CN115685232A - Positioning method and device of self-guiding vehicle, server and storage medium - Google Patents
Positioning method and device of self-guiding vehicle, server and storage medium Download PDFInfo
- Publication number
- CN115685232A CN115685232A CN202211408079.2A CN202211408079A CN115685232A CN 115685232 A CN115685232 A CN 115685232A CN 202211408079 A CN202211408079 A CN 202211408079A CN 115685232 A CN115685232 A CN 115685232A
- Authority
- CN
- China
- Prior art keywords
- target
- calibration
- scene
- determining
- coordinate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The application provides a positioning method, a positioning device, a server and a storage medium of a self-guiding vehicle, wherein the positioning method of the self-guiding vehicle comprises the following steps: acquiring target point cloud data of a plurality of target calibration rods in a current visual angle by adopting a laser radar, wherein the target point cloud data comprises a first coordinate and a reflection intensity range of points on the target calibration rods, and the first coordinate is a coordinate under a laser radar coordinate system; aiming at a target calibration rod, determining a target distance between the target calibration rod and a self-guided vehicle according to a first coordinate, and determining a target scene coordinate of the target calibration rod in a preset scene according to a reflection intensity range, wherein a plurality of calibration rods are arranged in the preset scene, the calibration rods have corresponding scene coordinates, and the reflection intensity ranges of the calibration rods correspond to the scene coordinates of the calibration rods one to one; and determining the coordinates of the self-guiding vehicle in a preset scene according to the target distance corresponding to the target calibration rod and the target scene coordinates. This application can realize the accurate location of homing vehicle.
Description
Technical Field
The embodiment of the application relates to the technical field of unmanned driving, in particular to a positioning method and device of a self-guiding vehicle, a server and a storage medium.
Background
An Automated Guided Vehicle (AGV) is an unmanned vehicle with autonomous navigation capabilities. In which the AGV is required to have a high precision positioning capability to ensure its normal travel.
At present, aiming at the limited driving area of the AGV, a non-artificial road sign mode, namely an instant positioning and map construction (SLAM) scheme is adopted, and matching features and map coordinate information are provided for the practical passing AGV through a pre-map construction mode, but the scheme easily generates large errors in a single-structure or excessively noisy environment, has higher performance requirements on a processor, and also has higher learning cost and debugging cost.
In view of the above, a need exists for an accurate method for positioning an AGV.
Disclosure of Invention
The application provides a positioning method and device of a self-guiding vehicle, a server and a storage medium, and aims to solve the problem of inaccurate positioning of an AGV.
In a first aspect, the present application provides a method for positioning a self-guided vehicle, where a laser radar is disposed on the self-guided vehicle, the method including: acquiring target point cloud data of a plurality of target calibration rods in a current visual angle by adopting a laser radar, wherein the target point cloud data comprises a first coordinate of a point on the target calibration rod and a reflection intensity range, and the first coordinate is a coordinate under a laser radar coordinate system; aiming at a target calibration rod, determining a target distance between the target calibration rod and a self-guided vehicle according to a first coordinate, determining a target scene coordinate of the target calibration rod in a preset scene according to a reflection intensity range, wherein a plurality of calibration rods are arranged in the preset scene, the calibration rods have corresponding scene coordinates, the reflection intensity ranges of the calibration rods correspond to the scene coordinates of the calibration rods one by one, and the self-guided vehicle moves in the preset scene; and determining the coordinates of the self-guiding vehicle in a preset scene according to the target distance corresponding to the target calibration rod and the target scene coordinates.
In one possible implementation, acquiring target point cloud data of a target calibration bar in a current view by using a laser radar includes: acquiring total point cloud data of a current visual angle by adopting a laser radar; and filtering the environmental point cloud data in the total point cloud data according to a plurality of preset reflecting intensity ranges to obtain the target point cloud data of the target calibration rod.
In one possible implementation, determining a target distance of the target calibration bar from the homing vehicle based on the first coordinates comprises: determining a second coordinate of a point on the calibration rod under a coordinate system of the fixed bearing surface according to a preset transfer matrix and the first coordinate, wherein the transfer matrix represents a transformation relation from a laser radar coordinate system to the coordinate system of the fixed bearing surface, the self-guided vehicle moves on the fixed bearing surface, and an orthographic projection of an origin of the laser radar coordinate system on the fixed bearing surface is the origin of the coordinate system of the fixed bearing surface; clustering the target point cloud data according to the second coordinates and the preset diameter of the calibration rod to obtain multiple clusters of target point clouds, wherein the width of the target point clouds belonging to one cluster is consistent with the preset diameter, and the target point clouds belonging to one cluster are point clouds of the same calibration rod; and determining the target distance between the calibration rod corresponding to the target point cloud and the self-guided vehicle according to the average value of the second coordinates of each point in the target point cloud.
In one possible implementation manner, determining target scene coordinates of the target calibration rod in a preset scene according to the reflection intensity range includes: classifying the target point cloud data according to the reflection intensity range and a plurality of preset reflection intensity ranges to obtain a plurality of categories, wherein points belonging to the same preset reflection intensity range are of the same category; determining a target code of the target calibration rod according to the category, wherein the target code comprises at least one number, and the number corresponds to the category one to one; and determining target scene coordinates of the target calibration rod in a preset scene according to the target codes, wherein the target scene coordinates correspond to the target codes one by one.
In one possible implementation, determining the target code of the target calibration bar according to the category includes: determining the type of points corresponding to the partitions belonging to the target calibration rod according to the preset partitions of the calibration rod; and determining the target code of the target calibration rod according to the category of the points corresponding to the partitions, wherein the target code is the combination of the numbers corresponding to the categories of the partitions.
In a possible implementation manner, before the total point cloud data of the current view angle is acquired by using the laser radar, the method further includes: acquiring corrected point cloud data of a fixed bearing surface by using a laser radar; determining a normal vector of a fixed bearing surface according to the corrected point cloud data; determining roll angle, pitch angle and height values transferred from a laser radar coordinate system to a fixed bearing surface coordinate system according to the normal vector; and determining a transfer matrix according to the roll angle, the pitch angle and the height value.
In one possible implementation manner, the calibration rod is vertically arranged in a preset scene, the calibration rod comprises a plurality of partitions, each partition corresponds to a reflection intensity range in a different range, the calibration rod is provided with codes associated with the reflection intensity ranges, the calibration rod and the codes are in one-to-one correspondence, and the calibration rod is partitioned in the vertical direction.
In a second aspect, the present application provides a positioning device for a self-guided vehicle, wherein a laser radar is arranged on the self-guided vehicle, comprising:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring target point cloud data of a plurality of target calibration rods in a current visual angle by adopting a laser radar, the target point cloud data comprises a first coordinate of points on the target calibration rods and a reflection intensity range, and the first coordinate is a coordinate under a laser radar coordinate system;
the first determining module is used for determining a target distance between a target calibration rod and a self-guided vehicle according to a first coordinate and determining target scene coordinates of the target calibration rod in a preset scene according to a reflection intensity range, a plurality of calibration rods are arranged in the preset scene, the calibration rods have corresponding scene coordinates, the reflection intensity range of the calibration rods corresponds to the scene coordinates of the calibration rods one by one, and the self-guided vehicle moves in the preset scene;
and the second determining module is used for determining the coordinates of the self-guiding vehicle in the preset scene according to the target distance corresponding to the target calibration rod and the target scene coordinates.
In a third aspect, the present application provides a server, comprising: at least one processor and memory;
the memory stores computer-executable instructions;
the at least one processor executes the computer-executable instructions stored by the memory to cause the at least one processor to perform the method of locating an autonomous vehicle as described above in the first aspect.
In a fourth aspect, the present application provides a computer-readable storage medium, in which a computer executed instruction is stored, and when the processor executes the computer executed instruction, the method for locating a homing vehicle as described in the first aspect above is implemented.
In a fifth aspect, the present application provides a computer program product comprising a computer program which, when executed by a processor, implements the method of locating a self-guided vehicle as described in the first aspect.
The application provides a method, a device, a server and a storage medium for positioning a self-guided vehicle, wherein target point cloud data of a plurality of target calibration rods in a current visual angle are obtained by adopting a laser radar, a reflection intensity range for identifying the unique identity of the calibration rods is arranged on the calibration rods, and the one-to-one correspondence relationship between the reflection intensity range and scene coordinates is preset, so that when the self-guided vehicle runs in a preset scene, the laser radar can be adopted to measure the target distance from the calibration rods to the self-guided vehicle, the laser radar is adopted to measure the scene coordinates of the reflection intensity range so as to position the calibration rods, and then the coordinates of the self-guided vehicle in the preset scene can be calculated according to the target distance and the scene coordinates, so that the self-guided vehicle can be accurately positioned.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a schematic view of an application scenario of a positioning method of a homing vehicle according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a positioning method for a homing vehicle according to an embodiment of the present disclosure;
FIG. 3 is a schematic view of a calibration rod provided in an embodiment of the present application;
FIG. 4 is a schematic view of another calibration rod provided in accordance with an embodiment of the present application;
FIG. 5 is a schematic view of yet another calibration rod provided in accordance with an embodiment of the present application;
fig. 6 is a schematic view illustrating positioning of another autonomous vehicle according to an embodiment of the present application;
fig. 7 is a schematic flowchart of another location method of an autonomous vehicle according to an embodiment of the present disclosure;
fig. 8 is a schematic structural diagram of a positioning device of an autonomous vehicle according to an embodiment of the present application;
fig. 9 is a schematic diagram of a hardware result of the server according to the embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.
At present, for the positioning of the AGV, two positioning modes of an artificial road sign and a non-artificial road sign are common. Wherein, to artifical road sign scene, can carry out the affirmation of AGV self position through the road sign characteristic that matching recognition set up in advance, the identification process can be active, for example, carry out the perception in order to obtain the positional information of preset road sign to the environment through AGV's on-vehicle sensor, also can be passive form, for example, preset road sign self has the detectability, the information of AGV that will discern is passed on for AGV again, artifical road sign scene needs the multisensor to fuse the use, it has certain requirement also to establish to AGV travelable regional road sign.
In the related technology, an AGV positioning method is that a plurality of reflectors are deployed in a driving area of the AGV, reflectors are attached to the reflectors, pairwise relative poses between the reflectors are calculated according to azimuth information of the reflectors actually detected by the AGV and are matched with a true value, a marker number and a real coordinate of the reflectors are determined, and the position of the AGV is calculated. However, the prefabricated reflector has no individual characteristic difference, the relative pose between the reflectors needs to be newly calculated according to the detected directions of the reflectors, the calculation amount in the process is heavy, and the difference of the relative pose between the reflectors needs to be considered when the reflectors are actually arranged, so that the limitation is more. According to another AGV positioning method, a plurality of reflective markers are prefabricated in a scene map, reflective pieces with different widths and numbers are attached to the markers to serve as characteristic information, the real markers are matched with the identification characteristics of the reflective markers according to AGV loading laser, and the position of the AGV is calculated.
In order to solve the above technical problem, the embodiments of the present application provide the following technical concepts for solving the problems: the characteristic that laser point clouds irradiate on different materials and return to different strength intervals and the characteristic that single-frame point clouds are in linear distribution are utilized, a calibration rod of codes which are easy to be identified and sensed by lasers is designed, the coding mode has good expansibility, for example, more reflecting materials with different reflectivity can be used or the calibration rod intervals are further subdivided to form wider coding values, more rigorous identification means is provided, and the method can be used for quickly positioning the AGV in a large-area closed area and extending to modules such as navigation, odometer optimization, sensor calibration and the like. In addition, the method and the device can achieve low cost, high precision and good real-time performance, greatly reduce the learning threshold and operation difficulty of a user, and have the potential of being popularized to the application of the industrial field. Specifically, the AGVs which are not calibrated in advance and only carry a single laser radar sensor can be globally positioned (the installation pose of the laser radar is parallel to the road surface as far as possible) only by arranging calibration rods with lower-cost codes in a limited flat area (a preset scene) in which the AGVs are to run in advance and measuring the real coordinates of each calibration rod in the preset scene in advance. The method and the device have the advantages of simple arrangement, low learning cost, low required computing resource, good real-time performance, effective guarantee of the success rate of single-frame positioning and centimeter-level high precision.
Fig. 1 is a schematic view of an application scenario of a positioning method of a homing vehicle according to an embodiment of the present application, as shown in fig. 1, including: the method comprises the steps of presetting a scene 10, setting a plurality of calibration rods (such as A1 to A8) in the preset scene 10, and driving a self-guiding vehicle AGV in the preset scene, wherein the AGV is used for positioning.
Fig. 2 is a schematic flowchart of a positioning method for a self-guiding vehicle according to an embodiment of the present disclosure, and an execution subject of the embodiment may be the self-guiding vehicle AGV in the embodiment shown in fig. 1, or may be related to other computers, and the embodiment is not particularly limited.
As shown in fig. 2, the positioning method of the self-guided vehicle specifically includes the following steps: the method comprises the following steps:
s201, acquiring target point cloud data of a plurality of target calibration rods in the current view angle by adopting a laser radar.
In the embodiment of the present application, a preset scenario for driving of the AGV is first prepared, and the preset scenario is shown in fig. 1. The predetermined scene 10 is a closed area. A plurality of calibration rods are arranged in the closed area and are uniformly arranged. The top of the AGV is provided with a laser radar.
Furthermore, the stickers with different reflectivity are selected according to the laser radar laser, the surface of the calibration rod is coated with the sticker, if the surface of the calibration rod is only coated with the sticker with one reflectivity, the reflectivity of the stickers coated by different calibration rods is different, and if the surface of the calibration rod is coated with the stickers with multiple reflectivities, the reflectivity combinations of the stickers coated by different calibration rods are different.
In addition, the calibration rods are coded according to the reflection intensity range of the reflectivity sticker coated by the calibration rods, so that the codes correspond to the reflection intensity of the reflectivity sticker, and each calibration rod has a code with a unique identifier. Further, when the calibration rod is vertically inserted into the preset scene, the scene coordinates of the calibration rod in the preset scene are predetermined, and the scene coordinates correspond to the codes of the calibration rod one to one.
The calibration rod is vertically arranged in a preset scene and comprises a plurality of partitions, each partition corresponds to a reflection intensity range in different ranges, the calibration rod is provided with codes related to the reflection intensity ranges, the calibration rod corresponds to the codes one by one, and the calibration rod is partitioned in the vertical direction. In particular, the calibration rod is equally divided, i.e. each division has the same length in the vertical direction of the calibration rod.
To sum up, in an alternative embodiment, referring to fig. 3, each calibration rod uses a sticker, and the reflectivity ranges of different calibration plates are different, for example, the reflection intensity range of the calibration rod A1 is 0 to 40, and the corresponding code is 0; the reflecting intensity of the calibration rod A2 ranges from 40 to 80, and the corresponding code is 1; the range of the reflection intensity of the calibration rod A3 is 80-120, the corresponding code is 2, the range of the reflection intensity of the calibration rod A4 is 120-160, and the code is 3; the reflecting intensity range corresponding to the calibration rod A5 is 160-200, and the code is 4; the reflecting intensity range corresponding to the calibration rod A6 is 200-240, and the code is 5; the range of the reflective intensity corresponding to the calibration rod A7 is 240 to 280, and the code is 6; the range of reflective intensity for calibration bar A8 is 280 to 320, and the code is 7. This method requires a high recognition accuracy of the reflection rate by the laser radar.
In an alternative embodiment, the calibration rod is preferably made of wood (with a reflection intensity of 30 to 50, for example), and two types of reflective stickers are selected. The calibration rod is wrapped with one or two kinds of stickers, wherein the reflection intensity of one kind of sticker with medium reflectivity is 140-180, and the reflection intensity of another kind of sticker with high reflectivity is 215-255. Referring to fig. 4, the number corresponding to the uncoated sticker is 0, the number corresponding to the reflectivity sticker in the coating is 1, and the number corresponding to the high reflectivity sticker in the coating is 2. Then, the calibration rod is divided into two subareas in the vertical direction, the paster is coated on different subareas, and the calibration rod is coded according to the reflectivity paster coated on the subareas, so that each calibration rod has a code with a unique identifier. Specifically, the rod body of the calibration rod corresponds to the codes from top to bottom from high to low, the corresponding number of the area without the sticker is 0, the corresponding number of the sticker with the medium reflectivity is 1, and the corresponding number of the sticker with the high reflectivity is 2. In fig. 4, the calibration rod A1 is not covered by any sticker, and the calibration rod A1 corresponds to the reflection intensity of the material itself, and the corresponding code is 00. The upper section of the calibration rod A2 is not covered with any sticker and corresponds to the reflection intensity of the material of the calibration rod A, and the lower section is covered with the middle-reflectivity sticker and corresponds to the reflection intensity of the middle-reflectivity sticker, so that the corresponding code is 01. In the same way, it can be concluded that the code for calibration bar A3 is 10, the code for calibration bar A4 is 11, the code for calibration bar A5 is 02, the code for calibration bar A6 is 20, the code for calibration bar A7 is 12 and the code for calibration bar A8 is 21.
In fig. 5, the code of the calibration bar A1 is 000, the code of the calibration bar A2 is 010, the code of the calibration bar A3 is 100, the code of the calibration bar A4 is 001, the code of the calibration bar A5 is 102, the code of the calibration bar A6 is 021, the code of the calibration bar A7 is 210, and the code of the calibration bar A8 is 220.
Furthermore, the quantity of the reflectivity stickers and the quantity of the division areas of the calibration rods can be selected according to the demand of the calibration rods in the actual scene and the identification precision of the laser radar, and the quantity is not limited.
In the embodiment of the application, the calibration rod is preferably cylindrical, so that the identification of the laser radar can be more convenient.
In summary, the calibration rod corresponds to the corresponding reflection intensity range (combination mode) one to one, the reflection intensity range corresponds to the number one to one, the combination mode of the reflection intensity range corresponds to the code one to one, and the code corresponds to the scene coordinate of the calibration rod in the preset scene one to one.
The target point cloud data comprises a first coordinate of a point on the target calibration rod and a reflection intensity range, and the first coordinate is a coordinate under a laser radar coordinate system.
Specifically, the laser radar emits laser at the current view angle to obtain a point cloud consisting of a plurality of points, and each point represents a first coordinate and a reflection intensity range of a point on the target calibration rod at the current view angle.
S202, aiming at the target calibration rod, determining the target distance between the target calibration rod and the self-guided vehicle according to the first coordinate, and determining the target scene coordinate of the target calibration rod in a preset scene according to the reflection intensity range.
The self-guiding vehicle is characterized in that a plurality of calibration rods are arranged in a preset scene, the calibration rods have corresponding scene coordinates, the reflection intensity ranges of the calibration rods correspond to the scene coordinates of the calibration rods one to one, and the self-guiding vehicle moves in the preset scene. Specifically, if the calibration rod is not partitioned, the reflection intensity ranges of the calibration rod correspond to the scene coordinates of the calibration rod one to one, and if the calibration rod is partitioned, the combination of the reflection intensity ranges of the calibration rod corresponds to the scene coordinates of the calibration rod one to one.
In the embodiment of the application, the target distance and the target scene coordinates may be determined for each target calibration bar in the current view. Or selecting three target calibration rods closer to the self-guided vehicle from the current view angle, and determining the respective target distances and target scene coordinates of the three target calibration rods.
Further, the first coordinate is a coordinate in a lidar coordinate system, wherein an origin of the lidar coordinate system is a lidar which is disposed on the self-guided vehicle, and therefore a target distance from the target calibration rod to the self-guided vehicle can be determined according to the first coordinate.
In addition, the combination of the reflection intensity ranges corresponds to the target scene coordinates one by one, so the target scene coordinates of the target calibration rod can be determined according to the reflection intensity ranges.
For example, referring to fig. 1, with the calibration rod A6 as the coordinate origin in the preset scene coordinate system, the scene coordinates of the calibration rod A1 are (-1, 2), the scene coordinates of the calibration rod A2 are (0, 2), the scene coordinates of the calibration rod A3 are (1, 2), the scene coordinates of the calibration rod A4 are (1, 1), the scene coordinates of the calibration rod A5 are (1, 0), the scene coordinates of the calibration rod A6 are (0, 0), the scene coordinates of the calibration rod A7 are (-1, 0), the scene coordinates of the calibration rod A8 are (-1, 1), and the scene coordinates of the calibration rod A8 are (-1, 1).
Further, referring to fig. 1, the target calibration levers are a calibration lever A4, a calibration lever A5, and a calibration lever A6. If the calibration method shown in fig. 4 is adopted in the present application, the combination of the reflection intensity ranges of the identified calibration rod A4 is {140 to 180, 215 to 255}, and the corresponding target scene coordinates are (1, 1). The combination of the reflection intensity ranges of the calibration rod A5 is identified as {30 to 50, 215 to 255}, and the corresponding target scene coordinates are (1, 0). The combination of the reflection intensity ranges of the calibration rod A6 is identified as {215 to 255, 30 to 50}, and the corresponding target scene coordinates are (0, 0).
And S203, determining the coordinates of the self-guiding vehicle in a preset scene according to the target distance corresponding to the target calibration rod and the target scene coordinates.
The calculation method comprises the steps of determining a target scene coordinate of a target calibration rod as an origin, determining a target distance as a radius circle, determining an intersection point between every two circles, and determining a coordinate of a central point of a plurality of intersection points as a coordinate of the self-guiding vehicle in a preset scene.
Specifically, referring to fig. 6, if the target scene coordinates of the target calibration bar A4 are (x 1, y 1), the target distance is r1. The target scene coordinates of the target calibration bar A5 are (x 2, y 2), and the target distance is r2. The target scene coordinates of the target calibration bar A6 are (x 3, y 3), and the target distance is r3. And the intersection point obtained by intersecting every two circles is the real coordinate possibly corresponding to the current laser radar in the preset scene. Two circles are selected as C1 and C2 respectively, and when the distance between the circle centers of the C1 and C2 is larger than the sum of the radiuses of the two circles, the midpoint of the intersection point of a line segment formed by the two circle centers on the boundary of the two circles is taken as a probability coordinate point (at the moment, 1 probability coordinate point exists). When the circle center distance of C1 and C2 is equal to the sum of the two circle radiuses, a unique intersection point is obtained as a probability coordinate point (in this case, 1 probability coordinate point is available). When the distance between the centers of the C1 and C2 is smaller than the sum of the radiuses of the two circles, two intersection points are obtained as probability coordinate points (2 probability coordinate points are available at this time). Wherein, the intersection point of the two circles can be directly calculated and obtained by a triangulation method. And setting the probability coordinate point set calculated by C1 and C2 as CROSS _1, the probability coordinate point set calculated by C1 and C3 as CROSS _2, the probability coordinate point set calculated by C2 and C3 as CROSS _3, respectively taking one point from the CROSS _1, the CROSS _2 and the CROSS _3, calculating the central point of the three points, and making the sum of the distances from the central point to the three points minimum, namely the real coordinate point obtained by positioning. As shown in fig. 6, the coordinates of the mean point n in the center of the three intersection points (m 1, m2, and m 3) are the coordinates of the homing vehicle in the preset scene.
In addition, the coordinates of the homing vehicle in the preset scene can be determined by other means, such as solving an equation system, which is not limited herein.
This application is through adopting laser radar to acquire the target point cloud data of a plurality of target calibration poles in the current visual angle, through having the reflection intensity scope of the only identity of sign calibration pole on making the calibration pole, and predetermine the one-to-one relation of reflection intensity scope and scene coordinate, then the self-guided vehicle is when predetermineeing the scene and travel, can adopt laser radar to measure the target distance of calibration pole to the self-guided vehicle, and adopt laser radar survey reflection intensity scope with the scene coordinate of positioning the calibration pole, and then can calculate the coordinate that obtains the self-guided vehicle in predetermineeing the scene according to target distance and scene coordinate, realize the accurate positioning of self-guided vehicle.
Referring to fig. 7, a schematic flow chart of another positioning method for an autonomous vehicle provided in the embodiment of the present application is shown, which specifically includes the following steps:
and S701, acquiring corrected point cloud data of a fixed bearing surface by using a laser radar.
Here, S501 to S504 may be performed only once during the self-guiding vehicle traveling, or may be performed once at intervals.
Specifically, when the AGV is initially placed on a fixed bearing surface in a preset scene, a point cloud placed on the fixed bearing surface by laser is first roughly extracted through experience to obtain corrected point cloud data. In the present embodiment, the fixed bearing surface bears against a surface of the self-guided vehicle, such as the ground. The correction of the point cloud data includes: and fixing the coordinates of the point on the bearing surface under the laser radar coordinate system.
S702, determining a normal vector of the fixed bearing surface according to the corrected point cloud data.
The correction point cloud data is subjected to RANSAC (Random Sample Consensus) sampling to obtain a sampling point cloud, and then the sampling point cloud is subjected to least square to obtain a normal vector fitting a fixed bearing surface. The RANSAC sampling inner group points are defined to be not more than a preset distance (such as 5 cm) away from a fitting fixed bearing surface, an iteration sampling frequency upper limit of a preset frequency (such as 1 ten thousand) is set, when the number of the inner group points is equal to the number of the fixed bearing surface points, iteration can be stopped in advance and a current normal vector can be recorded, and when the maximum iteration frequency is reached, a primary normal vector with the highest proportion of the number of the inner group points is used as the normal vector of the fixed bearing surface.
And S703, determining roll angle, pitch angle and height values transferred from the laser radar coordinate system to the fixed bearing surface coordinate system according to the normal vector.
Specifically, after the roll angle and the pitch angle of the left system of the laser radar are determined to be adjusted, when the x-y axis of the coordinate system of the laser radar is parallel to the fixed bearing surface, the projection of the center of the laser radar on the fixed bearing surface is taken as the origin of the coordinate system of the fixed bearing surface, and the x-y axis parallel to the fixed bearing surface is taken as the x axis and the y axis of the coordinate system of the fixed bearing surface to establish the coordinate system of the fixed bearing surface.
And S704, determining a transfer matrix according to the roll angle, the pitch angle and the height value.
And further, calculating roll angle, pitch angle and height values transferred from the laser radar coordinate system to the fixed bearing surface coordinate system according to normal vectors (0, 1) of the fixed bearing surface coordinate system under the fixed bearing surface coordinate system, and generating a transfer matrix.
S705, total point cloud data of the current view angle are obtained by adopting a laser radar.
The total point cloud data obtained by the laser radar comprises: target point cloud data of the target calibration bar at the current view angle also includes point cloud data of objects in the environment at the current view angle.
S706, according to the plurality of preset reflecting intensity ranges, filtering out environment point cloud data in the total point cloud data to obtain target point cloud data of the target calibration rod.
And the reflection intensity of the target point cloud data is in a plurality of preset reflection intensity ranges.
Illustratively, reference is made to the above and fig. 4, wherein one predetermined reflective intensity range is 30 to 50, one predetermined reflective intensity range is 140 to 180, and another predetermined reflective intensity range is 215 to 255. The resulting reflectance intensity of the target point cloud data is in these ranges.
And S707, determining a second coordinate of the point on the calibration rod under the coordinate system of the fixed bearing surface according to the preset transfer matrix and the first coordinate.
The transfer matrix represents a transformation relation from a laser radar coordinate system to a fixed bearing surface coordinate system, the self-guiding vehicle moves on the fixed bearing surface, and the orthographic projection of the origin of the laser radar coordinate system on the fixed bearing surface is the origin of the fixed bearing surface coordinate system.
Specifically, if the first coordinate is (u, v), the transition matrix is T. The second coordinate (i, j) = (u, v) T.
And S708, clustering the target point cloud data according to the second coordinate and the preset diameter of the calibration rod to obtain a plurality of clusters of target point clouds.
The width of the target point cloud belonging to one cluster is consistent with the preset diameter, and the target point cloud belonging to one cluster is the point cloud of the same calibration rod.
Specifically, DBSCAN (Density-Based Spatial Clustering of Applications with Noise, density-Based Clustering algorithm) Clustering is performed on the point cloud converted in S707 on an x-y plane under a fixed bearing surface coordinate system, the diameter of the cross section of the calibration rod is used as the field radius of Clustering, and then target point cloud data can be clustered according to each calibration rod to obtain a multi-cluster target point cloud.
And S709, determining a target distance between the calibration rod corresponding to the target point cloud and the self-guiding vehicle according to the average value of the second coordinates of each point in the target point cloud.
Specifically, for each cluster of target point clouds, an average value is obtained for x and y coordinates in a second coordinate of each point, and the average value is used as a projection of a corresponding target calibration rod on an x-y plane in a coordinate system of a fixed bearing surface, so that a target distance between the calibration rod corresponding to the target point cloud and the self-guided vehicle is obtained.
And S710, classifying the target point cloud data according to the reflection intensity range and a plurality of preset reflection intensity ranges to obtain a plurality of categories.
The target point cloud data is classified according to the reflection intensity range of the points in the target point cloud data and a plurality of preset reflection intensity ranges to obtain a plurality of categories, and the points belonging to the same preset reflection intensity range are of the same category. For example, the points belonging to the preset reflection intensity range 140 to 180 are of the category S1, and the points belonging to the preset reflection intensity range 215 to 255 are of the category S2.
And S711, determining the target code of the target calibration rod according to the category.
The target code comprises at least one number, and the number corresponds to the category one to one.
Further, determining a target code for the target calibration bar according to the category, comprising: determining the type of points corresponding to the partitions belonging to the target calibration rod according to the preset partitions of the calibration rod; determining a target code of the target calibration bar according to the category of the points belonging to the corresponding partition, the target code being a combination of numbers corresponding to the category of the partition,
specifically, according to a preset partition mode of the calibration rod, N equal partition is performed on the target point cloud of the target calibration rod, where N is 2 in fig. 4, and N is 3 in fig. 5. If the point clouds of each partition belong to the same category S1 or S2, the number corresponding to the interval is 1 or 2, and if the number of the points of the point clouds in the partition belonging to the same category (S1 or S2) is smaller than the threshold value, the number corresponding to the partition is 0. And combining the determined numbers according to the sequence of the target calibration rod from top to bottom to obtain the target code.
The specific implementation process of this step can refer to the description of the pre-coding of the calibration rod, which is not described herein again.
And S712, determining the target scene coordinates of the target calibration rod in the preset scene according to the target code.
And the target scene coordinates correspond to the target codes one by one.
And determining the target scene coordinates corresponding to the target codes in the preset corresponding relation according to the target codes.
And S713, determining the coordinates of the self-guiding vehicle in a preset scene according to the target distance corresponding to the target calibration rod and the target scene coordinates.
The specific implementation process of this step refers to S703, which is not described herein again.
To sum up, the calibration rod used in the application carries the codes which can be decoded by the laser point cloud, and how to arrange each road sign is not needed to spend a large amount of time to ensure that the position and the orientation of every two road signs are obviously different. Compared with the prior art that the design difficulty is greatly improved when the scene is large, the method and the device can realize quick decoding and pairing through the perceived calibration lever by uniformly arranging the roadside, greatly reduce the time required for matching with a true value, increase the success rate of identification of the calibration lever, and be still usable when the preset scene area is large. In addition, this application does not have the restraint to calibration rod orientation information, only need guarantee a certain amount and pencil the laser projection on the calibration rod can, reduce the requirement of the horizontal, longitudinal resolution of laser, very big increase self-guided vehicle's location success rate.
Fig. 8 is a schematic structural diagram of a positioning device of an autonomous vehicle according to an embodiment of the present application, where as shown in fig. 8, the device includes: an obtaining module 81, a first determining module 82 and a second determining module 83, wherein:
the acquisition module 81 is configured to acquire target point cloud data of a plurality of target calibration rods at a current view angle by using a laser radar, where the target point cloud data includes a first coordinate of an upper point of the target calibration rod and a reflection intensity range, and the first coordinate is a coordinate under a laser radar coordinate system.
The first determining module 82 is configured to determine, for a target calibration bar, a target distance between the target calibration bar and the self-guided vehicle according to the first coordinate, and determine, according to a reflection intensity range, target scene coordinates of the target calibration bar in a preset scene, where a plurality of calibration bars are set in the preset scene, where the calibration bars have corresponding scene coordinates, the reflection intensity ranges of the calibration bars correspond to the scene coordinates of the calibration bars one to one, and the self-guided vehicle moves in the preset scene;
and a second determining module 83, configured to determine coordinates of the homing vehicle in a preset scene according to the target distance and the target scene coordinates corresponding to the target calibration rod.
In an optional embodiment of the present application, the obtaining module 81 is specifically configured to: acquiring total point cloud data of a current visual angle by adopting a laser radar; and filtering out the environmental point cloud data in the total point cloud data according to a plurality of preset reflecting intensity ranges to obtain the target point cloud data of the target calibration rod.
In an optional embodiment of the present application, the first determining module 82 is specifically configured to: determining a second coordinate of a point on the calibration rod under a coordinate system of the fixed bearing surface according to a preset transfer matrix and the first coordinate, wherein the transfer matrix represents a transformation relation from a laser radar coordinate system to the coordinate system of the fixed bearing surface, the self-guided vehicle moves on the fixed bearing surface, and the orthographic projection of the origin of the laser radar coordinate system on the fixed bearing surface is the origin of the coordinate system of the fixed bearing surface; clustering the target point cloud data according to the second coordinate and the preset diameter of the calibration rod to obtain multiple clusters of target point clouds, wherein the width of the target point clouds belonging to one cluster is consistent with the preset diameter, and the target point clouds belonging to one cluster are point clouds of the same calibration rod; and determining the target distance between the calibration rod corresponding to the target point cloud and the self-guided vehicle according to the average value of the second coordinates of each point in the target point cloud.
In an optional embodiment of the present application, the first determining module 82 is specifically configured to: classifying the target point cloud data according to the reflection intensity range and a plurality of preset reflection intensity ranges to obtain a plurality of categories, wherein points belonging to the same preset reflection intensity range are of the same category; determining a target code of the target calibration rod according to the category, wherein the target code comprises at least one number, and the number corresponds to the category one to one; and determining target scene coordinates of the target calibration rod in a preset scene according to the target codes, wherein the target scene coordinates correspond to the target codes one by one.
In an optional embodiment of the present application, when determining the target calibration bar according to the category, the first determining module 82 is specifically configured to: determining the type of points corresponding to the partitions belonging to the target calibration rod according to the preset partitions of the calibration rod; and determining the target code of the target calibration rod according to the category of the points corresponding to the partitions, wherein the target code is the combination of the numbers corresponding to the categories of the partitions.
In an optional embodiment of the present application, the obtaining module 81 is configured to obtain corrected point cloud data of a fixed bearing surface by using a laser radar; the system also comprises a transfer matrix determining module (not shown) for determining a normal vector of the fixed bearing surface according to the corrected point cloud data; determining roll angle, pitch angle and height values transferred from a laser radar coordinate system to a fixed bearing surface coordinate system according to the normal vector; determining a transfer matrix according to the roll angle, the pitch angle and the height value
In an optional embodiment of the present application, the calibration rod is vertically disposed in a preset scene, the calibration rod includes a plurality of partitions, each partition corresponds to a reflection intensity range in a different range, the calibration rod has a code associated with the reflection intensity range, the calibration rod and the code correspond to each other one by one, and the calibration rod is partitioned in a vertical direction.
The positioning device of the homing vehicle provided in this embodiment may be used to implement the technical solutions of the above method embodiments, and the implementation principle and technical effects are similar, which are not described herein again.
Fig. 9 is a schematic diagram of a hardware result of an electronic device according to an embodiment of the present application, and as shown in fig. 9, the electronic device includes: at least one processor 901 and memory 902.
The processor 901 is configured to store computer executable instructions.
Alternatively, the memory 902 may be separate or integrated with the processor 901.
When the memory 902 is provided separately, the controller further includes a bus 903 for connecting the memory 902 and the processor 901.
The embodiment of the invention also provides a computer-readable storage medium, wherein a computer executing instruction is stored in the computer-readable storage medium, and when the processor executes the computer executing instruction, the positioning method of the self-guiding vehicle is realized.
Embodiments of the present application also provide a computer program product, including a computer program, which when executed by a processor, implements the localization method of the homing vehicle as above.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the above-described modules is only one logical functional division, and other divisions may be realized in practice, for example, a plurality of modules may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to implement the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each module may exist alone physically, or two or more modules are integrated into one unit. The unit formed by the modules can be realized in a hardware mode, and can also be realized in a mode of hardware and a software functional unit.
The integrated module implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor to execute some steps of the methods according to the embodiments of the present application.
It should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of hardware and software modules.
The memory may comprise a high speed RAM memory, and may further comprise a non-volatile storage NVM, such as at least one magnetic disk memory, and may also be a usb disk, a removable hard disk, a read-only memory, a magnetic or optical disk, or the like.
The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present application are not limited to only one bus or one type of bus.
The storage medium may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the storage medium may reside as discrete components in an electronic device or host device.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
To illustrate the technical solution of the present application, not to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.
Claims (11)
1. A positioning method of a self-guided vehicle is characterized in that a laser radar is arranged on the self-guided vehicle, and comprises the following steps:
acquiring target point cloud data of a plurality of target calibration rods in a current visual angle by adopting a laser radar, wherein the target point cloud data comprises a first coordinate of an upper point of each target calibration rod and a reflection intensity range, and the first coordinate is a coordinate under a laser radar coordinate system;
for a target calibration rod, determining a target distance between the target calibration rod and the self-guided vehicle according to the first coordinate, and determining a target scene coordinate of the target calibration rod in a preset scene according to the reflection intensity range, wherein a plurality of calibration rods are arranged in the preset scene, the calibration rods have corresponding scene coordinates, the reflection intensity range of the calibration rods corresponds to the scene coordinate of the calibration rods one by one, and the self-guided vehicle moves in the preset scene;
and determining the coordinates of the self-guiding vehicle in a preset scene according to the target distance corresponding to the target calibration rod and the target scene coordinates.
2. The method of claim 1, wherein the acquiring target point cloud data of a target calibration bar in a current view using lidar comprises:
acquiring total point cloud data of a current visual angle by adopting a laser radar;
and filtering out the environmental point cloud data in the total point cloud data according to a plurality of preset reflecting intensity ranges to obtain the target point cloud data of the target calibration rod.
3. The method of claim 2, wherein determining the target distance of the target calibration bar from the homing vehicle based on the first coordinates comprises:
determining a second coordinate of a point on the target calibration rod under a coordinate system of a fixed bearing surface according to a preset transfer matrix and the first coordinate, wherein the transfer matrix represents a transformation relation from the laser radar coordinate system to the coordinate system of the fixed bearing surface, the self-guided vehicle moves on the fixed bearing surface, and an orthographic projection of an origin of the laser radar coordinate system on the fixed bearing surface is the origin of the coordinate system of the fixed bearing surface;
clustering the target point cloud data according to the second coordinates and the preset diameter of the calibration rod to obtain multiple clusters of target point clouds, wherein the width of the target point clouds belonging to one cluster is consistent with the preset diameter, and the target point clouds belonging to one cluster are point clouds of the same calibration rod;
and determining a target calibration rod corresponding to the target point cloud and a target distance of the self-guiding vehicle according to the average value of the second coordinates of each point in the target point cloud.
4. The method according to claim 2, wherein the determining the target scene coordinates of the target calibration stick in a preset scene according to the reflection intensity range comprises:
classifying the target point cloud data according to the reflection intensity range and a plurality of preset reflection intensity ranges to obtain a plurality of categories, wherein points belonging to the same preset reflection intensity range are of the same category;
determining a target code of the target calibration rod according to the category, wherein the target code comprises at least one number, and the number corresponds to the category one to one;
and determining target scene coordinates of the target calibration rod in a preset scene according to the target codes, wherein the target scene coordinates correspond to the target codes one by one.
5. The method of claim 4, wherein determining the target code for the target calibration bar according to the category comprises:
determining the type of points corresponding to the partitions belonging to the target calibration rod according to the preset partitions of the calibration rod;
and determining a target code of the target calibration rod according to the category of the points corresponding to the partitions, wherein the target code is a combination of numbers corresponding to the categories of the partitions.
6. The method as claimed in any one of claims 3 to 5, wherein before the acquiring the total point cloud data of the current view angle by using lidar, the method further comprises:
acquiring corrected point cloud data of a fixed bearing surface by using the laser radar;
determining a normal vector of the fixed bearing surface according to the corrected point cloud data;
determining roll angle, pitch angle and height values transferred from the laser radar coordinate system to the fixed bearing surface coordinate system according to the normal vector;
and determining the transfer matrix according to the roll angle, the pitch angle and the height value.
7. The method according to any one of claims 1 to 5, wherein a calibration bar is vertically disposed in the preset scene, the calibration bar includes a plurality of sections, each section corresponds to a different range of reflective intensity range, the calibration bar has a code associated with the reflective intensity range, the calibration bar and the code correspond one to one, and the calibration bar is divided in a vertical direction.
8. A positioning device for a self-guided vehicle, wherein a lidar is disposed on the self-guided vehicle, the positioning device comprising:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring target point cloud data of a plurality of target calibration rods in a current visual angle by adopting a laser radar, the target point cloud data comprises a first coordinate of a point on the target calibration rod and a reflection intensity range, and the first coordinate is a coordinate under a laser radar coordinate system;
the first determining module is used for determining a target distance between a target calibration rod and the self-guided vehicle according to the first coordinate and determining target scene coordinates of the target calibration rod in a preset scene according to the reflection intensity range, wherein a plurality of calibration rods are arranged in the preset scene, the calibration rods have corresponding scene coordinates, the reflection intensity range of the calibration rods corresponds to the scene coordinates of the calibration rods one by one, and the self-guided vehicle moves in the preset scene;
and the second determination module is used for determining the coordinates of the self-guiding vehicle in a preset scene according to the target distance corresponding to the target calibration rod and the target scene coordinates.
9. An electronic device, comprising: at least one processor and a memory;
the memory stores computer-executable instructions;
the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the method of locating an autonomous vehicle as recited in any of claims 1 to 7.
10. A computer-readable storage medium having stored thereon a computer executable instruction which, when executed by a processor, implements the method of locating an autonomous vehicle as recited in any one of claims 1 to 7.
11. A computer program product, characterized in that it comprises a computer program which, when being executed by a processor, carries out a method for locating a homing vehicle according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211408079.2A CN115685232A (en) | 2022-11-10 | 2022-11-10 | Positioning method and device of self-guiding vehicle, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211408079.2A CN115685232A (en) | 2022-11-10 | 2022-11-10 | Positioning method and device of self-guiding vehicle, server and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115685232A true CN115685232A (en) | 2023-02-03 |
Family
ID=85051225
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211408079.2A Pending CN115685232A (en) | 2022-11-10 | 2022-11-10 | Positioning method and device of self-guiding vehicle, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115685232A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024174580A1 (en) * | 2023-02-21 | 2024-08-29 | 广西柳工机械股份有限公司 | Vehicle pose determination method and apparatus, device, and storage medium |
-
2022
- 2022-11-10 CN CN202211408079.2A patent/CN115685232A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024174580A1 (en) * | 2023-02-21 | 2024-08-29 | 广西柳工机械股份有限公司 | Vehicle pose determination method and apparatus, device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109143207B (en) | Laser radar internal reference precision verification method, device, equipment and medium | |
| CN110082747B (en) | Method for increasing reliability of determining vehicle position based on multiple detection points | |
| CN109270545B (en) | Positioning true value verification method, device, equipment and storage medium | |
| US11500083B2 (en) | Method for determining the position of a vehicle | |
| US9625908B2 (en) | Methods and systems for mobile-agent navigation | |
| CN111060946B (en) | Method and apparatus for estimating position | |
| CN108734780B (en) | Method, device and equipment for generating map | |
| CN110501036A (en) | The calibration inspection method and device of sensor parameters | |
| CN112363158A (en) | Pose estimation method for robot, and computer storage medium | |
| EP3828587A1 (en) | Method for determining the position of a vehicle | |
| CN113822944B (en) | External parameter calibration method and device, electronic equipment and storage medium | |
| US11327155B2 (en) | Radar sensor misalignment detection for a vehicle | |
| CN113984044A (en) | Vehicle pose acquisition method and device based on vehicle-mounted multi-perception fusion | |
| CN115494533A (en) | Vehicle positioning method, device, storage medium and positioning system | |
| CN111856499A (en) | Map construction method and device based on laser radar | |
| CN115685232A (en) | Positioning method and device of self-guiding vehicle, server and storage medium | |
| CN110109165B (en) | Method and device for detecting abnormal points in driving track | |
| CN113448340B (en) | Unmanned aerial vehicle path planning method and device, unmanned aerial vehicle and storage medium | |
| CN112154355B (en) | High-precision map positioning method, system, platform and computer readable storage medium | |
| CN112629547A (en) | Method and apparatus for creating positioning map | |
| CN114127511A (en) | Method and communication system for assisting at least partially automatic vehicle control | |
| KR20210010309A (en) | Apparatus and method for generating three dimensional map using aerial images | |
| CN117572395A (en) | External parameter calibration method, device, equipment and medium of vehicle-mounted laser radar | |
| WO2021112078A1 (en) | Information processing device, control method, program, and storage medium | |
| CN113203424A (en) | Multi-sensor data fusion method and device and related equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |