CN115079202A - Laser radar mapping method and device, electronic equipment and storage medium - Google Patents
Laser radar mapping method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115079202A CN115079202A CN202210748090.7A CN202210748090A CN115079202A CN 115079202 A CN115079202 A CN 115079202A CN 202210748090 A CN202210748090 A CN 202210748090A CN 115079202 A CN115079202 A CN 115079202A
- Authority
- CN
- China
- Prior art keywords
- frame
- loop
- point cloud
- cloud data
- matching
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000013507 mapping Methods 0.000 title claims abstract description 38
- 238000003860 storage Methods 0.000 title claims abstract description 23
- 238000005457 optimization Methods 0.000 claims abstract description 74
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 29
- 239000011159 matrix material Substances 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 abstract description 7
- 230000000875 corresponding effect Effects 0.000 description 95
- 230000008569 process Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 12
- 238000004590 computer program Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Networks & Wireless Communication (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Electromagnetism (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The application discloses a laser radar mapping method, a device, an electronic device and a storage medium, wherein the method comprises the following steps: under the condition that current frame point cloud data of a laser radar meets a preset loop search condition, performing loop search based on the current frame point cloud data to obtain a loop search result, wherein the loop search result comprises a plurality of loop frame pairs; performing point cloud matching on the corresponding point cloud data according to each loop frame to obtain a point cloud matching result, wherein the point cloud matching result comprises a matching pose confidence coefficient; determining a noise value corresponding to each loop frame pair according to the corresponding matching pose confidence coefficient of each loop frame pair; and optimizing the pose of each frame of point cloud data by using a preset map optimization algorithm based on the noise value corresponding to each loop frame pair so as to obtain a laser point cloud map according to an optimization result. According to the laser radar mapping method, the corresponding noise values are respectively determined for each loop frame pair, and the optimization efficiency and the optimization effect of laser mapping are improved.
Description
Technical Field
The present application relates to the field of map construction technologies, and in particular, to a method and an apparatus for laser radar map construction, an electronic device, and a storage medium.
Background
In the current map building scheme of laser SLAM (Simultaneous Localization And Mapping), a loop strategy is indispensable, And in the loop process, a closed loop point matched with the current frame is mainly searched through the current frame, the relative pose between the current frame And the closed loop point is calculated And is added into the rear-end optimization as loop constraint.
In the actual operation process, if the matching result of the loop is poor, the confidence coefficient of the corresponding loop frame pair is low, and if the matching result of the loop is good, the confidence coefficient of the corresponding loop frame pair is high.
Disclosure of Invention
The embodiment of the application provides a laser radar mapping method and device, electronic equipment and a storage medium, so that the optimization efficiency and the optimization effect of laser mapping are improved.
The embodiment of the application adopts the following technical scheme:
in a first aspect, an embodiment of the present application provides a lidar mapping method, where the method includes:
performing loop search based on current frame point cloud data of a laser radar under the condition that the current frame point cloud data meet a preset loop search condition to obtain a loop search result, wherein the loop search result comprises a plurality of loop frame pairs;
performing point cloud matching on the corresponding point cloud data according to each loop frame to obtain a point cloud matching result, wherein the point cloud matching result comprises a matching pose confidence coefficient;
determining a noise value corresponding to each loop frame pair according to the corresponding matching pose confidence coefficient of each loop frame pair;
and optimizing the pose of each frame of point cloud data by using a preset graph optimization algorithm based on the corresponding noise value of each loop frame pair so as to obtain a laser point cloud map according to an optimization result.
Optionally, when the current frame point cloud data of the laser radar meets a preset loopback search condition, performing loopback search based on the current frame point cloud data to obtain a loopback search result, where the method further includes:
determining whether the frame number corresponding to the current frame point cloud data reaches a preset frame number threshold value;
if yes, determining that the current frame point cloud data meets the preset loopback searching condition;
otherwise, determining that the current frame point cloud data does not meet the preset loopback search condition.
Optionally, when the current frame point cloud data of the laser radar meets a preset loopback search condition, performing loopback search based on the current frame point cloud data to obtain a loopback search result includes:
determining a candidate frame corresponding to the current frame according to the frame number corresponding to the current frame point cloud data;
determining the distance between the current frame and the candidate frame according to the current frame point cloud data and the candidate frame point cloud data;
and determining the loopback frame pair according to the distance between the current frame and the candidate frame.
Optionally, the determining the loopback frame pair according to the distance between the current frame and the candidate frame includes:
comparing the distance between the current frame and the candidate frame with a preset distance threshold;
if the distance between the current frame and the candidate frame is smaller than the preset distance threshold, determining that the candidate frame and the current frame form the loopback frame pair;
otherwise, determining that the candidate frame and the current frame do not form the loopback frame pair.
Optionally, the determining, according to the confidence of the matching pose corresponding to each loopback frame pair, a noise value corresponding to each loopback frame pair includes:
and determining the noise value corresponding to each loop frame pair by using a preset negative correlation strategy according to the confidence coefficient of the matching pose corresponding to each loop frame pair.
Optionally, after determining a noise value corresponding to each loop frame pair according to the confidence of the matching pose corresponding to each loop frame pair, the method further includes:
and correspondingly storing the matching pose and the matching pose confidence coefficient of each loop frame pair and the key frame identification of each loop frame pair and the noise value corresponding to each loop frame pair into a loop container.
Optionally, the optimizing the pose of each frame of point cloud data by using a preset map optimization algorithm based on the noise value corresponding to each loopback frame pair to obtain the laser point cloud map according to the optimization result includes:
adjusting the diagonal value of an information matrix in the preset graph optimization algorithm according to the noise value corresponding to each loop frame pair;
constructing loop constraints based on the adjusted information matrix, and optimizing the pose of each frame of point cloud data by using the loop constraints to obtain the optimized pose of each frame of point cloud data;
and splicing the point cloud data of each frame according to the optimized pose of the point cloud data of each frame to obtain the laser point cloud map.
In a second aspect, an embodiment of the present application further provides a lidar mapping apparatus, where the apparatus includes:
the system comprises a loop search unit, a loop search unit and a processing unit, wherein the loop search unit is used for performing loop search based on current frame point cloud data of a laser radar under the condition that the current frame point cloud data meets a preset loop search condition to obtain a loop search result, and the loop search result comprises a plurality of loop frame pairs;
the point cloud matching unit is used for carrying out point cloud matching on the corresponding point cloud data according to each loop frame to obtain a point cloud matching result, and the point cloud matching result comprises a matching pose confidence coefficient;
the first determining unit is used for determining a noise value corresponding to each loop frame pair according to the corresponding matching pose confidence coefficient of each loop frame pair;
and the optimization unit is used for optimizing the pose of each frame of point cloud data by using a preset map optimization algorithm based on the noise value corresponding to each loop frame pair so as to obtain a laser point cloud map according to an optimization result.
In a third aspect, an embodiment of the present application further provides an electronic device, including:
a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to perform any of the methods described above.
In a fourth aspect, embodiments of the present application further provide a computer-readable storage medium storing one or more programs that, when executed by an electronic device including a plurality of application programs, cause the electronic device to perform any of the methods described above.
The embodiment of the application adopts at least one technical scheme which can achieve the following beneficial effects: according to the laser radar mapping method, under the condition that current frame point cloud data of a laser radar meets preset loopback search conditions, loopback search is conducted on the basis of the current frame point cloud data to obtain loopback search results, and the loopback search results comprise a plurality of loopback frame pairs; then carrying out point cloud matching on the corresponding point cloud data according to each loop frame to obtain a point cloud matching result, wherein the point cloud matching result comprises a matching pose confidence coefficient; then determining a noise value corresponding to each loop frame pair according to the corresponding matching pose confidence coefficient of each loop frame pair; and finally, optimizing the pose of each frame of point cloud data by using a preset map optimization algorithm based on the noise value corresponding to each loop frame pair so as to obtain a laser point cloud map according to an optimization result. According to the laser radar mapping method, the corresponding noise values are respectively determined for each loop frame pair, and the optimization efficiency and the optimization effect of laser mapping are improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a schematic flowchart of a laser radar mapping method in an embodiment of the present application;
fig. 2 is a schematic structural diagram of a laser radar mapping apparatus in an embodiment of the present application;
fig. 3 is a schematic structural diagram of an electronic device in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
The embodiment of the present application provides a lidar mapping method, and as shown in fig. 1, provides a flowchart illustration of the lidar mapping method in the embodiment of the present application, where the method at least includes the following steps S110 to S140:
step S110, performing loop search based on current frame point cloud data of the laser radar under the condition that the current frame point cloud data of the laser radar meets preset loop search conditions to obtain loop search results, wherein the loop search results comprise a plurality of loop frame pairs.
In an actual laser mapping scene, there are many constraints for back-end optimization, where a loop constraint is an important optimization strategy, and the laser radar mapping method in the embodiment of the application mainly aims at a scene where mapping optimization is performed based on the loop constraint.
When loop constraint is constructed, loop search needs to be performed first, in order to improve the efficiency of loop search, a preset loop search condition is defined in the embodiment of the application, and the preset loop search condition is mainly used for determining whether loop matching operation needs to be performed from current frame point cloud data, so that invalid matching is avoided. If the current frame point cloud data meets the preset loop searching condition, the loop searching operation can be carried out, a plurality of matched loop frame pairs can be obtained through a certain loop searching strategy, and the loop frame pairs can be understood that the two frames of point cloud data have greater similarity in the aspects of data characteristics and the like, which indicates that the vehicle may pass through the same position in the same scene.
And step S120, performing point cloud matching on the corresponding point cloud data according to each loop frame to obtain a point cloud matching result, wherein the point cloud matching result comprises a matching pose confidence coefficient.
After a plurality of loop frame pairs are obtained, a certain Point cloud matching algorithm is needed to perform Point cloud matching on two frames of Point cloud data related to each loop frame pair, and the process of Point cloud matching is mainly used for determining the transformation pose between the two frames of Point cloud data, so that the Point cloud matching algorithm adopted here can be any one of Point cloud matching algorithms such as NDT (Normal distribution Transform), ICP (Iterative Closest Point), and the like, and is not specifically limited here.
After the point cloud matching algorithm finishes the matching of the point cloud data, the matching pose between two frames of point cloud data is output, the confidence coefficient corresponding to the matching pose is also output, the better the point cloud matching result is, the higher the corresponding confidence coefficient score is, the worse the point cloud matching result is, the lower the corresponding confidence coefficient score is, namely the confidence degree of the matching pose between two frames of point cloud data is reflected, and the important basis for subsequent optimization is provided. In addition, the confidence of the matching pose and the key frame identification of the corresponding loop frame pair can be correspondingly stored, so that a basis is provided for the subsequent calculation of the noise value.
And step S130, determining a noise value corresponding to each loop frame pair according to the corresponding matching pose confidence of each loop frame pair.
In the process of laser mapping optimization based on loop constraints, the optimization process of an optimization algorithm is often accelerated by introducing a noise value, but the existing scheme adopts a uniform noise value for the confidence coefficient of the matching pose corresponding to each loop frame, so that the optimization efficiency and the optimization effect of the existing optimization scheme are still to be improved.
Based on this, according to the confidence coefficient of the matching pose corresponding to each loop frame pair, the noise value corresponding to each loop frame pair, that is, the size of the noise value corresponding to each loop frame pair, is automatically determined according to the confidence coefficient of the matching pose corresponding to the loop frame pair, and the higher the confidence coefficient is, the smaller the introduced noise value is, and the lower the confidence coefficient is, the larger the introduced confidence coefficient is, so as to improve the optimization efficiency and the optimization effect.
And step S140, optimizing the pose of each frame of point cloud data by using a preset map optimization algorithm based on the noise value corresponding to each loop frame pair so as to obtain a laser point cloud map according to an optimization result.
According to the embodiment of the application, a certain graph optimization algorithm is adopted for optimization, and after the SLAM algorithm obtains position information at the front end, due to the fact that the sensor measures noise, errors are generated on the pose and the observation model, and therefore positioning accuracy is affected, and therefore the pose, the landmark information and the like collected by the front end need to be corrected by the rear end. In the graph optimization process, the optimized object is the pose of each frame of point cloud data, and one of the basis of the optimization is the loop constraint constructed in the embodiment of the present application, for example, the loop constraint includes information such as matching poses between a plurality of loop frame pairs and corresponding confidence degrees of the matching poses, noise values, and the like.
The Graph Optimization algorithm used in the embodiment of the present application may be any one of Optimization algorithms such as G2O (General Graph Optimization), gtsam (georgia Tech Smoothing and mapping), and Ceres, and those skilled in the art can flexibly select the Optimization algorithm according to actual needs, and is not limited specifically herein.
After the pose optimization is completed, the optimized pose corresponding to each frame of point cloud data can be obtained, and then point cloud splicing can be performed according to the optimized pose of each frame of point cloud data, so that a constructed laser point cloud map is obtained.
According to the laser radar mapping method, the corresponding noise values are respectively determined for each loop frame pair, and the optimization efficiency and the optimization effect of laser mapping are improved.
In an embodiment of the present application, when current frame point cloud data of a laser radar satisfies a preset loopback search condition, performing loopback search based on the current frame point cloud data, and before a loopback search result is obtained, the method further includes: determining whether the frame number corresponding to the current frame point cloud data reaches a preset frame number threshold value; if yes, determining that the current frame point cloud data meets the preset loopback searching condition; otherwise, determining that the current frame point cloud data does not meet the preset loopback search condition.
The preset loop search condition of the embodiment of the application can be measured by a preset frame number threshold, and the minimum frame number for loop search is represented, that is, the loop may occur or has a high probability only when the frame number of the point cloud data reaches a certain frame number threshold. Based on this, the embodiment of the application can judge whether the frame number corresponding to the current frame point cloud data reaches the preset frame number threshold, if so, the current frame point cloud data meets the preset loop search condition, loop search matching can be performed, otherwise, the preset loop search condition is not met.
The preset frame number threshold may be flexibly determined according to the size of the coverage area of the actually constructed laser point cloud map, and is not specifically limited herein. For example, if the preset frame number threshold is set to 50 frames, the loop search condition is considered to be triggered when the current frame is the 50 th frame, and if the preset frame number threshold is set to 100 frames, the loop search condition is considered to be triggered when the current frame is the 100 th frame.
In an embodiment of the present application, in a case that current frame point cloud data of a laser radar satisfies a preset loopback search condition, performing loopback search based on the current frame point cloud data, and obtaining a loopback search result includes: determining a candidate frame corresponding to the current frame according to the frame number corresponding to the current frame point cloud data; determining the distance between the current frame and the candidate frame according to the current frame point cloud data and the candidate frame point cloud data; and determining the loopback frame pair according to the distance between the current frame and the candidate frame.
When performing loop search based on a current frame, the embodiment of the present application may determine a candidate frame corresponding to the current frame, where the candidate frame may be understood as a point cloud frame that may form a loop frame pair with the current frame, and may include an initial frame and several frames adjacent to the initial frame, for example, loop search is performed starting from the 50 th frame, loop matching may be performed on the 50 th frame and the 0 th frame, loop matching may be performed on the 51 th frame and the 0 th and 1 st frames, and … …, loop matching may be performed on the 50+ i th frame and a point cloud frame in the (0, i) th frame interval.
The loop matching process is mainly used for calculating the distance between two frames of point cloud data, specifically, the distance between two frames can be calculated according to the position information contained in each frame of point cloud data, and then whether the two frames of point cloud data form a loop frame pair or not can be determined according to the distance between the two frames of point cloud data.
In an embodiment of the present application, said determining the loopback frame pair according to the distance between the current frame and the candidate frame comprises: comparing the distance between the current frame and the candidate frame with a preset distance threshold; if the distance between the current frame and the candidate frame is smaller than the preset distance threshold, determining that the candidate frame and the current frame form the loopback frame pair; otherwise, determining that the candidate frame and the current frame do not form the loopback frame pair.
The closer the distance between two frames of point cloud data is, the more likely the two frames of point cloud data are corresponding to the same position point, that is, a loop appears, so a preset distance threshold min _ diff can be defined, if the distance between the two frames of point cloud data is less than min _ diff, the more likely the distance between the two frames of point cloud data is close, the more likely the distance between the two frames of point cloud data is to indicate that the two frames of point cloud data are corresponding to the same position point, so the two frames of point cloud data can be considered to form a loop frame pair, otherwise, the longer the distance between the two frames of point cloud data is, the corresponding two frames of point cloud data may not be the same position point, and the two frames of point cloud data can be considered not to form a loop frame pair. By the method, a plurality of distance-matched loop frame pairs can be obtained.
In an embodiment of the present application, the determining, according to the confidence of the matching pose corresponding to each loopback frame pair, a noise value corresponding to each loopback frame pair includes: and determining the noise value corresponding to each loop frame pair by using a preset negative correlation strategy according to the confidence coefficient of the matching pose corresponding to each loop frame pair.
When determining the noise value corresponding to each loop frame pair according to the matching pose confidence coefficient corresponding to each loop frame pair, the embodiment of the application can determine the noise value by adopting a certain negative correlation strategy, that is, the higher the matching pose confidence coefficient transprobality is, the smaller the corresponding noise value noise should be, and conversely, the lower the matching pose confidence coefficient transprobality is, the larger the corresponding noise value noise should be.
Through a plurality of experiments, the noise value noise corresponding to each loop frame pair can be determined in the following manner:
noise＝1/(transprobabilty+0.5) 2
of course, besides the above-mentioned manner to determine the noise value corresponding to each loop frame pair, those skilled in the art may also flexibly adopt other manners according to practical situations, and is not limited in particular herein.
In an embodiment of the present application, after determining a noise value corresponding to each loop frame pair according to the confidence of the matching pose corresponding to each loop frame pair, the method further includes: and correspondingly storing the matching pose and the matching pose confidence coefficient of each loop frame pair and the key frame identification of each loop frame pair and the noise value corresponding to each loop frame pair into a loop container.
After the matching pose, the matching pose confidence and the corresponding noise value corresponding to each loop frame are obtained, the information of each dimension can be stored in a correlated manner by combining the corresponding key frame identifier of each loop frame pair, for example, the information can be stored in a loop _ deque loop container for unified management, and the corresponding information can be stored in the loop container as a basis for back-end optimization when a new loop frame pair is obtained.
In a laser mapping scene, the laser point cloud map is constructed by mainly using the key frame data, so the key frame identifier of the loop frame pair can be understood as the unique identifier of the two key frame point cloud data forming one loop frame pair, such as the key frame ID.
In an embodiment of the application, the optimizing the pose of each frame of point cloud data by using a preset map optimization algorithm based on the noise value corresponding to each loopback frame pair to obtain the laser point cloud map according to the optimization result includes: adjusting the diagonal value of an information matrix in the preset graph optimization algorithm according to the noise value corresponding to each loop frame pair; constructing loop constraints based on the adjusted information matrix, and optimizing the pose of each frame of point cloud data by using the loop constraints to obtain the optimized pose of each frame of point cloud data; and splicing the point cloud data of each frame according to the optimized pose of the point cloud data of each frame to obtain the laser point cloud map.
Since many sensors are often involved in an automatic driving system, the higher the accuracy of the sensors is, the larger the weight coefficient of the corresponding sensor optimization constraint is, in a graph optimization algorithm, an information matrix is used as the weight loop _ weight of an error term to give different degrees of confidence to different sensors, and since the information matrix is an inverse matrix of a covariance matrix, the larger the weight coefficient of the information matrix is, the more information expressed by the matrix is, and the more important the information is in the optimization process.
The above weights only measure the importance of different sensor optimization constraints, and for a loop constraint, which is a specific optimization constraint, the embodiments of the present application need to further determine noise values of different edges for the confidence degrees of matching poses of different loop frame pairs, and influence the weight of each loop frame pair in the optimization process through the difference of the noise values, instead of using a uniform loop constraint weight loop _ weight.
Specifically, since the matching pose includes three-dimensional position information (x, y, z) and three-dimensional angle information (roll, pitch, yaw), the noise value corresponding to each loop frame pair calculated in the foregoing embodiment may also be regarded as an array (noise0, noise1, noise2, noise3, noise4, noise5) including six-dimensional noise information, and respectively corresponds to each dimension in the matching pose.
Based on this, when setting the information matrix in the graph optimization algorithm, the diagonal values of the covariance matrix cov may be set to the following form:
cov(0,0)＝noise[0]*noise[0]*(1/loop_weight)；
cov(1,1)＝noise[1]*noise[1]*(1/loop_weight)；
cov(2,2)＝noise[2]*noise[2]*(1/loop_weight)；
cov(3,3)＝noise[3]*noise[3]*(1/loop_weight)；
cov(4,4)＝noise[4]*noise[4]*(1/loop_weight)；
cov(5,5)＝noise[5]*noise[5]*(1/loop_weight)；
wherein loop _ weight is a loop constraint weight, which is a known adjustable parameter, and the inverse of cov is an information matrix.
It can be seen that the smaller the noise value noise, the larger the loop constraint loop _ weight, the smaller the corresponding covariance cov, and the larger the inverse of cov, i.e., the information matrix, indicates the higher confidence level of the loop frame pair in the loop constraint, whereas, the larger the noise value noise, the smaller the loop _ weight, the larger the corresponding covariance cov, and the smaller the inverse of cov, i.e., the information matrix, indicates the lower confidence level of the loop frame pair in the loop constraint.
Therefore, the noise value is determined in the dimension of each loop frame pair, and the weight in the corresponding information matrix is adjusted, so that the optimization efficiency and the optimization effect can be greatly improved.
Note that, the diagonal value of the covariance matrix cov is multiplied by two noise values, mainly to avoid the situation where the elements in the information matrix are negative.
The embodiment of the present application further provides a lidar mapping apparatus 200, as shown in fig. 2, provides a schematic structural diagram of the lidar mapping apparatus in the embodiment of the present application, and the apparatus 200 includes: a loop search unit 210, a point cloud matching unit 220, a first determination unit 230, and an optimization unit 240, wherein:
a loop search unit 210, configured to perform loop search based on current frame point cloud data of a laser radar when the current frame point cloud data meets a preset loop search condition, to obtain a loop search result, where the loop search result includes multiple loop frame pairs;
the point cloud matching unit 220 is configured to perform point cloud matching on the corresponding point cloud data according to each loopback frame to obtain a point cloud matching result, where the point cloud matching result includes a matching pose confidence level;
a first determining unit 230, configured to determine, according to the confidence of the matching pose corresponding to each loopback frame pair, a noise value corresponding to each loopback frame pair;
and the optimizing unit 240 is configured to optimize the pose of each frame of point cloud data by using a preset map optimization algorithm based on the noise value corresponding to each loop frame pair, so as to obtain a laser point cloud map according to an optimization result.
In one embodiment of the present application, the apparatus further comprises: a second determining unit, configured to determine whether a frame number corresponding to the current frame point cloud data reaches a preset frame number threshold; if yes, determining that the current frame point cloud data meets the preset loopback searching condition; otherwise, determining that the current frame point cloud data does not meet the preset loopback search condition.
In an embodiment of the present application, the loop search unit 210 is specifically configured to: determining a candidate frame corresponding to the current frame according to the frame number corresponding to the current frame point cloud data; determining the distance between the current frame and the candidate frame according to the current frame point cloud data and the candidate frame point cloud data; and determining the loopback frame pair according to the distance between the current frame and the candidate frame.
In an embodiment of the present application, the loop search unit 210 is specifically configured to: comparing the distance between the current frame and the candidate frame with a preset distance threshold; if the distance between the current frame and the candidate frame is smaller than the preset distance threshold, determining that the candidate frame and the current frame form the loopback frame pair; otherwise, determining that the candidate frame and the current frame do not form the loopback frame pair.
In an embodiment of the present application, the first determining unit 230 is specifically configured to: and determining the noise value corresponding to each loop frame pair by using a preset negative correlation strategy according to the confidence coefficient of the matching pose corresponding to each loop frame pair.
In one embodiment of the present application, the apparatus further comprises: and the storage unit is used for correspondingly storing the matching pose and the matching pose confidence coefficient of each loop frame pair and the key frame identification of each loop frame pair and the noise value corresponding to each loop frame pair into a loop container.
In an embodiment of the present application, the optimization unit 240 is specifically configured to: adjusting the diagonal value of an information matrix in the preset graph optimization algorithm according to the noise value corresponding to each loop frame pair; constructing loop constraints based on the adjusted information matrix, and optimizing the pose of each frame of point cloud data by using the loop constraints to obtain the optimized pose of each frame of point cloud data; and splicing the point cloud data of each frame according to the optimized pose of the point cloud data of each frame to obtain the laser point cloud map.
It can be understood that the lidar mapping apparatus can implement the steps of the lidar mapping method provided in the foregoing embodiment, and the explanations related to the lidar mapping method are applicable to the lidar mapping apparatus, and are not described herein again.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application. Referring to fig. 3, at a hardware level, the electronic device includes a processor, and optionally further includes an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory, such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, the network interface, and the memory may be connected to each other via an internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (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, only one double-headed arrow is shown in FIG. 3, but this does not indicate only one bus or one type of bus.
And the memory is used for storing programs. In particular, the program may include program code comprising computer operating instructions. The memory may include both memory and non-volatile storage and provides instructions and data to the processor.
The processor reads the corresponding computer program from the nonvolatile memory into the memory and runs the computer program to form the laser radar mapping device on the logic level. The processor is used for executing the program stored in the memory and is specifically used for executing the following operations:
under the condition that current frame point cloud data of a laser radar meets a preset loop search condition, performing loop search based on the current frame point cloud data to obtain a loop search result, wherein the loop search result comprises a plurality of loop frame pairs;
performing point cloud matching on the corresponding point cloud data according to each loop frame to obtain a point cloud matching result, wherein the point cloud matching result comprises a matching pose confidence coefficient;
determining a noise value corresponding to each loop frame pair according to the corresponding matching pose confidence coefficient of each loop frame pair;
and optimizing the pose of each frame of point cloud data by using a preset map optimization algorithm based on the noise value corresponding to each loop frame pair so as to obtain a laser point cloud map according to an optimization result.
The method performed by the lidar mapping apparatus disclosed in the embodiment of fig. 1 of the present application may be applied to or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.
The electronic device may further execute the method executed by the lidar mapping apparatus in fig. 1, and implement the functions of the lidar mapping apparatus in the embodiment shown in fig. 1, which are not described herein again in this embodiment of the present application.
An embodiment of the present application further provides a computer-readable storage medium storing one or more programs, where the one or more programs include instructions, which, when executed by an electronic device that includes multiple application programs, enable the electronic device to perform the method performed by the lidar mapping apparatus in the embodiment shown in fig. 1, and are specifically configured to perform:
under the condition that current frame point cloud data of a laser radar meets a preset loop search condition, performing loop search based on the current frame point cloud data to obtain a loop search result, wherein the loop search result comprises a plurality of loop frame pairs;
performing point cloud matching on the corresponding point cloud data according to each loop frame to obtain a point cloud matching result, wherein the point cloud matching result comprises a matching pose confidence coefficient;
determining a noise value corresponding to each loop frame pair according to the corresponding matching pose confidence coefficient of each loop frame pair;
and optimizing the pose of each frame of point cloud data by using a preset map optimization algorithm based on the noise value corresponding to each loop frame pair so as to obtain a laser point cloud map according to an optimization result.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both permanent and non-permanent, removable and non-removable media, may implement the information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art to which the present application pertains. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A lidar mapping method, wherein the method comprises the following steps:
performing loop search based on current frame point cloud data of a laser radar under the condition that the current frame point cloud data meet a preset loop search condition to obtain a loop search result, wherein the loop search result comprises a plurality of loop frame pairs;
performing point cloud matching on the corresponding point cloud data according to each loop frame to obtain a point cloud matching result, wherein the point cloud matching result comprises a matching pose confidence coefficient;
determining a noise value corresponding to each loop frame pair according to the corresponding matching pose confidence coefficient of each loop frame pair;
and optimizing the pose of each frame of point cloud data by using a preset map optimization algorithm based on the noise value corresponding to each loop frame pair so as to obtain a laser point cloud map according to an optimization result.
2. The method of claim 1, wherein in a case that current frame point cloud data of the lidar satisfies a preset loop search condition, before performing a loop search based on the current frame point cloud data to obtain a loop search result, the method further comprises:
determining whether the frame number corresponding to the current frame point cloud data reaches a preset frame number threshold value;
if yes, determining that the current frame point cloud data meets the preset loopback searching condition;
otherwise, determining that the current frame point cloud data does not meet the preset loopback search condition.
3. The method of claim 1, wherein in a case that current frame point cloud data of the laser radar meets a preset loopback search condition, performing loopback search based on the current frame point cloud data to obtain loopback search results comprises:
determining a candidate frame corresponding to the current frame according to the frame number corresponding to the current frame point cloud data;
determining the distance between the current frame and the candidate frame according to the current frame point cloud data and the candidate frame point cloud data;
and determining the loopback frame pair according to the distance between the current frame and the candidate frame.
4. The method of claim 3, wherein said determining the pair of loop frames according to the distance of the current frame from the candidate frame comprises:
comparing the distance between the current frame and the candidate frame with a preset distance threshold;
if the distance between the current frame and the candidate frame is smaller than the preset distance threshold, determining that the candidate frame and the current frame form the loopback frame pair;
otherwise, determining that the candidate frame and the current frame do not form the loopback frame pair.
5. The method of claim 1, wherein the determining the noise value corresponding to each loopback frame pair according to the confidence of the matching pose corresponding to each loopback frame pair comprises:
and determining the noise value corresponding to each loop frame pair by using a preset negative correlation strategy according to the confidence coefficient of the matching pose corresponding to each loop frame pair.
6. The method of claim 1, wherein after determining the noise value corresponding to each loop frame pair according to the matching pose confidence corresponding to each loop frame pair, the method further comprises:
and correspondingly storing the matching pose and the matching pose confidence coefficient of each loop frame pair and the key frame identification of each loop frame pair and the noise value corresponding to each loop frame pair into a loop container.
7. The method of claim 1, wherein optimizing the pose of each frame of point cloud data by using a preset map optimization algorithm based on the noise value corresponding to each loopback frame pair to obtain a laser point cloud map according to the optimization result comprises:
adjusting the diagonal value of an information matrix in the preset graph optimization algorithm according to the noise value corresponding to each loop frame pair;
constructing loop constraints based on the adjusted information matrix, and optimizing the pose of each frame of point cloud data by using the loop constraints to obtain the optimized pose of each frame of point cloud data;
and splicing the point cloud data of each frame according to the optimized pose of the point cloud data of each frame to obtain the laser point cloud map.
8. A lidar mapping apparatus, wherein the apparatus comprises:
the system comprises a loop search unit, a loop search unit and a processing unit, wherein the loop search unit is used for performing loop search based on current frame point cloud data of a laser radar under the condition that the current frame point cloud data meets a preset loop search condition to obtain a loop search result, and the loop search result comprises a plurality of loop frame pairs;
the point cloud matching unit is used for carrying out point cloud matching on the corresponding point cloud data according to each loop frame to obtain a point cloud matching result, and the point cloud matching result comprises a matching pose confidence coefficient;
the first determining unit is used for determining a noise value corresponding to each loop frame pair according to the corresponding matching pose confidence coefficient of each loop frame pair;
and the optimization unit is used for optimizing the pose of each frame of point cloud data by using a preset map optimization algorithm based on the noise value corresponding to each loop frame pair so as to obtain a laser point cloud map according to an optimization result.
9. An electronic device, comprising:
a processor; and
a memory arranged to store computer executable instructions which, when executed, cause the processor to perform the method of any of claims 1 to 7.
10. A computer readable storage medium storing one or more programs which, when executed by an electronic device comprising a plurality of application programs, cause the electronic device to perform the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210748090.7A CN115079202B (en) | 2022-06-16 | 2022-06-16 | Laser radar image construction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210748090.7A CN115079202B (en) | 2022-06-16 | 2022-06-16 | Laser radar image construction method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115079202A true CN115079202A (en) | 2022-09-20 |
| CN115079202B CN115079202B (en) | 2024-08-27 |
Family
ID=83256473
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210748090.7A Active CN115079202B (en) | 2022-06-16 | 2022-06-16 | Laser radar image construction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115079202B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116977226A (en) * | 2023-09-22 | 2023-10-31 | 天津云圣智能科技有限责任公司 | Point cloud data layering processing method and device, electronic equipment and storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110125928A (en) * | 2019-03-27 | 2019-08-16 | 浙江工业大学 | A kind of binocular inertial navigation SLAM system carrying out characteristic matching based on before and after frames |
| CN110706332A (en) * | 2019-09-25 | 2020-01-17 | 北京计算机技术及应用研究所 | Scene reconstruction method based on noise point cloud |
| CN111929699A (en) * | 2020-07-21 | 2020-11-13 | 北京建筑大学 | Laser radar inertial navigation odometer considering dynamic obstacles and mapping method and system |
| WO2020233724A1 (en) * | 2019-05-23 | 2020-11-26 | 全球能源互联网研究院有限公司 | Visual slam-based grid operating environment map construction method and system |
| CN112880674A (en) * | 2021-01-21 | 2021-06-01 | 深圳市镭神智能系统有限公司 | Positioning method, device and equipment of driving equipment and storage medium |
| WO2021128297A1 (en) * | 2019-12-27 | 2021-07-01 | 深圳市大疆创新科技有限公司 | Method, system and device for constructing three-dimensional point cloud map |
| CN113192142A (en) * | 2021-05-27 | 2021-07-30 | 中国人民解放军国防科技大学 | High-precision map construction method and device in complex environment and computer equipment |
| US20210303908A1 (en) * | 2018-11-16 | 2021-09-30 | Korea Advanced Institute Of Science And Technology | Strong laser scanner matching method and apparatus considering movement of ground robot |
| CN113920258A (en) * | 2021-09-26 | 2022-01-11 | 北京三快在线科技有限公司 | Map generation method, map generation device, map generation medium and electronic equipment |
| WO2022022256A1 (en) * | 2020-07-31 | 2022-02-03 | 湖北亿咖通科技有限公司 | Loopback detection method and system, readable storage medium, and electronic device |
| CN114089365A (en) * | 2022-01-20 | 2022-02-25 | 智道网联科技(北京)有限公司 | Automatic driving vehicle positioning method and device, electronic equipment and storage medium |
| CN114332221A (en) * | 2021-12-28 | 2022-04-12 | 北京易航远智科技有限公司 | Semantic-based loop detection method and device, electronic equipment and storage medium |
-
2022
- 2022-06-16 CN CN202210748090.7A patent/CN115079202B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210303908A1 (en) * | 2018-11-16 | 2021-09-30 | Korea Advanced Institute Of Science And Technology | Strong laser scanner matching method and apparatus considering movement of ground robot |
| CN110125928A (en) * | 2019-03-27 | 2019-08-16 | 浙江工业大学 | A kind of binocular inertial navigation SLAM system carrying out characteristic matching based on before and after frames |
| WO2020233724A1 (en) * | 2019-05-23 | 2020-11-26 | 全球能源互联网研究院有限公司 | Visual slam-based grid operating environment map construction method and system |
| CN110706332A (en) * | 2019-09-25 | 2020-01-17 | 北京计算机技术及应用研究所 | Scene reconstruction method based on noise point cloud |
| WO2021128297A1 (en) * | 2019-12-27 | 2021-07-01 | 深圳市大疆创新科技有限公司 | Method, system and device for constructing three-dimensional point cloud map |
| CN111929699A (en) * | 2020-07-21 | 2020-11-13 | 北京建筑大学 | Laser radar inertial navigation odometer considering dynamic obstacles and mapping method and system |
| WO2022022256A1 (en) * | 2020-07-31 | 2022-02-03 | 湖北亿咖通科技有限公司 | Loopback detection method and system, readable storage medium, and electronic device |
| CN112880674A (en) * | 2021-01-21 | 2021-06-01 | 深圳市镭神智能系统有限公司 | Positioning method, device and equipment of driving equipment and storage medium |
| CN113192142A (en) * | 2021-05-27 | 2021-07-30 | 中国人民解放军国防科技大学 | High-precision map construction method and device in complex environment and computer equipment |
| CN113920258A (en) * | 2021-09-26 | 2022-01-11 | 北京三快在线科技有限公司 | Map generation method, map generation device, map generation medium and electronic equipment |
| CN114332221A (en) * | 2021-12-28 | 2022-04-12 | 北京易航远智科技有限公司 | Semantic-based loop detection method and device, electronic equipment and storage medium |
| CN114089365A (en) * | 2022-01-20 | 2022-02-25 | 智道网联科技(北京)有限公司 | Automatic driving vehicle positioning method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 伍锡如 等: "改进ORB特征的机器人RGB-D SLAM算法", 计算机工程与应用, vol. 56, no. 14, 29 February 2020 (2020-02-29), pages 35 - 44 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116977226A (en) * | 2023-09-22 | 2023-10-31 | 天津云圣智能科技有限责任公司 | Point cloud data layering processing method and device, electronic equipment and storage medium |
| CN116977226B (en) * | 2023-09-22 | 2024-01-19 | 天津云圣智能科技有限责任公司 | Point cloud data layering processing method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115079202B (en) | 2024-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111709975A (en) | Multi-target tracking method and device, electronic equipment and storage medium | |
| CN112884054B (en) | Target labeling method and target labeling device | |
| CN115079202B (en) | Laser radar image construction method and device, electronic equipment and storage medium | |
| CN115390086B (en) | Fusion positioning method and device for automatic driving, electronic equipment and storage medium | |
| CN113868350A (en) | Parking lot map processing method, vehicle and equipment | |
| CN114089365B (en) | Automatic driving vehicle positioning method and device, electronic equipment and storage medium | |
| CN115546315A (en) | Sensor on-line calibration method and device for automatic driving vehicle and storage medium | |
| CN115371663A (en) | Laser mapping method and device, electronic equipment and computer readable storage medium | |
| CN114966632A (en) | Laser radar calibration method and device, electronic equipment and storage medium | |
| CN113935402B (en) | Training method and device of time difference positioning model and electronic equipment | |
| WO2024179207A1 (en) | Road object recognition method and apparatus | |
| CN114397671B (en) | Course angle smoothing method and device of target and computer readable storage medium | |
| CN116106869A (en) | Positioning evaluation method and device for automatic driving vehicle and electronic equipment | |
| CN112148817B (en) | SLAM optimization method, device and system based on panorama | |
| CN116740680A (en) | Vehicle positioning method and device and electronic equipment | |
| CN115127542A (en) | Laser mapping method and device, electronic equipment and computer readable storage medium | |
| CN116164763A (en) | Target course angle determining method and device, electronic equipment and storage medium | |
| CN114066958A (en) | Method and device for predicting depth information of target, electronic device and storage medium | |
| CN115797893A (en) | Method and device for determining effective driving area, electronic device and storage medium | |
| CN115014332A (en) | Laser SLAM mapping method and device, electronic equipment and computer readable storage medium | |
| CN113689422B (en) | Image processing method and device and electronic equipment | |
| CN112836745B (en) | Target detection method and device | |
| CN117572335A (en) | Updating method and device for laser positioning confidence coefficient and electronic equipment | |
| CN116580095A (en) | Target positioning method and device, electronic equipment and storage medium | |
| CN116625384B (en) | Data association method and device and electronic 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |