vehicles, spacecraft, and other systems that require autonomous navigation. According to different application scenarios and requirements, the path planning algorithm can have a variety of different implementation methods. Common path planning algorithms include Dijkstra algorithm, A* algorithm, RRT (fast random tree, genetic algorithm, etc.

[0123] In the above embodiment, in order to generate a transport path, the minimum value of the first safety slope and the second safety slope is first determined based on the first safety slope and the second safety slope, and the minimum value is used as the final safety slope. Then, the grid safety representative value corresponding to each non-edge grid is determined based on the grid slope value and the final safety slope. Finally, based on a pre-set path planning algorithm, a transport path is generated according to the grid safety representative value.

[0124] The embodiment of the present application also discloses a robot path planning system based on the industrial Internet of Things.

[0125] refer to Figure 2 The robot path planning system based on the industrial Internet of Things includes a management platform, a sensor network platform and an object platform which are sequentially connected in communication. The management platform is configured with:

[0126] The to-be-carried information acquisition module is used to acquire the current transport task of the robot and determine the to-be-carried information corresponding to the to-be-carried object according to the current transport task; the to-be-carried object includes a container and the contents in the container;

[0127] A first safety slope determination module, used to determine whether the contents are fluids according to the information to be transported, and if so, obtain container information corresponding to the container and content information corresponding to the contents, and determine a first safety slope according to the container information and the content information;

[0128] A second safety slope determination module, used to obtain placement part information corresponding to the placement part of the robot, and determine a second safety slope according to the placement part information, container information and content information;

[0129] The transport path generation module is used to obtain a grid map, determine the grid slope value corresponding to each non-edge grid according to the grid map, and generate a transport path according to the grid slope value, the first safety slope and the second safety slope.

[0130] The transport path generation module includes:

[0131] The elevation data acquisition submodule is used to acquire the coordinate data of the target grid and the elevation data corresponding to the target grid for each non-edge grid in the grid map; the target grid includes the non-edge grid and the adjacent grid, and the adjacent grid is the grid adjacent to the non-edge grid;

[0132] The elevation change value generation submodule is used to determine the elevation change value of the non-edge grid according to the preset formula, coordinate data and elevation data; the adjacent grid includes the edge adjacent grid and the corner adjacent grid, and the preset formula is:

[0133] d=w1*(|Z[i-1][j-1]-Z[i][j]|)+w2*(|Z[i-1][j]-Z[i][j]|)+w1

[0134] *(|Z[i-1][j+1]-Z[i][j]|)+w1*(|Z[i][j+1]-Z[i][j]|)+w2

[0135] *(|Z[i+1][j-1]-Z[i][j]|)+w2*(|Z[i+1][j+1]-Z[i][j]|)

[0136] Where (i, j) is the coordinate of the non-edge grid, d represents the elevation change value of the non-edge grid, Z represents the elevation of the grid, w1 represents the first weight corresponding to the corner adjacent grid, and w2 represents the second weight corresponding to the edge adjacent grid;

[0137] The elevation change value generation submodule is used to obtain the spatial resolution of the grid and determine the grid slope value corresponding to the non-edge grid according to the spatial resolution and the elevation change value.

[0138] The overall framework of another application scenario of the robot path planning system based on industrial Internet of Things of this application is as follows: Figure 3 As shown, it may include a user platform, a service platform, a management platform, a sensor network platform and an object platform that interact in sequence, forming a five-platform architecture based on the industrial Internet of Things. Among them, the management platform includes a module for obtaining information to be transported, a module for determining the first safety slope, a module for determining the second safety slope and a module for generating a transport path; the service platform includes a service general database, n service sub-platforms and n service sub-databases, each service sub-platform can communicate with the corresponding service sub-database, and each service sub-database can communicate with the service general database; the sensor network platform includes n sensor network sub-platforms, and each sensor network sub-platform is generally provided with a sensor sub-database.

[0139] Specifically, in another application scenario mentioned above, the robot path planning system based on the industrial Internet of Things includes a management platform, which is configured to: obtain the current handling task of the robot, and determine the to-be-handled information corresponding to the object to be handled based on the current handling task; the object to be handled includes a container and the contents in the container; determine whether the contents are fluid based on the to-be-handled information, and if so, obtain the container information corresponding to the container and the contents information corresponding to the contents, and determine the first safety slope based on the container information and the contents information; obtain the placement part information corresponding to the placement part of the robot, and determine the second safety slope based on the placement part information, the container information and the contents information; obtain the grid map, and determine the grid slope value corresponding to each non-edge grid based on the grid map, and generate a handling path based on the grid slope value, the first safety slope and the second safety slope.

[0140] Through the interaction between the various functional platforms of the robot path planning system based on the industrial Internet of Things based on the above three platforms or five platforms, a complete closed-loop information operation logic is established, ensuring the orderly operation of perception information and control information and realizing intelligent equipment management.

[0141] The robot path planning system based on industrial Internet of Things of the present invention can implement any one of the robot path planning methods based on industrial Internet of Things, and the specific working process of the robot path planning system based on industrial Internet of Things of the present invention can refer to the corresponding process in the above-mentioned robot path planning method based on industrial Internet of Things.

[0142] The embodiment of the present application also discloses a computer device.

[0143] refer to Figure 3 A computer device includes a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, any of the above-mentioned robot path planning methods based on the industrial Internet of Things is implemented.

[0144] The above are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Any feature disclosed in this specification (including the abstract and drawings), unless otherwise stated, can be replaced by other equivalent or alternative features with similar purposes. That is, unless otherwise stated, each feature is only an example of a series of equivalent or similar features.

Claims

1. A robot path planning method based on industrial Internet of Things, characterized in that: Applied to an industrial Internet of Things system, the industrial Internet of Things system includes a management platform, a sensor network platform and an object platform that are sequentially communicatively connected, and the method is executed by the management platform, including: Acquire the current handling task of the robot, and determine the to-be-handled information corresponding to the to-be-handled object according to the current handling task; the to-be-handled object includes a container and the contents in the container; Determine whether the content is a fluid according to the information to be transported, and if so, obtain container information corresponding to the container and content information corresponding to the content, and determine a first safety slope according to the container information and the content information; Acquire placement part information corresponding to the placement part of the robot, and determine a second safety slope according to the placement part information, the container information and the content information; A grid map is obtained, and grid slope values ​​corresponding to each non-edge grid are determined according to the grid map, and a transport path is generated according to the grid slope values, the first safety slope, and the second safety slope.

2. The robot path planning method based on industrial Internet of Things according to claim 1 is characterized in that: The step of determining the first safety slope according to the container information and the content information comprises: Acquire a container type and a container height corresponding to the container according to the container information, and acquire a content volume and a content type corresponding to the content according to the content information; Acquire historical fluid filling data corresponding to the container according to the container type, the historical fluid filling data including historical fluid volume data and historical fluid height data, and generate a fluid height calculation model according to the historical fluid filling data; Inputting the content volume into the fluid height calculation model to obtain the content height in the container; A first safety slope is determined according to the type of the container, the type of the contents, the height of the container, and the height of the contents.

3. The robot path planning method based on industrial Internet of Things according to claim 2 is characterized in that: The step of determining the first safety slope according to the type of the container, the type of the contents, the height of the container and the height of the contents comprises: Determine a corresponding height difference according to the height of the container and the height of the contents; Matching the container type and the content type in a preset table to obtain a target safety slope calculation model; the first preset table includes different container types, different content types and safety slope calculation models, and the first preset table is used to represent the mapping relationship between the different container types, the different content types and the safety slope calculation model; The height difference is input into the target safety slope calculation model to obtain a first safety slope.

4. The robot path planning method based on industrial Internet of Things according to claim 1 is characterized in that: The step of generating a fluid height calculation model according to the historical fluid filling data comprises: Cleaning the historical fluid filling data according to the historical fluid filling data to obtain corresponding cleaned data; Performing feature engineering processing on the cleaned data according to the cleaned data to obtain corresponding model feature data; Based on a K-fold cross-validation method, the model feature data is randomly divided into K data portions, where K is a positive integer, and a pre-selected neural network model is trained according to the K data portions to obtain K trained neural network models; The model evaluation indicators corresponding to the K trained neural network models are obtained, wherein the model evaluation indicators include a model complexity indicator, a model interpretability indicator, a training set performance indicator, and a validation set performance indicator, and a target model is selected from the K trained neural network models according to the model evaluation indicators, and the target model is used as a fluid height calculation model.

5. The robot path planning method based on industrial Internet of Things according to claim 2 is characterized in that: The step of determining the second safety slope according to the placement portion information, the container information and the content information comprises: Acquire a first material type corresponding to the placement portion according to the placement portion information, acquire a second material type and a container weight corresponding to the container according to the container information, and acquire a content density corresponding to the content according to the content information; determining a friction coefficient between an upper surface of the placement portion and a lower surface of the container according to the first material type and the second material type, and determining a content weight corresponding to the content according to the density of the content and the volume of the content; A second safety slope is determined according to the friction coefficient and the weight of the contents.

6. The robot path planning method based on industrial Internet of Things according to claim 1 is characterized in that: The step of determining the grid slope value corresponding to each non-edge grid according to the grid map comprises: For each non-edge grid in the grid map, coordinate data of a target grid and elevation data corresponding to the target grid are obtained; the target grid includes the non-edge grid and an adjacent grid, and the adjacent grid is a grid adjacent to the non-edge grid; The elevation change value of the non-edge grid is determined according to a preset formula, the coordinate data and the elevation data; the adjacent grid includes an edge adjacent grid and a corner adjacent grid, and the preset formula is: d=w1*(|Z[i-1][j-1]-Z[i][j]|)+w2*(|Z[i-1][j]-Z[i][j]|)+w1 *(|Z[i-1][j+1]-Z[i][j]|)+w1*(|Z[i][j+1]-Z[i][j]|)+w2*(|Z[i+1][j-1]-Z[i][j]|)+w2*(|Z[i+1][j+1]-Z[i][j]|) Wherein, (i, j) is the coordinate of the non-edge grid, d represents the elevation change value of the non-edge grid, Z represents the elevation of the grid, w1 represents the first weight corresponding to the corner adjacent grid, and w2 represents the second weight corresponding to the edge adjacent grid; The spatial resolution of the grid is obtained, and the grid slope value corresponding to the non-edge grid is determined according to the spatial resolution and the elevation change value.

7. The robot path planning method based on industrial Internet of Things according to claim 1 is characterized in that: The step of generating a transport path according to the grid slope value, the first safety slope and the second safety slope comprises: Determine a minimum value between the first safety slope and the second safety slope according to the first safety slope and the second safety slope, and use the minimum value as a final safety slope; Determine a grid safety representative value corresponding to each non-edge grid according to the grid slope value and the final safety slope; Based on a preset path planning algorithm, a transport path is generated according to the grid safety representative value.

8. The robot path planning system based on industrial Internet of Things is characterized by: It includes a management platform, a sensor network platform and an object platform which are sequentially connected in communication, and the management platform is configured with: The module for acquiring information about objects to be transported is used to acquire the current transport task of the robot and determine the information about objects to be transported corresponding to the objects to be transported according to the current transport task; the objects to be transported include containers and the contents in the containers; A first safety slope determination module, used to determine whether the content is a fluid according to the to-be-carried information, and if so, obtain container information corresponding to the container and content information corresponding to the content, and determine a first safety slope according to the container information and the content information; a second safety slope determination module, configured to obtain placement part information corresponding to the placement part of the robot, and determine a second safety slope according to the placement part information, the container information and the content information; The transport path generation module is used to obtain a grid map, determine the grid slope value corresponding to each non-edge grid according to the grid map, and generate a transport path according to the grid slope value, the first safety slope and the second safety slope.

9. The robot path planning system based on industrial Internet of Things according to claim 8, characterized in that: The transport path generation module comprises: The elevation data acquisition submodule is used to acquire the coordinate data of the target grid and the elevation data corresponding to the target grid for each non-edge grid in the grid map; the target grid includes the non-edge grid and an adjacent grid, and the adjacent grid is a grid adjacent to the non-edge grid; The elevation change value generating submodule is used to determine the elevation change value of the non-edge grid according to a preset formula, the coordinate data and the elevation data; the adjacent grid includes an edge adjacent grid and a corner adjacent grid, and the preset formula is: d=w1*(|Z[i-1][j-1]-Z[i][j]|)+w2*(|Z[i-1][j]-Z[i][j]|)+w1 *(|Z[i-1][j+1]-Z[i][j]|)+w1*(|Z[i][j+1]-Z[i][j]|)+w2*(|Z[i+1][j-1]-Z[i][j]|)+w2*(|Z[i+1][j+1]-Z[i][j]|) Wherein, (i, j) is the coordinate of the non-edge grid, d represents the elevation change value of the non-edge grid, Z represents the elevation of the grid, w1 represents the first weight corresponding to the corner adjacent grid, and w2 represents the second weight corresponding to the edge adjacent grid; The elevation change value generating submodule is used to obtain the spatial resolution of the grid, and determine the grid slope value corresponding to the non-edge grid according to the spatial resolution and the elevation change value.

10. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

Images