Mobile robot map verification method, chip and robot

Abstract

The present invention discloses a mobile robot map verification method, chip and robot, comprising: the mobile robot obtains the boundary outline of the current area through a laser radar to construct a matching template, and then the mobile robot uses the matching template to use the grid map with the highest matching degree with the matching template as the grid map matching the current area; the mobile robot identifies the position of the marked points in the grid map matching the current area, and then the mobile robot obtains corresponding points in the current area through a laser radar according to the position of the marked points; the mobile robot determines whether the current matching map is correct according to the number of corresponding points obtained, effectively avoiding the problem that the mobile robot cannot work normally due to matching map errors, and improving the accuracy of the mobile robot's map matching.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent robots, and in particular to a mobile robot map verification method, a chip, and a robot. Background Art

[0002] With the continuous development of autonomous mobile robots, robots are increasingly being used to replace human operators in various fields. However, when autonomously moving, robots often rely on navigation maps for positioning and navigation. Currently, autonomous mobile robots need to match their current environment to obtain a navigation map. However, if the matched map is inaccurate, the mobile robot cannot reach the designated location to perform the corresponding task based on the erroneous navigation map, which seriously affects user experience. Summary of the Invention

[0003] To solve the above problems, the present invention provides a mobile robot map verification method, chip, and robot. The specific technical solutions of the present invention are as follows:

[0004] A mobile robot map verification method includes the following steps: the mobile robot obtains the boundary outline of the current area through a laser radar to construct a matching template, and then the mobile robot traverses the grid map stored in the mobile robot through the matching template, and uses the grid map with the highest matching degree with the matching template as the grid map matching the current area; the mobile robot determines its own position in the grid map matching the current area based on the boundary outline of the current area, and identifies the position of the marked point in the grid map matching the current area, and then the mobile robot obtains corresponding points in the current area through the laser radar according to the position of the marked point; the mobile robot determines the number of corresponding points obtained, if the number of corresponding points obtained by the mobile robot is greater than or equal to the set number, then the grid map matching the current area is judged to be a correct map, if the number of corresponding points obtained by the mobile robot is less than the set number, then the grid map matching the current area is judged to be an incorrect map; wherein the corresponding point is point cloud data corresponding to the marked point obtained by the mobile robot in the current area.

[0005] Furthermore, before starting work, the mobile robot first walks in a bow shape in the current area, and obtains point cloud data through the lidar during the walking process, and places the point cloud data one by one into the grid map to obtain the grid map of the current area; then the mobile robot randomly selects several point cloud data in the grid map as annotation points, and then saves the grid map with the annotation points set into the robot.

[0006] Furthermore, the mobile robot obtains the boundary outline of the current area through the laser radar to construct a matching template, including the following steps: the mobile robot obtains the boundary outline of the current area through the laser radar, and then the mobile robot selects an area of ​​N*N pixels from the obtained boundary outline of the current area as a matching template; the mobile robot randomly selects a grid map from the stored grid maps, and then traverses the grid map of the house from left to right through the matching template, and scores the grid map; the mobile robot traverses all the grid maps stored by the mobile robot through the matching template, and then uses the grid map with the highest score as the grid map of the current area; wherein N is a natural number greater than 0.

[0007] Furthermore, the mobile robot determines its position in a grid map that matches the current area based on the boundary contour of the current area, including the following steps: the mobile robot stops moving, then obtains point cloud data of the current position through a lidar, and constructs a traversal grid with the current position of the mobile robot as the center through the point cloud data obtained at the current position; the mobile robot traverses the grid map that matches the current area through the traversal grid, obtains the area in the grid map that matches the traversal grid, and then obtains the position of the mobile robot in the grid map that matches the current area.

[0008] Furthermore, the mobile robot identifies the positions of the marked points in the grid map that matches the current area, including the following steps: the mobile robot traverses the grid map that matches the current area, and obtains the positions of several marked points in the grid map; the mobile robot labels several marked points according to the distance between the several marked points and the mobile robot in the grid map.

[0009] Furthermore, the mobile robot obtains corresponding points in the current area through the laser radar according to the position of the marked point, including the following steps: the mobile robot determines the position of the corresponding point corresponding to the marked point in the current area according to the position of the mobile robot in the grid map and the positions of several marked points in the grid map; the mobile robot moves to the position of the corresponding point corresponding to the marked point in turn according to the number of the marked point, and then obtains whether there is point cloud data at the position of the corresponding point corresponding to the marked point through the laser radar; if there is point cloud data at the position of the corresponding point corresponding to the marked point, the mobile robot determines that the marked point has a corresponding corresponding point, and if there is no point cloud data at the position of the corresponding point corresponding to the marked point, the mobile robot determines that the marked point does not have a corresponding corresponding point.

[0010] Furthermore, if the number of corresponding points obtained by the mobile robot is greater than or equal to 3, the grid map matching the current area is judged to be the correct map; if the number of corresponding points obtained by the mobile robot is less than 3, the grid map matching the current area is judged to be the wrong map.

[0011] Furthermore, after the mobile robot determines that the grid map matching the current area is an incorrect map, the mobile robot uses the grid map with the second highest score as the grid map of the current area, and obtains corresponding points in the current area based on the grid map.

[0012] A chip is used to store a program, and the program is configured to execute the above-mentioned mobile robot map verification method.

[0013] A mobile robot includes a main control chip, which is the chip mentioned above.

[0014] Compared with the existing technology, the beneficial effect of the present invention is that after the mobile robot described in the present application completes the map matching of the current area, it searches for corresponding points in the current area through the marked points pre-set on the grid map to verify whether the currently matched grid map is correct, effectively avoiding the problem of the mobile robot not being able to work normally due to matching map errors, improving the accuracy of the mobile robot's map matching, and thus improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 The figure is a flow chart of a mobile robot map verification method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0016] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions.

[0017] In the description of the present invention, it should be noted that, for directional words, such as the terms "center", "horizontal", "longitudinal", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and so on, indicating directions and positional relationships, are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and cannot be understood as limiting the specific scope of protection of the present invention.

[0018] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features. Therefore, the terms "first" and "second" may explicitly or implicitly include one or more of these features. Throughout the description of the present invention, "at least" means one or more than one, unless otherwise specifically defined.

[0019] In the present invention, unless otherwise specified or limited, the terms "assemble," "connect," and "connect" should be understood in a broad sense. For example, they may refer to fixed connection, detachable connection, or integral connection; mechanical connection; direct connection, connection through an intermediate medium, or internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0020] In the present invention, unless otherwise specified or limited, a first feature being "above" or "below" a second feature may include the first and second features being in direct contact, or may include the first and second features being in contact not directly but through another feature therebetween. Furthermore, a first feature being "above," "below," and "above" a second feature may include the first feature being directly above or obliquely above the second feature, or may simply mean that the first feature is higher in level than the second feature. A first feature being "above," "below," and "below" a second feature may include the first feature being directly below or obliquely below the second feature, or may simply mean that the first feature is lower in level than the second feature.

[0021] The following description of the embodiments of the present invention is provided in conjunction with the accompanying drawings to further describe the specific embodiments of the present invention so that the technical solutions and beneficial effects of the present invention will be more clearly understood. The following description of the embodiments with reference to the accompanying drawings is illustrative and intended to explain the present invention, but is not to be construed as limiting the present invention.

[0022] like Figure 1 As shown, a mobile robot map verification method includes the following steps:

[0023] After receiving a work instruction, the mobile robot generally leaves the charging station and moves to the room where it needs to work. The mobile robot then uses the lidar to obtain the laser point cloud data of the current area, thereby obtaining the boundary contour of the current area to construct a matching template. The mobile robot then traverses the raster map stored in the mobile robot through the matching template and uses the raster map with the highest matching degree with the matching template as the raster map that matches the current area.

[0024] As one of the embodiments, before starting work, the mobile robot first walks in a bow shape in the current area, and obtains point cloud data through the lidar during the walking process, and places the point cloud data one by one into the grid map to obtain the grid map of the current area; then the mobile robot randomly selects several point cloud data in the grid map as annotation points, and then saves the grid map with the annotation points set into the robot.

[0025] Based on the boundary contours of the current area, the mobile robot determines its position in the grid map that matches the current area and identifies the locations of the annotation points in the grid map that matches the current area. The mobile robot then uses a lidar sensor to acquire corresponding points in the current area based on the locations of the annotation points. These corresponding points are the point cloud data corresponding to the annotation points acquired by the mobile robot in the current area, i.e., data points that exist at corresponding locations in the grid map and the current area. When annotating the grid map, the mobile robot can convert the annotation points and corresponding points into annotation lines (which can also be considered as several adjacent annotation points) and corresponding lines. Specifically, the mobile robot forms an annotation line by combining several adjacent point cloud data in the grid map. After completing map matching, the mobile robot searches for corresponding lines in the real area, consisting of several point cloud data points, that correspond to the annotation lines. The point cloud data on the annotation line corresponds one-to-one with the point cloud data on the corresponding line.

[0026] As one embodiment, a mobile robot obtains a boundary outline of a current area through a laser radar to construct a matching template, including the following steps: the mobile robot obtains the boundary outline of the current area through the laser radar, and then the mobile robot selects an area of ​​N*N pixels from the obtained boundary outline of the current area as a matching template; the mobile robot randomly selects a grid map from the stored grid maps, and then traverses the grid map of the house from left to right through the matching template, and scores the grid map; the mobile robot traverses all the grid maps stored by the mobile robot through the matching template, and then uses the grid map with the highest score as the grid map of the current area; wherein N is a natural number greater than 0.

[0027] As one of the embodiments, a mobile robot determines its position in a grid map that matches the current area based on the boundary contour of the current area, including the following steps: the mobile robot stops, then obtains point cloud data of the current position through a lidar, and constructs a traversal grid with the current position of the mobile robot as the center through the point cloud data obtained at the current position; the mobile robot traverses the grid map that matches the current area through the traversal grid, obtains the area in the grid map that matches the traversal grid, and then obtains the position of the mobile robot in the grid map that matches the current area.

[0028] As one embodiment, a mobile robot identifies the positions of marked points in a grid map that matches the current area, including the following steps: the mobile robot traverses the grid map that matches the current area, and obtains the positions of several marked points in the grid map; the mobile robot numbers the several marked points according to their distance from the mobile robot in the grid map, that is, starting from the marked point closest to the mobile robot, and numbering them as 1, 2, 3, 4, 5, etc.

[0029] As one of the embodiments, a mobile robot obtains corresponding points in a current area through a laser radar according to the position of the marked point, comprising the following steps: the mobile robot determines the position of the corresponding point corresponding to the marked point in the current area according to the position of the mobile robot in the grid map and the positions of several marked points in the grid map; the mobile robot moves to the position of the corresponding point corresponding to the marked point in sequence according to the number of the marked point, and then obtains point cloud data at the position of the corresponding point corresponding to the marked point through a laser radar; if there is point cloud data at the position of the corresponding point corresponding to the marked point, the mobile robot determines that the marked point has a corresponding corresponding point, and if there is no point cloud data at the position of the corresponding point corresponding to the marked point, the mobile robot determines that the marked point does not have a corresponding corresponding point.

[0030] The mobile robot determines the number of corresponding points obtained. If the number of corresponding points obtained by the mobile robot is greater than or equal to the set number, the grid map matching the current area is determined to be a correct map. If the number of corresponding points obtained by the mobile robot is less than the set number, the grid map matching the current area is determined to be an incorrect map.

[0031] As one embodiment, if the number of corresponding points obtained by the mobile robot is greater than or equal to 3, the grid map matching the current area is judged to be a correct map; if the number of corresponding points obtained by the mobile robot is less than 3, the grid map matching the current area is judged to be an incorrect map.

[0032] In one embodiment, after the mobile robot determines that the raster map matching the current area is an incorrect map, the mobile robot uses the second-highest-scoring raster map as the raster map for the current area and, based on this raster map, obtains corresponding points in the current area using the above-described method. If the second-highest-scoring raster map is verified to be an incorrect map, the mobile robot uses the second-highest-scoring raster map as the raster map for the current area and, based on this raster map, obtains corresponding points in the current area using the above-described method. If the second-highest-scoring raster map is verified to be an incorrect map, the mobile robot re-acquires point cloud data using a lidar to construct a new matching template, and then matches the raster map using the new matching template.

[0033] A chip is used to store a program, and the program is configured to execute the above-mentioned mobile robot map verification method.

[0034] A mobile robot includes a main control chip, which is the chip mentioned above.

[0035] Compared with the existing technology, the beneficial effect of the present invention is that after the mobile robot described in the present application completes the map matching of the current area, it searches for corresponding points in the current area through the marked points pre-set on the grid map to verify whether the currently matched grid map is correct, effectively avoiding the problem of the mobile robot not being able to work normally due to matching map errors, improving the accuracy of the mobile robot's map matching, and thus improving the user experience.

[0036] In the description of the specification, reference to the terms "in one embodiment," "preferably," "example," "specific example," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. The schematic representations of the above terms in this specification do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. The connection method described in the description of the specification has obvious effects and practical effectiveness.

[0037] Through the description of the above structure and principle, technical personnel in the relevant technical field should understand that the present invention is not limited to the above specific implementation methods, and improvements and substitutions based on the present invention using the well-known technology in the field all fall within the scope of protection of the present invention and should be defined by the claims.

Claims

1. A mobile robot map verification method, characterized in that: The method comprises the following steps: The mobile robot uses the lidar to obtain the boundary outline of the current area to construct a matching template. The mobile robot then traverses the grid map stored in the mobile robot through the matching template and uses the grid map with the highest matching degree with the matching template as the grid map that matches the current area. The mobile robot determines its position in the grid map that matches the current area based on the boundary contour of the current area, and identifies the position of the marked points in the grid map that matches the current area. Then, the mobile robot uses the lidar to obtain the corresponding points in the current area based on the position of the marked points. The mobile robot determines the number of corresponding points obtained. If the number of corresponding points obtained by the mobile robot is greater than or equal to the set number, the grid map matching the current area is determined to be a correct map. If the number of corresponding points obtained by the mobile robot is less than the set number, the grid map matching the current area is determined to be an incorrect map. The mobile robot uses the laser radar to obtain corresponding points in the current area based on the position of the marked points, including the following steps: The mobile robot determines the position of the corresponding point corresponding to the marked point in the current area according to the position of the mobile robot in the grid map and the positions of the plurality of marked points in the grid map; The mobile robot moves to the position of the corresponding point according to the number of the marked point, and then uses the laser radar to obtain whether there is point cloud data at the position of the corresponding point corresponding to the marked point; If there is point cloud data at the position of the corresponding point corresponding to the marked point, the mobile robot determines that the marked point has a corresponding corresponding point; if there is no point cloud data at the position of the corresponding point corresponding to the marked point, the mobile robot determines that the marked point does not have a corresponding corresponding point; The corresponding points are point cloud data corresponding to the marked points acquired by the mobile robot in the current area.

2. The mobile robot map verification method according to claim 1, characterized in that: Before starting work, the mobile robot first walks in a bow shape in the current area. During the walking process, it obtains point cloud data through the lidar and places the point cloud data one by one into the grid map to obtain the grid map of the current area. The mobile robot then randomly selects several point cloud data on the grid map as annotation points, and then saves the grid map with the annotation points set to the robot.

3. The mobile robot map verification method according to claim 1, characterized in that: The mobile robot uses the lidar to obtain the boundary outline of the current area to build a matching template, which includes the following steps: The mobile robot obtains the boundary outline of the current area through the laser radar, and then selects an N*N pixel area from the obtained boundary outline of the current area as a matching template; The mobile robot randomly selects a grid map from the stored grid maps, then traverses the grid map of the house from left to right by matching the template, and scores the grid map; The mobile robot traverses all grid maps stored by the mobile robot by matching templates, and then uses the grid map with the highest score as the grid map of the current area; Where N is a natural number greater than 0.

4. The mobile robot map verification method according to claim 1, characterized in that: The mobile robot determines its position in a grid map that matches the current area based on the boundary contour of the current area, including the following steps: The mobile robot stops and uses the lidar to obtain point cloud data of its current position. The traversal grid is constructed based on the point cloud data obtained at the current position, with the current position of the mobile robot as the center. The mobile robot traverses the grid map that matches the current area by traversing the grids, obtains the area in the grid map that matches the traversed grids, and then obtains the position of the mobile robot in the grid map that matches the current area.

5. The mobile robot map verification method according to claim 4, characterized in that: The mobile robot identifies the location of the marked points in the grid map that match the current area, including the following steps: The mobile robot traverses the grid map that matches the current area and obtains the positions of several marked points in the grid map; The mobile robot labels the plurality of marked points according to their distances from the mobile robot in the grid map.

6. The mobile robot map verification method according to claim 1, characterized in that: If the number of corresponding points obtained by the mobile robot is greater than or equal to 3, the grid map matching the current area is judged to be the correct map. If the number of corresponding points obtained by the mobile robot is less than 3, the grid map matching the current area is judged to be the wrong map.

7. The mobile robot map verification method according to claim 6, characterized in that: After the mobile robot determines that the grid map matching the current area is an incorrect map, the mobile robot uses the grid map with the second highest score as the grid map of the current area and obtains corresponding points in the current area based on the grid map.

8. A chip for storing a program, characterized in that: The program is configured to execute the mobile robot map verification method according to any one of claims 1 to 7.

9. A mobile robot, characterized in that: The mobile robot includes a main control chip, and the main control chip is the chip according to claim 8.

Images