High-precision map generation method and device, electronic equipment and storage medium

Abstract

The invention provides a map generation method, and relates to the technical field of artificial intelligence, in particular to the technical field of high-precision maps, automatic driving and intelligent traffic. According to the specific implementation scheme, an initial map is generated according to initial point cloud data and initial movement track information; determining association relationship information between a plurality of initial points in the initial point cloud data and a plurality of surface features of a target plane in an initial map; according to the initial external parameters, the initial movement track information and the association relationship information, determining distance information between the surface feature corresponding to the initial point and the initial point; according to the multiple pieces of distance information, the initial external parameters and the initial movement track information are adjusted, and target movement track information and target external parameters are obtained; and generating a target map according to the target motion track information and the target external parameters. The invention further provides a map generation device, electronic equipment and a storage medium.

Description

[0001] The present disclosure is a divisional application of Chinese Invention Patent Application No. 202211341533.7, the application date of which is October 28, 2022, and the title of which is High-precision Map Generation Method, Device, Electronic Equipment, and Storage Medium. TECHNICAL FIELD

[0002] The present disclosure relates to the field of artificial intelligence, and more particularly to the fields of high-precision maps, autonomous driving, and intelligent transportation. More specifically, the present disclosure provides a map generation method, device, electronic equipment, and storage medium. BACKGROUND

[0003] A high-precision map, also known as a high-precision map, can be a map used by an autonomous vehicle. A high-precision map has precise vehicle position information and rich road element data information, which can help the vehicle predict complex road information such as slope, curvature, heading, etc., and better avoid potential risks. With the development of artificial intelligence technology and high-precision map technology, the application scenarios of autonomous driving technology and assisted driving technology are increasing. In autonomous driving mode or assisted driving mode, the position of the vehicle or other obstacles can be determined using a high-precision map to control the vehicle to travel. SUMMARY

[0004] The present disclosure provides a map generation method, device, equipment, and storage medium.

[0005] According to an aspect of the present disclosure, a map generation method is provided, which includes: generating an initial map according to initial point cloud data and initial motion trajectory information; determining association relationship information between a plurality of initial points in the initial point cloud data and a plurality of face features of a target plane in the initial map; determining distance information between a face feature corresponding to an initial point and the initial point according to initial extrinsic parameters, initial motion trajectory information, and the association relationship information; adjusting the initial extrinsic parameters and the initial motion trajectory information according to a plurality of distance information to obtain target motion trajectory information and target extrinsic parameters; and generating a target map according to the target motion trajectory information and the target extrinsic parameters.

[0006] According to another aspect of the present disclosure, a map generation apparatus is provided, which comprises: a first generation module configured to generate an initial map according to initial point cloud data and initial motion trajectory information; a first determination module configured to determine association relationship information between a plurality of initial points in the initial point cloud data and a plurality of face features of a target plane in the initial map; a second determination module configured to determine distance information between a face feature corresponding to an initial point and the initial point according to initial extrinsic parameters, the initial motion trajectory information and the association relationship information; an adjustment module configured to adjust the initial extrinsic parameters and the initial motion trajectory information according to a plurality of distance information to obtain target motion trajectory information and target extrinsic parameters; and a second generation module configured to generate a target map according to the target motion trajectory information and the target extrinsic parameters.

[0007] According to another aspect of the present disclosure, an electronic device is provided, which comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method provided by the present disclosure.

[0008] According to another aspect of the present disclosure, a non-transitory computer readable storage medium storing computer instructions is provided, the computer instructions being used to cause a computer to perform the method provided by the present disclosure.

[0009] According to another aspect of the present disclosure, a computer program product is provided, which comprises a computer program, the computer program being executed by a processor to implement the method provided by the present disclosure.

[0010] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0011] The accompanying drawings are used to better understand the present scheme, and do not constitute a limitation on the present disclosure. Among them:

[0012] Figure 1 is an exemplary system architecture schematic diagram to which the map generation method and apparatus according to one embodiment of the present disclosure can be applied;

[0013] Figure 2 is a flowchart of a map generation method according to one embodiment of the present disclosure;

[0014] Figure 3 is a flowchart of a map generation method according to another embodiment of the present disclosure;

[0015] Figure 4is an exemplary schematic diagram of a target map according to one embodiment of the present disclosure;

[0016] Figure 5 is a block diagram of a map generation apparatus according to one embodiment of the present disclosure; and

[0017] Figure 6 is a block diagram of an electronic device to which a map generation method can be applied according to one embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] Exemplary embodiments of the present disclosure are described herein with reference to the accompanying drawings, in which various specific details are set forth to assist in a thorough understanding of the embodiments. It will be understood by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the spirit and scope of the disclosure. Also, the description is made in the context of a detailed description of the preferred embodiments, and thus it will be understood that no limitation intended on the scope of the disclosure apart from that which is recited in the appended claims.

[0019] A laser radar (LiDAR) can collect data of a target region and send the data to a server after pre-processing. For example, the laser radar emits a laser scanning beam, and when the laser scanning beam encounters an object and is reflected back, it is received by the laser radar, completing one emission and reception of the laser scanning beam. In this way, a large amount of point cloud data can be continuously collected.

[0020] An inertial measurement unit (IMU) can determine a trajectory of a target object. The target object may, for example, be a vehicle or other device that is equipped with a laser radar and an inertial measurement unit.

[0021] Extrinsics parameters between the laser radar and the inertial measurement unit can include a space-time parameter relationship between the two. The space parameter can be a conversion relationship between a point cloud coordinate system related to the laser radar and an inertial coordinate system related to the inertial measurement unit. The time parameter can be a synchronization error of sensor measurement time. This error is caused by signal processing delay and communication delay between the laser radar and the inertial measurement unit. For example, at the same time, the time stamp of the point cloud data output by the laser radar and the time stamp of the inertial measurement data output by the inertial measurement unit are inconsistent.

[0022] In some embodiments, trajectory information related to the inertial measurement unit can be determined according to inertial measurement data and global navigation satellite data determined by a global navigation satellite system (GNSS). The trajectory information, in combination with the extrinsic parameters described above, can be used to determine trajectory information related to the lidar. According to the trajectory information related to the lidar, the point cloud data can be motion compensated. According to the compensated point cloud data and the initial trajectory information related to the lidar, revised trajectory information can be obtained. According to the revised trajectory information, a plurality of point cloud data can be spliced to obtain a point cloud map. According to the point cloud map, a high-definition map can be generated.

[0023] The accuracy of the extrinsic parameters and the initial trajectory information related to the lidar have a direct impact on the accuracy and mapping success rate of the high-definition map. For example, in the process of generating a high-definition map of a certain area, if the rotation error of the extrinsic parameters exceeds 0.8 degrees, a large range of ghosting problems can occur, resulting in mapping failure.

[0024] The data collection environment and working conditions are difficult to accurately control, resulting in a certain instability of the extrinsic parameters. For example, after a data collection vehicle breaks down and is towed to a repair shop by a tow truck, its extrinsic parameters can change. However, the changed extrinsic parameters are often not updated in time, resulting in an increase in the error of the extrinsic parameters used when generating the map.

[0025] The models of the data collection vehicles are different, and the sources of the extrinsic parameters in different data collection processes are not easy to control. For example, the data collection vehicle can be a level 4 (L4) autonomous driving collection vehicle. The maintenance methods of the extrinsic parameters of vehicles of different models are different, and the accuracy is also different.

[0026] The extrinsic parameters can be optimized using global navigation satellite data and lidar point cloud data to obtain optimized extrinsic parameters. However, this optimization method is strongly dependent on the accuracy of the global satellite navigation system, and errors in the global satellite navigation system can affect the optimization results.

[0027] The extrinsic parameters can also be optimized using point cloud data and inertial measurement data. However, the accuracy of this optimization method is limited.

[0028] Figure 1 is an exemplary system architecture schematic diagram to which the map generation method and device according to an embodiment of the present disclosure can be applied. It should be noted that, Figure 1 The diagram shown is only an example of a system architecture to which the embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0029] As Figure 1As shown, the system architecture 100 according to the embodiment can include sensors 101, 102, 103, a network 120, a server 130, and a road side unit (RSU) 140. The network 120 is a medium to provide a communication link between the sensors 101, 102, 103 and the server 130. The network 120 can include various connection types, such as wired and / or wireless communication links, and the like.

[0030] The sensors 101, 102, 103 can interact with the server 130 through the network 120 to receive or send messages, and the like.

[0031] The sensors 101, 102, 103 can be functional elements integrated on the vehicle 110, such as infrared sensors, ultrasonic sensors, millimeter wave radars, information collection devices, laser radars, inertial measurement units, and the like. The sensors 101, 102, 103 can be used to collect state data of perceived objects (such as pedestrians, vehicles, obstacles, and the like) and surrounding road data around the vehicle 110.

[0032] The vehicle 110 can communicate with the road side unit 140, receive information from the road side unit 140, or send information to the road side unit 140.

[0033] The road side unit 140 can be deployed on a signal light, for example, to adjust the duration or frequency of the signal light.

[0034] The server 130 can be disposed at a remote end capable of establishing communication with the vehicle terminal, can be implemented as a distributed server cluster composed of multiple servers, or can be implemented as a single server.

[0035] The server 130 can be a server providing various services. The server 130 can be installed with, for example, a map application, a data processing application, and the like. Taking the server 130 running the data processing application as an example: the server 130 receives state data of obstacles and map data transmitted from the sensors 101, 102, 103 through the network 120. One or more of the state data of obstacles and the map data can be used as to-be-processed data. The to-be-processed data is processed to obtain target data.

[0036] It should be noted that the map generation method provided by the embodiment of the present disclosure can generally be executed by the server 130. Correspondingly, the map generation apparatus provided by the embodiment of the present disclosure can also be disposed in the server 130. However, it is not limited thereto. The map generation method provided by the embodiment of the present disclosure can also generally be executed by the sensor 101, 102, or 103. Correspondingly, the map generation apparatus provided by the embodiment of the present disclosure can also be disposed in the sensor 101, 102, or 103.

[0037] It can be understood that Figure 1 The number of sensors, networks and servers in the above-mentioned system is only illustrative. Any number of sensors, networks and servers can be provided according to implementation needs.

[0038] It should be noted that the serial numbers of the various operations in the following method are only used as a representation of the operation for description, and should not be regarded as representing the execution order of the various operations. The method does not need to be executed in the order shown unless explicitly indicated.

[0039] Figure 2 is a flowchart of a map generation method according to one embodiment of the present disclosure.

[0040] As shown in Figure 2 The method 200 can include operations S210 to S250.

[0041] In operation S210, an initial map is generated according to initial point cloud data and initial motion trajectory information.

[0042] In embodiments of the present disclosure, the initial motion trajectory information can be motion trajectory information of an inertial measurement unit. For example, the initial motion trajectory information can be used to adjust the point cloud data to obtain adjusted point cloud data. According to the adjusted point cloud data, a point cloud map can be generated as the initial map.

[0043] In operation S220, association relationship information between a plurality of initial points in the initial point cloud data and a plurality of face features of a target plane in the initial map is determined.

[0044] In embodiments of the present disclosure, the target plane can be at least one. For example, a plurality of target planes can be perpendicular to each other. In one example, the target plane can be three. The three target planes can also be referred to as orthogonal faces.

[0045] In embodiments of the present disclosure, the face features of the target plane can be extracted in various ways. For example, the face features of the target plane can be extracted based on a laser radar odometry and mapping in real time (LOAM) algorithm.

[0046] In operation S230, distance information between the face features corresponding to the initial points and the initial points is determined according to the initial external parameters, the initial motion trajectory information and the association relationship information.

[0047] In the embodiments of the present disclosure, according to the initial external parameter, coordinate system conversion can be performed so that the initial motion trajectory information and the correlation information are in the same coordinate system. For example, the correlation information can be in the initial map coordinate system of the initial map. The initial motion trajectory information can be from the inertial coordinate system. According to the initial external parameter, the initial motion trajectory information can be converted into the initial map coordinate system, so as to determine the distance information between the initial points and the surface features in the same coordinate system.

[0048] In operation S240, according to the plurality of distance information, the initial external parameter and the initial motion trajectory information are adjusted to obtain target motion trajectory information and target external parameter.

[0049] In the embodiments of the present disclosure, according to the distance information, the external parameter and the initial motion trajectory information can be adjusted in various ways. For example, the target of adjustment can be to reduce the distance indicated by the distance information. For another example, the adjusted initial trajectory information and the initial external parameter can be taken as the target motion trajectory information and the target external parameter, respectively.

[0050] In operation S250, according to the target motion trajectory information and the target external parameter, a target map is generated.

[0051] For example, the point cloud data can be adjusted by using the target motion trajectory information. According to the point cloud data adjusted by the target motion trajectory information, a point cloud map can be generated as the target map.

[0052] By the embodiments of the present disclosure, when the external parameter is optimized according to the point cloud data and the inertial data, the dependence on the global satellite navigation system is reduced or even eliminated. Therefore, the influence of the error of the global satellite navigation system on the precision of the high-precision map is reduced, and the success rate and precision of generating the high-precision map are significantly improved.

[0053] In addition, by the embodiments of the present disclosure, the initial motion trajectory information and the initial external parameter are adjusted according to the distance information, which can also reduce the precision requirement for the initial motion trajectory information or the initial external parameter, and is helpful to improve the efficiency of map generation and reduce the cost required for map generation.

[0054] Some embodiments of generating the initial map will be described in detail below in combination with related embodiments.

[0055] In some embodiments, in some embodiments of operation S210 described above, generating the initial map according to the initial point cloud data and the initial motion trajectory information can include: determining point cloud compensation information according to the initial motion trajectory information and the initial external parameter. Adjusting the initial point cloud data by using the point cloud compensation information to obtain adjusted point cloud data. Performing point cloud splicing on the plurality of adjusted point cloud data to obtain initial map data. Generating the initial map according to the initial map data.

[0056] For example, according to the initial external parameters and the initial motion trajectory information of the inertial measurement unit, the motion trajectory information related to the lidar can be determined. Based on the motion trajectory information, the point cloud compensation information can be determined. The initial point cloud data is compensated for motion by using the point cloud compensation information, so as to realize adjustment of multiple point cloud data, and obtain adjusted point cloud data. The initial point cloud data can be multiple. Therefore, the adjusted point cloud data can also be multiple. The adjusted point cloud data is spliced to obtain spliced point cloud data as initial map data. According to the initial map data, an initial map can be generated.

[0057] It can be understood that some embodiments of generating an initial map are described in detail above, and some embodiments of determining the association relationship will be described in detail below in combination with related embodiments.

[0058] In some embodiments, in some embodiments of the operation S220 described above, determining the association relationship information between the multiple initial points in the initial point cloud data and the multiple face features of the target plane in the initial map includes: determining at least one target plane in the initial map. Extracting multiple face features of the target plane. Determine the association sub-relationship information between the initial points and the face features, wherein the association sub-relationship is used to indicate the face feature corresponding to the initial point. According to the multiple association sub-relationship information, the association relationship information is determined.

[0059] For example, the target plane can be 3. The 3 target planes can be perpendicular to each other. The 3 target planes can also be referred to as 3 orthogonal faces. Based on the lidar odometry measurement and the real-time mapping algorithm, the face features in the target plane can be extracted (for example, more than or equal to 80 face features are extracted from each target plane). The association sub-relationship information between the initial points and the face features can be determined, so that the initial points correspond to one face feature. It can be understood that one face feature can correspond to multiple initial points. The association sub-relationship information of the multiple initial points is used as the association relationship information.

[0060] It can be understood that some ways of determining the association relationship information are described in detail above, and some embodiments of determining the distance information between the face feature corresponding to the initial point and the initial point will be described in detail below in combination with related embodiments.

[0061] In some embodiments, in some implementations of operation S230 described above, determining, according to the initial extrinsic parameter, the initial motion trajectory information, and the association relationship information, distance information between the initial point and the face feature corresponding to the initial point can include: determining, according to the initial motion trajectory information, initial rotation estimation information and initial displacement estimation information. Obtaining initial map coordinate data of the initial point according to the initial extrinsic parameter, point cloud coordinate data of the initial point, the initial rotation estimation information, and the initial displacement estimation information. Determining the distance information according to the initial map coordinate data and the face feature corresponding to the initial point.

[0062] In embodiments of the present disclosure, the initial rotation estimation information can include an initial rotation estimation value. The initial displacement estimation information can include an initial displacement estimation value. For example, according to the initial motion trajectory information , the initial rotation estimation value , and the initial displacement estimation value may be determined.

[0063] In embodiments of the present disclosure, the point cloud coordinate data is used to indicate a position of the initial point in an initial point cloud coordinate system, and the initial map coordinate data is used to indicate a position of the initial point in an initial map coordinate system of an initial map.

[0064] In embodiments of the present disclosure, obtaining initial map coordinate data of the initial point according to the initial extrinsic parameter, point cloud coordinate data of the initial point, initial rotation estimation information, and initial displacement estimation information can include: obtaining inertial coordinate data of the initial point according to the initial extrinsic parameter and the point cloud coordinate data, the inertial coordinate data being used to indicate a position of the initial point in an inertial coordinate system. Determining conversion information according to the initial rotation estimation information and the initial displacement estimation information. Processing the inertial coordinate data by using the conversion information to obtain the initial map coordinate data.

[0065] For example, according to the initial extrinsic parameter and the point cloud data of the initial point i , inertial coordinate data of the initial point i may be obtained. The inertial coordinate data can indicate a position of the initial point i in an inertial coordinate system. For another example, according to the initial rotation estimation value and the initial displacement estimation value , a conversion matrix may be determined. The conversion matrix can be used as the conversion information. For another example, multiplying the conversion matrix and the inertial coordinate data can obtain initial map coordinate data of the initial point i .

[0066] For example, according to the initial map coordinate data and feature parameters of the face feature , a distance measurement residual , as distance information. In one example, according to the laser radar odometry measurement and the real-time mapping algorithm described above, a distance measurement residual can be determined.

[0067] It can be understood that some embodiments of determining distance information are described in detail above. In order to adjust the initial extrinsic parameter and the initial motion trajectory information, acceleration information and angular velocity information can also be obtained, which will be described in detail below.

[0068] In some embodiments, in some embodiments of operation S240, adjusting the initial extrinsic parameter and the initial motion trajectory information according to the plurality of distance information can include: adjusting the initial extrinsic parameter and the initial motion trajectory information according to the acceleration information, the angular velocity information and the plurality of distance information.

[0069] In some embodiments, the inertial measurement data collected by the inertial measurement unit can include inertial rotation data and inertial translation data.

[0070] In some embodiments, according to the inertial translation data and the initial motion trajectory information, the acceleration information can be determined.

[0071] In embodiments of the present disclosure, according to the initial motion trajectory information, initial rotation estimation information and initial acceleration estimation information are determined. For example, the initial acceleration estimation information can include an initial acceleration estimation value .

[0072] In embodiments of the present disclosure, according to the inertial translation data, initial acceleration measurement information can be determined. For example, the initial acceleration measurement information can include an initial acceleration measurement value .

[0073] In embodiments of the present disclosure, according to the initial rotation estimation information, the initial acceleration estimation information and the initial acceleration measurement information, the acceleration information can be determined.

[0074] In embodiments of the present disclosure, the initial acceleration estimation information is subjected to first operation processing by using first preset acceleration information, and first acceleration estimation information can be obtained. For example, the first preset acceleration information can include a gravitational acceleration value . For another example, the first operation processing can include subtraction operation processing. In one example, the difference between the gravitational acceleration value and the initial acceleration estimation value may be taken as the first acceleration estimation information.

[0075] In the embodiments of the present disclosure, the second operation processing is performed on the initial acceleration estimation value by using the initial acceleration estimation information, so that the second acceleration estimation information can be obtained. For example, the second operation processing can include multiplication operation processing. For another example, the initial acceleration estimation value can be converted to obtain the reciprocal of the initial acceleration estimation value, and the reciprocal is multiplied by the difference value to obtain a product, and the product can be used as the second acceleration estimation information.

[0076] In the embodiments of the present disclosure, the acceleration difference information between the initial acceleration measurement information and the second acceleration estimation information can be determined. For example, the initial acceleration measurement value can be subtracted by the product to obtain an acceleration difference value, and the acceleration difference value can be used as the acceleration difference information.

[0077] In the embodiments of the present disclosure, the acceleration difference information can be adjusted by using the preset translation bias, so that the acceleration information can be obtained. For example, the acceleration difference value can be added by the preset translation bias to obtain an acceleration measurement residual value, and the acceleration measurement residual value can be used as the acceleration information.

[0078] In one example, the acceleration measurement residual value can be determined by the following formula:

[0079] (Formula One)

[0080] The first acceleration estimation value can be the initial acceleration estimation value. The second acceleration estimation value can be the initial acceleration estimation value. The initial acceleration estimation value can be the initial acceleration estimation value. The initial acceleration estimation value can be the initial acceleration estimation value. The initial acceleration measurement value can be the initial acceleration measurement value. The preset translation bias can be the initial acceleration measurement value. The gravity acceleration value can be the initial acceleration measurement value.

[0081] In some embodiments, according to the inertial rotation data and the initial motion trajectory information, the angular velocity information can be determined.

[0082] In the embodiments of the present disclosure, according to the initial motion trajectory information, the initial angular velocity estimation information can be determined. For example, the initial angular velocity estimation information can include an initial angular velocity estimation value.

[0083] In the embodiments of the present disclosure, according to the inertial rotation data, the initial angular velocity measurement information can be determined. For example, the initial angular velocity measurement information can include an initial angular velocity measurement value. ​​​​​​​​

[0084] In the embodiments of the present disclosure, the angular velocity information can be determined according to the initial angular velocity estimation information and the initial angular velocity measurement information.

[0085] In the embodiments of the present disclosure, the angular velocity difference information between the initial angular velocity measurement information and the initial angular velocity estimation information can be determined. For example, the initial angular velocity measurement value is subtracted from the initial angular velocity estimation value to obtain an angular velocity difference value as the angular velocity difference information.

[0086] In the embodiments of the present disclosure, the angular velocity difference information is adjusted by using a preset rotation deviation to obtain the angular velocity information. For example, the angular velocity measurement residual is obtained by subtracting the preset rotation deviation from the angular velocity difference value, as the angular velocity information.

[0087] In one example, the acceleration measurement residual may be determined by the following formula:

[0088] (Formula Two)

[0089] may be the angular velocity difference value. may be the initial angular velocity estimation value. may be the initial angular velocity measurement value. may be the preset rotation deviation

[0090] It can be understood that the above describes in detail the way of obtaining the acceleration information, the angular velocity information and the distance information. Some embodiments of adjusting the initial external parameter and the initial trajectory information will be described in detail below.

[0091] In some embodiments, the initial external parameter and the initial motion trajectory information are adjusted to obtain the target motion trajectory information and the target external parameter according to the acceleration information, the angular velocity information and the plurality of distance information can include: determining fusion information according to the acceleration information, the angular velocity information and the plurality of distance information. The initial motion trajectory information and the initial external parameter are adjusted to make the fusion information converge to obtain the target motion trajectory information and the target external parameter.

[0092] For example, the fusion information can be realized as a target function shown in the following formula:

[0093] (Formula Three)

[0094] may be a variable value used to find the minimum value of the function value of the target function. may be the target motion trajectory information, The target external parameter can be obtained. , , The target gravity acceleration value, the target translation deviation, and the target rotation deviation can be respectively consistent with the gravity acceleration value , the preset translation deviation , and the preset rotation deviation , respectively, and can be regarded as invariable values. For example, the initial motion trajectory information and the initial external parameter are adjusted to obtain the target motion trajectory information and the target external parameter. The target is to reduce or converge the function value of the target function shown in formula three calculated according to the target motion trajectory information and the target external parameter.

[0095] It can be understood that the above describes in detail the manner of adjusting the initial motion trajectory information and the initial external parameter. In the embodiments of the present disclosure, the original motion trajectory information and the original external parameter can be iterated for N times to realize the convergence of the fused information. The initial motion trajectory information and the initial external parameter described above can be respectively regarded as the initial motion trajectory information of the nth iteration and the initial external parameter of the nth iteration. The target motion trajectory information and the target external parameter described above can be respectively regarded as the target motion trajectory information of the nth iteration and the target external parameter of the nth iteration. The following will be described in detail in combination with related embodiments.

[0096] Figure 3 is a flowchart of a map generation method according to an embodiment of the present disclosure.

[0097] As shown in Figure 3 , each operation in the method 300 is used to perform the nth iteration, and n is an integer greater than or equal to 1. n is an integer less than or equal to N. N is an integer greater than or equal to 1. In the embodiments of the present disclosure, before the first iteration is performed, an initialization operation can be performed to determine the original motion trajectory information and the original external parameter. For example, the original motion trajectory information can be used as the initial motion trajectory information of the first iteration. The original external parameter can also be determined as the initial external parameter of the first iteration. For another example, the initialization can be performed according to various manners to obtain the original motion trajectory information and the original external parameter. In one example, the local trajectory output by the laser radar inertial odometry (LiDAR Inertial Odometry, LIO) or the trajectory output by the vehicle end positioning module can be used as the original motion trajectory information.

[0098] In operation S310, the initial map of the nth iteration is generated according to the initial motion trajectory information of the nth iteration and the initial point cloud data.

[0099] For example, according to the initial extrinsic parameter of the n th iteration and the initial motion trajectory information of the n th iteration, the n th level laser radar related motion trajectory information can be determined. Based on the n th level laser radar related motion trajectory information, the n th level point cloud compensation information can be determined. The initial point cloud data is compensated by using the n th level point cloud compensation information, so as to realize the adjustment of the multiple point cloud data, and the n th level adjusted point cloud data is obtained. The initial point cloud data can be multiple. Therefore, the n th level adjusted point cloud data can also be multiple. The n th level adjusted point cloud data is spliced to obtain the n th level spliced point cloud data as the n th level initial map data. According to the n th level initial map data, the initial map of the n th iteration can be generated.

[0100] In operation S320, the n th level association relationship information between the multiple initial points and the multiple surface features of the target plane in the initial map of the n th iteration is determined.

[0101] For example, three target planes can be determined in the initial map of the n th iteration, the surface features of the target planes are extracted, and the n th level association sub-relationship information between the initial points in the initial point cloud data which is not compensated and the surface features is determined. The n th level association sub-relationship information of the multiple initial points is taken as the n th level association relationship information.

[0102] In operation S330, according to the inertial measurement data, the initial extrinsic parameter of the n th iteration, the initial motion trajectory information of the n th iteration and the n th level association relationship information, the n th level acceleration information, the n th level angular velocity information and the multiple n th level distance information are determined.

[0103] For example, according to the inertial translation data and the initial motion trajectory information of the n th iteration, the n th level acceleration measurement residual can be determined as the n th level acceleration information.

[0104] For example, according to the inertial rotation data and the initial motion estimation information of the n th iteration, the n th level angular velocity measurement residual can be determined as the n th level angular velocity information.

[0105] For example, according to the initial extrinsic parameter of the n th iteration, the initial motion trajectory information of the n th iteration and the multiple n th level association sub-relationship information, the multiple distance measurement residuals can be determined respectively as the multiple n th level distance information.

[0106] In operation S341, according to the n th level acceleration information, the n th level angular velocity information and the multiple n th level distance information, the n th level fusion information is determined.

[0107] For example, the n th level acceleration measurement residual, the n th level angular velocity measurement residual and the multiple n th level distance measurement residuals are processed by using the objective function shown in formula three, and the n th level function value is obtained as the n th level fusion information.

[0108] In operation S342, it is determined whether the n-th level fusion information converges.

[0109] For example, it can be determined whether the difference between the n-th level function value and the (n-1)-th level function value is less than a preset difference threshold. If it is less than the preset difference threshold, it can be determined that the n-th level fusion information converges. It can be understood that other ways can also be used to determine whether the fusion information converges. For another example, in the case of n=1, it can be determined that the first level fusion information does not converge.

[0110] In the embodiments of the present disclosure, in response to determining that the n-th level fusion information converges, operation S350 is performed.

[0111] In the embodiments of the present disclosure, in response to determining that the n-th level fusion information does not converge, operation S343 is performed.

[0112] In operation S343, the initial external parameter of the n-th iteration and the initial motion trajectory information of the n-th iteration are adjusted to obtain the target external parameter of the n-th iteration and the target motion trajectory information of the n-th iteration.

[0113] For example, various ways can be used to adjust the initial external parameter of the n-th iteration and the initial motion trajectory information of the n-th iteration to obtain the target external parameter of the n-th iteration and the target motion trajectory information of the n-th iteration.

[0114] In operation S344, the target external parameter of the n-th iteration and the target motion trajectory information of the n-th iteration are taken as the initial external parameter of the (n+1)-th iteration and the initial motion trajectory information of the (n+1)-th iteration respectively, and the process returns to operation S310.

[0115] For example, according to the initial external parameter of the (n+1)-th iteration and the initial motion trajectory information of the (n+1)-th iteration, the (n+1)-th iteration is performed.

[0116] In operation S350, a target map is generated according to the motion trajectory information and the external parameter corresponding to the converged fusion information.

[0117] For example, in the case where the n-th level fusion information converges, the target motion trajectory information of the (n-1)-th iteration and the target external parameter of the (n-1)-th iteration can be used to generate the target map. For another example, in the case where the fusion information converges, the target motion trajectory information of the n-th iteration and the target external parameter of the n-th iteration can be used to generate the target map. It can be understood that in the process of the two iterations before and after the convergence of the fusion information, the difference between the two related motion trajectory information is small, and at least one of the trajectory information can be used to generate the target map. It can also be understood that in the process of the two iterations before and after the convergence of the fusion information, the difference between the two related external parameters is small, and can be used to generate the target map.

[0118] In the embodiments of the present disclosure, if the fusion information converges after N iterations, the Nth level laser radar related motion trajectory information can be determined. Based on the Nth level laser radar related motion trajectory information, the Nth level point cloud compensation information can be determined. The initial point cloud data is compensated by using the Nth level point cloud compensation information, so as to adjust the point cloud data and obtain the Nth level adjusted point cloud data. The initial point cloud data can be multiple. Therefore, the Nth level adjusted point cloud data can also be multiple. The Nth level adjusted point cloud data is spliced to obtain the Nth level spliced point cloud data as the target map data. According to the target map data, the target map can be generated.

[0119] It can be understood that some embodiments of generating a map are described in detail above. In order to improve the accuracy of the generated map, some information or data can be checked in each operation process, which will be described in detail below.

[0120] In some embodiments, determining the association sub-relation information between the initial point and the surface feature comprises: in response to determining that the data of the surface feature is greater than or equal to a preset surface feature quantity threshold, determining the association sub-relation information between the initial point and the surface feature. For example, the preset surface feature quantity threshold can be 80. If the surface feature quantity is less than 80, the last iteration can be re-executed, and the initial trajectory information and / or the initial external parameter of the last iteration can be re-adjusted.

[0121] In some embodiments, the acceleration measurement residual, the angular velocity measurement residual and the distance measurement residual described above can also be checked.

[0122] It can be understood that the map generation method and the checking method of the related data in the map generation process are described in detail above. The data required for map generation will be described in detail below.

[0123] In some embodiments, the initial point cloud data and the original motion trajectory information come from a target object driving according to a preset driving route, and the preset driving route includes at least one preset driving sub-route with an arc greater than or equal to a preset arc threshold. For example, the target object can be a data collection vehicle. For another example, the preset driving route can be an 8-shaped driving route. For another example, the preset driving route can indicate a vehicle U-turn.

[0124] As described above, the extrinsic parameters include temporal extrinsic parameters and spatial extrinsic parameters. The spatial extrinsic parameters can include 6 degrees of freedom components, respectively, translational x, translational y, translational z, rotational x, rotational y, and rotational z. According to the embodiments of the present disclosure, in the case of following the preset driving route, the translational z component in the spatial extrinsic parameters related to the data collection vehicle is unobservable, and it can be considered that the component is constant and does not need to be optimized. “Unobservable” is a control theory term, which indicates whether the data can be mined or estimated from existing data. In the embodiments of the present disclosure, the true value change of the translational z component does not cause the change of other components, that is, other components are not sensitive to the true value change of the translational z. Therefore, the difficulty of map generation can be reduced.

[0125] In the embodiments of the present disclosure, the theoretical basis of the above method can be a B-spline curve.

[0126] As described above, the inertial measurement data can include inertial translational data and inertial rotational data. Therefore, based on the inertial translational data and the inertial rotational data, two B-spline curves can be used to model the continuous time trajectory of the translational process and the continuous time trajectory of the rotational process of the inertial measurement unit, respectively. The two B-spline curves can be fitted by a 4th order linear function.

[0127] The control nodes of the B-spline curve of the trajectory are uniformly distributed in time, which is highly related to the shape of the B-spline curve. Based on the B-spline curve, the first and second derivatives of the state with respect to time can be determined. For the B-spline curve of the translational process, the first and second derivatives are the velocity state and the acceleration state, respectively. For the B-spline curve of the rotational process, the first and second derivatives are the angular velocity state and the angular acceleration state, respectively.

[0128] Figure 4 is an exemplary schematic diagram of a target map according to one embodiment of the present disclosure.

[0129] As Figure 4 shown, the target map M400 has high accuracy. Most of the points of the target map M400 are at positions corresponding to objects (e.g., office buildings) in the real scene. There are fewer points that are not aligned with the objects in the real scene.

[0130] Figure 5 is a block diagram of a map generation apparatus according to one embodiment of the present disclosure.

[0131] As Figure 5 shown, the apparatus 500 can include a first generation module 510, a first determination module 520, a second determination module 530, an adjustment module 540, and a second generation module 550.

[0132] The first generation module 510 is configured to generate an initial map according to the initial point cloud data and the initial motion trajectory information.

[0133] The first determination module 520 is configured to determine association relationship information between a plurality of initial points in the initial point cloud data and a plurality of face features of the target plane in the initial map.

[0134] The second determination module 530 is configured to determine distance information between the face features corresponding to the initial points and the initial points according to the initial extrinsic parameters, the initial motion trajectory information and the association relationship information.

[0135] The adjustment module 540 is configured to adjust the initial extrinsic parameters and the initial motion trajectory information according to the plurality of distance information to obtain target motion trajectory information and target extrinsic parameters.

[0136] The second generation module 550 is configured to generate a target map according to the target motion trajectory information and the target extrinsic parameters.

[0137] In some embodiments, the second determination module comprises: a first determination submodule configured to determine initial rotation estimation information and initial displacement estimation information according to the initial motion trajectory information; a first obtaining submodule configured to obtain initial map coordinate data of the initial points according to the initial extrinsic parameters, point cloud coordinate data of the initial points, the initial rotation estimation information and the initial displacement estimation information, the point cloud coordinate data being used to indicate positions of the initial points in an initial point cloud coordinate system, and the initial map coordinate data being used to indicate positions of the initial points in an initial map coordinate system of the initial map; and a second determination submodule configured to determine the distance information according to the initial map coordinate data and the association relationship.

[0138] In some embodiments, the first obtaining submodule comprises: a first obtaining unit configured to obtain inertial coordinate data of the initial points according to the initial extrinsic parameters and the point cloud coordinate data, the inertial coordinate data being used to indicate positions of the initial points in an inertial coordinate system; a first determining unit configured to determine conversion information according to the initial rotation estimation information and the initial displacement estimation information; and a first processing unit configured to process the inertial coordinate data by using the conversion information to obtain the initial map coordinate data.

[0139] In some embodiments, the adjustment module comprises: a third determination submodule configured to determine acceleration information according to the inertial translation data and the initial motion trajectory information; a fourth determination submodule configured to determine angular velocity information according to the inertial rotation data and the initial motion trajectory information; and a first adjustment submodule configured to adjust the initial extrinsic parameters and the initial motion trajectory information according to the acceleration information, the angular velocity information and the plurality of distance information to obtain the target motion trajectory information and the target extrinsic parameters.

[0140] In some embodiments, the third determining sub-module comprises: a second determining unit, configured to determine initial rotation estimation information and initial acceleration estimation information according to the initial motion trajectory information; a third determining unit, configured to determine initial acceleration measurement information according to the inertial translation data; and a fourth determining unit, configured to determine the acceleration information according to the initial rotation estimation information, the initial acceleration estimation information and the initial acceleration measurement information.

[0141] In some embodiments, the fourth determining unit comprises: a first operation processing sub-unit, configured to perform first operation processing on the initial acceleration estimation information by using first preset acceleration information to obtain first acceleration estimation information; a second operation processing sub-unit, configured to perform second operation processing on the first acceleration estimation information by using the initial rotation estimation information to obtain second acceleration estimation information; a first determining sub-unit, configured to determine acceleration difference information between the initial acceleration measurement information and the second acceleration estimation information; and a first adjusting sub-unit, configured to adjust the acceleration difference information by using a preset translation bias to obtain the acceleration information.

[0142] In some embodiments, the fourth determining sub-module comprises: a fifth determining unit, configured to determine initial angular velocity estimation information according to the initial motion trajectory information; a sixth determining unit, configured to determine initial angular velocity measurement information according to the inertial rotation data; and a seventh determining unit, configured to determine the angular velocity information according to the initial angular velocity estimation information and the initial angular velocity measurement information.

[0143] In some embodiments, the seventh determining unit comprises: a second determining sub-unit, configured to determine angular velocity difference information between the initial angular velocity measurement information and the initial angular velocity estimation information; and a second adjusting sub-unit, configured to adjust the angular velocity difference information by using a preset rotation bias to obtain the angular velocity information.

[0144] In some embodiments, the first adjusting sub-module comprises: an eighth determining unit, configured to determine fusion information according to the acceleration information, the angular velocity information and the plurality of distance information; and an adjusting unit, configured to adjust the initial motion trajectory information and the initial external parameter to make the fusion information converge to obtain target motion trajectory information and target external parameter.

[0145] In some embodiments, the first generating module comprises: a fifth determining sub-module, configured to determine point cloud compensation information according to the initial motion trajectory information and the initial external parameter; a second adjusting sub-module, configured to adjust the initial point cloud data by using the point cloud compensation information to obtain adjusted point cloud data; a point cloud splicing sub-module, configured to perform point cloud splicing on the plurality of adjusted point cloud data to obtain initial map data; and a first generating sub-module, configured to generate the initial map according to the initial map data.

[0146] In some embodiments, the first initial motion trajectory information is initial motion trajectory information of the n th iteration, and the first generation module comprises a second generation submodule configured to generate initial map data of the n th iteration according to the initial motion trajectory information of the n th iteration and the initial point cloud data. n is an integer greater than or equal to 1, n is an integer less than or equal to N, and N is an integer greater than 1.

[0147] In some embodiments, the initial external parameters are initial external parameters of the n th iteration, and the first determination module comprises a sixth determination submodule configured to determine n th level association relationship information between the plurality of initial points and a plurality of face features of the target plane in the initial map of the n th iteration. The adjustment module comprises a third adjustment submodule configured to adjust the initial external parameters of the n th iteration and the initial motion trajectory information of the n th iteration to obtain target motion trajectory information of the n th iteration and target external parameters of the n th iteration. The seventh determination submodule is configured to take the target motion trajectory information of the n th iteration as initial motion trajectory information of the (n+1) th iteration. The eighth determination submodule is configured to take the target external parameters of the n th iteration as initial external parameters of the (n+1) th iteration.

[0148] In some embodiments, the first generation module comprises a ninth determination submodule configured to determine original motion trajectory information and original external parameters. The tenth determination submodule is configured to determine the original motion trajectory information as initial motion trajectory information of the 1 st iteration and to determine the original external parameters as initial external parameters of the 1 st iteration.

[0149] In some embodiments, the first determination module comprises an eleventh determination submodule configured to determine at least one target plane in the initial map. The extraction submodule is configured to extract a plurality of face features of the target plane. The twelfth determination submodule is configured to determine association sub-relationship information between the initial points and the face features, wherein the association sub-relationship is used to indicate the face features corresponding to the initial points. The thirteenth determination submodule is configured to determine the association relationship information according to the plurality of association sub-relationship information.

[0150] In some embodiments, the twelfth determination submodule comprises a ninth determination unit configured to determine the association sub-relationship information between the initial points and the face features in response to determining that the data of the face features is greater than or equal to a preset face feature quantity threshold.

[0151] In some embodiments, the initial point cloud data and the original motion trajectory information are from a target object driving along a preset driving route, and the preset driving route comprises at least one preset driving sub-route with an arc greater than or equal to a preset arc threshold.

[0152] In the technical solutions of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information comply with relevant laws and regulations and do not violate public order and good customs.

[0153] According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0154] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0155] As shown in Figure 6 The device 600 includes a computing unit 601 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 602 or loaded into a random access memory (RAM) 603 from a storage unit 608. Various programs and data required for the operation of the device 600 can also be stored in the RAM 603. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0156] Various components in the device 600 are connected to the I / O interface 605, including an input unit 606, such as a keyboard, a mouse, etc., an output unit 607, such as various types of displays, speakers, etc., a storage unit 608, such as a magnetic disk, an optical disk, etc., and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0157] The computing unit 601 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs various methods and processes described above, such as the map generation method. For example, in some embodiments, the map generation method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded onto the RAM 603 and executed by the computing unit 601, one or more steps of the map generation method described above can be performed. Alternatively, in other embodiments, the computing unit 601 can be configured to perform the map generation method by any other suitable means, such as by means of firmware.

[0158] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0159] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or the block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0160] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0161] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) monitor or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0162] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0163] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

[0164] It should be understood that the various forms of flow shown above can be used to reorder, add, or remove steps. For example, the steps recited in the present disclosure can be performed in parallel, in series, or in a different order, as long as the desired results of the technology disclosed in the present disclosure are achieved, which is not limited herein.

[0165] The specific implementation described above does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for generating a map, comprising: generating an initial map according to initial point cloud data and initial motion trajectory information; determining association relationship information between a plurality of initial points in the initial point cloud data and a plurality of face features of a target plane in the initial map; determining distance information between a face feature corresponding to an initial point and the initial point according to initial extrinsic parameters, the initial motion trajectory information and the association relationship information; adjusting the initial extrinsic parameters and the initial motion trajectory information according to a plurality of the distance information to obtain target motion trajectory information and target extrinsic parameters, including: determining acceleration information according to inertial translation data and the initial motion trajectory information; determining angular velocity information according to inertial rotation data and the initial motion trajectory information; and adjusting the initial extrinsic parameters and the initial motion trajectory information according to the acceleration information, the angular velocity information and a plurality of the distance information to obtain the target motion trajectory information and the target extrinsic parameters; and generating a target map according to the target motion trajectory information and the target extrinsic parameters.

2. The method of claim 1, wherein, The determining distance information between a face feature corresponding to an initial point and the initial point according to initial extrinsic parameters, the initial motion trajectory information and the association relationship information comprises: determining initial rotation estimation information and initial displacement estimation information according to the initial motion trajectory information; obtaining initial map coordinate data of the initial point according to the initial extrinsic parameters, point cloud coordinate data of the initial point, the initial rotation estimation information and the initial displacement estimation information, wherein the point cloud coordinate data is used to indicate a position of the initial point in an initial point cloud coordinate system, and the initial map coordinate data is used to indicate a position of the initial point in an initial map coordinate system of the initial map; and determining the distance information according to the initial map coordinate data and the association relationship information.

3. The method of claim 2, wherein, The obtaining initial map coordinate data of the initial point according to the initial extrinsic parameters, point cloud coordinate data of the initial point, the initial rotation estimation information and the initial displacement estimation information comprises: obtaining inertial coordinate data of the initial point according to the initial extrinsic parameters and the point cloud coordinate data, wherein the inertial coordinate data is used to indicate a position of the initial point in an inertial coordinate system; determining conversion information according to the initial rotation estimation information and the initial displacement estimation information; and processing the inertial coordinate data by using the conversion information to obtain the initial map coordinate data.

4. The method of claim 1, wherein, The determining acceleration information according to inertial translation data and the initial motion trajectory information comprises: determining initial rotation estimation information and initial acceleration estimation information according to the initial motion trajectory information; determining initial acceleration measurement information according to the inertial translation data; and determining the acceleration information according to the initial rotation estimation information, the initial acceleration estimation information and the initial acceleration measurement information.

5. The method of claim 4, wherein, The determining the acceleration information according to the initial rotation estimation information, the initial acceleration estimation information and the initial acceleration measurement information comprises: performing first operation processing on the initial acceleration estimation information by using first preset acceleration information, to obtain first acceleration estimation information; performing second operation processing on the first acceleration estimation information by using the initial rotation estimation information, to obtain second acceleration estimation information; determining acceleration difference information between the initial acceleration measurement information and the second acceleration estimation information; and adjusting the acceleration difference information by using preset translation bias, to obtain the acceleration information.

6. The method of claim 1, wherein, The determining the angular velocity information according to the inertial rotation data and the initial motion trajectory information comprises: determining initial angular velocity estimation information according to the initial motion trajectory information; determining initial angular velocity measurement information according to the inertial rotation data; and determining the angular velocity information according to the initial angular velocity estimation information and the initial angular velocity measurement information.

7. The method of claim 6, wherein, The determining the angular velocity information according to the initial angular velocity estimation information and the initial angular velocity measurement information comprises: determining angular velocity difference information between the initial angular velocity measurement information and the initial angular velocity estimation information; adjusting the angular velocity difference information by using preset rotation bias, to obtain the angular velocity information.

8. The method of claim 1, wherein, The adjusting the initial external parameter and the initial motion trajectory information according to the acceleration information, the angular velocity information and a plurality of the distance information, to obtain the target motion trajectory information and the target external parameter comprises: determining fusion information according to the acceleration information, the angular velocity information and a plurality of the distance information; and adjusting the initial motion trajectory information and the initial external parameter, to make the fusion information converge, to obtain the target motion trajectory information and the target external parameter.

9. The method of claim 1, wherein, The generating an initial map according to initial point cloud data and the initial motion trajectory information comprises: determining point cloud compensation information according to initial motion trajectory information and the initial external parameter; adjusting the initial point cloud data by using the point cloud compensation information, to obtain adjusted point cloud data; performing point cloud splicing on a plurality of the adjusted point cloud data, to obtain initial map data; and generating the initial map according to the initial map data.

10. The method of claim 1, wherein, The initial motion trajectory information is initial motion trajectory information of the n th iteration, The generating an initial map according to initial point cloud data and the initial motion trajectory information comprises: generating an initial map of the n th iteration according to the initial motion trajectory information of the n th iteration and the initial point cloud data, wherein n is an integer greater than or equal to 1, n is an integer less than or equal to N, and N is an integer greater than 1.

11. The method of claim 10, wherein, The initial external parameter is initial external parameter of the n th iteration, The determining the association relationship information between a plurality of initial points in the initial point cloud data and a plurality of face features of a target plane in the initial map comprises: determining n th level association relationship information between a plurality of the initial points and a plurality of face features of a target plane in the initial map of the n th iteration; The adjusting the initial external parameter and the initial motion trajectory information, to obtain target motion trajectory information and target external parameter comprises: adjust the initial external parameter of the n th iteration and the initial motion trajectory information of the n th iteration to obtain target motion trajectory information of the n th iteration and target external parameter of the n th iteration; use the target motion trajectory information of the n th iteration as initial motion trajectory information of the n+1 th iteration; and use the target external parameter of the n th iteration as initial external parameter of the n+1 th iteration.

12. The method of claim 10, wherein, The generating an initial map according to initial point cloud data and initial motion trajectory information includes: determining original motion trajectory information and original external parameter; using the original motion trajectory information as initial motion trajectory information of the 1 st iteration; and determining the original external parameter as initial external parameter of the 1 st iteration.

13. The method of claim 1, wherein, The determining the association relationship information between the plurality of initial points in the initial point cloud data and the plurality of face features of the target plane in the initial map includes: determining at least one target plane in the initial map; extracting a plurality of face features of the target plane; determining association sub-relationship information between the initial point and the face feature, wherein the association sub-relationship is used to indicate the face feature corresponding to the initial point; and determining the association relationship information according to a plurality of association sub-relationship information.

14. The method of claim 13, wherein, The determining the association sub-relationship information between the initial point and the face feature includes: in response to determining that the data of the face feature is greater than or equal to a preset face feature quantity threshold, determining the association sub-relationship information between the initial point and the face feature.

15. The method of claim 12, wherein, The initial point cloud data and the original motion trajectory information are from a target object driving according to a preset driving route, and the preset driving route includes at least one preset driving sub-route with an arc greater than or equal to a preset arc threshold.

16. A map generation apparatus, comprising: a first generation module configured to generate an initial map according to initial point cloud data and initial motion trajectory information; a first determination module configured to determine association relationship information between a plurality of initial points in the initial point cloud data and a plurality of face features of a target plane in the initial map; a second determination module configured to determine distance information between a face feature corresponding to the initial point and the initial point according to initial external parameter, the initial motion trajectory information and the association relationship information; an adjustment module configured to adjust the initial external parameter and the initial motion trajectory information according to a plurality of distance information to obtain target motion trajectory information and target external parameter; and a second generation module configured to generate a target map according to the target motion trajectory information and the target external parameter. The adjustment module includes: a third determination submodule configured to determine acceleration information according to inertial translation data and the initial motion trajectory information; a fourth determination submodule configured to determine angular velocity information according to inertial rotation data and the initial motion trajectory information; a first adjustment submodule configured to adjust the initial external parameter and the initial motion trajectory information according to the acceleration information, the angular velocity information and a plurality of distance information to obtain the target motion trajectory information and the target external parameter.

17. An electronic device, comprising: ​ at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 15.

18. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, the computer instructions are for causing the computer to perform the method of any one of claims 1 to 15.

19. A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1 to 15.

Images