A laser robot mapping optimization method, a chip and a laser robot

Abstract

The application discloses a laser robot mapping optimization method, a chip and a laser robot. The optimization method comprises the following steps: acquiring all rooms in a laser robot mapping result, scanning the edges of each room, and counting the total edge length and unknown edge length of each room; calculating the ratio of the unknown edge length of each room to the total edge length thereof; according to the ratio of the unknown edge length of each room to the total edge length thereof, iteratively judging whether the room is to be deleted from the mapping result, if yes, deleting the room from the mapping result, and if no, keeping the room in the mapping result, until all rooms are iteratively judged, and the optimization of the robot mapping result is completed. The ratio of the unknown edge length of each room to the total edge length thereof is used to screen the laser robot mapping result, so that the room with incomplete mapping is optimized, and the reliability of the laser robot mapping result is improved.

Description

Technical Field

[0001] This invention relates to the field of robot mapping technology, specifically to a laser robot mapping optimization method, chip, and laser robot. Background Technology

[0002] With the development of technology, intelligent mobile robots are being applied in more and more fields. Intelligent mobile robots primarily utilize their onboard sensors to perceive their surroundings and plan their work paths based on the environmental maps they acquire, ensuring safe and reliable movement. Currently, intelligent mobile robots mainly rely on LiDAR for mapping, with only a few relying on visual information. However, the presence of translucent objects such as glass and plastic, or mirrored objects, in the working environment of intelligent mobile robots can lead to inaccurate environmental information perceived by LiDAR, resulting in incomplete mapping and chaotic work paths. This negatively impacts the safety and efficiency of the intelligent mobile robot's movement. Summary of the Invention

[0003] To address the aforementioned problems, this invention provides a laser robot mapping optimization method, chip, and laser robot. By filtering the mapping results generated from environmental information perceived by the robot using lidar, it optimizes incomplete mappings of rooms without requiring additional sensing sensors. This achieves low-cost resolution of the impact of mirrored objects on the laser robot's mapping results, improving the reliability of laser robot mapping. The specific technical solution of this invention is as follows:

[0004] A laser robot mapping optimization method includes: acquiring all rooms in the laser robot mapping result; scanning the edges of each room and calculating the total edge length and unknown edge length of each room; calculating the ratio of the unknown edge length to the total edge length of each room; based on the ratio of the unknown edge length to the total edge length of each room, iterating through and determining whether to delete the room from the mapping result; if yes, deleting the room from the mapping result; otherwise, retaining the room in the mapping result, until all rooms have been traversed and determined, thus completing the optimization of the robot mapping result.

[0005] Furthermore, the method for determining whether to delete a room from the mapping result based on the ratio of the unknown edge length of the room to its total edge length specifically includes: if the ratio of the unknown edge length of the room to its total edge length is greater than a first threshold, then the room is deleted from the mapping result.

[0006] Furthermore, the method for determining whether to delete a room from the mapping result based on the ratio of the unknown edge length of the room to its total edge length also includes: if the ratio of the unknown edge length of the room to its total edge length is less than a second threshold, then the room will be retained in the mapping result; wherein the second threshold is less than the first threshold.

[0007] Furthermore, the method for determining whether to delete a room from the mapping result based on the ratio of the unknown edge length of the room to its total edge length also includes: if the ratio of the unknown edge length of the room to its total edge length is less than or equal to a first threshold and greater than or equal to a second threshold, then the room is horizontally and vertically projected, and the room is deleted from the mapping result based on the shape of the horizontal and vertical projections.

[0008] Furthermore, the method for determining whether to delete a room from the drawing results based on the resulting shapes of the room's horizontal and vertical projections specifically includes: deleting the room from the drawing results when the resulting shapes of the room's horizontal and vertical projections satisfy a triangular or trapezoidal shape.

[0009] Furthermore, the laser robot mapping optimization method also includes: after obtaining all rooms in the laser robot mapping results, obtaining the area of ​​each room, selecting a specified room from all rooms based on the room size according to the room selection rules, and optimizing the specified room using a preset optimization method.

[0010] Furthermore, the method for the room selection rule includes: selecting the room with the largest area from all rooms, or selecting the room with an area greater than a preset area threshold from all rooms.

[0011] Furthermore, the step of optimizing the specified room using a preset optimization method specifically includes: performing a line scan of the specified room row by row and column by column, traversing and judging whether the gray value of each pixel in the specified room is less than a preset gray value threshold. If the gray value of a pixel is less than the preset gray value threshold, the pixel is deleted; if the gray value of a pixel is greater than or equal to the preset gray value threshold, the pixel is retained, until all the gray values ​​of all pixels in the specified room have been traversed and judged, and the optimization of the specified room ends.

[0012] The present invention also discloses a chip that stores a computer program inside, and the computer program stored inside the chip is executed by a processor to perform the laser robot mapping optimization method as described above.

[0013] The present invention also discloses a laser robot, comprising: a laser sensor for acquiring environmental data around the laser robot; a laser mapping module for generating a laser robot mapping result based on the environmental data acquired by the laser sensor; a chip as described above, internally storing a computer program, which is executed by a processor to perform the laser robot mapping optimization method as described above; and a processor for running the computer program stored internally in the chip.

[0014] The beneficial effects of this invention are as follows: the mapping results obtained by the laser robot are filtered for incomplete rooms based on the ratio of the unknown edge length of each room to its total edge length, thereby optimizing the mapping results of the laser robot. There is no need to add a new sensor to the laser sensor to compensate for the problem of incomplete mapping caused by the presence of transparent objects such as glass and plastic or mirror objects in the working environment. This solves the problem of the influence of mirror objects on the mapping results of the laser robot with low perception cost. Attached Figure Description

[0015] Figure 1 This is a schematic flowchart of a laser robot mapping optimization method according to an embodiment of the present invention.

[0016] Figure 2 This is a schematic diagram of the structure of the laser robot mapping optimization method based on threshold comparison according to an embodiment of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0018] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms “a,” “an,” “an,” “the,” and similar words used in this application do not indicate quantity limitation and may represent singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion, for example: a process, method, system, product, or apparatus that includes a series of steps or modules is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to such processes, methods, products, or apparatus.

[0019] In this invention, intelligent robots that use laser sensors as their environmental perception tools are collectively referred to as laser robots. Currently, intelligent mobile robots mainly rely on lidar for mapping, with only a few based on visual information. However, in the working environment of intelligent mobile robots, the presence of translucent objects such as glass and plastic, or mirrored objects, leads to inaccurate environmental information perceived by lidar, resulting in incomplete mapping and thus chaotic working paths, affecting the safety and efficiency of the intelligent mobile robot's movement. Based on this background, how to eliminate the influence of translucent or mirrored objects on the mapping results of laser robots, and how to improve the reliability of the mapping results, are the problems that this application aims to solve.

[0020] As a preferred embodiment of the present invention, the first embodiment of the present invention provides a laser robot mapping optimization method, such as... Figure 1 As shown, the laser robot mapping optimization method specifically includes the following steps:

[0021] Obtain all rooms from the laser robot mapping results; scan the edges of each room in the laser robot mapping results, and calculate the total edge length and unknown edge length of each room in the laser robot mapping results; wherein, the unknown edge length of the room refers to the cumulative length of unknown edges identified in the room during the edge scanning process; the total edge length of the room refers to the cumulative recorded edge length of the room during the edge scanning process, including the unknown edge length and the known edge length, wherein, the known edge refers to the edge that is known to be occupied by an obstacle or is known to be not occupied by an obstacle, and the unknown edge refers to the edge whose status as occupied by an obstacle is unknown.

[0022] The ratio of the unknown edge length to the total edge length of each room in the laser robot mapping results is calculated. Specifically, the ratio of the unknown edge length to the total edge length of a room reflects the proportion of whether the room's edges have been completely explored. Through repeated experiments, it has been found that when the proportion of unknown edges in a room is too high, the room is more likely to be an incomplete room. Therefore, in this method, the ratio of the unknown edge length to the total edge length of a room is used to determine whether the room is incomplete, thereby deleting incomplete rooms from the mapping results.

[0023] The algorithm determines whether there are any unoptimized rooms in the laser robot mapping results. If no unoptimized rooms are found, the optimization process ends. Conversely, if unoptimized rooms are found, one unoptimized room is selected. Based on the ratio of the unknown edge length to the total edge length of each room in the laser robot mapping results, the algorithm determines whether the room needs to be deleted from the mapping results. If so, the room is deleted; otherwise, the room is optimized. This process is repeated until all rooms are optimized.

[0024] This embodiment determines whether the proportion of unknown edges in a room is too high by statistically analyzing the ratio of the length of unknown edges to the total length of the room's edges, thereby determining whether the room is an incomplete room. By deleting incomplete rooms from the laser robot mapping results, the laser robot mapping results are optimized, solving the problem of incomplete laser robot mapping caused by translucent or mirrored objects in the working environment.

[0025] Based on the above embodiments, as a preferred embodiment of the present invention, the second embodiment provides a laser robot mapping optimization method based on threshold comparison. This method more accurately determines the optimization method for incomplete rooms in the laser robot mapping results by comparing the ratio of the unknown edge length of a room to its total edge length with the magnitude of a set first threshold and a second threshold. Figure 2 As shown, the method specifically includes:

[0026] Step 1: Obtain all rooms from the laser robot mapping results, then proceed to Step 2;

[0027] Step 2: Scan the edges of each room in the laser robot mapping results, and calculate the total edge length and unknown edge length of each room in the laser robot mapping results, then proceed to Step 3;

[0028] Step 3: Calculate the ratio of the unknown edge length to the total edge length of each room, then proceed to Step 4;

[0029] Step 4: Determine if there are any unoptimized rooms in the total number of rooms in the laser robot mapping results. If there are unoptimized rooms in the laser robot mapping results, proceed to Step 5. If there are no unoptimized rooms in the laser robot mapping results, the optimization of the laser robot mapping results is completed.

[0030] Step 5: Select an unoptimized room from all rooms and determine whether the ratio of the unknown edge length of the room to its total edge length is greater than the first threshold. If the ratio is greater than the first threshold, delete the room from the laser robot mapping results, complete the optimization of the room, and return to step 4. Conversely, if the ratio is less than or equal to the first threshold, proceed to step 6.

[0031] Step 6: Determine whether the ratio of the unknown edge length of the room to its total edge length is less than the second threshold. If the ratio is less than the second threshold, keep the room in the laser robot mapping results, complete the room optimization, and return to step 4. Conversely, if the ratio is greater than or equal to the second threshold, proceed to step 7.

[0032] Step 7: Perform horizontal and vertical projections on the room to obtain the resulting shapes of the horizontal and vertical projections, then proceed to Step 8.

[0033] Step 8: Determine whether at least one of the resulting shapes of the horizontal projection and the vertical projection of the room satisfies a triangular or trapezoidal shape. If at least one of the resulting shapes of the horizontal and vertical projections of the room satisfies a triangular or trapezoidal shape, then delete the room from the laser robot mapping results, completing the room optimization, and return to Step 4. Conversely, if neither the resulting shape of the horizontal nor the vertical projection of the room conforms to a triangular or trapezoidal shape, then retain the room in the laser robot mapping results, completing the room optimization, and return to Step 4.

[0034] Specifically, the second threshold is less than the first threshold. Specifically, the first threshold is a pre-set threshold used to determine whether the ratio of the unknown edge length to the total edge length of a room is too high; it is a threshold that can directly determine whether a room is incomplete. The setting of the first threshold can be, but is not limited to, an empirical value statistically calculated from the ratio of the unknown edge length to the total edge length of incomplete rooms in laser robot room division. The second threshold is a pre-set threshold used to determine whether the ratio of the unknown edge length to the total edge length of a room does not affect the integrity of the room. The setting of the second threshold can be, but is not limited to, an empirical value statistically calculated from the ratio of the unknown edge length to the total edge length of complete rooms in laser robot room division. This embodiment compares the ratio of the unknown edge length of a room to its total edge length with the set first and second thresholds to determine whether a room is incomplete. The first and second thresholds are set based on a large number of empirical values ​​of the ratio of the unknown edge length to the total edge length of complete and incomplete rooms in the laser robot mapping results. This allows the optimization method to cover most application scenarios and obtain better judgment results for incomplete and complete rooms, ensuring the effectiveness of the mapping optimization method.

[0035] Specifically, the method described in the first and second embodiments for scanning the edges of each room in the laser robot mapping results and calculating the total edge length and unknown edge length of each room in the laser robot mapping results may include, but is not limited to, the following steps: scanning all pixels of the room to obtain the edge pixels of the room; sorting the edge pixels of the room in a clockwise or counterclockwise direction, and traversing according to the sorting of the edge pixels of the room to determine whether each edge pixel belongs to a pixel occupied by an obstacle, a pixel in an open area (i.e., a pixel clearly not occupied by an obstacle), or a pixel in an unknown area; calculating the sum of the Euclidean distances between adjacent pixels in all edge pixels of the room to obtain the total edge length of the room; calculating the sum of the Euclidean distances between adjacent pixels in the unknown area in all edge pixels of the room to obtain the unknown edge length of the room; wherein, the method for determining whether each edge pixel belongs to a pixel occupied by an obstacle, a pixel in an open area, or a pixel in an unknown area may include, but is not limited to, determining it by the grayscale value of each edge pixel. The calculation of the sum of Euclidean distances between adjacent pixels refers to adding the Euclidean distances between all adjacent pixels. The Euclidean distance is also known as the Euclidean distance, which is often used to calculate the distance between two points. In this invention, the distance between two pixels is calculated based on the Euclidean distance.

[0036] Based on the above embodiments, as a preferred embodiment of the present invention, the third embodiment of the present invention provides another method for optimizing the mapping results of laser robots. Unlike the first and second embodiments, in the optimization method for the mapping results of laser robots provided in this embodiment, after obtaining all rooms in the mapping results of laser robots, the area of ​​each room in the mapping results of laser robots is obtained, and based on the area of ​​each room, a specified room is selected from all rooms in the mapping results of laser robots according to the room selection rules, and a preset optimization method is applied to optimize the specified room.

[0037] Specifically, the method for obtaining the area of ​​each room in the laser robot mapping result can be, but is not limited to, using a polygon area calculation method, which calculates the area by obtaining the coordinates of each vertex of the room. The room selection rule is a pre-set rule used to filter rooms based on their area size. The room selection rule can be, but is not limited to: selecting the room with the largest area from all rooms in the laser robot mapping result as the designated room, or selecting rooms with an area greater than a preset area threshold from all rooms in the laser robot mapping result. The preset area threshold can be set with reference to the area of ​​the largest room in the real environment or an empirical value for the largest room, etc.

[0038] Specifically, the optimization of the designated room using a preset optimization method can be, but is not limited to, performing a line scan of the designated room row by row and column by column, iterating and determining whether the grayscale value of each pixel in the designated room is less than a preset grayscale threshold. If the grayscale value of a pixel is less than the preset grayscale threshold, the pixel is deleted from the designated room; if the grayscale value of a pixel is greater than or equal to the preset grayscale threshold, the pixel is retained in the designated room. This process continues until the grayscale values ​​of all pixels in the designated room have been traversed and determined, at which point the optimization of the designated room ends. This method achieves partial optimization of the designated room by iterating and determining the grayscale values ​​of pixels and deleting some pixels.

[0039] Based on the support of a large amount of experimental data, it can be found that the room area in the laser robot mapping results is closely related to whether it belongs to the case where multiple real rooms are merged into one room. Therefore, the laser robot mapping result optimization method provided in this embodiment selects the room area as a reference, selects a specified room in combination with the room selection rules, and applies a preset optimization method to the specified room. This allows for special optimization methods to be applied to these special rooms, making the optimization of the laser robot mapping results of the present invention more targeted and with better optimization effect.

[0040] As a preferred embodiment of the present invention, the fourth embodiment of the present invention provides a chip, which stores a computer program inside the chip. When the computer program stored inside the chip is run by a processor, the laser robot mapping optimization method described in the previous embodiment is executed.

[0041] As a preferred embodiment of the present invention, the fifth embodiment of the present invention provides a laser robot, the laser robot comprising: a laser sensor for acquiring environmental data around the laser robot; a laser mapping module for generating a laser robot mapping result based on the environmental data acquired by the laser sensor; a chip as described in the ninth embodiment, internally storing a computer program, the computer program being executed by a processor to perform the laser robot mapping optimization method as described above; and a processor for running the computer program stored internally in the chip.

[0042] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (such as a smartphone) to execute the methods described in the various embodiments of the present invention.

[0043] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0044] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A laser robot mapping optimization method, characterized in that, The laser robot mapping optimization method includes: Retrieve all rooms from the laser robot mapping results; Scan the edges of each room and calculate the total edge length and unknown edge length for each room. Calculate the ratio of the unknown edge length to the total edge length of each room; Based on the ratio of the unknown edge length of each room to its total edge length, it iterates through the map to determine whether to delete the room from the mapping result. If yes, the room is deleted from the mapping result; otherwise, the room is retained in the mapping result. This process continues until all rooms have been traversed and determined, thus optimizing the robot's mapping result. The total edge length of the room refers to the total length of the room's edges recorded during the scanning process, including unknown edge length and known edge length; a known edge is one that is known to be occupied by an obstacle or is known not to be occupied by an obstacle; an unknown edge is one whose status as occupied by an obstacle is unknown.

2. The laser robot mapping optimization method according to claim 1, characterized in that, The method for determining whether to delete a room from the mapping result based on the ratio of the unknown edge length of the room to its total edge length includes: if the ratio of the unknown edge length of the room to its total edge length is greater than a first threshold, then the room is deleted from the mapping result.

3. The laser robot mapping optimization method according to claim 2, characterized in that, The method for determining whether to delete a room from the mapping result based on the ratio of the unknown edge length of the room to its total edge length further includes: if the ratio of the unknown edge length of the room to its total edge length is less than a second threshold, then the room will be retained in the mapping result; wherein the second threshold is less than the first threshold.

4. The laser robot mapping optimization method according to claim 3, characterized in that, The method for determining whether to delete a room from the mapping result based on the ratio of the unknown edge length of the room to its total edge length also includes: if the ratio of the unknown edge length of the room to its total edge length is less than or equal to a first threshold and greater than or equal to a second threshold, then the room is horizontally and vertically projected, and the result shape of the horizontal and vertical projections of the room is used to determine whether to delete the room from the mapping result.

5. The laser robot mapping optimization method according to claim 4, characterized in that, The method for determining whether to delete a room from the drawing results based on the resulting shapes of the room's horizontal and vertical projections specifically includes: deleting the room from the drawing results if the resulting shapes of the room's horizontal and vertical projections satisfy a triangular or trapezoidal shape.

6. The laser robot mapping optimization method according to claim 1, characterized in that, The laser robot mapping optimization method further includes: after obtaining all rooms in the laser robot mapping results, obtaining the area of ​​each room, selecting a specified room from all rooms based on the room size and room selection rules, and optimizing the specified room using a preset optimization method.

7. The laser robot mapping optimization method according to claim 6, characterized in that, The method for the room selection rule includes: selecting the room with the largest area from all rooms, or selecting the room with an area greater than a preset area threshold from all rooms.

8. The laser robot mapping optimization method according to claim 6, characterized in that, The steps of optimizing the specified room using a preset optimization method specifically include: performing line scanning row by row and column by column in the specified room, traversing and judging whether the gray value of each pixel in the specified room is less than a preset gray value threshold. If the gray value of a pixel is less than the preset gray value threshold, the pixel is deleted. If the gray value of a pixel is greater than or equal to the preset gray value threshold, the pixel is retained. This process continues until all the gray values ​​of all pixels in the specified room have been traversed and judged, at which point the optimization of the specified room ends.

9. A chip internally storing a computer program, characterized in that, The computer program stored inside the chip is executed by the processor to perform the laser robot mapping optimization method as described in any one of claims 1 to 8.

10. A laser robot, characterized in that, The laser robot includes: Laser sensors are used to acquire environmental data around the laser robot; The laser mapping module is used to generate laser robot mapping results based on environmental data acquired by laser sensors. The chip as described in claim 9 has a computer program stored inside, and the computer program is executed by the processor to perform the laser robot mapping optimization method as described in any one of claims 1 to 8; A processor is used to run computer programs stored inside a chip.

Images