New establishment method and device of backup map point cloud, medium and electronic equipment

Abstract

The invention provides a new backup map point cloud establishing method and device, a medium and electronic equipment. The method comprises the following steps: acquiring an actually measured local point cloud of a local area; evaluating the actually measured local point cloud based on the point cloud map to obtain an evaluation result; when an evaluation result meets a preset difference evaluation condition, a backup map point cloud of the local area is newly built based on the actually measured local point cloud of the local area and the point cloud map, and the backup map point cloud can be smoothly connected with the point cloud map in the local area of the point cloud map. And the backup map point cloud of the local area can be automatically created in real time through a common vehicle. The defects that the mapping cycle of a mapping vehicle is long and the map is not updated in time are overcome, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the technical field of navigation. Specifically, it relates to a method, device, medium, and electronic device for creating a backup map point cloud. Background Art

[0002] Point cloud (the full English name is point cloud data) refers to a collection of a large amount of point data representing the surface characteristics of an object in a three-dimensional coordinate system. Each point data includes a set of vectors.

[0003] When a lidar irradiates the surface of an object, the reflected laser will carry information such as azimuth and distance. If the laser beam is scanned along a certain trajectory, the information of the reflected laser points will be recorded while scanning. Since the scanning is extremely fine, a large number of laser points can be obtained, and thus a point cloud can be formed. Placing the point cloud in a three-dimensional coordinate system is a point cloud map. The point cloud map is created by a dedicated mapping vehicle.

[0004] However, when the environment in a certain area of the point cloud map changes, it is necessary for the mapping vehicle to re-record the point cloud data packet and update the global map. This situation will cause a long delay, resulting in pose jitter or even deviation from the route of other vehicles without knowing it.

[0005] Therefore, the present application provides a method for creating a backup map point cloud to solve the above technical problems. Summary of the Invention

[0006] The purpose of the present application is to provide a method, device, medium, and electronic device for creating a backup map point cloud, which can solve at least one of the above-mentioned technical problems. The specific solutions are as follows:

[0007] According to a specific embodiment of the present application, in a first aspect, the present application provides a method for creating a backup map point cloud, including:

[0008] Obtain the measured local point cloud of a local area;

[0009] Evaluate the measured local point cloud based on the point cloud map to obtain an evaluation result;

[0010] When the evaluation result meets a preset poor evaluation condition, create the backup map point cloud of the local area based on the measured local point cloud of the local area and the point cloud map, where the backup map point cloud can be smoothly connected to the point cloud map in the local area of the point cloud map.

[0011] Optionally, the step of creating the backup map point cloud of the local area based on the measured local point cloud of the local area and the point cloud map when the evaluation result meets a preset poor evaluation condition includes:

[0012] When the evaluation result meets the preset negative review condition, extract the local map point cloud of the local area based on the point cloud map;

[0013] Determine the difference frames in the measured local point cloud based on the map key frames in the local map point cloud and the measured key frames in the measured local point cloud;

[0014] Match the edge key frames and the difference frames of the measured local point cloud with the point cloud map to obtain a matching result;

[0015] When the matching result meets the preset new condition, determine that the newly created backup map point cloud is the measured local point cloud.

[0016] Optionally, the determining the difference frames in the measured local point cloud based on the map key frames in the local map point cloud and the measured key frames in the measured local point cloud includes:

[0017] Based on the preset map trajectory of the local map point cloud, perform difference comparison between the map key frames at each trajectory position in the local map point cloud and the measured key frames at the corresponding trajectory positions in the measured local point cloud to obtain the prior factor of the measured key frames at the corresponding trajectory positions;

[0018] When the prior factor of any measured key frame meets the preset difference condition, determine that the any measured key frame is a difference frame.

[0019] Optionally, when determining that the any measured key frame is a difference frame when the prior factor of any measured key frame meets the preset difference condition, it further includes:

[0020] Reconstruct the initial factor graph of the measured local point cloud based on the prior factors of each measured key frame of the measured local point cloud;

[0021] Perform a reduction process on each prior factor in the initial factor graph to obtain a target factor graph;

[0022] Reconstruct the measured local point cloud based on the target factor graph.

[0023] Optionally, the matching the edge key frames and the difference frames of the measured local point cloud with the point cloud map to obtain a matching result includes:

[0024] Register the positioning information of the edge key frames of the measured local point cloud and the positioning information of the difference frames of the measured local point cloud with the positioning information of the point cloud map to obtain a registration score value, and

[0025] Perform jitter evaluation on the trajectory pose information of the edge key frames of the measured local point cloud and the trajectory pose information of the difference frames of the measured local point cloud, and compare them with the trajectory pose information of the point cloud map to obtain a jitter evaluation result;

[0026] When the jitter evaluation result is normal jitter information and the registration score value is less than or equal to a preset normal registration threshold, determine that the matching result is normal matching information.

[0027] Optionally, the edge key frames include multiple first measured key frames obtained from multiple starting trajectory positions based on a preset map trajectory in the measured local point cloud and multiple second measured key frames obtained from multiple ending trajectory positions based on the preset map trajectory in the measured local point cloud.

[0028] Optionally, after creating the backup map point cloud of the local area, it further includes:

[0029] A local point cloud file generated based on the backup map point cloud;

[0030] Save the local point cloud file in a directory associated with the local area so that when navigating through the local area again, the backup map point cloud in the local point cloud file can be called to generate navigation information.

[0031] According to a specific embodiment of the present application, in a second aspect, the present application provides a device for creating a backup map point cloud, including:

[0032] An acquisition unit for acquiring a measured local point cloud of a local area;

[0033] An evaluation unit for evaluating the measured local point cloud based on the point cloud map to obtain an evaluation result;

[0034] A creation unit for, when the evaluation result meets a preset bad evaluation condition, creating the backup map point cloud of the local area based on the measured local point cloud of the local area and the point cloud map, where the backup map point cloud can be smoothly connected to the point cloud map in the local area of the point cloud map.

[0035] Optionally, when the evaluation result meets a preset bad evaluation condition, creating the backup map point cloud of the local area based on the measured local point cloud of the local area and the point cloud map includes:

[0036] When the evaluation result meets a preset bad evaluation condition, extract the local map point cloud of the local area based on the point cloud map;

[0037] Determine the difference frames in the measured local point cloud based on the map key frames in the local map point cloud and the measured key frames in the measured local point cloud;

[0038] Match the edge key frames of the measured local point cloud and the difference frames of the measured local point cloud with the point cloud map to obtain a matching result;

[0039] When the matching result meets the preset new condition, determine that the newly created backup map point cloud is the measured local point cloud.

[0040] Optionally, the determining the difference frames in the measured local point cloud based on the map key frames in the local map point cloud and the measured key frames in the measured local point cloud includes:

[0041] Based on the preset map trajectory of the local map point cloud, compare the map key frames at each trajectory position in the local map point cloud with the measured key frames at the corresponding trajectory positions in the measured local point cloud to obtain the prior factor of the measured key frames at the corresponding trajectory positions;

[0042] When the prior factor of any measured key frame meets the preset difference condition, determine that the any measured key frame is a difference frame.

[0043] Optionally, when determining that any measured key frame is a difference frame when the prior factor of any measured key frame meets the preset difference condition, it further includes:

[0044] Reconstruct the initial factor graph of the measured local point cloud based on the prior factors of each measured key frame of the measured local point cloud;

[0045] Perform a reduction process on each prior factor in the initial factor graph to obtain a target factor graph;

[0046] Reconstruct the measured local point cloud based on the target factor graph.

[0047] Optionally, the matching the edge key frames of the measured local point cloud and the difference frames of the measured local point cloud with the point cloud map to obtain a matching result includes:

[0048] Register the positioning information of the edge key frames of the measured local point cloud and the positioning information of the difference frames of the measured local point cloud with the positioning information of the point cloud map to obtain a registration score value, and

[0049] Perform a jitter evaluation on the trajectory pose information of the edge key frames of the measured local point cloud and the trajectory pose information of the difference frames of the measured local point cloud with the trajectory pose information of the point cloud map to obtain a jitter evaluation result;

[0050] When the jitter evaluation result is normal jitter information and the registration score value is less than or equal to a preset normal registration threshold, determine that the matching result is normal matching information.

[0051] Optionally, the edge key frames include a plurality of first measured key frames obtained from a plurality of starting trajectory positions based on a preset map trajectory in the measured local point cloud and a plurality of second measured key frames obtained from a plurality of ending trajectory positions based on the preset map trajectory in the measured local point cloud.

[0052] Optionally, after creating the backup map point cloud of the local area, it further includes:

[0053] A local point cloud file generated based on the backup map point cloud;

[0054] Save the local point cloud file in a directory associated with the local area so that when navigating through the local area again, the backup map point cloud in the local point cloud file is called to generate navigation information.

[0055] According to a specific embodiment of the present application, in a third aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the method for creating the backup map point cloud as described in any one of the above.

[0056] According to a specific embodiment of the present application, in a fourth aspect, the present application provides an electronic device, including: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method for creating the backup map point cloud as described in any one of the above.

[0057] The above solution of the embodiment of the present application has at least the following beneficial effects compared with the prior art:

[0058] The present application provides a method, device, medium, and electronic device for creating a backup map point cloud. The method includes: obtaining a measured local point cloud of a local area; evaluating the measured local point cloud based on the point cloud map to obtain an evaluation result; when the evaluation result meets a preset bad evaluation condition, creating a backup map point cloud of the local area based on the measured local point cloud of the local area and the point cloud map, wherein the backup map point cloud can be smoothly connected to the point cloud map in the local area of the point cloud map. The backup map point cloud of the local area can be created in real time and automatically by an ordinary vehicle. It avoids the drawbacks of the long mapping cycle of the mapping vehicle and the untimely map update, and improves the user experience. Description of the Drawings

[0059] Figure 1The flowchart of a method for creating a backup map point cloud according to an embodiment of the present application is shown;

[0060] Figure 2 The unit block diagram of a device for creating a backup map point cloud according to an embodiment of the present application is shown. Detailed implementation manners

[0061] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the scope of protection of the present application.

[0062] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms "a", "the" and "said" used in the embodiments of the present application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. "Plural" generally includes at least two.

[0063] It should be understood that the term "and / or" used herein is only an association relationship describing associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " herein generally represents an "or" relationship between the associated objects before and after.

[0064] It should be understood that although terms such as first, second, and third may be used in the embodiments of the present application for description, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0065] Depending on the context, the words "if", "when" as used herein may be interpreted as "when...", "when...", "in response to determining", or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detecting (stated condition or event)" may be interpreted as "when determined", "in response to determining", "when detecting (stated condition or event)", or "in response to detecting (stated condition or event)".

[0066] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the commodity or device comprising said element.

[0067] It should be particularly noted that symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0068] The optional embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0069] The embodiments provided in the present application are embodiments of a method for creating a backup map point cloud.

[0070] Below in conjunction with Figure 1 The embodiments of the present application will be described in detail.

[0071] Step S101, obtain the measured local point cloud of the local area.

[0072] A point cloud map refers to a collection of a large amount of point data representing the surface characteristics of an object in a three-dimensional coordinate system, and each point data includes a set of vectors.

[0073] If a large area (for example, the urban area of a city, or the area of a province, or the area of a country, the present application is not limited thereto) is regarded as a global area, the embodiments of the present application divide the global area into multiple local areas. In each vehicle of the present application, a lidar is installed. During the driving process of the vehicle, the lidar continuously scans to obtain the surrounding point cloud. When the vehicle passes through a local area, the point cloud of the local area will be collected in real time, that is, the measured local point cloud.

[0074] Step S102, evaluate the measured local point cloud based on the point cloud map to obtain an evaluation result.

[0075] The purpose of the evaluation is to determine whether the measured local point cloud of the local area has changed.

[0076] In some specific embodiments, the evaluating the measured local point cloud based on the point cloud map to obtain an evaluation result includes:

[0077] Step S102-1a, register the positioning information of the measured local point cloud with the positioning information of the point cloud map to obtain a registration score value.

[0078] For example, the registration score value is the root mean square error between two groups of point clouds after registration. The registration score value is used to evaluate the quality of registration.

[0079] Step S102-1b: Perform jitter evaluation on the trajectory pose information of the measured local point cloud and the trajectory pose information of the point cloud map to obtain a jitter evaluation result.

[0080] For example, under normal circumstances, the trajectory pose information of the measured local point cloud is smooth and conforms to the preset map trajectory. If there is a pose jump in the measured trajectory of the measured local point cloud, that is, the absolute value of the curvature error value between the curvature value of the measured trajectory and the curvature value of the preset map trajectory is greater than the preset curvature error threshold, and the absolute value of the position deviation value between the positioning information of the measured trajectory and the positioning information of the preset map trajectory is greater than the preset position deviation threshold, then it is determined that jitter occurs.

[0081] Step S102-2: When the jitter evaluation result is jitter abnormal information and the registration score value is greater than the preset registration normal threshold, determine that the matching result is matching abnormal information.

[0082] Step S103: When the evaluation result meets the preset bad review conditions, create a backup map point cloud for the local area based on the measured local point cloud of the local area and the point cloud map.

[0083] When the evaluation result is matching abnormal information, it is necessary to create a backup map point cloud for the local area; when the evaluation result is matching normal information, it is not necessary to create a backup map point cloud for the local area.

[0084] According to engineering experience, if the key frame with a registration score value greater than 0.5, or the absolute value of the curvature error value between the curvature value of the measured trajectory and the curvature value of the preset map trajectory is greater than the preset curvature error threshold, or the average value of the absolute value of the position deviation value between the positioning information of the measured trajectory and the positioning information of the preset map trajectory is greater than 0.3, it is necessary to create a backup map point cloud for the local area.

[0085] Among them, the backup map point cloud can be smoothly connected to the point cloud map in the local area of the point cloud map. So that during use, there can be a smooth transition between the backup map point cloud and the point cloud map. Reduce the impact of jitter on the navigation quality.

[0086] In some specific embodiments, when the evaluation result meets the preset bad review conditions, creating a backup map point cloud for the local area based on the measured local point cloud of the local area and the point cloud map includes:

[0087] Step S103-1: When the evaluation result meets the preset bad review conditions, extract the local map point cloud of the local area based on the point cloud map.

[0088] The local map point cloud is a partial point cloud map intercepted from the point cloud map. The projection coordinates of the position information are included in the local map point cloud. For example, taking the projection coordinates of the position information as the geometric center, a cube with a preset side length is intercepted from the preset point cloud map as the local point cloud map.

[0089] Step S103-2: Determine the difference frames in the measured local point cloud based on the map key frames in the local map point cloud and the measured key frames in the measured local point cloud.

[0090] The point cloud includes multiple key frames, and the key frame is the point cloud obtained after the vehicle-mounted radar scans the surrounding environment for one week.

[0091] The difference frame is the measured key frame that has a large gap from the map key frame.

[0092] In some specific embodiments, the determining the difference frames in the measured local point cloud based on the map key frames in the local map point cloud and the measured key frames in the measured local point cloud includes:

[0093] Step S103-21: Based on the preset map trajectory of the local map point cloud, compare the map key frames at each trajectory position in the local map point cloud with the measured key frames at the corresponding trajectory positions in the measured local point cloud to obtain the prior factor of the measured key frames at the corresponding trajectory positions.

[0094] For example, the prior factor is the deviation value between the poses of the map key frame and the measured key frame at the same trajectory position.

[0095] Step S103-22a: When the prior factor of any measured key frame meets the preset difference condition, determine the any measured key frame as a difference frame.

[0096] For example, if the absolute value of the prior factor of the measured key frame is greater than the preset factor threshold and the number of prior factors is greater than the preset normal factor number threshold, then the measured key frame is a difference frame.

[0097] In some specific embodiments, when determining that any measured key frame is a difference frame when the prior factor of any measured key frame meets the preset difference condition, it further includes:

[0098] Step S103-22b-1: Reconstruct the initial factor graph of the measured local point cloud based on the prior factors of each measured key frame of the measured local point cloud.

[0099] Step S103-22b-2, perform a reduction process on each prior factor in the initial factor graph to obtain a target factor graph.

[0100] For example, perform a halving process on each prior factor in the initial factor graph, that is, divide each prior factor by 2 to obtain a new prior factor, and then reconstruct the target factor graph of the measured local point cloud from the new prior factor. The purpose is to reduce the gap between the differential frame and the map key frame, reduce the jitter of the backup map point cloud of the newly built local area, and avoid the collapse of the navigation system.

[0101] Step S103-22b-3, reconstruct the measured local point cloud based on the target factor graph.

[0102] In this specific embodiment, the measured local point cloud is corrected, reducing the gap between the reconstructed measured local point cloud and the local map point cloud, reducing the jitter of the backup map point cloud of the newly built local area, and avoiding the collapse of the navigation system.

[0103] Step S103-3, match the edge key frames of the measured local point cloud and the differential frames of the measured local point cloud with the point cloud map to obtain a matching result.

[0104] In some specific embodiments, the edge key frames include a plurality of first measured key frames obtained from a plurality of starting trajectory positions based on a preset map trajectory in the measured local point cloud and a plurality of second measured key frames obtained from a plurality of ending trajectory positions based on the preset map trajectory in the measured local point cloud.

[0105] For example, 5 first measured key frames obtained from 5 starting trajectory positions based on a preset map trajectory in the measured local point cloud and 5 second measured key frames obtained from 5 ending trajectory positions based on the preset map trajectory in the measured local point cloud.

[0106] This specific embodiment verifies the backup map point cloud of the newly built local area. It checks whether the edge key frames of the measured local point cloud and the differential frames of the measured local point cloud match the point cloud map.

[0107] In some specific embodiments, the matching of the edge key frames of the measured local point cloud and the differential frames of the measured local point cloud with the point cloud map to obtain a matching result includes:

[0108] Step S103-31a, register the positioning information of the edge key frames of the measured local point cloud and the positioning information of the differential frames of the measured local point cloud with the positioning information of the point cloud map to obtain a registration score value.

[0109] For example, the registration score value is the root mean square error between the edge key frames of the actually measured local point cloud after registration and the difference frames of the actually measured local point cloud, and the matching between the difference frames and the point cloud map. The registration score value is used to evaluate the quality of registration.

[0110] Step S103-31b: Perform jitter evaluation on the trajectory pose information of the edge key frames of the actually measured local point cloud and the trajectory pose information of the difference frames of the actually measured local point cloud, and the trajectory pose information of the point cloud map, to obtain a jitter evaluation result.

[0111] For example, under normal circumstances, the trajectory pose information of the edge key frames and the difference frames is smooth and conforms to the preset map trajectory. If there are pose jumps in the trajectory pose information of the edge key frames and the difference frames, that is, the absolute value of the curvature error value between the actually measured trajectory curvature values of the edge key frames and the difference frames and the trajectory curvature value of the preset map trajectory is greater than the preset curvature error threshold, and the absolute value of the position deviation value between the positioning information of the edge key frames and the difference frames and the positioning information of the preset map trajectory is greater than the preset position deviation threshold (for example, the preset position deviation threshold is 10 cm), then it is determined that jitter occurs.

[0112] Step S103-32: When the jitter evaluation result is jitter normal information and the registration score value is less than or equal to the preset registration normal threshold, determine that the matching result is matching normal information.

[0113] In this specific embodiment, the degree of fit between the actually measured local point cloud and the point cloud map is evaluated from two aspects: registration quality and jitter.

[0114] Step S103-4: When the matching result meets the preset new construction condition, determine that the newly created backup map point cloud is the actually measured local point cloud.

[0115] In this specific embodiment, if the matching result meets the preset new construction condition, it indicates that the degree of fit between the actually measured local point cloud and the point cloud map is relatively high, then determine that the newly created backup map point cloud is the actually measured local point cloud. If the matching result does not meet the preset new construction condition, it indicates that the degree of fit between the actually measured local point cloud and the point cloud map is not high, and jitter and deviation phenomena are likely to occur during navigation. Therefore, abandon this actually measured local point cloud. Reconstruct the backup map point cloud after obtaining the actually measured local point cloud next time.

[0116] According to engineering experience, if the registration score value is greater than 0.5, or the absolute value of the curvature error value between the actually measured trajectory curvature values of the edge key frames and the difference frames and the trajectory curvature value of the preset map trajectory is greater than the preset curvature error threshold, or the average value of the absolute value of the position deviation value between the positioning information of the edge key frames and the difference frames and the positioning information of the preset map trajectory is greater than 0.3, determine that the newly created backup map point cloud is the actually measured local point cloud.

[0117] The embodiment of the present application obtains the measured local point cloud of a local area; the measured local point cloud is evaluated based on the point cloud map to obtain an evaluation result; when the evaluation result meets the preset bad evaluation condition, a backup map point cloud of the local area is newly created based on the measured local point cloud of the local area and the point cloud map, wherein the backup map point cloud in the local area of ​​the point cloud map can be smoothly connected with the point cloud map. The backup map point cloud of the local area can be automatically created in real time by an ordinary vehicle. The drawbacks of long mapping cycle and untimely map update of the mapping vehicle are avoided, and the user experience is improved.

[0118] When the vehicle is in the automatic driving state, the backup map point cloud of the local area can be automatically created. If the automatic driving is manually taken over, the backup map point cloud is abandoned.

[0119] In some specific embodiments, after creating the backup map point cloud of the local area, the method further includes:

[0120] Step S104-1, generating a local point cloud file based on the backup map point cloud.

[0121] Step S104-2: Save the local point cloud file in a directory associated with the local area, so that when navigating through the local area again, the backup map point cloud in the local point cloud file is called to generate navigation information.

[0122] For example, the directory associated with the local area is: the point cloud map file directory, which is stored in the folder corresponding to the area number of the local area; when the vehicle enters the local area, the vehicle first calls the backup map point cloud, and when leaving the local area, it calls the point cloud map again; if the backup map point cloud fails, a new backup map point cloud is created again. This enables the vehicle to create a new backup map point cloud and use it, shortening the correction cycle and improving the correction efficiency.

[0123] The present application also provides a device embodiment that is based on the above embodiment, which is used to implement the method steps described in the above embodiment. The explanation based on the same name meaning is the same as the above embodiment, and has the same technical effect as the above embodiment, which will not be repeated here.

[0124] like Figure 2 As shown, the present application provides a new device 200 for creating a backup map point cloud, comprising:

[0125] An acquisition unit 201 is used to acquire a measured local point cloud of a local area;

[0126] An evaluation unit 202 is used to evaluate the measured local point cloud based on the point cloud map to obtain an evaluation result;

[0127] A new unit 203 is used to create a backup map point cloud of the local area based on the measured local point cloud of the local area and the point cloud map when the evaluation result meets the preset bad review condition, wherein the backup map point cloud can be smoothly connected with the point cloud map in the local area of the point cloud map.

[0128] Optionally, when the evaluation result meets the preset bad review condition, creating the backup map point cloud of the local area based on the measured local point cloud of the local area and the point cloud map includes:

[0129] When the evaluation result meets the preset bad review condition, extracting the local map point cloud of the local area based on the point cloud map;

[0130] Determining the difference frames in the measured local point cloud based on the map key frames in the local map point cloud and the measured key frames in the measured local point cloud;

[0131] Matching the edge key frames and the difference frames of the measured local point cloud with the point cloud map to obtain a matching result;

[0132] When the matching result meets the preset creation condition, determining the newly created backup map point cloud as the measured local point cloud.

[0133] Optionally, determining the difference frames in the measured local point cloud based on the map key frames in the local map point cloud and the measured key frames in the measured local point cloud includes:

[0134] Based on the preset map trajectory of the local map point cloud, comparing the map key frames at each trajectory position in the local map point cloud with the measured key frames at the corresponding trajectory positions in the measured local point cloud to obtain the prior factor of the measured key frames at the corresponding trajectory positions;

[0135] When the prior factor of any measured key frame meets the preset difference condition, determining the any measured key frame as a difference frame.

[0136] Optionally, when determining that any measured key frame is a difference frame when the prior factor of any measured key frame meets the preset difference condition, it further includes:

[0137] Reconstructing the initial factor graph of the measured local point cloud based on the prior factors of each measured key frame of the measured local point cloud;

[0138] Performing a value reduction process on each prior factor in the initial factor graph to obtain a target factor graph;

[0139] Reconstructing the measured local point cloud based on the target factor graph.

[0140] Optionally, matching the edge key frame of the measured local point cloud and the difference frame of the measured local point cloud with the point cloud map to obtain a matching result includes:

[0141] Registering the positioning information of the edge key frame of the measured local point cloud and the positioning information of the difference frame of the measured local point cloud with the positioning information of the point cloud map to obtain a registration score value, and

[0142] Performing jitter evaluation on the trajectory pose information of the edge key frame of the measured local point cloud and the trajectory pose information of the difference frame of the measured local point cloud with the trajectory pose information of the point cloud map to obtain a jitter evaluation result;

[0143] When the jitter evaluation result is normal jitter information and the registration score value is less than or equal to a preset normal registration threshold, determining that the matching result is normal matching information.

[0144] Optionally, the edge key frame includes a plurality of first measured key frames obtained from a plurality of starting trajectory positions based on a preset map trajectory in the measured local point cloud and a plurality of second measured key frames obtained from a plurality of ending trajectory positions based on the preset map trajectory in the measured local point cloud.

[0145] Optionally, after creating the backup map point cloud of the local area, it further includes:

[0146] A local point cloud file generated based on the backup map point cloud;

[0147] Saving the local point cloud file in a directory associated with the local area so that when navigating through the local area again, the backup map point cloud in the local point cloud file is called to generate navigation information.

[0148] The embodiment of the present application obtains the measured local point cloud of the local area; evaluates the measured local point cloud based on the point cloud map to obtain an evaluation result; when the evaluation result meets a preset bad evaluation condition, creates a backup map point cloud of the local area based on the measured local point cloud of the local area and the point cloud map, where the backup map point cloud can be smoothly connected with the point cloud map in the local area of the point cloud map. A backup map point cloud of the local area can be automatically created in real time by an ordinary vehicle. It avoids the disadvantages of the long mapping cycle and untimely map update of the mapping vehicle and improves the user experience.

[0149] Embodiment 3

[0150] This embodiment provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method steps described in the above embodiment.

[0151] Embodiment 4

[0152] This embodiment of the present application provides a non-volatile computer storage medium, which stores computer-executable instructions that can execute the method steps described in the above embodiment.

[0153] Finally, it should be noted that the various embodiments in this specification are described in a progressive manner, and the key point of each embodiment is the difference from other embodiments. The same or similar parts between the various embodiments can be referred to each other. For the systems or devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0154] The above embodiments are only used to illustrate the technical solutions of the present application, rather than 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 on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present application.

Claims

1. A method for creating a backup map point cloud, characterized in that: include: Obtain the measured local point cloud of the local area; Evaluate the measured local point cloud based on the point cloud map to obtain an evaluation result; When the evaluation result meets the preset bad review condition, a backup map point cloud of the local area is newly created based on the measured local point cloud of the local area and the point cloud map, wherein the backup map point cloud can be smoothly connected with the point cloud map in the local area of ​​the point cloud map.

2. The method according to claim 1, characterized in that When the evaluation result meets the preset bad evaluation condition, based on the measured local point cloud of the local area and the point cloud map, a backup map point cloud of the local area is newly created, including: When the evaluation result meets the preset bad evaluation condition, extracting a local map point cloud of the local area based on the point cloud map; Determining a difference frame in the measured local point cloud based on a map key frame in the local map point cloud and a measured key frame in the measured local point cloud; Matching the edge key frame of the measured local point cloud and the difference frame of the measured local point cloud with the point cloud map to obtain a matching result; When the matching result satisfies the preset new creation condition, the newly created backup map point cloud is determined to be the measured local point cloud.

3. The method according to claim 2, characterized in that The determining of the difference frame in the measured local point cloud based on the map key frame in the local map point cloud and the measured key frame in the measured local point cloud comprises: Based on the preset map track of the local map point cloud, a map key frame at each track position in the local map point cloud is compared with a measured key frame at a corresponding track position of the measured local point cloud to obtain a priori factors of the measured key frame at the corresponding track position; When the priori factor of any measured key frame meets the preset difference condition, the any measured key frame is determined to be a difference frame.

4. The method according to claim 3, characterized in that: When the priori factor of any measured key frame meets the preset difference condition, determining that any measured key frame is a difference frame also includes: reconstructing an initial factor graph of the measured local point cloud based on a priori factors of each measured key frame of the measured local point cloud; Performing a decrement process on each prior factor in the initial factor graph to obtain a target factor graph; The measured local point cloud is reconstructed based on the target factor graph.

5. The method according to claim 2, characterized in that: The step of matching the edge key frame of the measured local point cloud and the difference frame of the measured local point cloud with the point cloud map to obtain a matching result includes: The positioning information of the edge key frame of the measured local point cloud and the positioning information of the difference frame of the measured local point cloud are registered with the positioning information of the point cloud map to obtain a registration score value, and Performing jitter evaluation on the trajectory pose information of the edge key frame of the measured local point cloud and the trajectory pose information of the difference frame of the measured local point cloud and the trajectory pose information of the point cloud map to obtain a jitter evaluation result; When the jitter evaluation result is normal jitter information, and the registration score value is less than or equal to a preset normal registration threshold, it is determined that the matching result is normal matching information.

6. The method according to claim 2, characterized in that The edge keyframes include a plurality of first measured keyframes obtained from a plurality of starting track positions of a preset map track in the measured local point cloud and a plurality of second measured keyframes obtained from a plurality of ending track positions of the preset map track in the measured local point cloud.

7. The method according to claim 1, characterized in that After creating the backup map point cloud of the local area, the method further includes: A local point cloud file generated based on the backup map point cloud; The local point cloud file is saved in a directory associated with the local area, so that the backup map point cloud in the local point cloud file is called to generate navigation information when navigating through the local area again.

8. A device for creating a backup map point cloud, characterized in that: include: An acquisition unit, used for acquiring a measured local point cloud of a local area; An evaluation unit, configured to evaluate the measured local point cloud based on the point cloud map to obtain an evaluation result; A new creation unit is used to create a backup map point cloud for the local area based on the measured local point cloud of the local area and the point cloud map when the evaluation result meets the preset bad review condition, wherein the backup map point cloud can be smoothly connected with the point cloud map in the local area of ​​the point cloud map.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method as claimed in any one of claims 1 to 7.

Images