CN116106927A - Two-dimensional grid map construction method, medium and system based on laser radar - Google Patents
Two-dimensional grid map construction method, medium and system based on laser radar Download PDFInfo
- Publication number
- CN116106927A CN116106927A CN202211685835.6A CN202211685835A CN116106927A CN 116106927 A CN116106927 A CN 116106927A CN 202211685835 A CN202211685835 A CN 202211685835A CN 116106927 A CN116106927 A CN 116106927A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- cloud data
- pose information
- dimensional point
- laser radar
- 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
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
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
- G01C21/3833—Creation or updating of map data characterised by the source of data
- G01C21/3841—Data obtained from two or more sources, e.g. probe vehicles
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- Automation & Control Theory (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The embodiment of the invention discloses a two-dimensional grid map construction method, medium and system based on a laser radar. The two-dimensional grid map construction method based on the laser radar comprises the following steps: acquiring first two-dimensional point cloud data of a target area obtained by scanning a laser radar on a target self-body at a first moment; obtaining first pose information of the target self-body according to the first two-dimensional point cloud data; predicting second two-dimensional point cloud data obtained by the laser radar when the target is located in the first pose information; optimizing the first pose information according to the first two-dimensional point cloud data and the second two-dimensional point cloud data to obtain second pose information; and constructing a two-dimensional grid map of the target area according to the second pose information. The embodiment of the invention realizes the efficient and low-occupation construction of the high-precision two-dimensional grid map.
Description
The application is a divisional application of an invention patent application with the name of 202010228792.3, namely a laser radar-based two-dimensional grid map construction method and system, applied for in the year 2020, month 03 and day 27.
Technical Field
The embodiment of the invention relates to positioning and mapping technologies, in particular to a two-dimensional grid map construction method, medium and system based on a laser radar.
Background
As humans enter the information industry revolution age, artificial intelligence technology has rapidly evolved, and intelligent robotics are developing innovations at unprecedented speeds and gradually penetrating into various industries.
The positioning and mapping technology is a core module which is indispensable in the fields of intelligent robots, unmanned robots and the like, and can tell the position of a robot body and guide the robot body to move and avoid obstacles.
Currently, there are Gmapping, cartographer and other positioning and mapping technologies commonly used in engineering, which respectively use particle filtering and mapping optimization technologies to realize 2D positioning and mapping. Gmapping adopts adaptive Monte Carlo positioning, a plurality of particles are utilized to represent the possible pose of the robot, each particle is one possible assumption of the pose of the robot in real space, and in the motion process, the state of all particles needs to be updated and the pose and map of each particle are maintained.
Disclosure of Invention
The embodiment of the invention provides a two-dimensional grid map construction method, medium and system based on a laser radar, which are used for realizing high-efficiency and low-occupation construction of a high-precision two-dimensional grid map.
To achieve the object, an embodiment of the present invention provides a two-dimensional grid map construction method based on a laser radar, including:
acquiring first two-dimensional point cloud data of a target area obtained by scanning a laser radar on a target self-body at a first moment;
obtaining first pose information of the target self-body according to the first two-dimensional point cloud data;
predicting second two-dimensional point cloud data obtained by the laser radar when the target is located in the first pose information;
optimizing the first pose information according to the first two-dimensional point cloud data and the second two-dimensional point cloud data to obtain second pose information;
and constructing a two-dimensional grid map of the target area according to the second pose information.
Further, the acquiring the first two-dimensional point cloud data of the target area obtained by scanning the target at the first moment from the laser radar on the main body includes:
When the laser radar on the target self-body is a single-line laser radar, first two-dimensional point cloud data of a target area at a first moment are directly obtained through the laser radar;
the laser radar on the target self-body is a multi-line laser radar, a first laser of a preset emission angle in the multi-line laser radar is confirmed, and point cloud data acquired by the first laser are projected onto a horizontal plane according to the preset emission angle so as to acquire first two-dimensional point cloud data of a target area at a first moment.
Further, the obtaining the first pose information of the target self-body according to the first two-dimensional point cloud data includes:
acquiring third two-dimensional point cloud data of a target area obtained by scanning at a second moment by the laser radar, wherein the second moment is the moment before the first moment;
acquiring third pose information of the target at a second moment of the main body;
matching the first two-dimensional point cloud data and the third two-dimensional point cloud data according to an NDT algorithm to obtain a first relative pose relationship between the first moment and the second moment;
and determining first pose information of the target self-body according to the first relative pose relation and the third pose information.
Further, the matching the first two-dimensional point cloud data and the third two-dimensional point cloud data according to the NDT algorithm to obtain the first relative pose relationship between the first moment and the second moment includes:
acquiring the moving speed of the target at the second moment of the main body;
predicting fourth pose information of the target at a first moment of the self-body according to the moving speed and the third pose information;
and matching the first two-dimensional point cloud data and the third two-dimensional point cloud data by using an NDT algorithm according to the fourth pose information to obtain a first relative pose relation between the first moment and the second moment.
Further, the predicting the second two-dimensional point cloud data obtained by the laser radar when the target is located in the first pose information includes:
acquiring performance parameters of the laser radar and a pre-established two-dimensional environment map;
and predicting second two-dimensional point cloud data obtained by the laser radar when the target is in the first pose information according to the performance parameters and the two-dimensional environment map.
Further, the optimizing the first pose information according to the second two-dimensional point cloud data to obtain second pose information includes:
Confirming a mapping relation between the first pose information and the second two-dimensional point cloud data;
and adjusting the first pose information according to the mapping relation to obtain second pose information when the error between the first two-dimensional point cloud data and the second two-dimensional point cloud data is minimum.
Further, the confirming the mapping relationship between the first pose information and the second two-dimensional point cloud data includes:
defining a mapping function f i (x) Wherein f i (x) And (3) representing second two-dimensional point cloud data obtained by theoretical scanning of the laser radar when pose information is x, wherein x represents the pose information, and i represents the number of times of determining the pose information of the target from the main body.
Further, the adjusting the first pose information according to the mapping relationship to obtain second pose information when the error between the first two-dimensional point cloud data and the second two-dimensional point cloud data is minimum includes:
defining an error function e i (x) Wherein e is i (x)＝f i (x)-z i ，e i (x) Is representative of an error, z, between the first two-dimensional point cloud data and the second two-dimensional point cloud data i Representing the first two-dimensional point cloud data;
defining an objective function F (x), wherein
An objective function F (x) is derived from the error function e i (x) Square and then obtain covariance matrix;
adjusting x to obtain x when the value of the objective function F (x) is minimum min And apply the x min As second pose information.
Further, the adjusting of x to obtain x when the objective function F (x) is minimum min Comprising the following steps:
taking the first pose information as an initial value x 0 ；
From the initial value x 0 Starting to iterate the objective function F (x) a plurality of times until F (x) k+1 ) The value of (2) reaches a minimum value, where x k+1 ＝x k +△x k K represents the number of iterations, when Deltax k When the number of the iterations is smaller than the first threshold value, stopping the iteration and x at the moment k As x min 。
In one aspect, an embodiment of the present invention further provides a computer readable storage medium storing a computer program, where the program is executed by a processor to implement the steps of the method described above.
In one aspect, the embodiment of the invention further provides a two-dimensional grid map construction system based on the laser radar, which comprises:
the data acquisition module is used for acquiring first two-dimensional point cloud data of a target area obtained by scanning a target from a laser radar on a main body at a first moment;
the pose acquisition module is used for acquiring first pose information of the target self-body according to the first two-dimensional point cloud data;
The data prediction module is used for predicting second two-dimensional point cloud data obtained by the laser radar when the target is located in the first pose information;
the pose optimization module is used for optimizing the first pose information according to the first two-dimensional point cloud data and the second two-dimensional point cloud data to obtain second pose information;
and the map construction module is used for constructing a two-dimensional grid map of the target area according to the second pose information.
On the other hand, the embodiment of the invention also provides a two-dimensional grid map construction device based on the laser radar, which comprises: one or a processor; and a storage means for storing one or a program which, when executed by the one or a processor, causes the one or a processor to implement a method as provided by any of the embodiments of the present invention.
In yet another aspect, embodiments of the present invention further provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method as provided by any of the embodiments of the present invention.
The method comprises the steps of obtaining first two-dimensional point cloud data of a target area, which is obtained by scanning a laser radar on a target body at a first moment; obtaining first pose information of the target self-body according to the first two-dimensional point cloud data; predicting second two-dimensional point cloud data obtained by the laser radar when the target is located in the first pose information; optimizing the first pose information according to the second two-dimensional point cloud data to obtain second pose information; and constructing the two-dimensional grid map of the target area according to the second pose information, so that the problem of insufficient precision of the existing two-dimensional grid map construction is solved.
Drawings
Fig. 1 is a schematic flow chart of a two-dimensional grid map construction method based on a laser radar according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a two-dimensional grid map construction method based on a laser radar according to a second embodiment of the present invention;
FIG. 3 is a flowchart of step S230 in the embodiment shown in FIG. 2;
FIG. 4 is a flowchart illustrating step S260 in the embodiment shown in FIG. 2;
fig. 5 is a schematic structural diagram of a two-dimensional grid map building system based on a laser radar according to a third embodiment of the present invention;
fig. 6 is a schematic structural diagram of a two-dimensional grid map building device based on a laser radar according to a fourth embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are for purposes of illustration and not of limitation. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart depicts steps as a sequential process, many of the steps may be implemented in parallel, concurrently, or with other steps. Furthermore, the order of the steps may be rearranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figures. The processes may correspond to methods, functions, procedures, subroutines, and the like.
Furthermore, the terms "first," "second," and the like, may be used herein to describe various directions, acts, steps, or elements, etc., but these directions, acts, steps, or elements are not limited by these terms. These terms are only used to distinguish one direction, action, step or element from another direction, action, step or element. For example, the first two-dimensional point cloud data may be referred to as second two-dimensional point cloud data, and similarly, the second two-dimensional point cloud data may be referred to as first two-dimensional point cloud data, without departing from the scope of the present application. Both the first two-dimensional point cloud data and the second two-dimensional point cloud data are two-dimensional point cloud data, but they are not the same two-dimensional point cloud data. The terms "first," "second," and the like, are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the embodiments of the present invention, the meaning of "plurality" is at least two, for example, two, three, etc., unless explicitly defined otherwise.
Example 1
As shown in fig. 1, a first embodiment of the present invention provides a two-dimensional grid map construction method based on a laser radar, which includes:
s110, acquiring first two-dimensional point cloud data of a target area obtained by scanning a laser radar on a target body at a first moment.
In this embodiment, the target self-body may be a robot, a self-moving vehicle, or other self-body with a self-moving function. The target self-body is an exemplary sweeping robot, the target area is a room area to be swept, the construction of the two-dimensional grid map can be real-time construction or off-line non-real-time construction, in this embodiment, the two-dimensional grid map is a real-time map construction process, the first moment is the current real-time moment, and the first two-dimensional point cloud data is the point cloud data acquired in real time. In other embodiments, the two-dimensional grid map may be an offline map building process, where the first moment refers to any moment when pose determination needs to be performed in the walking process of the sweeping robot, and the first two-dimensional point cloud data is point cloud data obtained by laser radar scanning at the first moment. The lidar may be mounted from the side or top of the subject, just to ensure that it is able to effect a scan of the target area. The laser radar can be a multi-line laser radar or a single-line laser radar, and the laser radar can be a mechanical laser radar or a mixed solid-state or solid-state laser radar.
S120, obtaining first pose information of the target self-body according to the first two-dimensional point cloud data.
After the first two-dimensional point cloud data is obtained, the first pose information of the target self-body at the first moment can be determined according to a registration algorithm or a deep learning algorithm which are commonly used in the field. The first two-dimensional point cloud data may be matched, for example, according to an NDT (Normal Distributions Transform, normal distribution transformation) registration algorithm to obtain first pose information of the target subject. Specifically, the first two-dimensional point cloud data of the two-dimensional NDT registration module based on the NDT registration algorithm is matched with the two-dimensional point cloud data acquired at the previous moment, so that the first pose information at the first moment is determined.
S130, predicting second two-dimensional point cloud data obtained by the laser radar when the target is located in the first pose information.
The performance parameters of the lidar installed on the main body are generally known fixedly, and the environment of the target on the main body can be scanned by the lidar in advance, and a corresponding two-dimensional grid map is constructed in advance. Therefore, when the target is in any pose, the target can be predicted in theory, the laser radar can scan to obtain theoretical two-dimensional point cloud data, namely second two-dimensional point cloud data which can be obtained by the laser radar in theory when the target is in the first pose information.
And S140, optimizing the first pose information according to the first two-dimensional point cloud data and the second two-dimensional point cloud data to obtain second pose information.
In the embodiment, the NDT registration algorithm can realize efficient real-time point cloud data registration in a three-dimensional space, and has good registration precision, and one dimension is omitted in a two-dimensional space, so that the matching efficiency of the algorithm is further improved under the condition that the precision is not lost, and enough time and resources are used for optimization. In this embodiment, after the first pose information is obtained, the first pose information is further optimized, so that the optimized pose information with higher precision is used for mapping.
The second two-dimensional point cloud data are two-dimensional point cloud data which can be obtained by the laser radar in theory when the laser radar is located in the first pose information at the first moment, and the first two-dimensional point cloud data are two-dimensional point cloud data which are actually obtained by the laser radar at the first moment, so that the first pose information can be optimized according to actual and theoretical deviation, and further second pose information which is more accurate relative to the first pose information can be obtained.
Specifically, a preset algorithm is used for optimizing the first pose information by combining the first two-dimensional point cloud data and the second two-dimensional point cloud data to obtain second pose information, wherein the preset algorithm can be an algorithm based on a nonlinear optimization technology, specifically, the second two-dimensional point cloud data obtained by the laser radar when a target is in the first pose information is predicted, then errors of the second two-dimensional point cloud data and the first two-dimensional point cloud data are obtained, and the first pose information with the minimum errors is used as the second pose information.
And S150, constructing a two-dimensional grid map of the target area according to the second pose information.
And constructing a two-dimensional grid map of the target area according to the second pose information, and completing the construction of the high-precision two-dimensional grid map with high efficiency and low occupancy. The two-dimensional grid map is built by utilizing two-dimensional point cloud data obtained by the current scanning of the laser radar.
The method comprises the steps of obtaining first two-dimensional point cloud data of a target area, which is obtained by scanning a laser radar on a target body at a first moment; obtaining first pose information of the target self-body according to the first two-dimensional point cloud data; predicting second two-dimensional point cloud data obtained by the laser radar when the target is located in the first pose information; optimizing the first pose information according to the second two-dimensional point cloud data to obtain second pose information; the two-dimensional grid map of the target area is constructed according to the second pose information, the problems that the existing method for constructing the two-dimensional grid map occupies too high computer resources and is insufficient in precision are solved, and the effect of constructing the high-precision two-dimensional grid map with high efficiency and low occupation is achieved.
Example two
As shown in fig. 2-4, a second embodiment of the present invention provides a two-dimensional grid map construction method based on a laser radar, and the second embodiment of the present invention is further explained based on the first embodiment of the present invention, as shown in fig. 2, the method includes:
and S210, when the laser radar on the target self-body is a single-line laser radar, directly acquiring first two-dimensional point cloud data of a target area at a first moment through the laser radar.
S220, the laser radar on the target self-body is a multi-line laser radar, a first laser of a preset emission angle in the multi-line laser radar is confirmed, and point cloud data acquired by the first laser are projected onto a horizontal plane according to the preset emission angle to acquire first two-dimensional point cloud data of a target area at a first moment.
In this embodiment, if the target is a single-line laser radar, the first two-dimensional point cloud data of the target area under the first moment may be directly obtained through the laser radar, if the target is a multi-line laser radar, the first laser of the preset emission angle in the multi-line laser radar needs to be confirmed, and the point cloud data obtained by the first laser is projected onto a horizontal plane according to the preset emission angle to obtain the first two-dimensional point cloud data of the target area under the first moment, where the preset emission angle is determined by the self parameters of the multi-line laser radar, so that the two-dimensional grid map can be constructed by both the single-line laser radar and the multi-line laser radar.
That is, in the present embodiment, step S210 and step S220 are one or the relationship, that is, one of the steps needs to be selectively performed according to the type of the lidar, and step S230 is performed after step S210 or step S220 is performed.
S230, obtaining first pose information of the target self-body according to the first two-dimensional point cloud data.
S240, acquiring performance parameters of the laser radar and a pre-established two-dimensional environment map.
The performance parameters of the lidar may include information such as the firing frequency, the firing angle of the laser beam, and the scan angle. The pre-established two-dimensional environment map is that the whole environment is scanned by a laser radar before the steps in the method are executed, so that the two-dimensional environment map is pre-established, and the pre-established two-dimensional environment map is a static map. The two-dimensional environment map can be directly stored after being established so as to be directly called by a subsequent operation process. It will be appreciated that when a static object in the environment changes, a two-dimensional environment map is updated.
S250, predicting second two-dimensional point cloud data obtained by the laser radar when the target is located in the first pose information according to the performance parameters and the two-dimensional environment map.
In this embodiment, the performance parameters of the laser radar and the two-dimensional environment map established in advance are obtained first, and then the second two-dimensional point cloud data which may be obtained by the laser radar when the target is located in the first pose information can be predicted according to the performance parameters and the two-dimensional environment map. That is, according to the performance parameters of the laser radar, the scanning area of the laser radar can be known when the laser radar is located in the first pose information, and according to the pre-established two-dimensional environment map, the environment distribution situation corresponding to the scanning area can be known, so that the distribution situation of point cloud data formed after the laser beam is reflected by the corresponding environment object can be determined, and theoretical second two-dimensional point cloud data can be obtained.
And S260, optimizing the first pose information according to the second two-dimensional point cloud data to obtain second pose information.
S270, constructing a two-dimensional grid map of the target area according to the second pose information.
Further, as shown in fig. 3, in the two-dimensional grid map construction method based on the laser radar provided in the second embodiment of the present invention, step S230 may specifically include:
s231, acquiring third two-dimensional point cloud data of a target area obtained by scanning the laser radar at a second moment, wherein the second moment is the moment before the first moment.
The second moment is the moment before the first moment, so that the third two-dimensional point cloud data of the target area obtained by scanning the laser radar at the second moment can be directly used as the third two-dimensional point cloud data by reading the two-dimensional point cloud data with the timestamp of the second moment from the point cloud data acquired by the laser radar.
S232, acquiring third pose information of the target at a second moment of the main body.
And the third pose information at the second time can be determined according to the third two-dimensional point cloud data at the second time. In the mapping process at the second moment, the third pose information is obtained and determined, and the third pose information is directly read.
S233, acquiring the moving speed of the target at the second moment of the main body.
The moving speed of the self-body at the second moment can be determined according to the third two-dimensional point cloud data obtained at the second moment or by combining the second moment and the point cloud data of at least one frame in front of the second moment. The moving speed is a vector including a direction and a magnitude.
S234, fourth pose information of the target at the first moment of the main body is predicted according to the moving speed and the third pose information.
In the case that the moving speed of the target from the subject is known, pose information of the target at a future time can be predicted approximately according to the speed. Therefore, the pose information of the target self-body at the first time next to the second time can be approximately predicted as the fourth pose information based on the moving speed at the second time and the third pose information.
And S235, matching the first two-dimensional point cloud data and the third two-dimensional point cloud data by using an NDT algorithm according to the fourth pose information so as to obtain a first relative pose relation between the first moment and the second moment.
Specifically, the fourth pose information is used as an initial value of NDT algorithm matching to register the first two-dimensional point cloud data and the third two-dimensional point cloud data, so that the data volume in the matching process can be greatly reduced, and the matching efficiency is improved.
S236, determining first pose information of the target self-body according to the first relative pose relation and the third pose information.
In this embodiment, a two-dimensional NDT registration module based on an NDT registration algorithm is required to register first two-dimensional point cloud data acquired by a target self-body at a first time and third two-dimensional point cloud data acquired by the target self-body at a second time. The laser radar is used for acquiring third two-dimensional point cloud data of the target area at a second moment, the second moment is the moment before the first moment, the NDT registration algorithm is then used for matching the first two-dimensional point cloud data with the third two-dimensional point cloud data to obtain a first relative pose relation between the first moment and the second moment, and pose information of the target self-body at the second moment is determined, so that third pose information of the target self-body at the second moment can be directly acquired, and finally, the first pose information of the target self-body is determined according to the first relative pose relation and the third pose information. If the first moment is the moment when the object moves initially, namely, when the previous moment does not exist, the first moment is directly used as map data of the two-dimensional grid map.
Further, as shown in fig. 4, in the two-dimensional grid map construction method based on the laser radar provided in the second embodiment of the present invention, step S260 may specifically include:
s261, defining a mapping function f i (x) Wherein f i (x) And (3) representing second two-dimensional point cloud data obtained by theoretical scanning of the laser radar when the pose information is x, wherein x represents the pose information, and i represents the number of times of determining the pose information of the target from the main body.
S262, defining an error function e i (x) Wherein e is i (x)＝f i (x)-z i ，e i (x) Is representative of an error, z, between the first two-dimensional point cloud data and the second two-dimensional point cloud data i Representing the first two-dimensional point cloud data.
S263, defining an objective function F (x), wherein
An objective function F (x) is derived from the error function e i (x) Square and takeThe covariance matrix is obtained.
In this embodiment, when the nonlinear optimization technique is used to combine the first two-dimensional point cloud data and the first pose information to obtain the second pose information, it is first required to define i to represent the number of times of determining the pose information of the target self-body, then define x as pose information, x as a state vector, the pose information including the position information and the direction information of the x-axis and the y-axis of the target self-body in the rectangular coordinate system, and because the final objective is to build a two-dimensional grid map, the position information, the roll angle information and the pitch angle information of the z-axis in the rectangular coordinate system are not considered, and define z i For first two-dimensional point cloud data obtained by actual scanning when a target self-body is in first pose information, defining f i (x) For a nonlinear mapping to represent third two-dimensional point cloud data, wherein the third two-dimensional point cloud data is obtained by predicting point cloud data which will be scanned from a target area when the target self-body is in a state x, then f i (x) Predicting point cloud data which can be scanned from a target area based on the first pose information after any action of a target slave body is represented, thereby defining the error of the first two-dimensional point cloud data and the third two-dimensional point cloud data as e i (x) Wherein e is i (x)＝f i (x)-z i 。
Further, the error is generally considered to follow a gaussian distribution, and thus the error e is defined i (x) Is the square of (1)
Re-taking E i (x) Can be obtained the objective function ++of the nonlinear least squares>
When the x value corresponding to the minimum value of the objective function F (x) is obtained, the optimal first pose information can be determined.
S264, taking the first pose information as an initial value x 0 。
S265, from the initial value x 0 Starting to iterate the objective function F (x) a plurality of times until F (x) k+1 ) The value of (2) reaches a minimum value ofX in the middle k+1 ＝x k +△x k K represents the number of iterations, when Deltax k When the number of the iterations is smaller than the first threshold value, stopping the iteration and x at the moment k As x min And apply the x min As second pose information.
In the present embodiment, in order to obtain the x value corresponding to the minimum value of the objective function F (x), the first pose information is first set as the initial value x 0 Because the first pose information is the pose information which is preliminarily obtained through a registration algorithm according to the first two-dimensional point cloud data obtained through laser radar scanning, the number of iterative processes can be reduced by taking the pose information as an initial value, and the efficiency of the iterative processes is accelerated.
Specifically, first, e i (x) Performing first-order Taylor expansion to obtain:
e i (x+△x)＝e i (x)+J i (x)△x
where J is a Jacobian matrix, meaning the derivative of x. The objective function F (x) can thus be converted into:
further expansion and simplification of the right side of the formula can be obtained:
the delta Deltax is solved, and the quantity irrelevant to Deltax is expressed by a coefficient to obtain:
at this point, the derivative of F (x+. DELTA.x) with respect to DELTA.x is taken and the result is equal to 0:
further simplified to obtain:
△x * ＝-H -1 b
from an initial value x on the basis of the above 0 Starting to iterate the objective function F (x) k times until F (x) k +△x k ) F (x) k+1 ) Reach a minimum value where x k+1 ＝x k +△x k In k iterations of the objective function F (x), if Deltax k Less than a first threshold, stop iteration and x will be at that time k As x min And x is taken as min And as the second pose information, constructing a two-dimensional grid map of the target area according to the second pose information, thereby obtaining a map with extremely high precision.
Example III
As shown in fig. 5, a third embodiment of the present invention provides a two-dimensional grid map building system 100 based on a laser radar, where the two-dimensional grid map building system 100 based on a laser radar provided in the third embodiment of the present invention can execute the two-dimensional grid map building method based on a laser radar provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method. The laser radar-based two-dimensional grid map construction system 100 includes a data acquisition module 200, a pose acquisition module 300, a data prediction module 400, a pose optimization module 500, and a map construction module 600.
Specifically, the data acquisition module 200 is configured to acquire first two-dimensional point cloud data of a target area obtained by scanning at a first moment from a laser radar on a subject; the pose acquisition module 300 is configured to obtain first pose information of the target self-body according to the first two-dimensional point cloud data; the data prediction module 400 is configured to predict second two-dimensional point cloud data obtained by the laser radar when the target is located in the first pose information; the pose optimization module 500 is configured to optimize the first pose information according to the first two-dimensional point cloud data and the second two-dimensional point cloud data to obtain second pose information; the map construction module 600 is configured to construct a two-dimensional grid map of the target area according to the second pose information.
In this embodiment, the data acquisition module 200 is specifically configured to directly acquire, when the laser radar on the target self-body is a single-line laser radar, first two-dimensional point cloud data of the target area at the first moment through the laser radar; the laser radar on the target self-body is a multi-line laser radar, a first laser of a preset emission angle in the multi-line laser radar is confirmed, and point cloud data acquired by the first laser are projected onto a horizontal plane according to the preset emission angle so as to acquire first two-dimensional point cloud data of a target area at a first moment.
The pose acquisition module 300 is specifically configured to acquire third two-dimensional point cloud data of a target area obtained by scanning the laser radar at a second moment, where the second moment is a moment before the first moment; acquiring third pose information of the target at a second moment of the main body; matching the first two-dimensional point cloud data and the third two-dimensional point cloud data according to an NDT algorithm to obtain a first relative pose relationship between the first moment and the second moment; and determining first pose information of the target self-body according to the first relative pose relation and the third pose information. The pose obtaining module 300 is specifically further configured to obtain a moving speed of the target at a second moment of the self-body; predicting fourth pose information of the target at a first moment of the self-body according to the moving speed and the third pose information; and matching the first two-dimensional point cloud data and the third two-dimensional point cloud data by using an NDT algorithm according to the fourth pose information to obtain a first relative pose relation between the first moment and the second moment.
The data prediction module 400 is specifically configured to obtain performance parameters of the lidar and a pre-established two-dimensional environment map; and predicting second two-dimensional point cloud data obtained by the laser radar when the target is in the first pose information according to the performance parameters and the two-dimensional environment map.
The pose optimization module 500 is specifically configured to confirm a mapping relationship between the first pose information and the second two-dimensional point cloud data; adjusting the first pose information according to the mapping relation to obtain a second when the error between the first two-dimensional point cloud data and the second two-dimensional point cloud data is minimumPose information. The pose optimization module 500 is specifically further configured to define a mapping function f i (x) Wherein f i (x) And (3) representing second two-dimensional point cloud data obtained by theoretical scanning of the laser radar when the pose information is x, wherein x represents the pose information, and i represents the number of times of determining the pose information of the target from the main body. The pose optimization module 500 is specifically further configured to define an error function e i (x) Wherein e is i (x)＝f i (x)-z i ，e i (x) Is representative of an error, z, between the first two-dimensional point cloud data and the second two-dimensional point cloud data i Representing the first two-dimensional point cloud data; defining an objective function F (x), wherein 
An objective function F (x) is derived from the error function e i (x) Square and then obtain covariance matrix; adjusting x to obtain x when the value of the objective function F (x) is minimum min And apply the x min As second pose information. The pose optimization module 500 is specifically further configured to use the first pose information as an initial value x 0 The method comprises the steps of carrying out a first treatment on the surface of the From the initial value x 0 Starting to iterate the objective function F (x) a plurality of times until F (x) k+1 ) The value of (2) reaches a minimum value, where x k+1 ＝x k +△x k K represents the number of iterations, when Deltax k When the number of the iterations is smaller than the first threshold value, stopping the iteration and x at the moment k As x min 。
Example IV
Fig. 6 is a schematic structural diagram of a two-dimensional grid map building computer device based on a laser radar according to a fourth embodiment of the present invention. FIG. 6 illustrates a block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention. The computer device 12 shown in fig. 6 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in FIG. 6, the computer device 12 is in the form of a general purpose computing device. Components of computer device 12 may include, but are not limited to: one or a processor or processing unit 16, a system memory 28, and a bus 18 that connects the various system components, including the system memory 28 and the processing unit 16.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 30 and/or cache memory 32. The computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from or write to non-removable, nonvolatile magnetic media (not shown in FIG. 6, commonly referred to as a "hard disk drive"). Although not shown in fig. 6, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be coupled to bus 18 through one or more data medium interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored in, for example, memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 42 generally perform the functions and/or methods of the embodiments described herein.
The computer device 12 may also communicate with one or external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with the computer device 12, and/or with any device (e.g., network card, modem, etc.) that enables the computer device 12 to communicate with one or other computing devices. Such communication may occur through an input/output (I/O) interface 22. Moreover, the computer device 12 may also communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, through a network adapter 20. As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with computer device 12, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, for example, implementing the methods provided by embodiments of the present invention:
acquiring first two-dimensional point cloud data of a target area at a first moment through a laser radar on a target self-body;
obtaining first pose information of the target self-body according to the first two-dimensional point cloud data;
predicting second two-dimensional point cloud data obtained by the laser radar when the target is located in the first pose information;
optimizing the first pose information according to the second two-dimensional point cloud data to obtain second pose information;
and constructing a two-dimensional grid map of the target area according to the second pose information.
Example five
The fifth embodiment of the present invention further provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method as provided by all the inventive embodiments of the present application:
acquiring first two-dimensional point cloud data of a target area at a first moment through a laser radar on a target self-body;
obtaining first pose information of the target self-body according to the first two-dimensional point cloud data;
Predicting second two-dimensional point cloud data obtained by the laser radar when the target is located in the first pose information;
optimizing the first pose information according to the second two-dimensional point cloud data to obtain second pose information;
and constructing a two-dimensional grid map of the target area according to the second pose information.
The computer storage media of embodiments of the present invention may take the form of any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the above embodiments, but may include many other equivalent embodiments without departing from the spirit of the invention, the scope of which is determined by the scope of the appended claims.
Claims (10)
1. The two-dimensional grid map construction method based on the laser radar is characterized by comprising the following steps of:
acquiring first two-dimensional point cloud data of a target area obtained by scanning a laser radar on a target body at a first moment;
obtaining first pose information of the target self-body according to the first two-dimensional point cloud data;
predicting second two-dimensional point cloud data obtained by the laser radar when the target is located in the first pose information;
optimizing the first pose information according to the first two-dimensional point cloud data and the second two-dimensional point cloud data to obtain second pose information;
Constructing a two-dimensional grid map of the target area according to the second pose information;
the optimizing the first pose information according to the second two-dimensional point cloud data to obtain second pose information includes:
defining a mapping relation between the first pose information and the second two-dimensional point cloud data by taking the pose information as an independent variable;
constructing an objective function of the error between the first two-dimensional point cloud data and the second two-dimensional point cloud data according to the mapping relation;
and defining the corresponding pose information as second pose information when the objective function is the minimum value.
2. The method of claim 1, wherein obtaining first two-dimensional point cloud data of the target area scanned by the lidar on the subject at the first time comprises:
when the laser radar on the target self-body is a single-line laser radar, first two-dimensional point cloud data of a target area at a first moment are directly obtained through the laser radar;
the laser radar on the target self-body is a multi-line laser radar, a first laser of a preset emission angle in the multi-line laser radar is confirmed, and point cloud data acquired by the first laser are projected onto a horizontal plane according to the preset emission angle so as to acquire first two-dimensional point cloud data of a target area at a first moment.
3. The method according to claim 1 or 2, wherein the obtaining the first pose information of the target self-body from the first two-dimensional point cloud data comprises:
acquiring third two-dimensional point cloud data of a target area obtained by scanning the laser radar at a second moment, wherein the second moment is the moment before the first moment;
acquiring third pose information of the target at a second moment of the main body;
matching the first two-dimensional point cloud data and the third two-dimensional point cloud data according to an NDT algorithm to obtain a first relative pose relationship between the first moment and the second moment;
and determining first pose information of the target self-body according to the first relative pose relation and the third pose information.
4. The method of claim 3, wherein said matching the first and third two-dimensional point cloud data according to an NDT algorithm to obtain a first relative pose relationship for the first and second moments comprises:
acquiring the moving speed of the target at the second moment of the main body;
predicting fourth pose information of the target at a first moment of the self-body according to the moving speed and the third pose information;
And matching the first two-dimensional point cloud data and the third two-dimensional point cloud data by using an NDT algorithm according to the fourth pose information to obtain a first relative pose relation between the first moment and the second moment.
5. The method of claim 1, 2 or 4, wherein defining the mapping relationship between the first pose information and the second two-dimensional point cloud data using the pose information as an argument comprises:
defining a mapping function f i (x) Wherein f i (x) And (3) representing second two-dimensional point cloud data obtained by theoretical scanning of the laser radar when the pose information is x, wherein x represents the pose information, and i represents the number of times of determining the pose information of the target from the main body.
6. The method of claim 5, wherein constructing an objective function of the error between the first two-dimensional point cloud data and the second two-dimensional point cloud data based on the mapping relationship comprises:
defining an error function e i (x) Wherein e is i (x)＝f i (x)-z i ，e i (x) Is representative of an error, z, between the first two-dimensional point cloud data and the second two-dimensional point cloud data i Representing the first two-dimensional point cloud data;
defining an objective function F (x), wherein
An objective function F (x) is derived from the error function e i (x) And squaring and taking the covariance matrix of the square result to obtain the square result.
7. The method of claim 6, wherein defining the corresponding pose information as the second pose information when the objective function is at a minimum value comprises:
taking the first pose information as an initial value x 0 ；
From the initial value x 0 Starting to iterate the objective function F (x) a plurality of times until F (x) k+1 ) The value of (2) reaches a minimum value, where x k+1 ＝x k +△x k K represents the number of iterations, when Deltax k When the number of the iterations is smaller than the first threshold value, stopping the iteration and x at the moment k As x min The x is min Is the second pose information.
8. The method of claim 1, 2, 4, 6, or 7, wherein predicting second two-dimensional point cloud data obtained by the lidar when the target is autonomous in the first pose information comprises:
acquiring performance parameters of the laser radar and a pre-established two-dimensional environment map;
and predicting second two-dimensional point cloud data obtained by the laser radar when the target is in the first pose information according to the performance parameters and the two-dimensional environment map.
9. A computer-readable storage medium, characterized in that a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 8.
10. A laser radar-based two-dimensional grid map construction system, comprising:
the data acquisition module is used for acquiring first two-dimensional point cloud data of a target area obtained by scanning the laser radar on the target self-body at a first moment;
the pose acquisition module is used for acquiring first pose information of the target self-body according to the first two-dimensional point cloud data;
the data prediction module is used for predicting second two-dimensional point cloud data obtained by the laser radar when the target is located in the first pose information;
the pose optimization module is used for optimizing the first pose information according to the first two-dimensional point cloud data and the second two-dimensional point cloud data to obtain second pose information;
the map construction module is used for constructing a two-dimensional grid map of the target area according to the second pose information;
the pose optimization module further comprises the following functions:
defining a mapping relation between the first pose information and the second two-dimensional point cloud data by taking the pose information as an independent variable;
constructing an objective function of the error between the first two-dimensional point cloud data and the second two-dimensional point cloud data according to the mapping relation;
And defining the corresponding pose information as second pose information when the objective function is the minimum value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211685835.6A CN116106927A (en) | 2020-03-27 | 2020-03-27 | Two-dimensional grid map construction method, medium and system based on laser radar |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211685835.6A CN116106927A (en) | 2020-03-27 | 2020-03-27 | Two-dimensional grid map construction method, medium and system based on laser radar |
| CN202010228792.3A CN111427060B (en) | 2020-03-27 | 2020-03-27 | Two-dimensional grid map construction method and system based on laser radar |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010228792.3A Division CN111427060B (en) | 2020-03-27 | 2020-03-27 | Two-dimensional grid map construction method and system based on laser radar |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116106927A true CN116106927A (en) | 2023-05-12 |
Family
ID=71549006
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211685835.6A Pending CN116106927A (en) | 2020-03-27 | 2020-03-27 | Two-dimensional grid map construction method, medium and system based on laser radar |
| CN202010228792.3A Active CN111427060B (en) | 2020-03-27 | 2020-03-27 | Two-dimensional grid map construction method and system based on laser radar |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010228792.3A Active CN111427060B (en) | 2020-03-27 | 2020-03-27 | Two-dimensional grid map construction method and system based on laser radar |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN116106927A (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111856499B (en) * | 2020-07-30 | 2021-06-18 | 浙江华睿科技有限公司 | Map construction method and device based on laser radar |
| CN112098971B (en) * | 2020-09-16 | 2022-07-15 | 上海商汤临港智能科技有限公司 | Method and device for configuring radar, electronic equipment and storage medium |
| 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 |
| CN112902951A (en) * | 2021-01-21 | 2021-06-04 | 深圳市镭神智能系统有限公司 | Positioning method, device and equipment of driving equipment and storage medium |
| CN112799096B (en) * | 2021-04-08 | 2021-07-13 | 西南交通大学 | Map construction method based on low-cost vehicle-mounted two-dimensional laser radar |
| CN113933861B (en) * | 2021-11-12 | 2022-06-07 | 成都航维智芯科技有限公司 | Airborne laser radar point cloud generation method and system |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108732584B (en) * | 2017-04-17 | 2020-06-30 | 百度在线网络技术（北京）有限公司 | Method and device for updating map |
| CN108917759A (en) * | 2018-04-19 | 2018-11-30 | 电子科技大学 | Mobile robot pose correct algorithm based on multi-level map match |
| CN108921947B (en) * | 2018-07-23 | 2022-06-21 | 百度在线网络技术（北京）有限公司 | Method, device, equipment, storage medium and acquisition entity for generating electronic map |
| CN109901139B (en) * | 2018-12-28 | 2023-07-04 | 文远知行有限公司 | Laser radar calibration method, device, equipment and storage medium |
| CN109870157B (en) * | 2019-02-20 | 2021-11-02 | 苏州风图智能科技有限公司 | Method and device for determining pose of vehicle body and mapping method |
| CN110276834B (en) * | 2019-06-25 | 2023-04-11 | 达闼科技（北京）有限公司 | Construction method of laser point cloud map, terminal and readable storage medium |
| CN110260867B (en) * | 2019-07-29 | 2021-06-15 | 浙江华睿科技有限公司 | Method, equipment and device for determining and correcting neutral position in robot navigation |
-
2020
- 2020-03-27 CN CN202211685835.6A patent/CN116106927A/en active Pending
- 2020-03-27 CN CN202010228792.3A patent/CN111427060B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111427060B (en) | 2023-03-07 |
| CN111427060A (en) | 2020-07-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111427060B (en) | Two-dimensional grid map construction method and system based on laser radar | |
| CN110927740B (en) | Mobile robot positioning method | |
| CN109579849B (en) | Robot positioning method, robot positioning device, robot and computer storage medium | |
| CN109781119B (en) | Laser point cloud positioning method and system | |
| CN114862932B (en) | BIM global positioning-based pose correction method and motion distortion correction method | |
| CN110561420B (en) | Arm profile constraint flexible robot track planning method and device | |
| CN109885073B (en) | Prediction method for free floating motion state of space non-cooperative target | |
| CN115218891B (en) | Autonomous positioning and navigation method for mobile robot | |
| CN116604557A (en) | Double-arm robot cooperative collision avoidance planning optimization method in unstructured environment | |
| CN116681733A (en) | Near-distance real-time pose tracking method for space non-cooperative target | |
| CN115061499B (en) | Unmanned aerial vehicle control method and unmanned aerial vehicle control device | |
| CN114047766B (en) | Mobile robot data acquisition system and method for long-term application of indoor and outdoor scenes | |
| Kitsukawa et al. | Robustness Evaluation of Vehicle Localization in 3D Map Using Convergence of Scan Matching | |
| CN114815899A (en) | Unmanned aerial vehicle three-dimensional space path planning method based on 3D laser radar sensor | |
| CN111504276B (en) | Visual projection scale factor set-based joint target function multi-propeller attitude angle acquisition method | |
| CN112747752A (en) | Vehicle positioning method, device, equipment and storage medium based on laser odometer | |
| He et al. | Indoor Robot SLAM with Multi-Sensor Fusion | |
| CN113129361B (en) | Pose determining method and device for movable equipment | |
| Kaneko et al. | PCD map creation from factory design drawing for LiDAR self-localization of autonomous mobile robot | |
| Xie et al. | Lidar-IMU fusion for 2.5 D mapping | |
| Wang et al. | Limited environmental information path planning based on 3D point cloud reconstruction | |
| Du et al. | Interactive Sensing and Planning for a Quadrotor Vehicle in Partially Known Environments | |
| CN118196192A (en) | Real-time positioning point cloud acquisition method, medium and device for unmanned platform | |
| CN117853548A (en) | Improved NDT method and device based on point cloud state probability estimation | |
| CN118149847A (en) | Method, medium and equipment for generating real-time positioning state of unmanned platform |
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 |