Visual robot grid map construction method

Abstract

The invention relates to the technical field of grid map construction, and discloses a visual robot grid map construction method comprising the following steps: 1, grid granularity size selection; step 2, grid order marking; step 3, obstacle grid adjustment; step 4, establishing a grid map; in the third step, feature extraction is carried out on obstacles, images and videos in the surrounding environment are obtained through a visual sensor assembly, and then the images and the videos are processed and analyzed to extract useful information, so that information of the obstacles in the grids can be sensed. According to the method, in the grid map construction process, the particle sizes of a plurality of grids are set to be large, for example, when obstacles exist in part of grids and the particle sizes of the grids are adjusted, the grids with the obstacles are subdivided into a plurality of 10 * 10 small grids, so that grid map construction can be carried out more accurately; and the subsequent decision-making speed is improved while the information storage amount of grid map construction is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of grid map construction, and more specifically to a visual robot grid map construction method. Background Art

[0002] In recent years, with the rapid development of artificial intelligence and robotics, visual robots are an artificial intelligence technology that collects images through visual systems (such as cameras), processes and analyzes them through computers, simulates the functions of human vision, and then controls the robot to perform corresponding movements based on the visual results to achieve the desired functions. With the development of science and technology, this technology is gradually becoming a key component of industrial production. In addition, the application of robot vision is not limited to industrial production, but is also widely used in many fields such as intelligent transportation, security, and medical equipment.

[0003] At present, there are many forms of representation of maps in the eyes of visual robots, including three-dimensional point cloud maps, two-dimensional point cloud maps, two-dimensional grid maps, topological maps, semantic maps, etc. Among them, the grid map is a grid-based map representation method, in which the map area is divided into uniform grid units, and specific attribute information is assigned to each grid unit. Each grid unit can represent different geographical features, types of objects, heights, obstacles and other information. However, in the process of constructing the grid map, there is a principle that the size of the obstacle is always equal to the size of N grids, and there will not be a situation like half a grid. The selection of the grid granularity is particularly critical. The smaller the grid is, the higher the environmental resolution, the larger the environmental information storage capacity, and the slower the decision-making speed; the larger the grid is, the smaller the environmental resolution, the smaller the environmental information storage capacity, and the faster the decision-making speed, but the ability to find a path in a dense obstacle environment is weak. The larger or smaller the grid granularity is, the greater the impact on the construction of the grid map. Therefore, the present invention provides a method for constructing a grid map of a visual robot. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides a visual robot grid map construction method to solve the problems existing in the above-mentioned background technology.

[0005] The present invention provides the following technical solution: a method for constructing a grid map of a visual robot, comprising the following steps:

[0006] Step 1: Select the grid size;

[0007] Step 2: Grid marking;

[0008] Step 3: Obstacle grid adjustment;

[0009] Step 4: Grid map creation;

[0010] In step three, features of obstacles are extracted, and images and videos of the surrounding environment are acquired through the visual sensor component. These images and videos are then processed and analyzed to extract useful information, so that the obstacle information in the grid can be sensed. If there are obstacles in the grid, the grid granularity of the obstacle is adjusted. If there are no obstacles in the grid, the grid granularity does not need to be adjusted.

[0011] Furthermore, in the step 1, the map size is obtained and the space is divided according to the map size ratio to form a plurality of grids.

[0012] Furthermore, in the step 1, the grid granularity sizes are set to be large. The large grid granularity has the advantages of smaller environmental resolution, smaller environmental information storage volume, and faster decision-making speed.

[0013] Furthermore, in the step 2, a number of grids are numbered using a serial numbering method, and are marked as 1, 2, 3, ..., N in sequence from left to right and from top to bottom in the visual robot workspace, and each serial number represents a grid.

[0014] Furthermore, in step 2, the coordinates of grids with different serial numbers in the coordinate system are expressed by the following formula: x=mod(Ni / N)-0.5; y=N-ceil(Ni / N)+0.5; wherein mod is the remainder operation, ceil represents rounding backwards, Ni is the number of the corresponding grid, N represents the number of grids in each column, and the center position of the grid is taken as the coordinate of the grid in the coordinate system.

[0015] Furthermore, in step three, when the grid granularity is adjusted, the grid with obstacles is subdivided into several small grids of 10*10 using an artificial intelligence grid algorithm, and the several small grids are numbered in the same way.

[0016] Furthermore, in step three, an artificial intelligence visual algorithm is used to calculate the small grids occupied by obstacles, so that the grid map can be constructed more accurately.

[0017] Furthermore, in the step 4, when the grid map is established, the grid map is projected into the simulation program, so that the staff can understand the construction of the visual robot grid map through the simulation program.

[0018] Technical effects and advantages of the present invention:

[0019] 1. In the process of grid map construction, the present invention sets the granularity of several grids to be large, so that the map environment resolution is small, the environmental information storage volume is small, and the decision-making speed is fast. For example, when there are obstacles in some grids, when the grid granularity is adjusted, the grid with obstacles is subdivided into several small grids of 10*10, so that the grid map can be constructed more accurately, and the subsequent decision-making speed is improved while reducing the information storage volume of the grid map construction.

[0020] 2. The present invention projects the grid map into a simulation program when establishing the grid map, so that the staff can understand the construction of the visual robot grid map through the simulation program. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 The present invention is a flowchart of the visual robot grid map construction method.

[0022] Figure 2 It is a simulated grid map of the simulation program of the present invention. DETAILED DESCRIPTION

[0023] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. In addition, the forms of the various structures recorded in the following embodiments are merely illustrative. The visual robot grid map construction method involved in the present invention is not limited to the various structures recorded in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0024] Embodiment 1:

[0025] like Figure 1-2 As shown, a method for constructing a grid map of a visual robot comprises the following steps:

[0026] Step 1: Select the grid size;

[0027] Step 2: Grid marking;

[0028] Step 3: Obstacle grid adjustment;

[0029] Step 4: Grid map creation;

[0030] In step one, the map size is obtained and the space is divided according to the map size ratio to form a number of grids. In step one, the granularity of the grids is set to be large. The large granularity of the grid has the advantages of smaller environmental resolution, smaller environmental information storage, and faster decision-making speed.

[0031] In this embodiment, the grid map can be constructed more accurately through four steps, and the decision-making speed can be improved while reducing the information storage amount of the grid map construction. In the process of grid map construction, several grid granularity sizes are first set to large, so that the map environment resolution is smaller, the environment information storage amount is small, and the decision-making speed is fast.

[0032] Embodiment 2:

[0033] like Figure 1-2 As shown, in step 2, a number of grids are numbered using a serial numbering method. In the visual robot workspace, they are marked with serial numbers 1, 2, 3, ..., N in order from left to right and from top to bottom. Each serial number represents a grid. In step 2, the coordinates of grids with different serial numbers in the coordinate system are expressed by the following formula: x = mod(Ni / N)-0.5; y = N-ceil(Ni / N)+0.5; where mod is the remainder operation, ceil represents rounding backwards, Ni is the number of the corresponding grid, N represents the number of grids in each column, and the center position of the grid is taken as the coordinate of the grid in the coordinate system.

[0034] In this embodiment, by marking a number of grids, the map area is divided into regular grid units. The grid map has a simple and easy-to-implement map representation method, which is convenient for processing and calculation. The grid map can adjust the resolution and accuracy of the grid as needed, and the appropriate grid size and map resolution can be selected according to the requirements of the application scenario.

[0035] Embodiment three:

[0036] like Figure 1-2 As shown, in step three, the features of the obstacles are extracted, and the images and videos of the surrounding environment are obtained through the visual sensor component, and then these images and videos are processed and analyzed to extract useful information, so that the obstacle information in the grid can be sensed. If there is an obstacle in the grid, the grid granularity of the obstacle is adjusted at this time. If there is no obstacle in the grid, the grid granularity does not need to be adjusted. In step three, when the grid granularity is adjusted, the artificial intelligence grid algorithm is used to subdivide the grid with obstacles into several small grids of 10*10, and the several small grids are marked in the same way. In step three, the artificial intelligence visual algorithm is used to calculate the small grids occupied by the obstacles, so that the grid map can be constructed more accurately.

[0037] In this embodiment, images and videos of the surrounding environment are acquired through a visual sensor component, and then these images and videos are processed and analyzed to extract useful information, so that obstacle information in the grid can be sensed. For example, when there are obstacles in some grids, the grid granularity is adjusted in time, and the grid with obstacles is subdivided into several small grids of 10*10, and then the small grids occupied by the obstacles are calculated, so that the grid map can be constructed more accurately.

[0038] Embodiment 4:

[0039] like Figure 1-2 As shown, in step 4, when the grid map is established, the grid map is projected into the simulation program, so that the staff can understand the construction of the visual robot grid map through the simulation program.

[0040] In this embodiment, in the grid map, the working environment is divided into many grids, including grids with obstacles and grids without obstacles. The grid with obstacles is further subdivided into several small grids. Through the setting of the simulation program, it is convenient for the staff to understand the construction of the visual robot grid map. In the simulation program, the robot can accurately pass through the grid without obstacles, and the robot cannot pass through the grid with obstacles and needs to select other grids.

[0041] In summary, if Figure 1-2As shown, a visual robot grid map construction method, when used, obtains the map size and divides the space according to the map size ratio to form a plurality of grids. In step one, the granularity of the plurality of grids is set to be large. The large granularity of the grid has the advantages of small environmental resolution, small environmental information storage, and fast decision-making speed. Then, the plurality of grids are numbered by the marking method. In the visual robot workspace, they are marked as 1, 2, 3, ..., N in sequence from left to right and from top to bottom. Each number represents a grid. The coordinates of grids with different numbers in the coordinate system are expressed by the following formula: x = mod (Ni / N) - 0.5; y = N - ceil (Ni / N) + 0.5; wherein mod is the remainder operation, ceil represents rounding backward, Ni is the number of the corresponding grid, N represents the number of grids in each column, and the center position of the grid is taken as the grid in the coordinate system. The coordinates in the standard system are then extracted, and the obstacle information in the grid is sensed by the visual sensor component. If there is an obstacle in the grid, the grid granularity of the obstacle is adjusted. If there is no obstacle in the grid, the grid granularity does not need to be adjusted. When adjusting the grid granularity, the artificial intelligence grid algorithm is used to subdivide the grid with obstacles into several small grids of 10*10, and the same method is used to sequence several small grids, and then the artificial intelligence visual algorithm is used to calculate the small grids occupied by obstacles, so that the grid map can be constructed more accurately. When the grid map is established, the grid map is projected into the simulation program, which is convenient for the staff to understand the construction of the visual robot grid map through the simulation program. In the simulation program, the robot can accurately pass through the obstacle-free grid, and the robot cannot pass through the grid with obstacles, and needs to select other grids as the path.

[0042] Finally, a few points should be explained: First, in the description of this application, it should be noted that, unless otherwise specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, which may refer to mechanical connection or electrical connection, or internal communication between two components, or direct connection. "upper", "lower", "left", "right", etc. are only used to indicate relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship may change;

[0043] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0044] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for constructing a grid map of a visual robot, characterized in that: The following steps are involved: Step 1: Select the grid size; Step 2: Grid marking; Step 3: Obstacle grid adjustment; Step 4: Grid map creation; In step three, features of obstacles are extracted, and images and videos of the surrounding environment are acquired through the visual sensor component. These images and videos are then processed and analyzed to extract useful information, so that the obstacle information in the grid can be sensed. If there are obstacles in the grid, the grid granularity of the obstacle is adjusted. If there are no obstacles in the grid, the grid granularity does not need to be adjusted.

2. A visual robot grid map construction method according to claim 1, characterized in that: In the step 1, the map size is obtained and the space is divided according to the map size ratio to form a plurality of grids.

3. A visual robot grid map construction method according to claim 2, characterized in that: In the step 1, the grid granularity sizes are set to be large. The large grid granularity has the advantages of smaller environmental resolution, smaller environmental information storage volume, and faster decision-making speed.

4. A visual robot grid map construction method according to claim 1, characterized in that: In the step 2, a plurality of grids are numbered using a serial numbering method, and are marked as 1, 2, 3, ..., N in sequence from left to right and from top to bottom in the visual robot workspace, where each number represents a grid.

5. A visual robot grid map construction method according to claim 4, characterized in that: In step 2, the coordinates of grids with different serial numbers in the coordinate system are expressed by the following formula: x=mod(Ni / N)-0.5; y=N-ceil(Ni / N)+0.5; wherein mod is the remainder operation, ceil represents rounding backward, Ni is the number of the corresponding grid, N represents the number of grids in each column, and the center position of the grid is taken as the coordinate of the grid in the coordinate system.

6. A visual robot grid map construction method according to claim 5, characterized in that: In the step three, when the grid granularity is adjusted, the grid with obstacles is subdivided into several small grids of 10*10 using an artificial intelligence grid algorithm, and the several small grids are numbered in the same way.

7. A visual robot grid map construction method according to claim 6, characterized in that: In step three, an artificial intelligence visual algorithm is used to calculate the small grids occupied by obstacles, so that the grid map can be constructed more accurately.

8. A visual robot grid map construction method according to claim 1, characterized in that: In the step 4, when the grid map is established, the grid map is projected into the simulation program, so that the staff can understand the construction of the visual robot grid map through the simulation program.

Images