Map updating method and device and electronic equipment

Abstract

The invention discloses a map updating method and device and electronic equipment. The method comprises the following steps: acquiring a reference ground texture map; if it is determined that a target area in the reference ground texture map needs to be updated, a first vehicle in an automatic guided vehicle group is controlled to move to a first position of the target area, and a second vehicle in the automatic guided vehicle group is controlled to move to a second position of the target area, the first position and the second position are located at the two ends of the target area; acquiring environment image data acquired by the first vehicle when the second vehicle is used as a temporary reference object; and updating map data of a target area in the reference ground texture map based on the environment image data to obtain a target ground texture map. By adopting the method, the ground texture map can be automatically updated when the ground texture map is locally invalid, manual intervention is avoided, and the maintenance cost is reduced.

Description

Technical Field

[0001] The present application relates to the field of computer technologies, and more specifically, to a method and apparatus for map updating and an electronic device. Background Art

[0002] AGV (Automated Guided Vehicle) is widely used in scenarios such as logistics handling and production line handling. Generally, an AGV handling system includes a scheduling system and a robot group. The AGV handling system issues tasks to each automated guided vehicle through the scheduling system, and the automated guided vehicle realizes cargo handling based on a specific positioning and navigation method. When the automated guided vehicle executes a task, it provides pose information with its positioning and navigation module. Specifically, the positioning and navigation methods include LiDAR SLAM positioning (simultaneous localization and mapping based on lidar) or ground texture positioning, etc.

[0003] In related technologies, when each automated guided vehicle in an AGV handling system operates based on texture positioning and navigation, there is a problem of failure caused by ground pollution. Since there is a dependency relationship between the ground texture map and the ground trajectory, when the local ground texture is polluted and changes, the ground texture map is more likely to have a failure risk. However, in related technologies, manual intervention is required to solve the above risks, so there is a problem of high maintenance cost. Summary of the Invention

[0004] In view of the above problems, the present application provides a method and apparatus for map updating and an electronic device, which can automatically update the ground texture map and solve the problem of high manual maintenance cost in related technologies.

[0005] In a first aspect, an embodiment of the present application provides a method for map updating. The method includes: obtaining a reference ground texture map; if it is determined that a target area in the reference ground texture map needs to be updated, controlling a first vehicle in an automated guided vehicle group to move to a first position of the target area and controlling a second vehicle in the automated guided vehicle group to move to a second position of the target area, where the first position and the second position are located at both ends of the target area, the first vehicle is an automated guided transport vehicle with a ground texture map acquisition function and an environmental image data acquisition function, and the second vehicle is used as a temporary reference object when the first vehicle acquires image data; obtaining environmental image data acquired by the first vehicle when the second vehicle is used as a temporary reference object; updating map data of the target area in the reference ground texture map based on the environmental image data to obtain a target ground texture map.

[0006] Second aspect, an embodiment of the present application provides a map updating device, the device comprising: a reference map obtaining module, configured to obtain a reference ground texture map; a movement control module, configured to, when determining that a target area in the reference ground texture map needs to be updated, control a first vehicle in an automated guided vehicle group to move to a first position of the target area and control a second vehicle in the automated guided vehicle group to move to a second position of the target area, wherein the first position and the second position are located at two ends of the target area, the first vehicle is an automated guided transport vehicle having a ground texture map acquisition function and an environmental image data acquisition function, and the second vehicle serves as a temporary reference object when the first vehicle acquires image data; an image data obtaining module, configured to obtain environmental image data acquired by the first vehicle when the second vehicle serves as a temporary reference object; a map updating module, configured to update map data of the target area in the reference ground texture map based on the environmental image data to obtain a target ground texture map.

[0007] Third aspect, an embodiment of the present application provides an electronic device, comprising one or more processors; a memory, and one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the above method.

[0008] Fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which program code is stored, and the program code can be called by a processor to execute the above method.

[0009] The map updating method, device and electronic device provided by the embodiments of the present application obtain a reference ground texture map; and when determining that a target area in the reference ground texture map needs to be updated, control a first vehicle in an automated guided vehicle group to move to a first position of the target area and control a second vehicle in the automated guided vehicle group to move to a second position of the target area, wherein the first position and the second position are located at two ends of the target area, the first vehicle is an automated guided transport vehicle having a ground texture map acquisition function and an environmental image data acquisition function, and the second vehicle serves as a temporary reference object when the first vehicle acquires image data; obtain environmental image data acquired by the first vehicle when the second vehicle serves as a temporary reference object; update map data of the target area in the reference ground texture map based on the environmental image data to obtain a target ground texture map. By adopting the above method, it is possible to automatically update the ground texture map when a local failure of the ground texture map occurs, avoiding manual intervention and reducing the maintenance cost. Description of the Drawings

[0010] To more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those skilled in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0011] Figure 1 It shows a schematic flowchart of a map update method provided by an embodiment of the present application;

[0012] Figure 2 It shows Figure 1 a schematic flowchart of step S110 in

[0013] Figure 3 It shows a schematic diagram of a map provided by an embodiment of the present application;

[0014] Figure 4 It shows a schematic diagram of the positional relationship between a first vehicle and a second vehicle provided by an embodiment of the present application and a target area;

[0015] Figure 5 It shows another schematic flowchart of a map update method provided by an embodiment of the present application;

[0016] Figure 6 It shows a schematic diagram of a scenario of a map update method provided by an embodiment of the present application;

[0017] Figure 7 It shows a schematic diagram of an automated guided vehicle group provided by an embodiment of the present application;

[0018] Figure 8 It shows a block diagram of modules of a map update device provided by an embodiment of the present application;

[0019] Figure 9 It shows a block diagram of an electronic device for executing the map update method according to the embodiments of the present application;

[0020] Figure 10 It shows a storage unit for storing or carrying program codes for implementing the map update method according to the embodiments of the present application. Detailed implementation manners

[0021] To enable those skilled in the art to better understand the solutions of the present application, the following clearly and completely describes the technical solutions in the embodiments of the present application in conjunction with the accompanying drawings in the embodiments of the present application.

[0022] Please refer to Figure 1 , Figure 1Schematic flowchart of a map update method provided by one embodiment of the present application. This method can be applied to an electronic device, which can be an automated guided vehicle (AGV) in an AGV fleet (e.g., the first vehicle), a terminal device associated with each AGV in the AGV fleet, or a server, etc. This method can also be jointly executed by each AGV in the AGV fleet, and specific limitations are not made here.

[0023] Among them, in some embodiments, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery network (CDN), and big data and artificial intelligence platforms.

[0024] The terminal device can be a smartphone, a tablet computer, a laptop computer, a desktop computer, a smart voice interaction device, a vehicle-mounted terminal, etc., but is not limited thereto.

[0025] The map update method specifically can include the following steps S110 to S140.

[0026] Step S110: Obtain a reference ground texture map.

[0027] Among them, the reference ground texture map refers to a navigation map that is pre-created and can be used for the navigation of each AGV in the AGV fleet.

[0028] The way to obtain the reference ground texture map can be to receive the reference ground texture map uploaded by any one of the AGVs in the AGV fleet, or to obtain the reference ground texture automated transportation map from the memory of the electronic device or the associated storage device.

[0029] Among them, the AGV can refer to any vehicle that can perform ground texture positioning through the reference ground texture map, and it can be specifically applied to scenarios such as logistics handling and production line handling to perform ground texture positioning through the reference ground texture map, so as to achieve logistics handling, production line handling, etc.

[0030] Among them, the AGV fleet includes multiple AGVs, such as including at least one AGV with a ground texture image acquisition function and an environmental image data acquisition function and multiple AGVs only with a ground texture image acquisition function.

[0031] In an implementable manner, please refer to Figure 2 , the reference ground texture map can be created based on the following method:

[0032] Step S111: Obtain multiple initial ground texture images and multiple groups of initial environmental image data collected during the driving of the first vehicle.

[0033] Herein, the first vehicle refers to an automated guided vehicle with a ground texture image acquisition function and an environmental image data acquisition function. For example, the first vehicle can be an automated guided vehicle including a downward-looking imaging device (such as a camera) and a LiDAR (Light Detection and Ranging) device, or an automated guided vehicle including a downward-looking imaging device and an environmental imaging device.

[0034] It is worth mentioning that the LiDAR device constructs a three-dimensional point cloud map of the surrounding environment by emitting laser light and measuring the reflection time, while the environmental imaging device and the downward-looking imaging device generally refer to color or black-and-white cameras for capturing visual images. When the first vehicle is an automated guided vehicle including a downward-looking imaging device and a LiDAR device, the initial environmental image data is specifically point cloud data; when the first vehicle is an automated guided vehicle including a downward-looking imaging device and an environmental imaging device, the initial environmental image data is an RGB image.

[0035] Step S112: Construct an initial ground texture map based on multiple initial ground texture images.

[0036] In an implementable manner, multiple initial ground texture images can be processed using image processing and computer vision techniques (such as image stitching, feature matching, etc.), and then the processed images can be integrated into a continuous ground texture map.

[0037] Specifically, each initial ground texture image can be preprocessed (such as performing one or more of denoising, correction, and enhancement). Corner detection is performed on the preprocessed initial ground texture image to find stable feature points in the image, and a descriptor is calculated for each feature point. Then, based on the descriptors of each feature point, the matching feature points between each adjacent pair of images are searched, and the geometric transformation parameters (rotation angle, scaling ratio, translation distance, etc.) between each adjacent pair of images are obtained according to the matching feature points between each adjacent pair of images; according to the geometric transformation parameters between each adjacent pair of images, multiple preprocessed initial ground texture maps are transformed to the same coordinate system and then aligned and fused to obtain the initial ground texture map.

[0038] Step S113: Construct an initial environmental map based on multiple groups of initial environmental image data.

[0039] In one possible implementation, if the initial environmental image data is RGB image, preprocessing is performed on each group of initial environmental image data (e.g., one or more preprocessing methods such as denoising, color correction, and image correction are used for preprocessing) to obtain a preprocessed image. Thereafter, object detection can be performed on the preprocessed image to obtain the objects in the preprocessed image, or semantic segmentation can be performed on the image to obtain the category corresponding to each pixel in the preprocessed image. Then, visual technology can be used to estimate the depth information of each pixel point to construct a three-dimensional environmental model. The three-dimensional environmental models corresponding to multiple groups of initial environmental data are aligned and then fused to obtain an initial environmental map.

[0040] In another possible implementation, if the initial environmental image data is point cloud data, preprocessing is performed on each group of initial environmental image data (e.g., preprocessing methods such as denoising, downsampling, and ground segmentation are used for preprocessing) to obtain processed point cloud data. Thereafter, local features and global features in the processed point cloud data are extracted; the multiple groups of preprocessed point cloud data are aligned according to the local features and global features corresponding to each group of preprocessed point cloud data to ensure that the aligned multiple groups of point cloud data are in the same coordinate system, and the aligned multiple groups of point cloud data are fused to obtain a three-dimensional environmental model. Machine learning or deep learning methods are used to classify the point cloud data in the three-dimensional environmental model, and the semantics of the objects in the three-dimensional environmental model (such as roads, buildings, vegetation, etc.) are labeled according to the classification results, thereby obtaining a three-dimensional environmental map.

[0041] Step S114: Fuse the initial environmental map and the initial ground texture map to obtain a reference ground texture map.

[0042] In one possible implementation, the initial environmental map and the initial ground texture map can be aligned in the same coordinate system to fuse the aligned initial environmental map and the initial ground texture map.

[0043] Specifically, the initial environmental map and the initial ground texture map are converted into the same global coordinate system. Thereafter, a registration algorithm is used to align the feature points in the initial environmental map and the initial ground texture in the global coordinate system. For point cloud data, the registration algorithm used can be the iterative closest point algorithm; for image data, the registration algorithm used can be feature matching and homography matrix. Then, a fusion algorithm, such as Bayesian fusion or Kalman filtering algorithm, can be used to fuse the registered initial environmental map and the registered initial ground texture map to obtain a reference ground texture map.

[0044] By adopting the above steps S111 - S114, the initial environmental map and the initial ground texture map are aligned and fused in the same coordinate system to realize the image data collected by the fusion image acquisition device, forming a unified map model. This not only improves the accuracy of the map but also enhances the flexibility and adaptability of the system. Further, when the initial environmental map is generated based on the point cloud data obtained by the LiDAR device or the RGB image obtained by the environmental imaging device, it can effectively overcome the influence of external factors such as lighting changes and weather conditions, improving the robustness of map construction. Even under extreme conditions, the accuracy and integrity of the map can be guaranteed.

[0045] As Figure 3 shown, a schematic diagram of the driving direction of a reference ground texture map and a schematic diagram of the initial environmental map are shown, and a texture image of the reference ground texture map at a specified position in Figure 3 is shown. It can be seen that the spatial coverage ranges of the initial environmental map and the reference ground texture map are the same. Among them, the initial environmental map usually contains relatively macroscopic information, such as large-scale structures like building outlines and road directions. The reference ground texture map, on the other hand, provides more detailed surface texture information, which can reflect minute details such as ground materials, colors, and patterns.

[0046] In another implementable embodiment, the reference ground texture map can be created based on the following method:

[0047] Obtain multiple initial ground texture images collected during the driving process of the first vehicle. Among them, each first initial texture image is collected when there are no interfering objects (such as stains, shadows, water accumulation, and obstacles, any object that affects the texture map effect) on the corresponding ground. Construct a reference ground texture map based on the multiple initial ground texture images.

[0048] For the specific description of the above embodiment, reference can be made to the specific description of steps S111 and S112 in the previous text, and details will not be repeated here.

[0049] By adopting the above embodiment, by collecting the initial ground texture images without interfering objects (such as stains, shadows, water accumulation, and obstacles), it can ensure that the obtained initial ground texture images have higher quality and clearer texture details. Subsequently, it is easier to perform feature extraction and matching on the ground texture images without interfering objects, and the geometric transformation parameters between the initial texture images can be calculated more accurately, thereby improving the accuracy of the finally obtained reference ground texture map.

[0050] Step S120: If it is determined that the target area in the reference ground texture map needs to be updated, control the first vehicle in the automated guided vehicle group to move to the first position of the target area and control the second vehicle in the automated guided vehicle group to move to the second position of the target area, where the first position and the second position are located at both ends of the target area, the first vehicle is an automated guided transport vehicle with the functions of ground texture map acquisition and environmental image data acquisition, and the second vehicle serves as a temporary reference object when the first vehicle acquires image data.

[0051] Among them, it can be when it is determined that the target area fails (for example, when determining that the target area in the reference ground texture map fails during the feature point matching process between the ground texture maps collected by multiple automated guided vehicles in the automated guided vehicle group during driving). It can also be when the time duration since the last update of the target area reaches a preset time, it is determined that the target area in the reference ground texture map needs to be updated; it can also be when receiving an update instruction for the target area in the reference ground texture map sent by the user through the client, it is determined that the target area in the reference ground texture map needs to be updated.

[0052] Among them, the reasons for the failure of the target area may be that the ground in the target area has undergone physical changes (such as the appearance of new cracks, potholes, repair marks, etc.), the appearance of temporary obstacles, the appearance of stains, cleaning and maintenance, or changes due to natural factors (such as the ground being slippery due to rain or snow, or the ground color changing due to long-term sunlight exposure), etc.

[0053] It is worth mentioning that the position of the second vehicle does not change during the process of the first vehicle acquiring image data as a reference object for the first vehicle, and the first vehicle can move towards the second vehicle serving as a temporary reference object and acquire environmental image data during the movement. It should be understood that the first vehicle can also acquire ground texture images during the movement.

[0054] Considering that the road surface width covered by the target area may be relatively wide, therefore, the second vehicle can be one or multiple, such as at least two. At this time, at least two second vehicles are arranged on the edge of the target area, and the direction of this edge is the vertical direction of the navigation direction of the reference ground texture map. As Figure 4 shown, Figure 4 (a) in shows the case where the second vehicle is one, Figure 4 (a) in shows the case where the second vehicle is two.

[0055] It should be understood that the above-mentioned target area can be one or multiple. When there are multiple target areas, the above S120 can be executed for each target area.

[0056] Step S130: Obtain the environmental image data collected by the first vehicle with the second vehicle as a temporary reference object.

[0057] Among them, the electronic device can receive the environmental image data collected and uploaded by the first vehicle in real time, or can also set according to actual needs after receiving the data packet in which the collected environmental image data is packaged and uploaded after the first vehicle completes the collection of the environmental image data.

[0058] Step S140: Update the map data of the target area in the reference ground texture map based on the environmental image data to obtain a target ground texture map.

[0059] Among them, the environmental image data can be a group or multiple groups. The above environmental image data can be environmental point cloud data or environmental visual image data (such as RGB images).

[0060] In an implementable manner, when the environmental image data is a group and specifically environmental point cloud data, the above step S140 can be: intercept the point cloud data of the target area from the environmental point cloud data according to the positions of the first vehicle and the second vehicle in the environmental point cloud data; extract the ground texture information of the target area from the point cloud data of the target area; map the ground texture information of the target area to the target area in the reference ground texture map to obtain a target ground texture map.

[0061] Among them, in some scenarios, before performing intercepting the point cloud data of the target area from the environmental point cloud data according to the positions of the first vehicle and the second vehicle in the environmental point cloud data, the environmental image data (environmental point cloud data) can also be aligned with the reference ground texture map by using a registration algorithm. The above process can specifically be intercepting the point cloud data of the target area from the aligned environmental image data (environmental point cloud data). Then, perform semantic classification on the point cloud data of the target area, separate the ground points from the point cloud data of the target area based on the semantic classification result, extract the texture information from the ground points, and map the texture information to the target area in the reference ground texture map to replace the texture information in the target area of the reference ground texture map to obtain a target ground texture map.

[0062] In another possible implementation, if there are multiple sets of environmental image data, and the environmental image data is specifically environmental point cloud data, the above step S140 may be: aligning the multiple sets of environmental image data to ensure that the multiple sets of environmental image data are in the same coordinate system. Thereafter, fusing the multiple sets of aligned environmental image data (environmental point cloud data) to generate a complete three-dimensional environmental model. Thereafter, performing semantic classification on the three-dimensional environmental model, and separating the ground points in the target area from the three-dimensional environmental model based on the semantic classification result, the first position, and the second position; and extracting texture information from the ground points, and mapping the texture information to the target area of the reference ground texture map to replace the texture information in the target area of the reference ground texture map, thereby obtaining the target ground texture map.

[0063] In another possible implementation, if there is one set of environmental image data, and the environmental image data is specifically environmental visual image data (RGB image), the above step S140 may be: aligning the RGB image with the reference ground texture map according to the position information of the first vehicle, and preprocessing the aligned RGB image (for example, using one or more preprocessing methods such as denoising, calibration, and enhancement for preprocessing) to obtain a preprocessed RGB image; determining the image area corresponding to the target area in the RGB image according to the positions of the first vehicle and the second vehicle, extracting texture information from the image area, and mapping the texture information to the target area of the reference ground texture map to replace the texture information in the target area of the reference ground texture map, thereby obtaining the target ground texture map.

[0064] In another possible implementation, if there are multiple sets of environmental image data, and the environmental image data is specifically environmental visual image data (RGB image), the above step S140 may be: aligning the multiple sets of RGB images to ensure that the multiple sets of RGB images are in the same coordinate system. Preprocessing each of the aligned RGB images (for example, using one or more preprocessing methods such as denoising, calibration, and enhancement for preprocessing) to obtain preprocessed RGB images. Thereafter, stitching the preprocessed RGB images to obtain scene map data, determining the image area corresponding to the target area in the scene map data based on the first position and the second position, extracting texture information from the image area, and mapping the texture information to the target area of the reference ground texture map to replace the texture information in the reference ground texture map, thereby obtaining the target ground texture map.

[0065] In some scenarios, if the first vehicle collects ground texture images while collecting environmental image data (i.e., the aforementioned environmental point cloud data or environmental visual image data), the above step S140 may be to update the map data of the target area in the reference ground texture map based on the environmental image data and the ground texture images to obtain a target ground texture map. In this case, a similar method to steps S111 - S113 in the foregoing embodiment may be adopted to align the environmental image data with the ground texture images, extract the first ground texture information corresponding to the target area from the aligned environmental image data, and extract the second ground texture information corresponding to the target area from the aligned ground texture images; then, map the first ground texture information and the second ground texture information to the target area of the reference ground texture map respectively, and use a fusion algorithm (such as Bayesian fusion or Kalman filtering, etc.) to fuse the first ground texture information and the second ground texture information mapped to the target area respectively and then replace the texture information in the target area of the reference ground texture map to obtain a target ground texture map.

[0066] Through the above implementation manner, it is possible to combine environmental image data and ground texture images to provide more comprehensive and accurate texture information for the target area in the reference ground texture map.

[0067] By adopting the map update method of the present application, when a local area in the reference ground texture map used for navigation in an automated guided vehicle group fails, it is only necessary to use an automated guided vehicle (the first vehicle) with a ground texture map acquisition function and an environmental image data acquisition function in the automated guided vehicle group and a second vehicle as a temporary reference object to update the map data of the target area in the reference ground texture map according to the environmental image data collected by the first vehicle when the second vehicle is used as a temporary reference object. This not only reduces the required human and material resources but also speeds up the map update speed. Compared with the method of map update in the related art by manual on-site surveying or using multiple devices for complex operations, the map update speed of the present application is more efficient. In addition, during the map update process, it is not necessary to largely suspend or re-plan the entire work process of the automated guided vehicle group. Only the tasks of a small number of automated guided vehicles (i.e., the first vehicle and the second vehicle) need to be adjusted to complete the map update of the local area, so that the reference ground texture map can be kept in the latest state on the premise of minimizing the impact on the overall operation efficiency of the automated guided vehicle group.

[0068] To enable each automated guided vehicle in the automated guided vehicle group to navigate in a timely manner according to the updated ground texture map, please refer to Figure 5, in one implementable manner, after performing step S140, the method further includes: sending the target ground texture map to each automated guided vehicle in the automated guided vehicle group, so that each automated guided vehicle replaces the target ground texture map with a new reference ground texture map.

[0069] In one implementable manner, before performing step S120, the method further includes steps S160 - S180.

[0070] Step S160: Obtain texture maps collected in real time by a plurality of automated guided vehicles in the automated guided vehicle group when driving according to the reference ground texture map.

[0071] Among them, the texture maps collected in real time by the plurality of automated guided vehicles when driving according to the reference ground texture map are specifically ground texture maps. The above - mentioned manner of obtaining the texture maps collected by each automated guided vehicle may be to receive the texture maps periodically uploaded by each automated guided vehicle or the texture maps collected and uploaded in real time.

[0072] Step S170: Compare the texture maps collected in real time by each automated guided vehicle with the reference ground texture map to obtain a comparison result of the texture maps collected in real time by each automated guided vehicle and the reference ground texture map. The comparison result is used to indicate whether each texture map collected in real time by the automated guided vehicle matches the reference ground texture map.

[0073] In one implementable manner, the texture maps collected in real time by each automated guided vehicle when driving according to the reference ground texture map correspond to collection positions; the above - mentioned step S170 includes: for each texture map, align the texture map with the reference ground texture map according to the collection position corresponding to the texture map; determine the map area corresponding to the aligned texture map from the reference ground texture map; compare the map area with the texture map to obtain a comparison result of each texture map of each navigation transport vehicle and the map area corresponding to it in the reference ground texture map.

[0074] Among them, the process of comparing the map area with the texture map may specifically be, for each texture map, extract feature points from the texture map and the map area corresponding to the texture map, and use the nearest neighbor algorithm to match the feature points of the texture map with the feature points in the map area corresponding to the texture map to obtain multiple groups of matching point pairs. Each group of matching point pairs includes a feature point of the texture map and a feature point in the map area corresponding to the texture map; obtain the similarity between the texture map and the map area corresponding to the texture map according to the proportion of the matching point pairs in the total feature points or the average distance between multiple groups of matching point pairs. If the similarity is lower than a preset threshold, it is determined that the map area has changed.

[0075] The process of comparing the map area with the texture map can specifically be as follows: For each texture map, the texture map and the corresponding map area are pixel-by-pixel compared to obtain a pixel difference matrix. The pixel ratio of pixels in the difference matrix with a pixel difference greater than a preset difference threshold is statistically calculated. If the pixel ratio is greater than a preset ratio threshold, it is determined that the map area has changed.

[0076] Step S180: Based on the comparison results of the texture maps collected in real time by each of the automatic guided vehicles with the reference ground texture map, determine whether there is a target area in the reference ground texture map that needs to be updated.

[0077] In an implementable manner, if it is determined based on the comparison results of the texture maps collected in real time by each of the automatic guided vehicles with the reference ground texture map that there is a texture map with a comparison failure, the area corresponding to this texture map in the reference ground texture map can be used as the target area.

[0078] In another implementable manner, a heat map method can be used to determine, as the target area, the area that is determined to be invalid by the comparison results of multiple automatic guided vehicles within a certain time period.

[0079] Specifically, the reference ground texture map includes a plurality of pre-divided grid areas, and the comparison results include the comparison results of each texture map with the map area corresponding to it in the reference ground texture map. The process of using the heat map method to determine the target area specifically includes the following steps: Based on the comparison results of the texture maps collected in real time by multiple automatic guided vehicles with the map areas corresponding to them in the reference ground texture map, and the grid areas covered by each map area, the number of times of comparison failure corresponding to each grid area is statistically obtained; If there is a target grid area with a number of times greater than a preset number among the corresponding numbers of multiple grid areas, it is determined that there is a target area in the reference ground texture map that needs to be updated, and the target area is composed of the target grid areas; If there is no target grid area with a number of times greater than a preset number among the corresponding numbers of multiple map areas, it is determined that there is no target area in the reference ground texture map that needs to be updated.

[0080] Exemplarily, if there are N texture maps (e.g., 5 texture maps) in the comparison results of the texture maps collected in real time by multiple automatic guided vehicles with the map areas corresponding to them in the reference ground texture map, and the comparison results indicate comparison failure, the texture Figure 1 The grid areas covered by the corresponding map area are K1, K2, and K3, and the texture Figure 2 The grid areas covered by the corresponding map area are K2, K3, and K4, and the texture Figure 3 The grid areas covered by the corresponding map area are K1, K2, and K3, and the texture Figure 4The grid areas covered by the corresponding map area are K3, K4, and K5, and the texture Figure 5 The grid areas covered by the corresponding map area are K5, K6, and K7. Through the above statistics, it can be obtained that the number of comparison failures corresponding to grid area K1 is 2, the number of comparison failures corresponding to grid area K2 is 3, the number of comparison failures corresponding to grid area K3 is 4, the number of comparison failures corresponding to grid area K5 is 2, the number of comparison failures corresponding to grid area K6 is 1, and the number of comparison failures corresponding to grid area K7 is 1; if the preset number is 1, then the target grid areas can be determined as K1, K2, K3, K4, and K5, that is, the target area is the area jointly formed by K1, K2, K3, K4, and K5.

[0081] It is worth mentioning that the above steps S160 - S180 can be executed by an electronic device or jointly executed by the electronic device and each automatic guided vehicle in the automatic guided vehicle group.

[0082] Exemplarily, as Figure 6 shown, when the above steps S160 - S180 are jointly executed by the electronic device and each automatic guided vehicle in the automatic guided vehicle group, each automatic guided vehicle can execute steps S160 - S170 to determine the validity of the reference ground texture map, and when it is determined that there is a mismatch between each texture map it collects and the reference ground texture map, that is, when the reference ground texture map fails, send the texture map, the map area (failed area) corresponding to the texture map, and the matching result to the electronic device, so that the electronic device executes the aforementioned step S180. When it is determined that the target area needs to be updated, execute the aforementioned steps S120 - S140 to call the first vehicle and the second vehicle, so that the first vehicle with a fusion positioning function (with a ground texture map acquisition function and an environmental image data acquisition function) can collect environmental image data when the second vehicle is used as a temporary reference object, and the second vehicle uploads the environmental image data it collects to the electronic device, so that the electronic device updates the map data of the target area in the reference ground texture map based on the environmental image data to obtain a target ground texture map and distributes it to each automatic guided vehicle group.

[0083] By adopting the above steps S160-S180, it is possible to collect texture maps in real time and compare them with reference ground texture maps during the operation of the automated guided vehicle group, so that changes in ground texture can be discovered in time, thereby quickly determining which areas need to be updated, thereby helping to maintain the accuracy and timeliness of the ground texture maps. Furthermore, by comparing the real-time texture maps of multiple automated guided vehicles with the reference texture map, and uploading the map area corresponding to the real-time texture map in the reference texture base map when the comparison fails, so that the heat map method can be used later to identify the target area where the map is invalid, it can reduce misjudgments caused by errors or anomalies in the data collected by a single automated guided vehicle, and improve the accuracy of ground texture map updates.

[0084] For example, Figure 7 As shown, the automatic guided vehicle group of the present application includes at least one automatic guided vehicle with fusion positioning (first vehicle) and multiple automatic guided vehicles with only texture positioning (second vehicle) as an example for explanation. Among them, texture positioning refers to the ability to locate the texture downward, that is, the automatic guided vehicle has a downward imaging device; fusion positioning refers to the ability to locate LiDAR and texture at the same time, and can also have the ability to build a map by fusing texture and LiDAR and update the texture map based on LiDAR positioning information, that is, the automatic guided vehicle is equipped with LiDAR equipment and downward imaging equipment at the same time.

[0085] Before the automated guided vehicle group starts transportation, a map can be established using the first vehicle, that is, the first vehicle is controlled to collect multiple initial ground texture images and multiple sets of initial environment image data during operation, and then the aforementioned steps S111-S114 are executed to complete the creation of the initial ground texture map and the initial environment map (LiDAR map), and the initial ground texture map and the initial environment map are aligned and fused to obtain a reference ground texture map.

[0086] After that, the reference ground texture map can be sent to each automatic guided vehicle in the automatic guided vehicle group, so that each automatic guided vehicle can run according to the reference ground texture map. During the running process, each automatic guided vehicle can execute the foregoing steps S160-S180 to determine whether there is a target area failure and needs to be updated. If it is determined that there is a target area failure, a local update of the reference ground texture map is triggered. At this time, the automatic guided vehicle (the first vehicle) that can fuse positioning is used to jointly update the map of the failure area with any automatic guided vehicle. Specifically, at both ends of the failure area, the first vehicle and the second vehicle are respectively set. The second vehicle can be installed with a reflector on the body as a temporary reference object identifier and execute the foregoing steps S120-S140 to update the map of the target area. Based on the above, the solution provided by the embodiment of the present application has the characteristics of automatically detecting and automatically updating the reference ground texture map, so that this solution can automatically and quickly respond to the problem that the texture positioning navigation system fails due to ground pollution, avoiding the need for manual intervention in the long-term use of the texture positioning system in the related art, and greatly reducing the maintenance cost.

[0087] Please refer to Figure 8 , Figure 8 which shows a block diagram of a map update device provided by an embodiment of the present application. The following will elaborate on the Figure 8 process shown. The map update device 200 is applied to the above-mentioned electronic device. The map update device 200 includes: a reference map acquisition module 210, a movement control module 220, an image data acquisition module 230, and a map update module 240, where:

[0088] The reference map acquisition module 210 is used to acquire a reference ground texture map; the movement control module 220 is used to control the first vehicle in the automatic guided vehicle group to move to the first position of the target area and control the second vehicle in the automatic guided vehicle group to move to the second position of the target area when it is determined that the target area in the reference ground texture map needs to be updated. The first position and the second position are located at both ends of the target area. The first vehicle is an automatic guided transport vehicle with a ground texture map acquisition function and an environmental image data acquisition function. The second vehicle is used as a temporary reference object when the first vehicle acquires image data; the image data acquisition module 230 is used to acquire the environmental image data acquired by the first vehicle when the second vehicle is used as a temporary reference object; the map update module 240 is used to update the map data of the target area in the reference ground texture map based on the environmental image data to obtain a target ground texture map.

[0089] Further, the map update device 200 further includes a texture map acquisition module, a comparison module, and an update determination module. The texture map acquisition module is configured to acquire texture maps collected in real time by a plurality of automated guided vehicles in the automated guided vehicle group when driving according to the reference ground texture map. The comparison module is configured to compare the texture maps collected in real time by each of the automated guided vehicles with the reference ground texture map to obtain a comparison result between the texture maps collected in real time by each of the automated guided vehicles and the reference ground texture map, and the comparison result is used to indicate whether each texture map collected in real time by the automated guided vehicle matches the reference ground texture map. The update determination module is configured to determine whether there is a target area in the reference ground texture map that needs to be updated based on the comparison results between the texture maps collected in real time by each of the automated guided vehicles and the reference ground texture map.

[0090] Further, the reference ground texture map includes a plurality of map area maps, and the comparison result includes the comparison result of each texture map with its corresponding map area in the reference ground texture map. The update determination module is further configured to, based on the comparison results between the texture maps collected in real time by a plurality of the automated guided vehicles and their corresponding map areas in the reference ground texture map, and the grid areas covered by each map area, statistically obtain the number of times the comparison result corresponding to each grid area is a comparison failure. If there is a target grid area in which the corresponding number among the multiple grid areas is greater than a preset number, it is determined that there is a target area in the reference ground texture map that needs to be updated, and the target area is composed of the target grid area. If there is no target grid area in which the corresponding number among the multiple map area maps is greater than the preset number, it is determined that there is no target area in the reference ground texture map that needs to be updated.

[0091] In an implementable manner, the texture maps collected in real time by each automated guided vehicle when driving according to the reference ground texture map correspond to collection positions. The comparison module includes an alignment sub-module, a region determination sub-module, and a comparison sub-module. The alignment sub-module is configured to, for each texture map, align the texture map with the reference ground texture map according to the collection position corresponding to the texture map. The region determination sub-module is configured to determine, from the reference ground texture map, the map area corresponding to the aligned texture map. The comparison sub-module is configured to compare the map area with the texture map to obtain the comparison result between each texture map of each navigation transport vehicle and its corresponding map area in the reference ground texture map.

[0092] In an implementable manner, the reference map acquisition module includes a data acquisition sub-module, a texture map creation sub-module, an environment map creation sub-module, and a reference map acquisition sub-module. The data acquisition sub-module is configured to acquire multiple initial ground texture images and multiple groups of initial environment image data collected during the driving of the first vehicle; the texture map creation sub-module is configured to construct an initial ground texture map based on the multiple initial ground texture images; the environment map creation sub-module is configured to construct an initial environment map based on the multiple groups of initial environment image data; the reference map acquisition sub-module is configured to fuse the initial environment map and the initial ground texture map to obtain a reference ground texture map.

[0093] In an implementable manner, the environment image data collected by the first vehicle includes environment point cloud data or environment visual image data.

[0094] In an implementable manner, the map update device 200 further includes a map sending module, configured to send the target ground texture map to each automatic guided vehicle in the automatic guided vehicle group, so that each automatic guided vehicle replaces the target ground texture map with a new reference ground texture map.

[0095] In an implementable manner, if the environment image data is point cloud data; the map update module is further configured to intercept the point cloud data of the target area from the point cloud data according to the positions of the first vehicle and the second vehicle in the point cloud data respectively; extract the ground texture information of the target area from the point cloud data of the target area; map the ground texture information of the target area to the target area in the reference ground texture map to obtain a target ground texture map.

[0096] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0097] In several embodiments provided in the present application, the coupling between modules can be electrical, mechanical, or other forms of coupling.

[0098] In addition, in each embodiment of the present application, the various functional modules can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules.

[0099] Please refer to Figure 9 , Figure 9The schematic structural diagram of the electronic device provided by the embodiment of the present application is shown. The electronic device 300 may include the following components: a memory 310, one or more processors 320, and one or more applications. One or more applications are stored in the memory 310 and are used to cause the electronic device 400 to execute a map update method applied to the electronic device when called by the one or more processors 320.

[0100] Among them, the processor 320 may include one or more processing cores. The processor 320 connects various parts within the entire electronic device 400 through various interfaces and lines, and executes various functions of the electronic device and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory, and by calling the data stored in the memory. Optionally, the processor may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor may integrate a central processing unit (CPU), a graphics processing unit (GPU), a modem, etc. in one or several combinations. It can be understood that the above modem may not be integrated into the processor 320 and may be implemented separately by a communication chip.

[0101] The memory 310 may include a random access memory (RAM) and may also include a read-only memory (ROM). The memory 310 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 310 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing the above various method embodiments, etc. The data storage area may store data created during the use of the electronic device.

[0102] Please refer to again Figure 7 As shown, the embodiment of the present application further provides a transport vehicle system, including an electronic device and an automated guided vehicle group. The electronic device is respectively communicatively connected to a plurality of automated guided vehicles in the automated guided vehicle group. The plurality of automated guided vehicles include at least one automated guided transport vehicle having a ground texture map acquisition function and an environmental image data acquisition function, and a plurality of automated guided transport vehicles having only a ground texture map acquisition function.

[0103] Please refer to Figure 10 , which shows a structural block diagram of a computer-readable storage medium provided by an embodiment of the present application. Program code is stored in the computer-readable medium 400, and the program code can be called by a processor to execute the method described in the above method embodiment.

[0104] The computer-readable storage medium 400 can be an electronic memory such as a flash memory, EEPROM (electrically erasable programmable read-only memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium 400 includes a non-transitory computer-readable storage medium. The computer-readable storage medium 400 has a storage space for the program code 410 that executes any method step in the above method. These program codes can be read out from or written into one or more computer program products. The program code 410 can be compressed in an appropriate form, for example.

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A map updating method, characterized in that: The method comprises: Get the reference ground texture map; If it is determined that the target area in the reference ground texture map needs to be updated, controlling a first vehicle in the group of automated guided vehicles to move to a first position of the target area and controlling a second vehicle in the group of automated guided vehicles to move to a second position of the target area, wherein the first position and the second position are located at two ends of the target area, the first vehicle is an automated guided transport vehicle with ground texture map acquisition functions and environment image data acquisition functions, and the second vehicle serves as a temporary reference object when the first vehicle acquires image data; Acquire environmental image data collected by the first vehicle when the second vehicle serves as a temporary reference object; The map data of the target area in the reference ground texture map is updated based on the environmental image data to obtain a target ground texture map.

2. The method according to claim 1, characterized in that Before controlling the first vehicle in the group of automated guided vehicles to move to a first end position of the target area and controlling the second vehicle in the group of automated guided vehicles to move to a second end position of the target area, the method further includes: Acquire texture maps collected in real time by multiple automated guided vehicles in the automated guided vehicle group when they travel according to the reference ground texture map; Comparing the texture map collected by each of the automatic guided vehicles in real time with the reference ground texture map to obtain a comparison result between the texture map collected by each of the automatic guided vehicles in real time and the reference ground texture map, wherein the comparison result is used to indicate whether each texture map collected by the automatic guided vehicle in real time matches the reference ground texture map; Based on the comparison result between the texture map collected in real time by each of the automatic guided vehicles and the reference ground texture map, it is determined whether there is a target area in the reference ground texture map that needs to be updated.

3. The method according to claim 2, characterized in that The reference ground texture map includes a plurality of pre-divided grid areas, and the comparison result includes a comparison result between each texture map and its corresponding map area in the reference ground texture map; The step of determining whether there is a target area in the reference ground texture map that needs to be updated based on a comparison result between the texture map collected in real time by each of the automatic guided vehicles and the reference ground texture map comprises: Based on the comparison results of the texture images collected by the multiple automated guided vehicles in real time and the map areas corresponding to them in the reference ground texture map, and the grid areas covered by each map area, the comparison result corresponding to each grid area is obtained by counting the number of comparison failures; If there is a target grid area greater than a preset number of times in the corresponding times of the plurality of grid areas, it is determined that there is a target area in the reference ground texture map that needs to be updated, and the target area is composed of the target grid areas; If there is no target grid area greater than a preset number of times in the corresponding times in the plurality of map area maps, it is determined that there is no target area in the reference ground texture map that needs to be updated.

4. The method according to claim 2, characterized in that: The texture map collected in real time by each automatic guided vehicle when driving according to the reference ground texture map corresponds to a collection position; The step of comparing the texture map collected in real time by each of the automatic guided vehicles with the reference ground texture map to obtain a comparison result between the texture map collected in real time by each of the automatic guided vehicles and the reference ground texture map includes: For each of the texture maps, aligning the texture map with the reference ground texture map according to a collection position corresponding to the texture map; Determining a map area corresponding to the aligned texture map from the reference ground texture map; The map area is compared with the texture map to obtain a comparison result between each texture map of each navigation transport vehicle and its corresponding map area in the reference ground texture map.

5. The method according to claim 1, characterized in that Get a reference ground texture map, including Acquire a plurality of initial ground texture images and a plurality of groups of initial environment image data collected during the driving process of the first vehicle; Constructing an initial ground texture map based on multiple initial ground texture images; Constructing an initial environment map based on multiple sets of initial environment image data; The initial environment map is merged with the initial ground texture map to obtain a reference ground texture map.

6. The method according to any one of claims 1 to 5, characterized in that: The environmental image data collected by the first vehicle includes environmental point cloud data or environmental visual image data.

7. The method according to any one of claims 1 to 5, characterized in that: After updating the map data of the target area in the reference ground texture map based on the image data to obtain the target ground texture map, the method further includes: The target ground texture map is sent to each automated guided vehicle in the automated guided vehicle group, so that each automated guided vehicle replaces the target ground texture map with a new reference ground texture map.

8. The method according to claims 1-5, characterized in that: If the environmental image data is point cloud data; The updating of the map data of the target area in the reference ground texture map based on the environment image data to obtain the target ground texture map comprises: According to the positions of the first vehicle and the second vehicle in the point cloud data, respectively, intercepting point cloud data of a target area from the point cloud data; Extracting ground texture information of the target area from the point cloud data of the target area; The ground texture information of the target area is mapped to the target area in the reference ground texture map to obtain a target ground texture map.

9. A map updating device, characterized in that: The device comprises: A reference map acquisition module, used to acquire a reference ground texture map; A mobile control module, for controlling a first vehicle in an automated guided vehicle group to move to a first position of the target area and controlling a second vehicle in the automated guided vehicle group to move to a second position of the target area when it is determined that the target area in the reference ground texture map needs to be updated, wherein the first position and the second position are located at two ends of the target area, the first vehicle is an automated guided transport vehicle with ground texture map acquisition functions and environment image data acquisition functions, and the second vehicle serves as a temporary reference object when the first vehicle acquires image data; An image data acquisition module, used to acquire environmental image data collected by the first vehicle when the second vehicle serves as a temporary reference object; The map updating module is used to update the map data of the target area in the reference ground texture map based on the environmental image data to obtain a target ground texture map.

10. An electronic device, characterized in that: include: one or more processors; Memory; One or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the method according to any one of claims 1-8.

11. A transport vehicle system, characterized in that: It includes the electronic device and an automated guided vehicle group as described in claim 10, wherein the electronic device is communicatively connected to a plurality of automated guided vehicles in the automated guided vehicle group respectively, and the plurality of automated guided vehicles include at least one automated guided transport vehicle having a ground texture map acquisition function and an environmental image data acquisition function, and a plurality of automated guided transport vehicles having only a ground texture map acquisition function.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 8.

Images