CN115421161A - Unmanned mine car control method based on laser radar ranging - Google Patents
Unmanned mine car control method based on laser radar ranging Download PDFInfo
- Publication number
- CN115421161A CN115421161A CN202211365347.7A CN202211365347A CN115421161A CN 115421161 A CN115421161 A CN 115421161A CN 202211365347 A CN202211365347 A CN 202211365347A CN 115421161 A CN115421161 A CN 115421161A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- scale space
- cloud data
- scale
- data
- 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
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
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
- G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- 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
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Electromagnetism (AREA)
- Aviation & Aerospace Engineering (AREA)
- Automation & Control Theory (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a control method of an unmanned mine car based on laser radar ranging, belonging to the technical field of radio navigation; the method comprises the following steps: acquiring point cloud data of the surrounding environment of the unmanned tramcar; the point cloud data comprises three-dimensional coordinates of all measuring points of the surrounding environment; taking the compression parameter corresponding to the minimum value in all the data quantities as an optimal compression parameter; acquiring compressed data of point cloud data coordinates; sharing and transmitting compressed data comprising point cloud data coordinates, first scale space vertex coordinates and optimal compression parameters to other adjacent running unmanned mine cars; building a road condition model; and controlling the unmanned mine car according to the road condition model. According to the road condition model established, the invention can realize the control of the unmanned mine car to avoid obstacles in advance.
Description
Technical Field
The invention relates to the technical field of radio navigation, in particular to a method for controlling an unmanned mine car based on laser radar ranging.
Background
In the large-scale open-pit mining, along with the continuous expansion of mining scale, the mining depth is explored, the road conditions that the slope is big, the bend is many are gradually increased, the mining degree of difficulty of mine is continuously increased, and the safety of mining area staff is threatened. Therefore, the unmanned mine car can be automatically driven to operate in a dangerous environment, so that the method is an effective way for realizing safe production, and meanwhile, the mining efficiency can be improved, and the labor cost can be reduced.
Existing unmanned systems typically detect the surrounding environment through a lidar on the vehicle. And because the mine slope is big the curve is many, when many unmanned mine cars travel, the front truck utilizes laser radar detectable curve and slope, and the back car probably can not in time detect curve and slope because the front truck shelters from and causes the accident. In order to avoid this situation, the unmanned mine cars need to share lidar ranging data.
The point cloud data of the surrounding environment of the unmanned mine car are obtained through the laser radar, the obtained point cloud data are large in size, and the point cloud data need to be compressed when the unmanned mine cars share transmission in the transmission process. The existing compression methods such as run length coding, huffman coding and the like have high compression efficiency on repeated data, and the point cloud data comprises three-dimensional coordinates of measuring points and intensity information of the measuring points. Run-length Coding (Run-length Coding) replaces a continuous string of the same value with a representative value and a string length, for example, a string "aaabcccdddd", which can be expressed as "3a1b2c5d" after Run-length Coding. The three-dimensional coordinates of each measuring point are different, and the three-dimensional coordinates of the measuring points cannot be compressed by adopting run length coding, huffman coding and the like, so that three-dimensional coordinate information is difficult to share among unmanned mine cars in real time, and the unmanned mine cars are difficult to control in real time and avoid danger urgently.
Disclosure of Invention
In order to solve the defects in the prior art, the invention provides a control method of an unmanned mine car based on laser radar ranging. And controlling the unmanned mine car to avoid obstacles in advance according to the established road condition model.
The invention aims to provide a method for controlling an unmanned mine car based on laser radar ranging, which comprises the following steps:
acquiring point cloud data of the surrounding environment of the unmanned tramcar; the point cloud data comprises three-dimensional coordinates of all measuring points of the surrounding environment; constructing a first scale space with minimum external connection of all measuring points according to the three-dimensional coordinates of all measuring points, and acquiring vertex coordinates of the first scale space;
classifying all the measuring points by using a density peak value clustering algorithm to obtain a plurality of categories of measuring points; acquiring a compression parameter corresponding to each category according to the distribution of all measuring points in each category in a first scale space; wherein the compression parameters comprise the number of three-dimensional divisions of the scale space;
sequentially dividing the first scale space according to each compression parameter until the scale space is smaller than or equal to the size of a preset voxel, and after each division, sequentially marking all the scale spaces after each division according to the scale space mark containing the measuring point as 1 and the scale space mark without the measuring point as 0 to obtain a binary sequence corresponding to the scale space after each division; combining the binary sequences corresponding to all the scale spaces according to the sequence of the scale spaces to obtain compressed data of point cloud data coordinates corresponding to each compression parameter;
acquiring the data volume of compressed data of a point cloud data coordinate corresponding to each compression parameter; acquiring optimal compression parameters according to the data volume of the compressed data of the point cloud data coordinate corresponding to each compression parameter;
the compressed data comprising the optimal compression parameters and point cloud data coordinates corresponding to the optimal compression parameters and a first data compression packet of a first scale space are transmitted to other unmanned mine cars running nearby in a sharing mode;
other unmanned mine cars receive the first data compression packet transmitted by the adjacent running unmanned mine car and build a road condition model after decompression; and controlling the unmanned mine car according to the road condition model.
In one embodiment, the data size of the compressed data of the point cloud data coordinate corresponding to each compression parameter is obtained according to the following steps:
acquiring the corresponding division times of each compression parameter; counting the proportion of the scale space containing the measuring points after each division to all the scale spaces after the division; wherein, in each division process, the scale space containing the measuring points is divided;
and acquiring the data volume of the compressed data of the point cloud data coordinate corresponding to each compression parameter according to each compression parameter, the corresponding division times of each compression parameter and the proportion of the scale space containing the measuring points after each division to all the scale spaces after the division.
In an embodiment, the optimal compression parameter is a compression parameter corresponding to a minimum value among all data amounts.
In an embodiment, the compression parameter corresponding to each category is obtained according to the following steps:
constructing a minimum circumscribed cube of each category according to the three-dimensional coordinates of all the measuring points in each category;
equally dividing the first scale space according to each minimum circumscribed cube serving as a dividing unit to obtain a plurality of minimum circumscribed scale spaces; and dividing the measuring points in each category into 1 to 8 minimum external scale spaces, and obtaining compression parameters corresponding to each category.
In one embodiment, when the measuring points in each category are divided into 1 minimum circumscribed scale space, the number of the three dimensions of the minimum circumscribed cube divided into the three dimensions of the first scale space is used as a first compression parameter corresponding to the category;
when the measuring points in each category are divided into 2 minimum external scale spaces, acquiring one dimension corresponding to the 2 minimum external scale spaces, dividing 2 times of the dimension into the corresponding dimension of the first scale space, and dividing the scales of the other two dimensions into the corresponding two dimensions of the first scale space respectively to serve as second compression parameters corresponding to the category;
when the measuring points in each category are divided into 4 minimum external scale spaces, acquiring two dimensions corresponding to the 4 minimum external scale spaces, and respectively dividing 2 times of the two dimensions into two corresponding dimensions of the first scale space and dividing the dimensions of the other one dimension into one corresponding dimension of the first scale space as third compression parameters corresponding to the category;
when the measuring points in each category are divided into 8 minimum circumscribed scale spaces, three dimensions corresponding to the 8 minimum circumscribed scale spaces are obtained, and the number of division of 2 times of the three dimensions to the corresponding three dimensions of the first scale space is used as a fourth compression parameter corresponding to the category.
In one embodiment, the point cloud data further comprises intensity information of each measuring point;
obtaining a final scale space according to the scale space which is divided to be less than or equal to the size of the preset voxel;
sequencing the intensity information of each measuring point according to the sequence of 1 in the binary sequence corresponding to the final scale space, and compressing by using a run length coding method to obtain compressed data of the point cloud data intensity;
sharing and transmitting compressed data including the point cloud data intensity, compressed data of point cloud data coordinates corresponding to the optimal compression parameters, first scale space vertex coordinates and second data compression packets of the optimal compression parameters to other unmanned mine cars running nearby;
other unmanned mine cars receive and decompress second data compression packets transmitted by the neighboring running unmanned mine cars and then construct a road condition model; and controlling the unmanned mine car according to the road condition model.
In one embodiment, the second data compression packet transmitted to other neighboring unmanned tramcars also includes GPS positioning information and coordinate system direction information of the point cloud data coordinate origin.
In one embodiment, the road condition model is constructed according to the following steps:
decompressing the second data compression packet to obtain compressed data of the intensity of the point cloud data, compressed data of point cloud data coordinates corresponding to the optimal compression parameters, first scale space vertex coordinates, the optimal compression parameters, GPS positioning information of point cloud data coordinate origin and coordinate system direction information;
establishing a coordinate system according to the direction information of the coordinate system; establishing a first scale space according to the vertex coordinates and the coordinate system of the first scale space;
sequentially reducing the measuring points into a first scale space according to compressed data of the decompressed point cloud data coordinates, and acquiring three-dimensional coordinates of all the decompressed measuring points;
decompressing compressed data of the point cloud data intensity by using a run length decoding method to obtain intensity information of each measuring point of the point cloud data, and corresponding the intensity information of the measuring point to coordinates of the measuring point in the point cloud data one by one to obtain the point cloud data;
and integrating the decompressed point cloud data and the point cloud data detected by the current unmanned mine car according to the GPS positioning information of the point cloud data coordinate origin, and constructing a road condition model by using the integrated point cloud data.
The invention has the beneficial effects that:
according to the unmanned mine car control method based on laser radar ranging, point cloud data of the surrounding environment of the mine car are obtained through the laser radar mounted on the unmanned mine car, compression transmission is carried out on the point cloud data, and data sharing among different unmanned mine cars is achieved. And the unmanned mine car carries out road condition modeling according to the received point cloud data, so that the unmanned mine car has a larger 'visual field', and the unmanned mine car is controlled to avoid obstacles in advance according to the established road condition model. The method for dividing the scale space is adopted, the compression of the three-dimensional coordinate data of the measuring points is realized, the optimal compression parameters are obtained through self-adaptation, and the highest compression efficiency of the method for dividing the scale space can be achieved. Compared with the conventional compression methods such as run length coding and Huffman coding, the compression method of the three-dimensional coordinate data of the measuring points has high compression efficiency and high compression speed. Meanwhile, coordinate data of measuring points in different areas can be decompressed in parallel, and the decompression speed is high.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic flow chart showing the general steps of an embodiment of a method for controlling an unmanned mining vehicle based on lidar ranging according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, 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 invention.
The specific scenes aimed by the invention are as follows: because the mine has a plurality of curves with large gradient, when a plurality of unmanned mine cars run, the front car can detect the curves and the gradient by utilizing the laser radar, and the rear car can cause accidents because the front car is shielded and can not detect the curves and the gradient in time. In order to avoid the situation, the unmanned mine cars need to share laser radar ranging data. According to the invention, the point cloud data of the surrounding environment of the mine car is obtained through the laser radar loaded on the unmanned mine car, and is compressed and transmitted, so that data sharing among different unmanned mine cars is realized. And the unmanned mine car carries out road condition modeling according to the received point cloud data, so that the unmanned mine car has a larger 'visual field', and the unmanned mine car is controlled to avoid obstacles in advance according to the established road condition model. The existing compression methods such as run length coding, huffman coding and the like have high compression efficiency on repeated data, and the point cloud data comprises three-dimensional coordinates of measuring points and the intensity of the measuring points. The three-dimensional coordinates of each measuring point are different, and the three-dimensional coordinates of the measuring points cannot be compressed by adopting run length coding, huffman coding and the like. The method for dividing the scale space is adopted, the compression of the three-dimensional coordinate data of the measuring points is realized, the optimal compression parameters are obtained through self-adaption, and the highest compression efficiency of the method for dividing the scale space can be achieved. Compared with the existing compression method, the compression method for the three-dimensional coordinate data of the measuring points has high compression efficiency and high compression speed. Meanwhile, coordinate data of measuring points in different regions can be decompressed in parallel, and the decompression speed is high.
According to the method, a laser radar detection system carried on the unmanned mine car is mainly utilized to carry out laser radar ranging on the surrounding environment, the obtained point cloud data is compressed and transmitted, data sharing among different unmanned mine cars is realized, and the unmanned mine car carries out road condition modeling according to the received point cloud data. And controlling the unmanned mine car to avoid obstacles in advance according to the established road condition model.
The invention provides a method for controlling an unmanned mine car based on laser radar ranging, which is shown in figure 1 and comprises the following steps:
s1, point cloud data of the surrounding environment of the unmanned mine car are obtained; the point cloud data comprises three-dimensional coordinates of all measuring points of the surrounding environment; constructing a first scale space with minimum external connection of all measuring points according to the three-dimensional coordinates of all measuring points, and acquiring vertex coordinates of the first scale space; the method comprises the steps of acquiring point cloud data of the surrounding environment of the unmanned mine car, wherein the detecting of the surrounding environment of the unmanned mine car is carried out through each laser radar carried on the unmanned mine car, and the point cloud data are acquired; the point cloud data comprises three-dimensional coordinates of each measuring point of the unmanned mine car surrounding environment by each laser radar; and the measuring point refers to a point for detecting the surrounding environment of the unmanned mine car by using a laser radar carried on the unmanned mine car.
In the embodiment, when the unmanned mine car runs, the surrounding environment of the unmanned mine car is detected by the laser radar in each direction carried on the unmanned mine car to obtain point cloud data; the point cloud data comprise three-dimensional coordinates X, Y and Z of each measuring point corresponding to each laser radar and intensity information of each measuring point;
it should be noted that the intensity information of each measurement point refers to the degree of reflection of a laser beam emitted by the lidar to a measurement point. A greater degree of back reflection indicates a more pronounced obstruction.
S2, constructing a compression model;
constructing a first scale space according to the three-dimensional coordinates of all the measuring points, wherein all the measuring points are in the first scale space;
it should be noted that, since the amount of point cloud data is very large, compressed transmission is required. The existing compression methods such as run length coding, huffman coding and the like have high compression efficiency on repeated data, and point cloud data comprises three-dimensional coordinates of measuring points. The three-dimensional coordinates of each measuring point are different, and the three-dimensional coordinates of the measuring points cannot be compressed by adopting run length coding, huffman coding and the like. In the embodiment, the optimal division parameter is acquired in a self-adaptive manner by a self-adaptive space division compression method, so that the compression efficiency is higher.
In this embodiment, the adaptive space is specifically established as follows:
firstly, three-dimensional coordinates of all measuring points are obtained
Maximum and minimum values of coordinates
、
；
Maximum and minimum values of coordinates
、
；
Maximum and minimum values of coordinates
、
. Establishing vertex coordinates of
、
、
、
、
、
、
、
Is long as
Width is
High is
A cubic space of (a); all the measuring points are distributed in the three-dimensional space, and the three-dimensional space is called as a first scale space;
manually and empirically setting a compressed essenceDegree of rotation
I.e. the voxel size, and the smallest partition unit of the three-dimensional space. The point cloud data is down-sampled according to the voxel size, so that each voxel only contains one point at most.
Secondly, the first scale space is equally divided into
Portioning to obtain
The second scale spaces are used for judging whether the measuring points after the down sampling exist in each second scale space, if so, the second scale spaces are marked as 1, and if not, the second scale spaces are marked as 0; all the marks of the second scale space together form a length of
A binary sequence of (a); the proportion of the second scale space with the statistical mark of 1 to all the second scale spaces
；
All the second scale spaces marked as 1 are processed
Equally dividing, and obtaining a second scale space marked as 1
A third scale space, all the second scale spaces marked as 1 are obtained together
A third scale space; judging whether each third scale space has a measuring point after down sampling, if yes, marking as 1, and if not, marking as 0; all the marks in the third scale space together form a length of
A binary sequence of (a); the proportion of the third scale space with the statistical mark of 1 to all the third scale spaces
；
By the same way, obtain
A first one
Scale space, get the 1 st
The scale space occupies all the
Scale of scale space
Wherein, in the step (A),
(ii) a Repeating the operation until the obtained scale space is less than or equal to the size of the voxel, and setting the scale space at the moment as the final scale space, namely the first scale space
A scale space; at this time, the coordinate information of all the measuring points after the down-sampling can be represented by the binary sequences with all the scales, and the binary sequences of all the scale spaces are the three-dimensional coordinate compressed data of all the measuring points after the down-sampling; the data amount of the three-dimensional coordinate compression data is
The calculation formula is as follows:
wherein, S represents the data amount of the three-dimensional coordinate compressed data;
is a first
The number of scale spaces, i.e. in
Obtained after the subdivision;
representing the data volume of the three-dimensional coordinate compressed data of all the measuring points, namely the length of a binary sequence formed by combining the binary sequences corresponding to all the scale spaces after each division according to the order of the scale spaces;
representing the number of equal divisions of the scale space;
representing the proportion of the second scale space marked as 1 to all the second scale spaces;
the third scale space marked as 1 accounts for the proportion of all the third scale spaces;
denotes the second labeled 1
The scale space occupies all the
Scale of scale space。
Directly dividing a first scale space into a space with the size of a third scale space, wherein the space comprises the proportion of the number of space of measuring points;
to directly divide the first scale space into
The space of the dimension space comprises the space number of the measuring points;
wherein the amount of data
The calculation formula can also be understood as: first item
Representing the number of second scale spaces obtained after the first scale space is divided for the first time; second item
Representing the number of third scale spaces obtained after the second division of all the second scale spaces marked as 1; last item
Denotes the second labeled 1
The scale space is in
Obtained after subdivision
The number of scale spaces.
Note that the number of equally divided scale spaces is
A smaller value means that the number of next scale spaces obtained by the division is smaller, and at this time, the next scale space having the measurement point in the next scale space has a larger proportion, that is, the next scale space marked as 1 occupies a larger proportion of all the next scale spaces, that is, the above formula is given
、
Is large; at the same time, the number of the scales is divided equally
When smaller, more equal divisions are required to achieve a maximum scale space of less than or equal to the voxel size, i.e., in the above equation
Is large; otherwise, when the scale space is divided equally
When the ratio of the next scale space to the next scale space is larger, the next scale space with the measuring points in the next scale space is smaller, namely the ratio of the next scale space marked as 1 to all the next scale spaces is smaller, namely the following scale spaces in the formula
Is relatively small. At the same time, the number of the equal division of the scale space is calculated
When the size is larger, the maximum scale space can reach the size less than or equal to the voxel size through fewer times of equal division, namely the formula
Is relatively small. In conclusion, when
When the ratio of the water to the oil is small,
、
、
、
is relatively large. When in use
When the size of the particles is larger than the required size,
is relatively small. And the data amount of the three-dimensional coordinate compressed data of the measuring point
And with
、
、
、
And
and (4) correlating. To achieve better compression effect, the data volume of the three-dimensional coordinate compression data of the measuring points is compressed
Minimum, need to find the optimum
To perform an aliquot of the scale space. Dividing the scale space equally into
Portion is related to
、
、
Division of dimension into
、
、
The division number of the dimension is respectively recorded as
、
、
. The number of divisions at a time is
. Will be provided with
、
、
I.e. the compression parameters. Therefore, by constructing the compression model, the point cloud data can be compressed in different regions, and higher compression efficiency can be achieved compared with the prior compression technology.
S3, acquiring a compression parameter candidate set;
obtaining a plurality of categories of measuring points from all measuring points by using a density peak value clustering algorithm;
constructing a minimum circumscribed cube of each category according to the three-dimensional coordinates of all the measuring points in each category;
equally dividing the first scale space according to each minimum circumscribed cube serving as a dividing unit to obtain a plurality of minimum circumscribed scale spaces;
dividing the measuring points in each category into 1 to 8 minimum external scale spaces, and acquiring compression parameters corresponding to each category; wherein the compression parameter is the number of three-dimensional divisions of the scale space; e.g. for the first scale space
The number of dimension divisions is
，
The number of dimension divisions is
，
The number of dimension divisions is
Then the number of three-dimensional partitions is
、
、
I.e. the compression parameters.
In this embodiment, the compression parameters for obtaining the optimal compression are
、
、
Firstly, acquiring a compression parameter candidate data set at a first scale space position by combining all measuring points; the method comprises the following specific steps:
it should be noted that, the three-dimensional coordinates of all the measuring points after the following sampling are used as sample data, and the sample data is clustered by using a density peak value clustering algorithm to obtain the sample data
And (4) each category. Measuring points of each category are concentrated, and measuring points of different categories are far away, so that blank areas exist among different categories; when the first scale space is equalized, one category is divided into one or more second scale spaces, and when blank areas among different categories are divided into other second scale spaces, a better compression effect can be achieved.
Get the first
In three-dimensional coordinates of all measuring points of each category
Maximum and minimum values of coordinates
、
；
Maximum and minimum values of coordinates
、
(ii) a And
maximum and minimum values of coordinates
、
(ii) a Construction of the first
A minimum bounding cube of individual categories. The vertex coordinate of the minimum circumscribed cube is
，
，
，
，
，
，
，
Is long as
Wide is
High is
。
Wherein, the compression parameter corresponding to each category is obtained according to the following steps:
when the measuring points in each category are divided into 1 minimum circumscribed scale space, dividing the three dimensions of the minimum circumscribed cube into three dimensions of the first scale space respectively, and taking the three dimensions of the minimum circumscribed cube as first compression parameters corresponding to the category;
when the measuring points in each category are divided into 2 minimum external scale spaces, acquiring one dimension corresponding to the 2 minimum external scale spaces, dividing 2 times of the dimension into the corresponding dimension of the first scale space, and dividing the scales of the other two dimensions into the corresponding two dimensions of the first scale space respectively to serve as second compression parameters corresponding to the category;
when the measuring points in each category are divided into 4 minimum external scale spaces, acquiring two dimensions corresponding to the 4 minimum external scale spaces, dividing 2 times of the two dimensions into two corresponding dimensions of the first scale space, and dividing the dimensions of the other dimension into one corresponding dimension of the first scale space as third compression parameters corresponding to the category;
when the measuring points in each category are divided into 8 minimum circumscribed scale spaces, three dimensions corresponding to the 8 minimum circumscribed scale spaces are obtained, and the number of the three dimensions which are 2 times of the number of the three dimensions corresponding to the first scale space is used as a fourth compression parameter corresponding to the category.
In this embodiment, assume that
The size of the minimum bounding cube of each category is used for equally dividing the first scale space, and the size of the first scale space is required to be equally divided
Dimension division
The preparation method comprises the following steps of (1),
dimension division
The weight portions of the raw materials are counted,
dimension division
Preparing; wherein the content of the first and second substances,
indicating a rounding down. By using the first
The category minimum circumscribed cube is used as a dividing unit to equally divide the first scale space to obtain a plurality of second scale spaces
A minimum circumscribed scale space corresponding to each category; that is to say that
、
、
Dividing the first scale space as a compression parameter, equally dividing three dimensions corresponding to the first scale space to obtain a plurality of second scale spaces
The minimum circumscribed scale space corresponding to each category may actually be
Classification of a category of minimal bounding cubes into
A plurality of,
A plurality of,
Or is
Within a minimum circumscribed scale space.
According to the first
The vertex of the minimum external cube of each category is judged to be
Under the parameters of
How many minimum circumscribed scale spaces the minimum bounding cubes of a category are divided into;
if it is first
The minimum bounding cubes of each class are divided into 1 minimum bounding scale space, then
Is the first
The compression parameters with optimal categories; namely, the number of the three dimensions of the minimum circumscribed cube divided into the three dimensions of the first scale space is taken as the number
Recording first compression parameters corresponding to the categories as optimal compression parameters;
if it is first
Dividing the minimum bounding cube of each category into 2 minimum bounding dimension spaces, and judging the second
Dividing each category into two second scale spaces in which dimension, multiplying the division number of the dimension by 2, and combining the division numbers of the other two dimensions to be used as the second scale space
The compression parameters with optimal categories; that is, one dimension divided into 2 minimum external scale spaces is obtained, 2 times of the number of the corresponding dimension division of the dimension on the first scale space and the number of the corresponding two dimension division of the scales of the other two dimensions on the first scale space are taken as the first dimension
The second compression parameters corresponding to the categories are the optimal compression parameters;
if it is first
Dividing the minimum bounding cube of each category into 4 minimum bounding scale spaces, and judging the first
Dividing each category into 4 second scale spaces in two dimensions, multiplying the division number of the two dimensions by 2 respectively, and combining the division number of the other dimension to be used as the first scale space
The compression parameters with optimal categories; that is, two dimensions corresponding to 4 minimum external scale spaces are obtained, and 2 times of the two dimensions are respectively divided into two corresponding dimensions of the first scale space, and the other dimensions are respectively divided into one corresponding dimension of the first scale space as the first scale space
The third compression parameter corresponding to each category is the optimal compression parameter;
if it is first
The minimum bounding cubes of the classes are divided into 8 minimum bounding scale spaces, then
、
、
Is as follows
The compression parameters with optimal categories; namely, three dimensions corresponding to the three dimensions divided into 8 minimum external scale spaces are obtained, and the number of the three dimensions divided into the three dimensions corresponding to the first scale space by 2 times is respectively used as the number of the three dimensions divided into the three dimensions corresponding to the first scale space
The fourth compression parameter corresponding to each category is the optimal compression parameter;
will be first
The compression parameters of the optimal class are recorded as
、
、
。
And similarly, acquiring the optimal compression parameter corresponding to each category, and taking the optimal compression parameters of all the categories as a compression parameter candidate set. By constructing the minimum circumscribed cube for each category, the optimal compression parameters of the current category, i.e., the locally optimal solution of the compression model of the present embodiment, can be obtained. By constructing the compression parameter candidate set, the acquisition range of the optimal compression parameters is greatly reduced, so that the global optimal solution, namely the optimal compression parameters, can be acquired according to the local optimal solution more quickly in the follow-up process. So that the compression speed is further increased.
S4, obtaining an optimal compression parameter;
according to each compression parameter, sequentially dividing the first scale space until the scale space is smaller than or equal to the size of a preset voxel, and stopping, and acquiring the data volume of the three-dimensional coordinate compression data of all the measuring points corresponding to each compression parameter; taking the compression parameter corresponding to the minimum value in all the data quantities as an optimal compression parameter;
the data volume of the compressed data of the point cloud data coordinate corresponding to each compression parameter is obtained according to the following steps:
acquiring the corresponding division times of each compression parameter; counting the proportion of the scale space containing the measuring points after each division to all the scale spaces after the division; wherein, in each division process, the scale space containing the measuring points is divided;
and acquiring the data volume of the compressed data of the point cloud data coordinate corresponding to each compression parameter according to each compression parameter, the corresponding division times of each compression parameter and the proportion of the scale space containing the measuring points after each division to all the scale spaces after the division.
In this embodiment, first, according to the compression parameter candidate set obtained in S3, the first compression parameter candidate set is used
A compression parameter
、
、
For example, the number of times that the partition is needed under the current compression parameters is calculated
I.e. the label of the scale space when the division is stopped; since the rule of division is to stop until the obtained scale space is voxel size or less, the first scale space is first calculated
Dimension division into less than voxel space
Number of dimensions
The calculation formula is as follows:
in the formula (I), the compound is shown in the specification,
is a first scale space
The size of the dimension;
is a voxel
The size of the dimension;
being a space of a first dimension
Dimension division
The number of sizes;
being a first scale space
Dimension division to less than voxel space
The number of times the dimension is large;
to compressIn the parameter
Compression parameters of the dimensions;
indicating rounding up.
similarly, a first scale space is obtained
Dimension partitioning into less-than-voxel spaces
Number of dimensions
The calculation formula is as follows:
in the formula,
is a first scale space
The size of the dimension;
is a voxel
The size of the dimension;
being a first scale space
Dimension division
The number of sizes;
being a first scale space
Dimension division into less than voxel space
The number of times the dimension is large;
as in the compression parameters
Compression parameters of the dimensions;
Similarly, a first scale space is obtained
Dimension division to less than voxel space
Number of times of dimension
The calculation formula is as follows:
in the formula (I), the compound is shown in the specification,
is a first scale space
The size of the dimension;
is a voxel
The size of the dimension;
being a space of a first dimension
Dimension division
The number of sizes;
being a first scale space
Dimension division into less than voxel space
The number of dimensions;
as in the compression parameters
Compression parameters of the dimensions;
indicating rounding up.
if the scale space obtained by the final division is less than or equal to the voxel size, the division times are required to be equal to
Next, the process is carried out.
Secondly, at the second place
A compression parameter
、
、
The number of divisions is
(ii) a The data amount of the compressed data is:
which is
Is shown in
A compression parameter
、
、
By passing
Division of the next step into
When the scale space is used as the final scale space, acquiring the data volume of the three-dimensional coordinate compressed data of all the measuring points; wherein the number of divisions at a time is
；
Representing the proportion marked as 1 in the second scale space, namely the number of the second scale spaces containing points in the second scale space;
representing the proportion marked as 1 in a third scale space divided by the second scale space marked as 1, then
Directly dividing a first scale space into a space with a size of a third scale space, wherein the space contains the proportion of the number of scale spaces of measuring points; in the same way, the method for preparing the composite material,
to directly divide the first scale space into
The scale space comprises the proportion of the number of the scale spaces of the measuring points.
Thus, the first scale space is carried out
Of dimensions of
The components are divided into equal parts, and the components are,
of dimensions of
The components are divided into equal parts, and the components are,
of dimensions
Is divided into equal parts to obtain
Counting the ratio of the scale space containing the measuring points to obtain
. Subjecting the first scale space to
Of dimensions of
The components are divided into equal parts, and the components are,
of dimensions of
The components are divided into equal parts, and the components are,
of dimensions of
Is divided equally to obtain
A space, the proportion of the space containing the points is counted to obtain
. By the same way, obtain
，…，
. Can be obtained at
A compression parameter
、
、
Data volume of compressed data
. Obtaining
、
、
，…，
The process of (2) can be calculated in parallel, and the efficiency is improved.
And similarly, acquiring the data volume of the compressed data under each compression parameter. And the compression parameter corresponding to the minimum value of the data quantity of the compressed data is the optimal compression parameter.
By obtaining the optimal compression parameters, the compression efficiency of the three-dimensional point cloud coordinate data is higher. Meanwhile, data in the process of obtaining the optimal compression parameters can be obtained through parallel calculation, so that the compression speed is high.
S5, carrying out compression transmission on the point cloud data;
sequentially dividing the first scale space into scale spaces smaller than or equal to the size of a preset voxel according to the optimal compression parameters, and stopping, wherein the scale spaces are the final scale spaces; after each division, marking all the scale spaces after each division according to the scale space mark containing the measuring points as 1 and the scale space mark without the measuring points as 0 to obtain a binary sequence corresponding to the scale space after each division; combining the binary sequences corresponding to all the scale spaces after each division according to the sequence of the scale spaces to obtain compressed data of the point cloud data coordinates; dividing a scale space marked as 1 in each division;
sharing and transmitting compressed data comprising point cloud data coordinates, first scale space vertex coordinates and optimal compression parameters to other adjacent running unmanned mine cars;
in the present embodiment, the optimum compression parameter obtained according to S4
、
、
Performing the step in S2 on the first scale space
Of dimensions
The components are divided into equal parts, and the components are,
of dimensions
Is divided equally，
Of dimensions
Dividing equally; to obtain
And judging whether the point cloud data after down sampling exists in each second scale space, if so, marking the point cloud data as 1, and otherwise, marking the point cloud data as 0. All the marks of the second scale space obtain a binary sequence;
all the second scale spaces marked with 1 are processed
Of dimensions
The components are divided into equal parts, and the equal parts are,
of dimensions
The components are divided into equal parts, and the components are,
of dimensions of
Dividing equally; obtaining a second scale space of each mark
A third scale space; judging whether the point cloud data after down sampling exists in each third scale space, if yes, marking the point cloud data as 1, and if not, marking the point cloud data as 0; acquiring a third scale space mark to obtain a binary sequence;
and similarly, repeating the operation of dividing the scale space until the obtained scaleStopping when the space is equal to or less than the voxel size, and recording the scale space at that time as the second
A scale space; combining the binary sequences obtained by all the scale spaces according to the sequence of the scale spaces to obtain compressed data of the point cloud data coordinates; in the process that the binary sequences obtained from all the scale spaces are combined according to the order of the scale spaces, firstly, the mark of the second scale space is placed to obtain a binary sequence, secondly, the mark of the third scale space is placed to obtain a binary sequence, the binary sequence is arranged according to the order of the mark of the second scale space being 1, and so on, the binary sequence is arranged from the second scale space to the third scale space
Arranging and combining all binary sequences in the scale space to obtain a longer binary sequence formed by combining a plurality of binary sequences, namely compressed data of point cloud data coordinates corresponding to the optimal compression parameters;
compressed data comprising point cloud data coordinates corresponding to the optimal compression parameters, first scale space vertex coordinates and first data compression packets of the optimal compression parameters are shared and transmitted to other unmanned tramcars running nearby;
in this embodiment, the point cloud data further includes intensity information of each measurement point;
obtaining a final scale space according to the scale space which is divided to be less than or equal to the size of the preset voxel;
sorting the intensity information of each measuring point according to the sequence of 1 in the binary sequence corresponding to the final scale space, and compressing by using a run length coding method to obtain compressed data of the intensity of the point cloud data;
sharing and transmitting compressed data including the point cloud data intensity, compressed data of point cloud data coordinates corresponding to the optimal compression parameters, first scale space vertex coordinates and second data compression packets of the optimal compression parameters to other unmanned mine cars running nearby;
and the second data compression packet which is transmitted to other unmanned mine cars running nearby in a shared mode also comprises GPS positioning information of a point cloud data coordinate origin and coordinate system direction information.
Therefore, in the embodiment, compressed data comprising point cloud data coordinates corresponding to the optimal compression parameters, first scale space vertex coordinates, the optimal compression parameters, compressed data of point cloud data intensity, GPS positioning information of point cloud data coordinate origin and coordinate system direction information are shared and transmitted to other unmanned mine cars running nearby; it should be noted that the coordinate system direction information is a coordinate system direction set when the first scale space is established; the point cloud data coordinate origin refers to the origin of the first scale space in the set coordinate system, so that the position information of each point in the first scale space can be determined by acquiring the GPS positioning information of the origin.
Thus, the compression and transmission of the point cloud data are completed.
It should be noted that, in this embodiment, a scale space segmentation method is adopted, so that compression of three-dimensional point cloud coordinate data is achieved, and the highest compression efficiency of the scale space segmentation method can be achieved by obtaining optimal compression parameters through self-adaptation. Compared with the existing compression method, the compression method for the three-dimensional point coordinate data has the advantages of high compression efficiency and high compression speed. Meanwhile, coordinate data of different region points can be decompressed in parallel, and the decompression speed is high.
S6, establishing a road condition model according to the point cloud data, and controlling the unmanned mine car to avoid obstacles in advance;
other unmanned mine cars receive compressed data which are transmitted by the adjacent running unmanned mine cars and comprise point cloud data intensity, compressed data of point cloud data coordinates corresponding to the optimal compression parameters, first scale space vertex coordinates and second data compression packets of the optimal compression parameters, and build a road condition model after decompression; and controlling the unmanned mine car according to the road condition model.
The road condition model is constructed according to the following steps:
decompressing the second data compression packet to obtain compressed data of the intensity of the point cloud data, compressed data of point cloud data coordinates corresponding to the optimal compression parameters, first scale space vertex coordinates, the optimal compression parameters, GPS positioning information of point cloud data coordinate origin and coordinate system direction information;
establishing a coordinate system according to the direction information of the coordinate system; establishing a first scale space according to the vertex coordinates and the coordinate system of the first scale space;
sequentially reducing each measuring point to a first scale space according to compressed data of the decompressed point cloud data coordinates, and acquiring three-dimensional coordinates of all the decompressed measuring points;
decompressing compressed data of the point cloud data intensity by using a run length decoding method to obtain intensity information of each measuring point of the point cloud data, and corresponding the intensity information of the measuring point to coordinates of the measuring point in the point cloud data one by one to obtain the point cloud data;
and integrating the decompressed point cloud data with the point cloud data detected by the unmanned mine car according to the GPS positioning information of the point cloud data coordinate origin, and constructing a road condition model by using the integrated point cloud data.
In this embodiment, the road condition model is built by other unmanned mine cars according to the received point cloud data transmitted by the neighboring mine cars, which is specifically as follows:
the other unmanned tramcars receive the compressed point cloud data and decompress the data at first; establishing a coordinate system according to coordinate system direction information, establishing a first scale space according to a first scale space vertex coordinate, dividing the first scale space according to a compression parameter to obtain a second scale space, marking the second scale space according to a compressed data binary sequence of a point cloud data coordinate, and dividing the second scale space marked as 1 according to the compression parameter to obtain a third scale space; in the same way, get the first
A scale space; labeled as 1 st
The scale space is the position of the measuring point after down sampling; by the number 1
And the coordinates of the central point of the scale space are used as the coordinates of the measuring point after down sampling.
Decompressing compressed data of the point cloud data intensity by using a run length decoding method to obtain intensity information of each measuring point of the point cloud data, and corresponding the intensity of the measuring point to coordinates of the measuring point in the point cloud data one by one to obtain the point cloud data; thus, the decompression of the point cloud data is completed;
integrating the decompressed point cloud data and the point cloud data detected by the current unmanned mine car according to the GPS positioning information of the point cloud data coordinate origin, and establishing a road condition model by using the integrated point cloud data;
and identifying the obstacles, the curves and the ramps on the driving route of the unmanned mine car according to the road condition model, and planning the driving route in advance according to the identified obstacles, curves and ramps.
For example: the unmanned mine car of adjacent front and back that is in the same route in-process of traveling, the unmanned mine car at adjacent rear can carry out coordinate system integration through the point cloud data of unmanned mine car transmission in adjacent the place ahead and the point cloud data that self detected and construct road conditions simulation, can be time under the condition that adjacent rear unmanned mine car can't detect place ahead road conditions information, can judge according to the point cloud data of unmanned mine car transmission in adjacent the place ahead, can be in advance to barrier and bend, the ramp is discerned, thereby realized planning the route of traveling in advance, make unmanned mine car have bigger "field of vision", and then control unmanned mine car keeps away the barrier in advance.
In conclusion, according to the unmanned mine car control method based on laser radar ranging, the point cloud data obtained by laser radar ranging is compressed and transmitted, and data sharing among different unmanned mine cars is achieved. And the unmanned mine car carries out road condition modeling according to the received point cloud data, so that the unmanned mine car has a larger 'visual field', and the unmanned mine car is controlled to avoid obstacles in advance according to the established road condition model. The method for dividing the scale space is adopted, the compression of the three-dimensional coordinate data of the measuring points is realized, the optimal compression parameters are obtained through self-adaption, and the highest compression efficiency of the method for dividing the scale space can be achieved. Compared with the conventional compression methods such as run length coding and Huffman coding, the compression method of the three-dimensional coordinate data of the measuring points has high compression efficiency and high compression speed. Meanwhile, coordinate data of measuring points in different regions can be decompressed in parallel, and the decompression speed is high.
The present invention is not limited to the above preferred embodiments, and any modifications, equivalent substitutions, improvements, etc. within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A control method of an unmanned mine car based on laser radar ranging is characterized by comprising the following steps:
acquiring point cloud data of the surrounding environment of the unmanned tramcar; the point cloud data comprises three-dimensional coordinates of all measuring points of the surrounding environment; constructing a first scale space of the minimum external connection of all the measuring points according to the three-dimensional coordinates of all the measuring points, and acquiring the vertex coordinates of the first scale space;
classifying all the measuring points by using a density peak value clustering algorithm to obtain a plurality of categories of measuring points; acquiring a compression parameter corresponding to each category according to the distribution of all measuring points in each category in a first scale space; wherein the compression parameters comprise the number of three-dimensional partitions of the scale space;
sequentially dividing the first scale space according to each compression parameter until the scale space is smaller than or equal to the size of a preset voxel, and after each division, sequentially marking all the scale spaces after each division according to the scale space mark containing the measuring point as 1 and the scale space mark without the measuring point as 0 to obtain a binary sequence corresponding to the scale space after each division; combining the binary sequences corresponding to all the scale spaces according to the sequence of the scale spaces to obtain compressed data of point cloud data coordinates corresponding to each compression parameter;
acquiring the data volume of compressed data of a point cloud data coordinate corresponding to each compression parameter; acquiring optimal compression parameters according to the data volume of the compressed data of the point cloud data coordinate corresponding to each compression parameter;
the compressed data comprising the optimal compression parameters and point cloud data coordinates corresponding to the optimal compression parameters and a first data compression packet of a first scale space are shared and transmitted to other unmanned tramcars running nearby;
other unmanned mine cars receive the first data compression packet transmitted by the adjacent running unmanned mine car and build a road condition model after decompression; and controlling the unmanned mine car according to the road condition model.
2. The unmanned mine car control method based on laser radar ranging as claimed in claim 1, wherein the data volume of the compressed data of each compressed parameter corresponding to the point cloud data coordinate is obtained according to the following steps:
acquiring the corresponding division times of each compression parameter; counting the proportion of the scale space containing the measuring points after each division to all the scale spaces after the division; in each dividing process, dividing a scale space containing measuring points;
and acquiring the data volume of the compressed data of the point cloud data coordinate corresponding to each compression parameter according to each compression parameter, the corresponding division times of each compression parameter and the proportion of the scale space containing the measuring points after each division to all the scale spaces after the division.
3. The unmanned mining vehicle control method based on laser radar ranging as claimed in claim 2, wherein the optimal compression parameter is a compression parameter corresponding to the minimum value of all data quantities.
4. The unmanned mine car control method based on laser radar ranging as claimed in claim 1, wherein the compression parameters corresponding to each category are obtained according to the following steps:
constructing a minimum circumscribed cube of each category according to the three-dimensional coordinates of all the measuring points in each category;
equally dividing the first scale space according to each minimum circumscribed cube serving as a dividing unit to obtain a plurality of minimum circumscribed scale spaces; and dividing the measuring points in each category into 1 to 8 minimum external scale spaces, and obtaining compression parameters corresponding to each category.
5. The unmanned mine car control method based on laser radar ranging as in claim 4,
when the measuring points in each category are divided into 1 minimum circumscribed scale space, dividing the three dimensions of the minimum circumscribed cube into three dimensions of the first scale space respectively, and taking the three dimensions of the minimum circumscribed cube as first compression parameters corresponding to the category;
when the measuring points in each category are divided into 2 minimum external scale spaces, acquiring one dimension corresponding to the 2 minimum external scale spaces, dividing 2 times of the dimension into the corresponding dimension of the first scale space, and dividing the scales of the other two dimensions into the corresponding two dimensions of the first scale space respectively to serve as second compression parameters corresponding to the category;
when the measuring points in each category are divided into 4 minimum external scale spaces, acquiring two dimensions corresponding to the 4 minimum external scale spaces, dividing 2 times of the two dimensions into two corresponding dimensions of the first scale space, and dividing the dimensions of the other dimension into one corresponding dimension of the first scale space as third compression parameters corresponding to the category;
when the measuring points in each category are divided into 8 minimum circumscribed scale spaces, three dimensions corresponding to the 8 minimum circumscribed scale spaces are obtained, and the number of division of 2 times of the three dimensions to the corresponding three dimensions of the first scale space is used as a fourth compression parameter corresponding to the category.
6. The unmanned mine car control method based on laser radar ranging as in claim 1, wherein the point cloud data further comprises intensity information of each measuring point;
obtaining a final scale space according to the scale space which is divided to be less than or equal to the size of the preset voxel;
sorting the intensity information of each measuring point according to the sequence of 1 in the binary sequence corresponding to the final scale space, and compressing by using a run length coding method to obtain compressed data of the intensity of the point cloud data;
sharing and transmitting compressed data including the point cloud data intensity, compressed data of point cloud data coordinates corresponding to the optimal compression parameters, first scale space vertex coordinates and second data compression packets of the optimal compression parameters to other unmanned mine cars running nearby;
other unmanned mine cars receive and decompress a second data compression packet transmitted by the adjacent running unmanned mine car and construct a road condition model; and controlling the unmanned mine car according to the road condition model.
7. The method as claimed in claim 6, wherein the second data compression packet transmitted to other unmanned mine cars traveling nearby is shared with GPS positioning information of point cloud data coordinate origin and coordinate system direction information.
8. The unmanned mine car control method based on laser radar ranging as claimed in claim 7, wherein the road condition model is constructed according to the following steps:
decompressing the second data compression packet to obtain compressed data of the intensity of the point cloud data, compressed data of point cloud data coordinates corresponding to the optimal compression parameters, first scale space vertex coordinates, the optimal compression parameters, GPS positioning information of point cloud data coordinate origin and coordinate system direction information;
establishing a coordinate system according to the direction information of the coordinate system; establishing a first scale space according to the vertex coordinates and the coordinate system of the first scale space;
sequentially reducing the measuring points into a first scale space according to compressed data of the decompressed point cloud data coordinates, and acquiring three-dimensional coordinates of all the decompressed measuring points;
decompressing compressed data of the intensity of the point cloud data by using a run length decoding method to obtain intensity information of each measuring point of the point cloud data, and corresponding the intensity information of the measuring point to coordinates of the measuring point in the point cloud data one by one to obtain the point cloud data;
and integrating the decompressed point cloud data and the point cloud data detected by the current unmanned mine car according to the GPS positioning information of the point cloud data coordinate origin, and constructing a road condition model by using the integrated point cloud data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211365347.7A CN115421161B (en) | 2022-11-03 | 2022-11-03 | Unmanned mine car control method based on laser radar ranging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211365347.7A CN115421161B (en) | 2022-11-03 | 2022-11-03 | Unmanned mine car control method based on laser radar ranging |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115421161A true CN115421161A (en) | 2022-12-02 |
| CN115421161B CN115421161B (en) | 2023-04-07 |
Family
ID=84207453
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211365347.7A Active CN115421161B (en) | 2022-11-03 | 2022-11-03 | Unmanned mine car control method based on laser radar ranging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115421161B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108335335A (en) * | 2018-02-11 | 2018-07-27 | 北京大学深圳研究生院 | A kind of point cloud genera compression method based on enhancing figure transformation |
| CN111273305A (en) * | 2020-02-18 | 2020-06-12 | 中国科学院合肥物质科学研究院 | Multi-sensor fusion road extraction and indexing method based on global and local grid maps |
| WO2021246843A1 (en) * | 2020-06-05 | 2021-12-09 | 엘지전자 주식회사 | Point cloud data transmission device, point cloud data transmission method, point cloud data reception device, and point cloud data reception method |
| CN114241026A (en) * | 2021-12-31 | 2022-03-25 | 西安邮电大学 | Point cloud simplification algorithm and device based on flatness division |
| CN114419291A (en) * | 2022-01-17 | 2022-04-29 | 北京三快在线科技有限公司 | Point cloud data compression and decompression method and device |
| CN114785998A (en) * | 2022-06-20 | 2022-07-22 | 北京大学深圳研究生院 | Point cloud compression method and device, electronic equipment and storage medium |
| CN115249033A (en) * | 2021-04-09 | 2022-10-28 | 华为技术有限公司 | Data processing method and device |
-
2022
- 2022-11-03 CN CN202211365347.7A patent/CN115421161B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108335335A (en) * | 2018-02-11 | 2018-07-27 | 北京大学深圳研究生院 | A kind of point cloud genera compression method based on enhancing figure transformation |
| CN111273305A (en) * | 2020-02-18 | 2020-06-12 | 中国科学院合肥物质科学研究院 | Multi-sensor fusion road extraction and indexing method based on global and local grid maps |
| WO2021246843A1 (en) * | 2020-06-05 | 2021-12-09 | 엘지전자 주식회사 | Point cloud data transmission device, point cloud data transmission method, point cloud data reception device, and point cloud data reception method |
| CN115249033A (en) * | 2021-04-09 | 2022-10-28 | 华为技术有限公司 | Data processing method and device |
| CN114241026A (en) * | 2021-12-31 | 2022-03-25 | 西安邮电大学 | Point cloud simplification algorithm and device based on flatness division |
| CN114419291A (en) * | 2022-01-17 | 2022-04-29 | 北京三快在线科技有限公司 | Point cloud data compression and decompression method and device |
| CN114785998A (en) * | 2022-06-20 | 2022-07-22 | 北京大学深圳研究生院 | Point cloud compression method and device, electronic equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| YUSHENG XU 等: "Voxel-based representation of 3D point clouds: Methods, applications, and its potential use in the construction industry", 《AUTOMATION IN CONSTRUCTION》 * |
| 黄源 等: "基于改进八叉树的三维点云压缩算法", 《光学学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115421161B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11836623B2 (en) | Object detection and property determination for autonomous vehicles | |
| US11475351B2 (en) | Systems and methods for object detection, tracking, and motion prediction | |
| US20220024485A1 (en) | Drivable surface identification techniques | |
| CN111383480B (en) | Method, apparatus, device and medium for hazard warning of vehicles | |
| JP2022536794A (en) | Techniques for volume estimation | |
| CN109872530B (en) | Road condition information generation method, vehicle-mounted terminal and server | |
| US11938926B2 (en) | Polyline contour representations for autonomous vehicles | |
| CN110632617B (en) | Laser radar point cloud data processing method and device | |
| CN111551938B (en) | Unmanned technology perception fusion method based on mining area environment | |
| Ye et al. | Semi-automated generation of road transition lines using mobile laser scanning data | |
| CN110716529A (en) | Automatic generation method and device for automatic driving test case | |
| US10916124B2 (en) | Method, device and system for wrong-way driver detection | |
| CN110688311A (en) | Test case management method and device for automatic driving typical scene | |
| CN115615445A (en) | Method, system and storage medium for processing map data | |
| CN115565149A (en) | Method, vehicle and storage medium for object detection | |
| CN116710961A (en) | Method and system for ground segmentation using graphic cutting | |
| CN110554409B (en) | Concave obstacle detection method and system | |
| CN116340307B (en) | Ramp layer generation method and device, high-precision map and electronic equipment | |
| CN115421161A (en) | Unmanned mine car control method based on laser radar ranging | |
| US20230394694A1 (en) | Methods and apparatus for depth estimation using stereo cameras in a vehicle system | |
| CN112015199A (en) | Flight path planning method and device applied to underground coal mine intelligent inspection unmanned aerial vehicle | |
| US10532750B2 (en) | Method, device and system for wrong-way driver detection | |
| Hong et al. | Safety decision of running speed based on real-time weather | |
| CN114511846A (en) | Real-time three-dimensional target detection method based on point cloud cross-view feature conversion | |
| Piecha | Digital camera as a data source of ITS solutions in traffic control and management |
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 |