Method and system for dynamically updating point cloud map

Abstract

The embodiment of the invention provides a point cloud map dynamic updating method and system, and the method is executed based on a mobile terminal, and comprises the steps: obtaining a static point cloud map and an initial dynamic point cloud map of a positioning region through a cloud processor; in response to a received update starting instruction, performing laser matching positioning based on the static point cloud map and the initial dynamic point cloud map, and obtaining dynamic point cloud elements of the positioning area; based on the dynamic point cloud elements, constructing a dynamic update map of the positioning area; in response to a received update ending instruction, evaluating the dynamic update map based on a positioning result of laser matching positioning; and uploading the dynamically updated map to the cloud processor in response to the situation that the evaluation result of the dynamically updated map meets a preset condition.

Description

Technical Field

[0001] This specification relates to the field of autonomous driving positioning, and in particular to a method and system for dynamically updating point cloud maps. Background Art

[0002] Unmanned vehicles can significantly improve transport efficiency and save costs during port container transport. Vehicles are typically equipped with multiple sensors, such as GPS, IMU, and LiDAR, to obtain the vehicle's current location information. LiDAR positioning often achieves this by matching online point clouds with offline point cloud maps. In container yards, GPS positioning can fail due to multipath effects. Furthermore, ports are constantly stacking and unloading containers, and container yards are a dynamically changing scene. This means offline maps cannot truly reflect the real-time environment, resulting in matching failures and inability to locate the vehicle. Therefore, to ensure successful laser matching, point cloud maps are updated during each yard operation.

[0003] In order to solve the problem that a single vehicle cannot update all container yard point cloud maps in a timely manner, it is necessary to provide a point cloud map dynamic update method and system to manage the dynamic point cloud map using a multi-vehicle update method. Summary of the Invention

[0004] One or more embodiments of the present specification provide a method for dynamically updating a point cloud map, which is executed on a mobile terminal and includes: obtaining a static point cloud map and an initial dynamic point cloud map of a positioning area through a cloud processor; in response to receiving a start update instruction, performing laser matching positioning based on the static point cloud map and the initial dynamic point cloud map, and obtaining dynamic point cloud elements of the positioning area; constructing a dynamically updated map of the positioning area based on the dynamic point cloud elements; in response to receiving an end update instruction, evaluating the dynamically updated map based on the positioning result of the laser matching positioning; and in response to the evaluation result of the dynamically updated map meeting a preset condition, uploading the dynamically updated map to the cloud processor.

[0005] One or more embodiments of the present specification provide a method for dynamically updating a point cloud map, which is executed based on a cloud processor and includes: sending a point cloud positioning map of a target positioning area to a mobile terminal, wherein the point cloud positioning map includes a static point cloud map and an initial dynamic point cloud map; in response to obtaining a dynamically updated map of the target positioning area uploaded by the mobile terminal, determining a target dynamic point cloud map of the target positioning area based on preset map update rules; sending the target dynamic point cloud map to a target terminal, and using the target dynamic point cloud map as the next round of initial dynamic point cloud map of the target positioning area.

[0006] One or more embodiments of the present specification provide a point cloud map dynamic update system, which is used to implement the above-mentioned point cloud map dynamic update method based on a mobile terminal, including an acquisition module, a positioning module, a construction module, an evaluation module and an upload module, wherein the acquisition module is configured to acquire a static point cloud map and an initial dynamic point cloud map of a positioning area through a cloud processor; the positioning module is configured to perform laser matching positioning based on the static point cloud map and the initial dynamic point cloud map in response to receiving a start update instruction, and acquire dynamic point cloud elements of the positioning area; the construction module is configured to construct a dynamically updated map of the positioning area based on the dynamic point cloud elements; the evaluation module is configured to evaluate the dynamically updated map based on the positioning result of the laser matching positioning in response to receiving an end update instruction; the upload module is configured to upload the dynamically updated map to the cloud processor in response to the evaluation result of the dynamically updated map meeting a preset condition.

[0007] One or more embodiments of the present specification provide a point cloud map dynamic update system, which is used to implement the above-mentioned point cloud map dynamic update method executed by a cloud processor, including a first sending module, an update module, and a second sending module, wherein the first sending module is configured to send a point cloud positioning map of a target positioning area to a mobile terminal, wherein the point cloud positioning map includes a static point cloud map and an initial dynamic point cloud map; the update module is configured to determine a target dynamic point cloud map of the target positioning area based on preset map update rules in response to obtaining a dynamically updated map of the target positioning area uploaded by the mobile terminal; the second sending module is configured to send the target dynamic point cloud map to a target terminal, and use the target dynamic point cloud map as the next round of initial dynamic point cloud map of the target positioning area.

[0008] One or more embodiments of this specification provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a method for dynamically updating a point cloud map. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein:

[0010] Figure 1A is an exemplary module diagram of a point cloud map dynamic update system according to some embodiments of this specification;

[0011] Figure 1B is an exemplary module diagram of a point cloud map dynamic update system according to other embodiments of this specification;

[0012] Figure 2 is an exemplary flow chart of a method for dynamically updating a point cloud map based on a mobile terminal according to some embodiments of this specification;

[0013] Figure 3 is an exemplary schematic diagram of determining quality assessment results according to some embodiments of this specification;

[0014] Figure 4 is an exemplary flow chart of a method for dynamically updating a point cloud map based on a cloud processor according to some embodiments of this specification;

[0015] Figure 5 is an exemplary flow chart of determining a target dynamic point cloud map according to some embodiments of this specification;

[0016] Figure 6 is an exemplary schematic diagram of a prediction model according to some embodiments of this specification. DETAILED DESCRIPTION

[0017] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0018] It should be understood that the terms "system," "device," "unit," and / or "module" used herein are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0019] As used in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not refer to the singular but also include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0020] Flowcharts are used throughout this specification to illustrate the operations performed by systems according to embodiments of this specification. It should be understood that preceding or following operations do not necessarily need to be performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0021] Figure 1A It is an exemplary module diagram of a mobile-based point cloud map dynamic update system (referred to as the first system 110 ) according to some embodiments of this specification.

[0022] In some embodiments, as Figure 1A As shown, the first system 110 may include an acquisition module 111 , a positioning module 112 , a construction module 113 , an evaluation module 114 and an upload module 115 .

[0023] In some embodiments, the acquisition module 111 may be configured to acquire a static point cloud map and an initial dynamic point cloud map of the positioning area from the cloud.

[0024] In some embodiments, the positioning module 112 is configured to perform laser matching positioning based on the static point cloud map and the initial dynamic point cloud map in response to receiving the start update instruction, and obtain dynamic point cloud elements of the positioning area.

[0025] In some embodiments, the construction module 113 is configured to construct a dynamically updated map of the positioning area based on the dynamic point cloud elements.

[0026] In some embodiments, the construction module 113 is further configured to construct a dynamically updated map of the positioning area based on the dynamic point cloud elements by using a point cloud accumulation method and / or a real-time positioning and map construction method.

[0027] In some embodiments, the evaluation module 114 is configured to evaluate the dynamically updated map based on the positioning result of the laser matching positioning in response to receiving the end-update instruction.

[0028] In some embodiments, the evaluation module 114 is further configured to determine an evaluation result of the dynamically updated map based on a comparison result of the positioning result of the laser matching positioning and the satellite positioning result.

[0029] In some embodiments, the uploading module 115 is configured to upload the dynamically updated map to the cloud in response to the evaluation result of the dynamically updated map meeting a preset condition.

[0030] Figure 1B It is an exemplary module diagram of a point cloud map dynamic update system based on a cloud processor (referred to as the second system 120) according to other embodiments of this specification.

[0031] In some embodiments, as Figure 1B As shown, the second system 120 may include a first sending module 121 , an updating module 122 and a second sending module 123 .

[0032] In some embodiments, the first sending module 121 is configured to send a point cloud positioning map of the target positioning area to the mobile terminal, where the point cloud positioning map includes a static point cloud map and an initial dynamic point cloud map.

[0033] In some embodiments, the first sending module 121 is further configured to send a point cloud positioning map of the target positioning area to the mobile terminal in response to receiving an update request uploaded by the mobile terminal, and the update request at least includes an area identifier of the target positioning area.

[0034] In some embodiments, the updating module 122 is configured to determine a target dynamic point cloud map of the target positioning area based on preset map updating rules in response to obtaining a dynamically updated map of the target positioning area uploaded by the mobile terminal.

[0035] In some embodiments, the preset map update rule includes determining a target dynamic point cloud map of the target positioning area based on upload time and / or map quality.

[0036] In some embodiments, the update module 122 is further configured to obtain one or more dynamically updated maps and target data uploaded by one or more mobile terminals within a preset time period, the target data including the collection parameters of the mobile terminal and the evaluation results of the dynamically updated map; based on the target data, determine the accuracy of one or more dynamically updated maps; based on the accuracy of the dynamically updated map, determine the target dynamic point cloud map of the target positioning area.

[0037] In some embodiments, the second sending module 123 is configured to send the target dynamic point cloud map to the target terminal, and use the target dynamic point cloud map as the next round of initial dynamic point cloud map of the target positioning area.

[0038] For more information about the functions of the modules of the first system 110 and the second system 120, please refer to Figure 2-6 Related description.

[0039] It should be noted that the above description of the point cloud map dynamic update system and its modules is for convenience only and does not limit this specification to the scope of the embodiments described. It is understood that those skilled in the art, after understanding the principles of the system, may arbitrarily combine the modules or form subsystems connected to other modules without departing from these principles.

[0040] Figure 2 This is an exemplary flow chart of a method for dynamically updating a point cloud map according to some embodiments of this specification. Figure 2 As shown, the process 200 includes the following steps. In some embodiments, the process 200 can be executed by the mobile terminal or the first system 110. For the description of the first system 110, please refer to Figure 1ACorresponding description.

[0041] A mobile terminal refers to a mobile device. For example, a mobile terminal may include a transport vehicle, drone, or other mobile device and / or a processing system configured within a vehicle, drone, or other device. In some embodiments, the mobile terminal may be configured to receive data or instructions from a cloud processor and execute corresponding operations, or it may upload data to the cloud processor. A description of the cloud processor is provided below.

[0042] In step 210 , a static point cloud map and an initial dynamic point cloud map of the positioning area are obtained through a cloud processor.

[0043] The cloud refers to a terminal that can be remotely accessed and / or processed through the network. For example, the cloud may include private clouds, public clouds, hybrid clouds, and industry clouds. In some embodiments, the cloud may include a cloud processor. A cloud processor refers to a processor based on a cloud computing platform. For example, a cloud processor may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), a microprocessor, or any combination thereof. In some embodiments, the cloud processor may be configured to receive data or requests uploaded by a mobile terminal and perform corresponding operations, and may also send data to the mobile terminal.

[0044] A positioning area refers to an area where a point cloud map update is required. For example, in a freight terminal scenario, a positioning area may be a pre-divided yard area. In some embodiments, each positioning area may correspond to an area identifier (e.g., an area ID).

[0045] A point cloud map is a map composed of a data set of points in a point cloud coordinate system. In some embodiments, the point cloud map can be collected and constructed using a mobile device such as a 3D imaging sensor or lidar, and uploaded to a cloud processor.

[0046] A static point cloud map refers to a point cloud map that contains only static elements. In some embodiments, the mobile terminal can use methods such as SLAM (Simultaneous Localization and Mapping) to construct a point cloud map, retaining only the static elements therein as a static point cloud map.

[0047] Static point cloud maps can be constructed when the positioning area is open (e.g., there are few vehicles and pedestrians), and can be reused multiple times after construction.

[0048] Static elements are those elements within the location area of ​​the point cloud map that are not prone to change in position. For example, static point cloud elements can include lane markings, railings, stone pillars, indicator lights, signboards, buildings, etc. within the location area. Static elements in the point cloud map can be selected based on algorithmic models or manual annotation. For example, the algorithmic model can be a binary classification model.

[0049] SLAM is a technology that can simultaneously achieve real-time positioning and map construction. In some embodiments, based on SLAM, a mobile device can autonomously move in an unknown environment, build a map, and locate its own position through autonomous detection and computer algorithm processing.

[0050] The initial dynamic point cloud map refers to an initial point cloud map containing only dynamic elements. In some embodiments, the mobile terminal can use SLAM methods to construct a point cloud map, retaining only the dynamic elements therein as the initial dynamic point cloud map. The method for selecting dynamic elements is similar to the method for selecting static elements described above.

[0051] In some embodiments, if an initial dynamic point cloud map has been constructed for a certain positioning area in the past, the initial dynamic point cloud map for the positioning area may be the previously constructed dynamic point cloud map.

[0052] Dynamic elements refer to elements in a point cloud map that may change position. For example, dynamic elements can include vehicles, containers, pedestrians, etc. within the positioning area. Taking the freight terminal scene as an example, the dynamic element is a container.

[0053] In some embodiments, the mobile terminal can obtain a static point cloud map and an initial dynamic point cloud map of the positioning area through the cloud processor in various ways. For example, the mobile terminal can obtain a static point cloud map and an initial dynamic point cloud map with a corresponding positioning representation through the cloud processor based on the positioning identifier of the positioning area.

[0054] Step 220 , in response to receiving the start update instruction, laser matching positioning is performed based on the static point cloud map and the initial dynamic point cloud map, and dynamic point cloud elements of the positioning area are obtained.

[0055] The start update instruction is an instruction for instructing to update the initial dynamic point cloud map.

[0056] In some embodiments, the mobile terminal can obtain the start update instruction based on various methods. For example, when a sensor at the entrance of a certain location area detects that the mobile terminal has entered the location area, the monitoring result is uploaded to the cloud processor, and the cloud processor sends the start update instruction to the mobile terminal. In some embodiments, the mobile terminal can also use its own sensors to automatically generate the start update instruction when the sensor detects that the mobile terminal has passed through the entrance of a certain location area.

[0057] Dynamic point cloud elements refer to real-time point cloud data of dynamic elements.

[0058] Laser matching positioning refers to a positioning method based on laser radar matching point cloud map.

[0059] In some embodiments, in response to receiving the start update instruction, the mobile terminal can perform laser matching positioning based on the static point cloud map and the initial dynamic point cloud map, and obtain dynamic point cloud elements of the positioning area.

[0060] For example, after detecting a vehicle entering a certain positioning area, the cloud processor can issue a start update command. After receiving the update command, the mobile terminal can merge the static point cloud map with the initial dynamic point cloud map to obtain a merged point cloud map. The current point cloud data is obtained through the lidar and matched with the merged point cloud map to obtain the location coordinates of the corresponding elements in the point cloud data in the point cloud map. At the same time, within the positioning area, the mobile terminal can obtain dynamic point cloud elements within the observation range through the lidar. As an example only, the observation range of the lidar can be a sphere with a radius of less than 100m centered on the lidar.

[0061] In some embodiments, the mobile terminal can also verify the results of laser matching positioning in combination with satellite positioning signals to make positioning more accurate. For example, the mobile terminal can compare the results of laser matching positioning with the results of satellite positioning to determine whether the positioning is consistent. Figure 3 The corresponding description.

[0062] Step 230: construct a dynamically updated map of the positioning area based on the dynamic point cloud elements.

[0063] A dynamically updated map refers to a dynamic point cloud map that is updated based on dynamic point cloud elements acquired in real time.

[0064] In some embodiments, the mobile terminal can construct a dynamically updated map of the positioning area based on the dynamic point cloud elements in various ways. For example, the mobile terminal can partially or globally replace the dynamic elements in the initial dynamic point cloud map of the positioning area based on the dynamic point cloud elements to construct a dynamically updated map of the positioning area.

[0065] In some embodiments, the mobile terminal may construct a dynamically updated map of the positioning area based on dynamic point cloud elements by using a point cloud accumulation method and / or a real-time positioning and map construction method.

[0066] Point cloud accumulation refers to a method of constructing a point cloud map by accumulating point cloud data obtained from multiple locations. In some embodiments, when laser matching positioning is sufficiently accurate, the mobile terminal can use the point cloud accumulation method to construct a dynamically updated map of the positioning area.

[0067] For example, when the satellite positioning results are basically consistent with the positioning of laser matching positioning, the mobile terminal can obtain point cloud data of multiple points in the positioning area based on the laser radar, obtain dynamic point cloud elements of multiple position ranges, and build a complete dynamically updated map of the positioning area by accumulating dynamic point cloud elements of different points. Basic consistency in positioning means that in the positioning information of the same point, the coordinate error of each dimension (such as longitude and latitude) is within a preset distance (such as 5cm). The preset distance can be set according to actual conditions. For relevant instructions on satellite positioning, please refer to Figure 3 The corresponding description.

[0068] Real-time positioning and mapping refers to the construction of point cloud maps based on real-time positioning data, laser odometry, and SLAM methods. For example, a mobile device can use SLAM methods to construct an initial map of the positioning area. The mobile device's own position is inferred based on the laser odometry. Real-time satellite positioning data and laser matching positioning data are used as global constraints to optimize the initial map and construct a dynamically updated map of the positioning area.

[0069] In some embodiments of this specification, by selecting an appropriate map construction method based on dynamic point cloud elements and considering actual conditions, a more reasonable dynamic map can be constructed. For example, to improve the efficiency of dynamically updated maps, a simpler point cloud accumulation method can be used; to build a more accurate dynamically updated map, a real-time positioning and map construction method can be used.

[0070] Step 240 : In response to receiving the end-update instruction, the dynamically updated map is evaluated based on the positioning result of the laser matching positioning.

[0071] The end update instruction is an instruction to instruct the end of updating the point cloud map.

[0072] In some embodiments, the mobile terminal can obtain the end-update instruction based on various methods. For example, when a sensor at the exit of a certain location area detects that the mobile terminal has left the location area, the monitoring result is uploaded to the cloud processor, which then sends the end-update instruction to the mobile terminal. In some embodiments, the mobile terminal can also use its own sensors to automatically generate an end-update instruction when the sensor detects that the mobile terminal has passed through the exit of a certain location area.

[0073] In some embodiments, in response to receiving the end update instruction, the mobile terminal can evaluate the dynamically updated map in a variety of ways based on the positioning results of the laser matching positioning to determine the evaluation results.

[0074] The evaluation result reflects the accuracy of the dynamically updated map. In some embodiments, the evaluation result can be represented by a numerical value, with a larger numerical value indicating higher quality of the dynamically updated map. For example, the mobile terminal can use the positioning results of laser matching positioning combined with human feedback to score the dynamically updated map as the evaluation result.

[0075] In some embodiments, the mobile terminal can determine the evaluation result of the dynamically updated map based on the comparison result of the laser matching positioning result and the satellite positioning result. The more points with consistent positioning in the comparison result, the higher the evaluation result score. For details, please refer to Figure 3 Related instructions.

[0076] Step 250 : In response to the evaluation result of the dynamically updated map meeting a preset condition, uploading the dynamically updated map to the cloud processor.

[0077] Preset conditions refer to pre-set conditions for evaluating map quality. In some embodiments, the pre-set condition may be that the score in the evaluation results of the dynamically updated map reaches a pre-set standard. When the score reaches the pre-set standard, the dynamically updated map is considered to be constructed successfully and valid. The pre-set standard can be preset based on actual circumstances.

[0078] In some embodiments, in response to the evaluation result of the dynamically updated map meeting a preset condition, the mobile terminal may upload the dynamically updated map to the cloud processor.

[0079] In some embodiments, the dynamically updated map uploaded by the mobile terminal to the cloud processor may include a map number.

[0080] The map number is a number that reflects the dynamically updated map-related information. In some embodiments, the map number may include the area identifier of the positioning area, the map generation time, the mobile terminal identifier, etc.

[0081] In some embodiments of the present specification, laser matching positioning is performed based on a static point cloud map and an initial dynamic point cloud map to obtain dynamic point cloud elements of the positioning area. Based on the dynamic point cloud elements, a dynamically updated map of the positioning area is constructed, and the dynamically updated map is evaluated. The dynamically updated map that meets preset conditions is uploaded to a cloud processor. The dynamically updated map can reflect the dynamic changes in the positioning area environment more accurately and promptly, so that the mobile terminal has a better map reference during operation, which is conducive to reducing labor costs and improving the efficiency of automated transportation.

[0082] Figure 3 is an exemplary schematic diagram of determining evaluation results according to some embodiments of this specification.

[0083] In some embodiments, as Figure 3As shown, the mobile terminal can determine the evaluation result 340 of the dynamic map update based on the comparison result 330 of the positioning result 310 of the laser matching positioning and the satellite positioning result 320. For the relevant description of the positioning result of the laser matching positioning, the dynamic map update and the evaluation result, please refer to Figure 2 The corresponding content.

[0084] Satellite positioning result 320 refers to the result of positioning based on satellite signals. For example, the satellite positioning result can be positioning information obtained based on the Global Positioning System (GPS). The satellite positioning result can include the geographic location, movement speed, and time information of each element.

[0085] In some embodiments, the mobile terminal can compare the positioning results 310 and the satellite positioning results 320 based on the laser matching positioning to determine the comparison result 330. For example, the mobile terminal can obtain the positioning results based on the laser matching positioning and the satellite positioning results of multiple points in the positioning area during the entire process of generating the dynamically updated map, compare the positioning information of the two positioning results of the same point, determine the proportion of points with consistent positioning in all the points being compared, and use the percentage as the aforementioned comparison result. Among them, the description of consistent positioning can be found in Figure 2 The corresponding description.

[0086] In some embodiments, the mobile terminal can determine the evaluation result 340 of the dynamically updated map based on the above-mentioned comparison results in various ways. For example, the mobile terminal can directly use the comparison result as the evaluation result. For another example, the mobile terminal can correspond the comparison results of different ratio ranges to different score levels, and use the corresponding score levels as the evaluation results. The correspondence between the ratio range and the score level can be set according to actual conditions. For example, a comparison result of less than 70% corresponds to an "unqualified" level, a comparison result of 70% to 80% corresponds to a "qualified" level, and a comparison result of more than 80% corresponds to an "accurate" level, etc.

[0087] In some embodiments of the present specification, by determining the evaluation results of the dynamically updated map by comparing the positioning results based on laser matching positioning with the satellite positioning results, the quality of the constructed dynamically updated map can be evaluated efficiently and automatically, ensuring that the dynamically updated map subsequently uploaded to the cloud processor is relatively accurate.

[0088] In some embodiments, in response to the evaluation result being lower than the first threshold, the mobile terminal may perform an accuracy check on the initial dynamic point cloud map.

[0089] The first threshold is used to determine whether to perform an accuracy check. In some embodiments, the evaluation result being lower than the first threshold can mean that the comparison result between the laser matching positioning result and the satellite positioning result is lower than a preset value. For example, the preset value can be 70%. The preset value can be set based on actual conditions.

[0090] Accuracy verification refers to a verification to determine whether the initial dynamic point cloud map is accurate. In some embodiments, in response to the evaluation result being lower than the first threshold, the mobile terminal can perform accuracy verification on the initial dynamic point cloud map in a variety of ways.

[0091] In some embodiments, the accuracy check can be: determining whether the creation time of the initial dynamic point cloud map meets the preset time condition; in response to not meeting the preset time condition, performing laser matching positioning based on the static point cloud map, and obtaining the dynamic point cloud elements of the positioning area to construct the next round of initial dynamic point cloud map.

[0092] The next round of initial dynamic point cloud map may refer to an initial dynamic point cloud map to be uploaded to the cloud processor so as to be used by the mobile terminal when it enters the positioning area next time.

[0093] In some embodiments, the preset time condition may be that the creation time of the current initial dynamic point cloud map is no more than a preset time threshold from the current time. For example, the preset time threshold may be 24 hours. The preset time threshold may be set according to actual circumstances.

[0094] In some embodiments, in response to the creation time of the initial dynamic point cloud map not meeting the preset time condition, the mobile terminal can perform laser matching positioning based on the static point cloud map and obtain the dynamic point cloud elements of the positioning area to construct the next round of initial dynamic point cloud map.

[0095] In some embodiments of the present specification, by abandoning the outdated initial dynamic point cloud map when the creation time of the initial dynamic point cloud map does not meet the preset time condition, obtaining dynamic point cloud elements based on the static point cloud map, and timely constructing a new initial dynamic point cloud map, the validity of the initial dynamic point cloud map can be guaranteed, the map accuracy can be improved, and the reduction in transportation efficiency due to failure to update the initial dynamic point cloud map in a timely manner can be avoided.

[0096] In some embodiments of the present specification, by performing accuracy verification on the initial dynamic point cloud map, when the dynamically updated map is not accurate enough, it can be determined whether to continue using the initial dynamic point cloud map or to construct a new initial dynamic point cloud map to ensure a more secure subsequent transportation process.

[0097] Figure 4 This is an exemplary flow chart of a method for dynamically updating a point cloud map according to some embodiments of this specification. Figure 4As shown, the process 400 includes the following steps. In some embodiments, the process 400 can be executed by a cloud processor or the second system 120. For the description of the second system 120, please refer to Figure 1B For details about cloud processors, see Figure 2 Corresponding description.

[0098] Step 410: Send the point cloud positioning map of the target positioning area to the mobile terminal.

[0099] For instructions on mobile devices, see Figure 2 The corresponding description.

[0100] The target location area refers to the area where the mobile terminal needs to perform operations. In some embodiments, the target location area can be the area where the mobile terminal is about to or is currently performing operations. Taking the freight terminal scenario as an example, the target location area can be the yard where the mobile terminal is about to enter to perform operations.

[0101] Point cloud positioning map refers to a point cloud map containing positioning information required for mobile terminal operations. In some embodiments, the point cloud positioning map may include a static point cloud map and an initial dynamic point cloud map. For details about static point cloud maps and initial dynamic point cloud maps, please refer to Figure 2 The corresponding description.

[0102] In some embodiments, in response to receiving an update request uploaded by the mobile terminal, the cloud processor may send a point cloud positioning map of the target positioning area to the mobile terminal.

[0103] An update request is a request from a mobile terminal to update a point cloud map. In some embodiments, the update request includes at least an area identifier of a target location area. Based on the area identifier of the target location area, the cloud processor can determine the point cloud location map of the target location area that needs to be sent to the mobile terminal.

[0104] Step 420 : In response to obtaining the dynamically updated map of the target positioning area uploaded by the mobile terminal, a target dynamic point cloud map of the target positioning area is determined based on a preset map update rule.

[0105] For instructions on dynamically updating maps, see Figure 2 The corresponding description.

[0106] The preset map update rule refers to a preset rule for updating the initial dynamic point cloud map. For example, the preset map update rule may include determining the most recently received dynamic update map as the target dynamic point cloud map.

[0107] The target dynamic point cloud map refers to the dynamic point cloud map of the target positioning area that needs to be sent to the mobile terminal. In some embodiments, for the same target positioning area, the cloud processor may receive dynamic update maps uploaded by multiple mobile terminals. Therefore, it is necessary to determine the target dynamic point cloud map based on the multiple dynamic update maps and according to the preset map update rules.

[0108] In some embodiments, in response to obtaining a dynamically updated map of the target positioning area uploaded by the mobile terminal, the cloud processor may determine a target dynamic point cloud map of the target positioning area based on preset map update rules. For example, the cloud processor may determine a dynamically updated map for updating based on the preset map update rules, and determine a target dynamic point cloud map of the target positioning area based on a portion or all of the dynamic updated map that covers the initial dynamic point cloud map.

[0109] In some embodiments, the preset map update rules may include determining a target dynamic point cloud map of the target positioning area based on upload time and / or map quality.

[0110] For example, the cloud processor can save the latest received dynamic update map of the target positioning area based on the upload time of the dynamic update map, and overwrite the corresponding initial dynamic point cloud map as the target dynamic point cloud map of the target positioning area; for another example, the cloud processor can use the dynamic update map of the target positioning area with the highest quality within a preset time period as the target dynamic point cloud map of the target positioning area based on the map quality. For more information about the preset time period, please refer to Figure 5 corresponding instructions.

[0111] In some embodiments, the map quality of the dynamically updated map can be determined based on the evaluation results of the dynamically updated map, or can be determined based on the accuracy of the dynamically updated map. Figure 2 、 3 For details on the accuracy of dynamically updated maps, see Figure 5 corresponding instructions.

[0112] In some embodiments of the present specification, by determining the target dynamic point cloud map of the target positioning area based on the upload time and / or map quality of the dynamically updated map, the process of determining the target dynamic point cloud map can be made more efficient, and the determined target dynamic point cloud map can be more reliable and accurate.

[0113] Step 430: Send the target dynamic point cloud map to the target terminal as the initial dynamic point cloud map of the target positioning area.

[0114] The target terminal refers to the mobile terminal in the target positioning area other than the mobile terminal that serves as the uploading terminal. The uploading terminal refers to the mobile terminal that uploads the dynamic update map corresponding to the target dynamic point cloud map.

[0115] In some embodiments, the cloud processor may send a target dynamic point cloud map to the target terminal as an initial dynamic point cloud map of the target positioning area. In some embodiments, when the cloud processor sends the target dynamic point cloud map to the target terminal, it may also send the creation time of the map and the area identifier of the corresponding target positioning area.

[0116] In some embodiments of the present specification, by updating the next round of initial dynamic point cloud maps of the target positioning area based on preset map update rules, the initial dynamic point cloud maps can be reconstructed in a timely manner, so that the next round of initial dynamic point cloud maps updated and sent to the target terminal have higher reliability and accuracy, accurately reflect environmental changes, and improve transportation efficiency.

[0117] Figure 5 This is an exemplary flow chart of determining a target dynamic point cloud map according to some embodiments of this specification. Figure 5 As shown, the process 500 includes the following steps. In some embodiments, the process 500 can be executed by a cloud processor or the second system 120. For the description of the second system 120, please refer to Figure 1B For details about cloud processors, see Figure 2 Corresponding description.

[0118] Step 510: Obtain one or more dynamically updated maps and target data uploaded by one or more mobile terminals within a preset time period.

[0119] For instructions on mobile devices and dynamically updated maps, see Figure 2 The corresponding description.

[0120] The preset time period refers to a preset period of time. For example, the preset time period may be 10 minutes before the current time.

[0121] Target data is data related to the dynamic update map. In some embodiments, the target data may include the acquisition parameters of the mobile terminal and the evaluation results of the dynamic update map. For the relevant description of the evaluation results of the dynamic update map, please refer to Figure 2 、 3 The corresponding description.

[0122] The collection parameters of the mobile terminal refer to the parameters related to the dynamic update map collected by the mobile terminal. In some embodiments, the collection parameters of the mobile terminal may include the map number corresponding to the dynamic update map, the operation time and operation path when the mobile terminal collects the dynamic update map, the number of collections of the dynamic update map collected by the mobile terminal, etc. For the description of the map number, please refer to Figure 2 The corresponding description.

[0123] Step 520 , determining the accuracy of one or more dynamically updated maps based on the target data.

[0124] Accuracy refers to data reflecting the accuracy of dynamically updated maps.

[0125] In some embodiments, the cloud processor can determine the accuracy of one or more dynamically updated maps based on the target data in various ways. For example, the cloud processor can determine the final accuracy based on a preset correspondence between the target data and the accuracy.

[0126] For example, the preset correspondence may include the operation duration of the mobile terminal, the operation path when collecting the dynamically updated map, and / or the correspondence between the number of collection times and the accuracy of the dynamically updated map.

[0127] In some embodiments, the correspondence between the operation time of the mobile terminal and the accuracy of the dynamically updated map can be positively correlated. The longer the operation time of the mobile terminal, the more data it collects, and therefore, the higher the accuracy of the generated dynamically updated map.

[0128] In some embodiments, when one or more mobile terminals perform multiple operations in a target positioning area, multiple dynamically updated maps may be generated accordingly. The corresponding relationship between the operation paths used when collecting the dynamically updated maps and the accuracy of the dynamically updated maps may be: the greater the similarity between the operation paths used when collecting the dynamically updated maps, the higher the accuracy of the dynamically updated maps. The more similar the operation paths used when collecting dynamically updated maps by different mobile terminals, the less likely the environment is to have changed, and the higher the accuracy of the dynamically updated maps.

[0129] In some embodiments, the correspondence between the number of collection times of the mobile terminal and the accuracy of the dynamically updated map can be positively correlated. The more collection times, the richer the data collected, and the higher the accuracy of the generated dynamically updated map.

[0130] In some embodiments, the cloud processor can also determine the accuracy of the dynamically updated map based on the target data through a prediction model. For details, please refer to Figure 6 and related instructions.

[0131] In some embodiments, the cloud processor may receive dynamically updated maps for multiple positioning areas uploaded by multiple mobile terminals. The cloud processor can then determine whether the dynamically updated map is a dynamically updated map of the target positioning area based on the area identifier of the dynamically updated map, and make an accuracy judgment on the dynamically updated map belonging to the target positioning area.

[0132] Step 530 : Determine a target dynamic point cloud map of the target positioning area based on the accuracy of the dynamically updated map.

[0133] For more information about the target dynamic point cloud map, see Figure 4 The corresponding description.

[0134] In some embodiments, the cloud processor can determine a target dynamic point cloud map for the target positioning area in various ways based on the accuracy of the dynamically updated map. For example, the cloud processor can use the most recently uploaded dynamically updated map with an accuracy exceeding a threshold as the target dynamic point cloud map for the target positioning area. The accuracy threshold can be manually preset.

[0135] In some embodiments of the present specification, by determining the accuracy of one or more dynamically updated maps and target data uploaded within a preset time period, and then determining a target dynamic point cloud map of the target positioning area, a more accurate target dynamic point cloud map can be determined, thereby improving map reliability and operational efficiency.

[0136] In some embodiments, in response to the difference between the acquisition time of the first update request and the acquisition time of the second update request meeting a preset time difference condition, the cloud processor can send the target dynamic point cloud map sent to the first mobile terminal to the second mobile terminal.

[0137] The first update request is an update request uploaded by the first mobile terminal.

[0138] The acquisition time of the first update request is the time when the first mobile terminal uploads the update instruction. In some embodiments, the acquisition time of the first update request may be the time when the first mobile terminal enters the target positioning area.

[0139] The second update request is an update request uploaded by the second mobile terminal.

[0140] The acquisition time of the second update request is the time when the second mobile terminal uploads the update instruction. In some embodiments, the acquisition time of the second update request may be the time when the second mobile terminal enters the target positioning area.

[0141] In some embodiments, the first update request and the second update request are for the same target positioning area. In some embodiments, the first mobile terminal and the second mobile terminal are two mobile terminals that enter the same target positioning area first and second respectively.

[0142] The preset time difference condition is a condition related to the time at which the update instruction is obtained. In some embodiments, the preset time difference condition may be that the interval between the time at which the first update request is obtained and the time at which the second update request is obtained does not exceed a time threshold. The time threshold is a preset maximum value of the time difference between the time at which the update instruction is uploaded by two mobile terminals and can be manually preset.

[0143] In some embodiments, in response to a difference between the acquisition time of the first update request and the acquisition time of the second update request meeting a preset time difference condition, the cloud processor may transmit the target dynamic point cloud map sent to the first mobile terminal to the second mobile terminal. For example, the cloud processor may directly use the target dynamic point cloud map of the target positioning area sent to the first mobile terminal as the target dynamic point cloud map to be transmitted to the second mobile terminal.

[0144] In some embodiments of the present specification, when the interval between the acquisition time of two update requests is small, the target dynamic point cloud map sent to the first mobile terminal is more effective. By directly sending the target dynamic point cloud map sent to the first mobile terminal to the second mobile terminal, the second mobile terminal does not need to update the target dynamic point cloud map of the target positioning area, which can save computing resources and improve work efficiency.

[0145] It should be noted that the above descriptions of processes 200, 400, and 500 are for illustrative purposes only and do not limit the scope of this specification. Those skilled in the art may, under the guidance of this specification, make various modifications and alterations to processes 200, 400, and 500. However, such modifications and alterations remain within the scope of this specification.

[0146] Figure 6 is an exemplary schematic diagram of a prediction model according to some embodiments of this specification.

[0147] In some embodiments, as Figure 6 As shown, the cloud processor can determine the path discreteness 620 based on the mobile terminal's operation path 610; determine the dynamic element distribution 640 based on the dynamically updated map 630; and determine the accuracy 670 of the dynamically updated map through a prediction model 660 based on the path discreteness 620, the dynamic element distribution 640, the mobile terminal's collection parameters 650, the dynamically updated map 630, and the evaluation results 340 of the dynamically updated map.

[0148] For instructions on mobile devices, see Figure 4 Related content.

[0149] The mobile terminal's operating path refers to the route the mobile terminal moves along while operating within the positioning area. The mobile terminal's operating path can be determined based on the mobile terminal's historical driving trajectory records.

[0150] The path discreteness refers to the discreteness of the mobile terminal's operation path in the entire positioning area.

[0151] The cloud processor can determine the degree of path dispersion in various ways. For example, the cloud processor can determine the degree of path dispersion based on the extent of the positioning area covered by the mobile terminal's operating path. As an example, the cloud processor can divide the entire positioning area into multiple sub-areas of predetermined shapes and sizes. The degree of path dispersion can then be calculated as the ratio of the total number of sub-areas traversed by the mobile terminal's operating path to the total number of sub-areas contained in the positioning area.

[0152] Dynamic element distribution refers to the distribution of dynamic elements in the positioning area.

[0153] The cloud processor can determine the distribution of dynamic elements based on the dynamically updated map in various ways. For example, the cloud processor can divide the positioning area into multiple sub-areas in the corresponding dynamically updated map according to the aforementioned method, and then count the number of dynamic elements in each sub-area of ​​the dynamically updated map.

[0154] As an example only, the distribution of dynamic elements determined based on the dynamically updated map a can be expressed as [N1 a , N2 a ,...,Nm a 】, where N1 a Represents the number of dynamic elements in the sub-area 1 of the dynamically updated map a, and m represents the number of sub-areas divided in the dynamically updated map a. For instructions on dynamically updating maps, see Figure 5 Related content.

[0155] The prediction model is a model used to determine the accuracy of the dynamically updated map. In some embodiments, the prediction model can be a machine learning model. For example, the prediction model can be a recurrent neural network (RNN) model, a deep neural network (DNN) model, etc.

[0156] In some embodiments, the input of the prediction model may include the degree of path discreteness, the distribution of dynamic elements in the target positioning area, the acquisition parameters of the mobile terminal, the dynamically updated map, and the evaluation results of the dynamically updated map, and the output is the accuracy of the dynamically updated map.

[0157] For details on the mobile terminal's collection parameters, target positioning area, and dynamic map update evaluation results, please refer to the above Figure 3 and Figure 4 Related content.

[0158] In some embodiments, the processor may acquire a prediction model through training based on a large number of labeled training samples. In some embodiments, the training samples may include the degree of sample path dispersion, the distribution of sample dynamic elements in the sample area, acquisition parameters of the sample mobile terminal, a sample dynamic update map of the sample area, and evaluation results of the sample dynamic update map. The training samples may be acquired based on historical data. The training labels may be the accuracy of the sample dynamic update map corresponding to the training samples.

[0159] In some embodiments, the processor can collect multiple continuous work images based on the sample mobile terminal corresponding to the training sample during operation, extract the dynamic element distribution of each of the multiple work images, and determine the comprehensive dynamic element distribution based on the dynamic element distribution of the multiple work images.

[0160] In some embodiments, the cloud processor may obtain the comprehensive dynamic element distribution by calculating the average distribution of dynamic elements in each sub-region in each operation image.

[0161] For example, suppose the sample mobile terminal captures three work images, and the corresponding dynamic element distributions are [N11, N21, ..., Nm1], [N12, N22, ..., Nm2], and [N13, N23, ..., Nm3], where Nm1 represents the number of dynamic elements in subregion m of the positioning area determined based on the first work image. The comprehensive dynamic element distribution can then be expressed as [(N11 + N12 + N13) ÷ 3, (N21 + N22 + N23) ÷ 3, ..., (Nm1 + Nm2 + Nm3) ÷ 3].

[0162] In some embodiments, the cloud processor can calculate the similarity between the comprehensive dynamic element distribution and the sample dynamic element distribution as a training sample, and use the final calculated similarity as the accuracy of the sample dynamic update map in the training sample, that is, as the value of the training label.

[0163] In some embodiments, the input of the prediction model also includes the distribution of static elements in the target positioning area and the area of ​​the target positioning area.

[0164] The method for determining the distribution of static elements is the same as that for determining the distribution of dynamic elements. For details, please refer to the description of the distribution of dynamic elements above. The area of ​​the target positioning area can be determined based on manual input or calculation based on the corresponding map.

[0165] In some embodiments, the training samples of the prediction model may further include the static element distribution of the sample region and the area of ​​the sample region.

[0166] In some embodiments of the present specification, by taking the static element distribution of the target positioning area and the area of ​​the target positioning area as inputs to the prediction model, the accuracy of the dynamically updated map output by the prediction model is combined with the influence of the static element distribution and the area, thereby improving the accuracy of the prediction model output results.

[0167] In some embodiments of this specification, through the prediction model, the self-learning ability of the machine learning model can be utilized to accurately obtain the accuracy of the dynamically updated map, thereby improving the timeliness and accuracy of updating the dynamic point cloud map.

[0168] While the basic concepts have been described above, it will be apparent to those skilled in the art that the detailed disclosure is merely illustrative and does not limit this specification. Although not explicitly stated herein, various modifications, improvements, and revisions to this specification may be made by those skilled in the art. Such modifications, improvements, and revisions are suggested in this specification and remain within the spirit and scope of the exemplary embodiments of this specification.

[0169] This specification also uses specific terms to describe the embodiments of this specification. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "one embodiment," "an embodiment," or "an alternative embodiment" two or more times in different locations in this specification do not necessarily refer to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of this specification may be appropriately combined.

[0170] In addition, unless expressly stated in the claims, the order of the processing elements and sequences, the use of alphanumeric characters, or the use of other names described in this specification are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the spirit and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0171] Similarly, it should be noted that, in order to simplify the presentation of this specification and thus facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of this specification sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of this specification requires more features than those recited in the claims. In fact, an embodiment may have fewer features than all of the features of a single disclosed embodiment.

[0172] In some embodiments, numbers are used to describe the quantity of components and attributes. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the description and claims are approximate values, which may change according to the required characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible range.

[0173] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, and documents, cited in this specification is hereby incorporated by reference in its entirety. This includes application history documents that are inconsistent with or conflict with the content of this specification, as well as documents (currently or subsequently attached to this specification) that limit the broadest scope of the claims of this specification. It should be noted that if the descriptions, definitions, and / or terminology used in the accompanying materials are inconsistent or conflicting with the content of this specification, the descriptions, definitions, and / or terminology used in this specification will control.

[0174] Finally, it should be understood that the embodiments described in this specification are intended only to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly described and illustrated in this specification.

Claims

1. A point cloud map dynamic update method, executed on a mobile terminal, characterized in that: include: Obtain the static point cloud map and initial dynamic point cloud map of the positioning area through the cloud processor; In response to receiving the start update instruction, performing laser matching positioning based on the static point cloud map and the initial dynamic point cloud map, and obtaining dynamic point cloud elements of the positioning area; constructing a dynamically updated map of the positioning area based on the dynamic point cloud elements; In response to receiving an end-update instruction, evaluating the dynamically updated map based on a positioning result of the laser matching positioning; In response to an evaluation result of the dynamically updated map satisfying a preset condition, uploading the dynamically updated map to the cloud processor.

2. The method according to claim 1, characterized in that The constructing a dynamically updated map of the positioning area based on the dynamic point cloud elements includes: Based on the dynamic point cloud elements, the dynamically updated map of the positioning area is constructed by adopting a point cloud accumulation method and / or a real-time positioning and map construction method.

3. The method according to claim 1, characterized in that The evaluating of the dynamically updated map based on the positioning result of the laser matching positioning includes: The evaluation result of the dynamically updated map is determined based on a comparison result of the positioning result of the laser matching positioning and a satellite positioning result.

4. A method for dynamically updating a point cloud map, executed based on a cloud processor, characterized in that: include: Sending a point cloud positioning map of the target positioning area to the mobile terminal, wherein the point cloud positioning map includes a static point cloud map and an initial dynamic point cloud map; In response to obtaining the dynamically updated map of the target positioning area uploaded by the mobile terminal, determining a target dynamic point cloud map of the target positioning area based on a preset map updating rule; The target dynamic point cloud map is sent to the target terminal, and the target dynamic point cloud map is used as the next round of initial dynamic point cloud map of the target positioning area.

5. The method according to claim 4, characterized in that The preset map update rule includes: determining the target dynamic point cloud map of the target positioning area based on upload time and / or map quality.

6. The method according to claim 4, characterized in that Sending the point cloud positioning map of the target positioning area to the mobile terminal includes: In response to receiving an update request uploaded by the mobile terminal, the point cloud positioning map of the target positioning area is sent to the mobile terminal, wherein the update request at least includes an area identifier of the target positioning area.

7. The method according to claim 6, characterized in that Determining the target dynamic point cloud map of the target positioning area based on a preset map update rule includes: Obtaining one or more dynamically updated maps and target data uploaded by one or more mobile terminals within a preset time period, wherein the target data includes acquisition parameters of the mobile terminals and evaluation results of the dynamically updated maps; determining an accuracy of one or more of the dynamically updated maps based on the target data; Based on the accuracy of the dynamically updated map, the target dynamic point cloud map of the target positioning area is determined.

8. A point cloud map dynamic update system, characterized in that: include: The acquisition module is used to obtain the static point cloud map and the initial dynamic point cloud map of the positioning area from the cloud; a positioning module, configured to, in response to receiving a start update instruction, perform laser matching positioning based on the static point cloud map and the initial dynamic point cloud map, and obtain dynamic point cloud elements of the positioning area; A construction module, configured to construct a dynamically updated map of the positioning area based on the dynamic point cloud elements; an evaluation module, configured to evaluate the dynamically updated map based on the positioning result of the laser matching positioning in response to receiving the end-update instruction; The uploading module is configured to upload the dynamically updated map to the cloud in response to an evaluation result of the dynamically updated map meeting a preset condition.

9. A point cloud map dynamic update system, characterized in that: include: A first sending module is used to send a point cloud positioning map of the target positioning area to the mobile terminal, wherein the point cloud positioning map includes a static point cloud map and an initial dynamic point cloud map; An updating module, configured to determine a target dynamic point cloud map of the target positioning area based on preset map updating rules in response to obtaining a dynamically updated map of the target positioning area uploaded by the mobile terminal; The second sending module is used to send the target dynamic point cloud map to the target terminal, and use the target dynamic point cloud map as the next round of initial dynamic point cloud map of the target positioning area.

10. A computer-readable storage medium storing computer instructions, which, when executed by a processor, implements the point cloud map dynamic update method according to any one of claims 1 to 3.

Images