CN115469659A - Automatic charging system of autonomous mobile robot based on V-shaped plate recognition and positioning - Google Patents
Automatic charging system of autonomous mobile robot based on V-shaped plate recognition and positioning Download PDFInfo
- Publication number
- CN115469659A CN115469659A CN202211074126.4A CN202211074126A CN115469659A CN 115469659 A CN115469659 A CN 115469659A CN 202211074126 A CN202211074126 A CN 202211074126A CN 115469659 A CN115469659 A CN 115469659A
- Authority
- CN
- China
- Prior art keywords
- charging pile
- charging
- positioning
- module
- unit
- 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
- 210000001503 joint Anatomy 0.000 claims abstract description 23
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 238000003032 molecular docking Methods 0.000 claims abstract description 9
- 238000007405 data analysis Methods 0.000 claims description 22
- 238000000034 method Methods 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 9
- 238000012417 linear regression Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 8
- 238000013461 design Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 6
- 238000011049 filling Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims 2
- 230000008569 process Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000002567 autonomic effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000001125 extrusion Methods 0.000 description 1
- 229910052731 fluorine Inorganic materials 0.000 description 1
- 125000001153 fluoro group Chemical group F* 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
- G05D1/024—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors in combination with a laser
-
- 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
- G01C21/20—Instruments for performing navigational calculations
-
- 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
- G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
- G01S17/06—Systems determining position data of a target
-
- 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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0225—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving docking at a fixed facility, e.g. base station or loading bay
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
- H02J7/0042—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries characterised by the mechanical construction
- H02J7/0045—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries characterised by the mechanical construction concerning the insertion or the connection of the batteries
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
- H02J7/0047—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries with monitoring or indicating devices or circuits
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Electromagnetism (AREA)
- Aviation & Aerospace Engineering (AREA)
- Computer Networks & Wireless Communication (AREA)
- Power Engineering (AREA)
- Optics & Photonics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention relates to the technical field of automatic robot charging, in particular to an automatic charging system of an autonomous mobile robot based on V-shaped plate recognition and positioning, which comprises: the system comprises a preprocessing module, an AMR database, a quick coarse positioning module, an identification module, a positioning module, a route planning and tracking module and a butt joint charging module; extracting charging pile characteristics from the point cloud data through the preprocessing module and registering the charging pile characteristics to the AMR database; storing point cloud data and charging pile characteristics through the AMR database; planning an optimal path to a charging pile through the quick coarse positioning module; acquiring real-time point cloud data through the identification module and identifying the charging pile; calculating the position of a docking point of the charging pile through the positioning module; planning a traveling route of the autonomous mobile robot through the route planning and tracking module; the autonomous mobile robot is in butt joint with a charging pile through the butt joint charging module and is charged; the time of the robot for searching the charging pile is saved, and the system efficiency is improved.
Description
Technical Field
The invention relates to the technical field of automatic robot charging, in particular to an automatic charging system of an autonomous mobile robot based on V-shaped plate recognition and positioning.
Background
With the development of autonomous mobile robots in the fields of industrial automation, logistics, intelligent manufacturing, services, medical treatment, fire protection, cleaning, etc., the autonomous mobile robots are gradually accepted and widely used by people with high degree of automation. The autonomous mobile robot has high autonomy, can automatically walk and execute work within a certain range, and basically does not need human participation in the operation process. In order to guarantee the long-time operation of the charging pile, when the energy of the energy storage device is insufficient, the charging pile can automatically return to charge, and the charging pile continues to work after the charging is finished.
In some early automatic charging methods, a charging system of a robot is configured by first building a charging pile guide line around a whole working area, the charging pile guide line is connected with a charging pile, and the robot walks along the charging pile guide line to find the charging pile for butt-joint charging. The whole process is built and is wasted time and energy, fill electric pile guide line that lay along whole workspace can make the robot look for fill electric pile guide line and do not have the principle nearby, and, the robot needs to remove along the border of whole workspace after seeking to fill electric pile boundary line, so, the robot seeks to fill electric pile process loaded down with trivial details lengthy, the power consumptive of robot has been increased in the intangible, and the robot seeks the time of finding filling electric pile and has the uncertainty, when the robot electric quantity is not enough, there is the possibility of charging failure. In addition, the robot charging pile can only be arranged at fixed positions in the method.
With the development of the autonomous positioning system of the autonomous mobile robot, some methods adopt the autonomous positioning system of the robot to search for the nearest charging pile, and guide the robot to charge through a charging guide line arranged around the charging pile. Although the method reduces the time for searching the charging pile, the charging guide line still needs to be laid manually, so that the position of the charging pile is limited, and the workload of manual laying is increased. In addition, some recent work is to add an infrared guide module and an infrared receiving module for automatic charging guide on the basis of an autonomous robot positioning system or a charging guide line, the method does not need to lay a guide line around the charging pile, but equipment investment is undoubtedly increased due to the introduction of the infrared guide module and the infrared receiving module, and the accuracy of the infrared guide module is not high, so that the use is limited.
Therefore, there is a need for an automatic charging system for an autonomous mobile robot based on V-shaped plate recognition and positioning to solve the above problems.
Disclosure of Invention
The invention aims to provide an automatic charging system of an autonomous mobile robot based on V-shaped plate identification and positioning, so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: an autonomous mobile robot automatic charging system based on V-shaped plate recognition and positioning, the system comprising: the system comprises a preprocessing module, an AMR database, a quick coarse positioning module, an identification module, a positioning module, a route planning and tracking module and a butt joint charging module;
acquiring single line laser radar point cloud data through the preprocessing module, extracting charging pile characteristics from the point cloud data and registering the charging pile characteristics to the AMR database;
storing all the acquired point cloud data and charging pile characteristics through the AMR database;
planning an optimal path to the charging pile by the rapid coarse positioning module by utilizing an AMR path planning algorithm, so that the autonomous mobile robot reaches the position near the charging pile;
acquiring real-time point cloud data by using a single-line laser radar through the identification module, identifying the charging pile, and sending the identified charging pile data to the positioning module;
calculating the position of a charging pile butt joint point by the positioning module through a charging pile positioning algorithm;
planning a traveling route of the autonomous mobile robot according to the position of the positioning module through the route planning and tracking module;
and the autonomous mobile robot is butted with the charging pile through the butting charging module and is charged.
Wherein the AMR represents an autonomous mobile robot.
Further, the preprocessing module comprises a data acquisition unit, a data analysis unit and a feature extraction and registration unit; the data acquisition unit is used for acquiring two-dimensional point cloud data of the charging pile by using a single-line laser radar; the data analysis unit is used for clustering the data of the data acquisition unit and uploading the clustered data to the feature extraction and registration unit; the characteristic extraction and registration unit is used for identifying and extracting characteristic data of the charging pile according to preset parameters of the charging pile, comprises a V-shaped plate structure design, and registers the characteristic data to the AMR database, wherein the V-shaped plate charging pile has a simple structure, does not need to be provided with any complex sensor, and can perform high-efficiency and high-precision positioning by combining a V-shaped charging pile positioning algorithm;
the data analysis unit comprises a down-sampling subunit, a filtering subunit and a dividing subunit; the down-sampling subunit is used for down-sampling the two-dimensional point cloud data set by using a voxel filter; the filtering subunit is used for removing the noisy measured value from the two-dimensional point cloud data set by using the radius and the neighbor point number of the data search of the radius filter, and the radius filter can also use a statistical filter to filter the two-dimensional point cloud data set; the segmentation subunit is configured to segment the two-dimensional point cloud data set by using an euclidean distance segmentation algorithm, so as to obtain a data set meeting requirements, where the euclidean distance segmentation algorithm belongs to a conventional technical means of a person skilled in the art, and therefore, redundant details are not given.
Further, the fast coarse positioning module comprises a detection unit and a coarse positioning unit; the detection unit is used for detecting the electric quantity of the autonomous mobile robot, and if the electric quantity is lower than a threshold value, an automatic charging mode is started to enter a coarse positioning unit; the rough positioning unit is used for generating a global path by utilizing heuristic search according to the cost map so as to obtain a charging pile rough positioning guide line, and calling a path tracking algorithm to the charging pile so as to enable the charging pile to reach the vicinity of the charging pile, wherein the calling of the path tracking algorithm belongs to the conventional technical means of the technical personnel in the field, and therefore, the calling of the path tracking algorithm is not described in detail.
Furthermore, the identification module comprises a data acquisition unit, a data analysis unit and a charging pile identification unit; the data acquisition unit is used for acquiring point cloud data of all charging piles within a search radius by using a single-line laser radar; the data analysis unit is used for clustering point cloud data; the charging pile identification unit is used for extracting point cloud data of the charging pile by using a charging pile identification algorithm and sending the data to the positioning module.
Further, the processing of the data acquisition unit and the data analysis unit in the identification module is consistent with that in the preprocessing module;
the charging pile identification algorithm is utilized to identify target point cloud data of the charging pile which can be matched with the autonomous mobile robot:
setting a charging pile point cloud data set within a search radius as P, and obtaining a data set meeting the requirements through data analysisThrough traversing A, obtaining traversal data P k =(p′ 1 ,p′ 2 ,…,p′ m ) And the characteristic data extracted from the preset parameters is P s =(p 1 ,p 2 ,…,p n ) Setting the minimum matching score of the charging pile to be min _ score =999, and setting the target point cloud data to be P e ;
Firstly, P is filled by adopting an edge data filling method k Length and P of s Alignment to obtain P k =(p′ 1 ,p′ 2 ,…,p′ n );
And then calculating the mass center and the centroid removing coordinates of the two groups of point clouds: order toTo obtain q i =p i -p,q′ i =p′ i -p'; obtaining a matrix
Further performing singular value decomposition on the matrix W: let W = U Σ V T (ii) a To obtain P k And P s Coordinate transformation relationship (R, t) between: r = UV T T = p-Rp'; by (R, t) to P s Coordinate transformation is carried out to obtain P' s =RP s +t;
Then calculating the transformed P s And P k Root mean square error of (d):at this time, the root mean square error RMSE is determined: if RMSE < min _ socre, let RMSE = min _ socre, P e =P k And returning to the coarse positioning unit until the traversal is finished;
and finally, judging whether min _ socre < [ epsilon ] is satisfied or not, determining whether epsilon is a preset matching error, if so, returning to identify the charging pile and returning to the target point cloud P e And otherwise, judging that the charging pile is not identified in the current frame.
Further, the positioning module calculates the position of the charging pile docking point identified by the identification module by using a charging pile positioning algorithm:
firstly, calculating target point cloud data P e Center of mass C e The point cloud P is processed according to the centroid and a preset distance threshold value e Is divided intoAndare respectively pairedAndlinear fitting is carried out through linear regression to obtain two straight lines y 1 =k 1 x 1 +b 1 And y 2 =k 2 x 2 +b 2 Calculating to obtain the intersection C of the two straight lines line ;
Then through C line Combining the preset distance threshold value with P again e Is split intoAndare respectively pairedAndlinear fitting is carried out through linear regression to obtain a linear equation y 1 ′=k 1 x 1 ′+b 1 ' and y 2 ′=k 2 ′x 2 ′+b 2 ' calculating to obtain the intersection C of two straight lines line ′;
And finally, calculating an angle theta of an angular bisector according to the slopes of the two straight lines, wherein the position coordinates of the virtual butt joint points of the charging pile are as follows: x is a radical of a fluorine atom v =x line -x offset cosθ,y v =y line -y offset sinθ,θ v =θ-θ offset 。
Further, the route planning and tracking module comprises a route planning unit and a path tracking unit; the route planning unit is used for planning the traveling route of the autonomous mobile robot according to the virtual docking point position of the charging pile; the path tracking unit is configured to track a real-time travel route of the robot by using a path tracking algorithm to reach a virtual control point, where the path tracking algorithm belongs to a conventional technical means of a person skilled in the art, and therefore, the description is not given herein.
Furthermore, the docking and charging module comprises a mobile control unit, a charging communication unit and a charging inquiry unit; the mobile control unit is used for controlling the autonomous mobile robot to perform linear motion according to a preset distance and a preset timeout so as to enable the autonomous mobile robot to be in butt joint with the charging pile; the charging connection unit is used for connecting a charging port; the charging inquiry unit is used for inquiring whether the autonomous mobile robot is charging: if the robot is in the charging state, setting the state of the autonomous mobile robot to be in charging; if the mobile phone is not in the charging state, a D0 signal is sent, a charging port is cut off, the charging pile is withdrawn, the mobile phone returns to the identification module, a route is re-planned, and the mobile phone is in butt joint with the charging pile for charging; and at the moment, if the failure times reach a preset value, quitting the charging pile, returning to the quick rough positioning module, re-identifying other charging piles, and if the failure times reach a preset maximum value, reporting the charging failure.
Compared with the prior art, the invention has the following beneficial effects:
the invention relates to an autonomous mobile robot which is guided by a single-line laser radar, wherein the single-line laser radar provides global positioning for the autonomous mobile robot through a positioning algorithm. Moreover, this system make full use of this advantage of autonomic mobile robot, autonomic mobile robot uses global positioning independently to plan the route, and when its electric quantity was not enough, automatic charging system can automatic planning one and walk to the shortest path that fills electric pile, compares in traditional approach and needs artificial charging circuit of laying, has saved the time of looking for filling electric pile greatly, has improved system efficiency. In addition, the appearance of the charging pile is designed by adopting a V-shaped plate structure, the design structure is simple, any complex sensor is not required, and a V-shaped plate recognition and positioning algorithm based on a single-line laser radar is arranged, so that the robot can be guided to automatically complete butt joint with the charging pile and carry out charging. Compared with the traditional guide line laying and infrared guiding technology, the charging station positioning method has the advantages that the installation position of the charging station is not limited, the charging pile guiding module does not need to be additionally installed, the adaptability to scenes is stronger, more use scenes can be covered, and the positioning accuracy of millimeter level can be achieved by the charging pile positioning method. The invention adopts the idea of machine learning in the process of identifying and positioning the charging pile, has no limit on the specific size of the V-shaped charging pile and the specific model of the single-line laser radar, and can be adapted to charging piles with different sizes and autonomous mobile robots with different types.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic diagram of the operation of an automatic charging system of an autonomous mobile robot based on V-shaped plate recognition and positioning according to the present invention;
FIG. 2 is an appearance design drawing of a V-shaped plate charging pile of the automatic charging system of the autonomous mobile robot based on V-shaped plate recognition and positioning;
FIG. 3 is a flow chart of the work flow of the preprocessing module of the automatic charging system of the autonomous mobile robot based on V-shaped plate recognition and positioning;
FIG. 4 is a flow chart of a positioning identification charging pile of the automatic charging system of the autonomous mobile robot based on V-shaped plate identification and positioning;
FIG. 5 is a flow chart of the present invention for acquiring and processing real-time data for an autonomous mobile robot automatic charging system based on V-shaped plate recognition and positioning;
FIG. 6 is a flow chart of the invention for automatic charging system of autonomous mobile robot for docking point confirmation and route planning based on V-shaped plate identification and positioning;
FIG. 7 is a flow chart of the work flow of the docking charging module of the automatic charging system of the autonomous mobile robot based on V-shaped plate recognition and positioning of the present invention;
FIG. 8 is a robot real-time route traveling diagram of an automatic charging system for an autonomous mobile robot based on V-shaped plate recognition and positioning according to the present invention;
fig. 9 is a two-dimensional point cloud data distribution diagram of an autonomous mobile robot automatic charging system based on V-shaped plate recognition and positioning according to the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
Referring to fig. 1-9, the present invention provides a technical solution: an automatic charging system of autonomous mobile robot based on V-shaped plate recognition and positioning, the system comprising: the system comprises a preprocessing module, an AMR database, a quick coarse positioning module, an identification module, a positioning module, a route planning and tracking module and a butt joint charging module;
acquiring single-line laser radar point cloud data through the preprocessing module, extracting charging pile characteristics from the point cloud data and registering the charging pile characteristics to the AMR database;
storing all the acquired point cloud data and charging pile characteristics through the AMR database;
planning an optimal path to the charging pile by the rapid coarse positioning module by utilizing an AMR path planning algorithm, so that the autonomous mobile robot reaches the position near the charging pile;
acquiring real-time point cloud data by using a single-line laser radar through the identification module, identifying a charging pile, and sending the identified charging pile data to the positioning module;
calculating the position of a charging pile butt joint point by the positioning module through a charging pile positioning algorithm;
planning a traveling route of the autonomous mobile robot according to the position of the positioning module through the route planning and tracking module;
and the autonomous mobile robot is butted with the charging pile through the butting charging module and is charged.
Wherein the AMR represents an autonomous mobile robot.
Further, the preprocessing module comprises a data acquisition unit, a data analysis unit and a feature extraction and registration unit; the data acquisition unit is used for acquiring two-dimensional point cloud data of the charging pile by using a single-line laser radar; the data analysis unit is used for clustering the data of the data acquisition unit and uploading the clustered data to the feature extraction and registration unit; the characteristic extraction and registration unit is used for identifying and extracting characteristic data of the charging pile according to preset parameters of the charging pile, comprises a V-shaped plate structure design, and registers the characteristic data to the AMR database, wherein the V-shaped plate charging pile has a simple structure, does not need to be provided with any complex sensor, and can perform high-efficiency and high-precision positioning by combining a V-shaped charging pile positioning algorithm;
wherein, V type plate fills electric pile appearance design drawing as shown in fig. 2, and V type fills electric pile and includes: charging port positive and negative electrodes, a V-shaped plate, a shell and a power adapter. The V-shaped plate provides V-shaped characteristics for the charging pile identification algorithm and geometric characteristics for the charging pile positioning algorithm. The internal work flow of the V-shaped charging pile is as follows:
A. the lower port of the naturally extended positive and negative electrodes has no voltage;
B. when the AMR charging port is in butt joint with the positive electrode and the negative electrode of the charging pile, the positive electrode and the negative electrode sink under the extrusion action of the AMR, the relay is triggered to be attracted, and the positive electrode and the negative electrode are connected with the power adapter;
C. fill electric pile and begin to charge AMR.
The data analysis unit comprises a down-sampling subunit, a filtering subunit and a segmentation subunit; the down-sampling subunit is used for down-sampling the two-dimensional point cloud data set by using a voxel filter; the filtering subunit is used for removing the noisy measured value from the two-dimensional point cloud data set by using the radius and the number of adjacent points searched by the radius filter, and the radius filter can also use a statistical filter to filter the two-dimensional point cloud data set; the segmentation subunit is configured to segment the two-dimensional point cloud data set by using an euclidean distance segmentation algorithm, so as to obtain a data set meeting requirements, where the euclidean distance segmentation algorithm belongs to a conventional technical means of a person skilled in the art, and therefore, redundant details are not given.
Further, the fast coarse positioning module comprises a detection unit and a coarse positioning unit; the detection unit is used for detecting the electric quantity of the autonomous mobile robot, if the electric quantity is lower than a threshold value, an automatic charging mode is started, and a coarse positioning unit is entered; the rough positioning unit is used for generating a global path by utilizing heuristic search according to the cost map so as to obtain a charging pile rough positioning guide line, and calling a path tracking algorithm to go to the charging pile so as to enable the path tracking algorithm to reach the vicinity of the charging pile, so that the time for searching the charging pile is greatly saved, and the system efficiency is improved.
Furthermore, the identification module comprises a data acquisition unit, a data analysis unit and a charging pile identification unit; the data acquisition unit is used for acquiring point cloud data of all charging piles within a search radius by using a single-line laser radar, so that the autonomous mobile robot can be favorably used for carrying out global positioning on the charging piles, and the positioning effect is better; the data analysis unit is used for clustering point cloud data; the charging pile identification unit is used for extracting point cloud data of the charging pile by using a charging pile identification algorithm and sending the data to the positioning module.
Further, the processing of the data acquisition unit and the data analysis unit in the identification module is consistent with that in the preprocessing module;
the charging pile identification algorithm is utilized to identify target point cloud data of the charging pile which can be matched with the autonomous mobile robot:
setting a charging pile point cloud data set within a search radius as P, and obtaining a data set meeting the requirements through data analysisThrough traversing A, obtaining traversal data P k =(p′ 1 ,p′ 2 ,…,p′ m ) And the characteristic data extracted from the preset parameters is P s =(p 1 ,p 2 ,…,p n ) Setting the minimum matching score of the charging pile to be min _ score =999, and setting the target point cloud data to be P e ;
Firstly, P is filled by adopting an edge data filling method k Length and P of s Alignment to obtain P k =(p′ 1 ,p′ 2 ,…,p′ n );
And then calculating the mass center and the centroid removing coordinates of the two groups of point clouds: order toTo obtain q i =p i -p,q′ i =p′ i -p'; obtaining a matrix
Further performing singular value decomposition on the matrix W: let W = U Σ V T (ii) a To obtain P k And P s Coordinate transformation relation (R, t) between: r = UV T T = p-Rp'; by (R, t) to P s Coordinate transformation is carried out to obtain P' s =RP s +t;
Then calculating the transformed P s And P k Root mean square error of (d):at this time, the root mean square error RMSE is determined: if RMSE < min _ socre, let RMSE = min _ socre, P e =P k And returning to the coarse positioning unit until the traversal is finished;
and finally, judging whether min _ socre < [ epsilon ] is satisfied or not, determining whether epsilon is a preset matching error, if so, returning to identify the charging pile and returning to the target point cloud P e Otherwise, judging that the charging pile is not identified in the current frame.
Further, the positioning module calculates the position of the charging pile docking point identified by the identification module by using a charging pile positioning algorithm:
firstly, target point cloud data P is calculated e Center of mass C e The point cloud P is processed according to the centroid and a preset distance threshold value e Is divided intoAndare respectively paired withAndlinear fitting is carried out through linear regression to obtain two straight lines y 1 =k 1 x 1 +b 1 And y 2 =k 2 x 2 +b 2 Calculating to obtain the intersection C of the two straight lines line ;
Then through C line Combining the preset distance threshold value with P again e Is split intoAndare respectively pairedAndlinear fitting is carried out through linear regression to obtain a linear equation y 1 ′=k 1 ′x 1 ′+b 1 ' and y 2 ′=k 2 ′x 2 ′+b 2 ', calculating to obtain the intersection C of two straight lines line ;
And finally, calculating an angle theta of an angular bisector according to the slopes of the two straight lines, wherein the position coordinates of the virtual butt joint points of the charging pile are as follows: x is the number of v =x line -x offset cosθ,y v =y line -y offset sinθ,θ v =θ-θ offset 。
Further, the route planning and tracking module comprises a route planning unit and a path tracking unit; the route planning unit is used for planning the traveling route of the autonomous mobile robot according to the virtual docking point position of the charging pile; the path tracking unit is configured to track a real-time travel route of the robot by using a path tracking algorithm to reach a virtual control point, where the path tracking algorithm belongs to a conventional technical means of a person skilled in the art, and therefore, no further description is given.
Furthermore, the docking and charging module comprises a mobile control unit, a charging communication unit and a charging inquiry unit; the mobile control unit is used for controlling the autonomous mobile robot to perform linear motion according to a preset distance and a preset timeout so as to enable the autonomous mobile robot to be in butt joint with the charging pile; the charging connection unit is used for connecting a charging port; the charging inquiry unit is used for inquiring whether the autonomous mobile robot is charging: if the robot is in the charging state, setting the state of the autonomous mobile robot to be in charging; if the charging system is not in the charging state, a DO signal is sent, a charging port is cut off, the charging pile is withdrawn, the charging system returns to the identification module, a route is re-planned, and the charging system is in butt joint with the charging pile for charging; and at the moment, if the failure times reach the preset value, quitting the charging pile, returning to the quick coarse positioning module, re-identifying other charging piles, and if the failure times reach the preset maximum value, reporting the charging failure.
The first embodiment is as follows:
before detecting that the electric quantity is insufficient, the autonomous mobile robot firstly enters a preprocessing mode, obtains the characteristic data of the charging pile and stores the characteristic data into an AMR database.
And when the electric quantity of the user is detected to be insufficient, starting an automatic charging mode, and automatically planning a shortest path which is traveled to the charging pile by utilizing a heuristic search and path tracking algorithm so as to reach the position near the charging pile.
Then, the charging pile is identified by utilizing a charging pile identification algorithm: setting a charging pile point cloud data set within a search radius as P, and obtaining a data set meeting the requirements through data analysisThen through traversing A, obtaining traversal data P k =(p′ 1 ,p′ 2 ,…,p′ m ) And the characteristic data extracted by the preset parameters is P s =(p 1 ,p 2 ,…,p n ) Setting the minimum matching score of the charging pile to be min _ score =999, and setting the target point cloud data to be P e (ii) a Firstly, P is filled by adopting an edge data filling method k Length and P of s Alignment to obtain P k =(p′ 1 ,p′ 2 ,…,p′ n ) (ii) a And then calculating the mass center and the centroid removing coordinates of the two groups of point clouds: order toTo obtain q i =p i -p,q′ i =p′ i -p'; obtaining a matrixFurther performing singular value decomposition on the matrix W: let W = U Σ V T (ii) a To obtain P k And P s Coordinate transformation relation (R, t) between: r = UV T T = p-Rp'; by (R, t) to P s Coordinate transformation is carried out to obtain P' s =RP s + t; then calculating the transformed P s And P k Root mean square error of (d):at this time, the root mean square error RMSE is determined: if RMSE < min _ socre, let RMSE = min _ socre, P e =P k And returning to the coarse positioning unit until the traversal is finished; finally, whether min _ socre < [ epsilon ] is established or not is judged, whether the epsilon is a preset matching error or not is judged, if the condition is established, the charging pile is returned and identified, and the target point cloud P is returned e Otherwise, judging that the charging pile is not identified in the current frame.
After the system identifies the charging pile, the position coordinates of the virtual charging pile butt joint point are calculated by using a charging pile positioning algorithm: firstly, target point cloud data P is calculated e Center of mass C e The point cloud P is processed according to the centroid and a preset distance threshold value e Is divided intoAndare respectively pairedAndlinear fitting is carried out through linear regression to obtain two straight lines y 1 =k 1 x 1 +b 1 And y 2 =k 2 x 2 +b 2 Calculating to obtain the intersection C of the two straight lines line (ii) a Then through C line Combining the preset distance threshold value with P again e Is split intoAndare respectively pairedAndlinear fitting is carried out through linear regression to obtain a linear equation y 1 ′=k 1 ′x 1 ′+b 1 ' and y 2 ′=k 2 ′x 2 ′+b 2 ' calculating to obtain the intersection C of two straight lines line '; and finally, calculating an angle theta of an angular bisector according to the slopes of the two straight lines, wherein the position coordinates of the virtual butt joint points of the charging pile are as follows: x is the number of v =x line -x offset cosθ,y v =y line -y offset sinθ,θ v =θ-θ offset 。
After the position of the virtual charging pile is confirmed, the system automatically plans an autonomous mobile robot advancing route, and tracks the robot real-time advancing route by using a path tracking algorithm so as to reach the position of a virtual docking point.
After the virtual charging point is reached, firstly, controlling the autonomous mobile robot to perform linear motion according to a preset distance and a preset timeout so as to enable the autonomous mobile robot to be in butt joint with a charging pile; then connecting the charging port to be connected; and finally, inquiring the charging state of the autonomous mobile robot by using an inquiry unit, displaying that the autonomous mobile robot is charged, quitting the charging pile after the electric quantity is full, completing charging, and finishing system work.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. The utility model provides an automatic charging system of autonomous mobile robot based on V template discernment and location which characterized in that: the system comprises: the system comprises a preprocessing module, an AMR database, a quick coarse positioning module, an identification module, a positioning module, a route planning and tracking module and a butt joint charging module;
acquiring single-line laser radar point cloud data through the preprocessing module, extracting charging pile characteristics from the point cloud data and registering the charging pile characteristics to the AMR database;
storing all the acquired point cloud data and charging pile characteristics through the AMR database;
planning an optimal path to the charging pile by the rapid coarse positioning module by utilizing an AMR path planning algorithm, so that the autonomous mobile robot reaches the position near the charging pile;
acquiring real-time point cloud data by using a single-line laser radar through the identification module, identifying the charging pile, and sending the identified charging pile data to the positioning module;
calculating the position of a docking point of the charging pile by using a charging pile positioning algorithm through the positioning module;
planning a traveling route of the autonomous mobile robot according to the position of the positioning module through the route planning and tracking module;
and the autonomous mobile robot is butted with a charging pile through the butting charging module and is charged.
2. The automatic charging system of autonomous mobile robot based on V-shaped plate recognition and positioning of claim 1, characterized in that: the preprocessing module comprises a data acquisition unit, a data analysis unit and a feature extraction and registration unit; the data acquisition unit is used for acquiring two-dimensional point cloud data of the charging pile by using a single line laser radar; the data analysis unit is used for clustering the data of the data acquisition unit and uploading the clustered data to the feature extraction and registration unit; the characteristic extraction and registration unit is used for identifying and extracting characteristic data of the charging piles according to preset parameters of the charging piles, comprises a V-shaped plate structure design, and registers the characteristic data to the AMR database;
the data analysis unit comprises a down-sampling subunit, a filtering subunit and a dividing subunit; the down-sampling subunit is used for down-sampling the two-dimensional point cloud data set by using a voxel filter; the filtering subunit is used for removing a noisy measured value from the two-dimensional point cloud data set by using the radius and the adjacent point number of the data search of the radius filter; the segmentation subunit is used for segmenting the two-dimensional point cloud data set by using an Euclidean distance segmentation algorithm so as to obtain a data set meeting the requirement.
3. The automatic charging system of autonomous mobile robot based on V-shaped plate recognition and positioning of claim 1, characterized in that: the quick coarse positioning module comprises a detection unit and a coarse positioning unit; the detection unit is used for detecting the electric quantity of the autonomous mobile robot, if the electric quantity is lower than a threshold value, an automatic charging mode is started, and a coarse positioning unit is entered; and the rough positioning unit is used for generating a global path by utilizing heuristic search according to the cost map so as to obtain a charging pile rough positioning guide line and calling a path tracking algorithm to go to the charging pile.
4. The automatic charging system of autonomous mobile robot based on V-shaped plate recognition and positioning as claimed in claim 1, characterized in that: the identification module comprises a data acquisition unit, a data analysis unit and a charging pile identification unit; the data acquisition unit is used for acquiring point cloud data of all charging piles within a search radius by using a single-line laser radar; the data analysis unit is used for clustering the point cloud data; the charging pile identification unit is used for extracting point cloud data of the charging pile by using a charging pile identification algorithm and sending the data to the positioning module.
5. The automatic charging system of autonomous mobile robot based on V-shaped plate recognition and positioning as claimed in claim 4, wherein: the processing of the data acquisition unit and the data analysis unit in the identification module is consistent with that in the preprocessing module;
the charging pile identification algorithm is utilized to identify target point cloud data of the charging pile which can be matched with the autonomous mobile robot:
setting a charging pile point cloud data set in a search radius as P, and obtaining a data set meeting the requirements through data analysis as A = { P = i },Then through traversing A, obtaining traversal data P k =(p′ 1 ,p′ 2 ,…,p′ m ) And the characteristic data extracted by the preset parameters is P s =(p 1 ,p 2 ,…,p n ) Setting the minimum matching score of the charging pile to be min _ score =999, and setting the target point cloud data to be P e ;
Firstly, P is filled by adopting an edge data filling method k Length and P of s Alignment to obtain P k =(p′ 1 ,p′ 2 ,…,p′ n );
And then calculating the mass center and the centroid removing coordinates of the two groups of point clouds: order toTo obtain q i =p i -p,q′ i =p′ i -p'; obtaining a matrix W:
further performing singular value decomposition on the matrix W: let W = U Σ V T (ii) a To obtain P k And P s Coordinate transformation relation (R, t) between: r = UV T T = p-Rp'; by (R, t) to P s Coordinate transformation is carried out to obtain P' s =RP s +t;
Then calculating the transformed P s And P k Root mean square error of (d):at this time, the root mean square error RMSE is determined: if RMSE < min _ socre, let RMSE = min _ socre, P e =P k And returning to the coarse positioning unit until the traversal is finished;
and finally, judging whether min _ socre < [ epsilon ] is satisfied or not, determining whether epsilon is a preset matching error, if so, returning to identify the charging pile and returning to the target point cloud P e And otherwise, judging that the charging pile is not identified in the current frame.
6. The automatic charging system of autonomous mobile robot based on V-shaped plate recognition and positioning of claim 1, characterized in that: the positioning module calculates the position of the charging pile docking point identified by the identification module by using a charging pile positioning algorithm:
firstly, calculating target point cloud data P e Center of mass C e The point cloud P is processed according to the centroid and a preset distance threshold value e Is divided intoAndare respectively pairedAndlinear fitting is carried out through linear regression to obtain two straight lines y 1 =k 1 x 1 +b 1 And y 2 =k 2 x 2 +b 2 Calculating to obtain the intersection C of the two straight lines line ;
Then through C line Combining the preset distance threshold value with P again e Is split intoAndare respectively pairedAndlinear fitting is carried out through linear regression to obtain a linear equation y 1 ′=k 1 ′x 1 ′+b 1 ' and y 2 ′=k 2 ′x 2 ′+b 2 ', calculating to obtain the intersection C of two straight lines line ′;
And finally, calculating an angle theta of an angular bisector according to the slopes of the two straight lines, wherein the position coordinates of the virtual butt joint points of the charging pile are as follows: x is the number of v =x line -x offset cosθ,y v =y line -y offset sinθ,θ v =θ-θ offset 。
7. The automatic charging system of autonomous mobile robot based on V-shaped plate recognition and positioning of claim 1, characterized in that: the route planning and tracking module comprises a route planning unit and a path tracking unit; the route planning unit is used for planning the traveling route of the autonomous mobile robot according to the virtual docking point positions of the charging piles; the path tracking unit is used for tracking the real-time traveling route of the robot by using a path tracking algorithm to reach a virtual control point.
8. The automatic charging system of autonomous mobile robot based on V-shaped plate recognition and positioning of claim 7, characterized in that: the route planning unit comprises a control point calculation subunit and a traveling route planning subunit; the control point calculation subunit is used for calculating control points M and N by using the positions of the virtual docking points of the charging piles and preset offsets; the travel route planning subunit is used for calculating a cubic Bezier curve through coordinates of the starting point, the M point, the N point and the virtual butt joint point to obtain a real-time travel route:
P(t)=P 0 ·(1-t) 3 +M·3(1-t) 2 t+N·3(1-t)t 2 +P v ·t 3 ,t∈[0,1]。
9. the automatic charging system of autonomous mobile robot based on V-shaped plate recognition and positioning of claim 1, characterized in that: the butt joint charging module comprises a mobile control unit, a charging connection unit and a charging inquiry unit; the mobile control unit is used for controlling the autonomous mobile robot to perform linear motion according to a preset distance and a preset timeout so as to enable the autonomous mobile robot to be in butt joint with the charging pile; the charging connection unit is used for connecting a charging port; the charging inquiry unit is used for inquiring whether the autonomous mobile robot is charging.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211074126.4A CN115469659A (en) | 2022-09-02 | 2022-09-02 | Automatic charging system of autonomous mobile robot based on V-shaped plate recognition and positioning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211074126.4A CN115469659A (en) | 2022-09-02 | 2022-09-02 | Automatic charging system of autonomous mobile robot based on V-shaped plate recognition and positioning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115469659A true CN115469659A (en) | 2022-12-13 |
Family
ID=84369320
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211074126.4A Pending CN115469659A (en) | 2022-09-02 | 2022-09-02 | Automatic charging system of autonomous mobile robot based on V-shaped plate recognition and positioning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115469659A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117519158A (en) * | 2023-11-14 | 2024-02-06 | 霞智科技有限公司 | Bezier curve-based robot charging station pile alignment algorithm |
-
2022
- 2022-09-02 CN CN202211074126.4A patent/CN115469659A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117519158A (en) * | 2023-11-14 | 2024-02-06 | 霞智科技有限公司 | Bezier curve-based robot charging station pile alignment algorithm |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104635730B (en) | A kind of robot autonomous charging method | |
CN109782770B (en) | Method for automatically charging mower | |
Wang et al. | Intelligent vehicle self-localization based on double-layer features and multilayer LIDAR | |
CN111337941A (en) | Dynamic obstacle tracking method based on sparse laser radar data | |
CN112561998B (en) | Robot positioning and autonomous charging method based on three-dimensional point cloud registration | |
WO2015024407A1 (en) | Power robot based binocular vision navigation system and method based on | |
CN109460032A (en) | A kind of localization method and autonomous charging of robots method based on laser-correlation | |
CN114812581A (en) | Cross-country environment navigation method based on multi-sensor fusion | |
CN112363500A (en) | Automatic recharging moving method and system | |
CN110806585B (en) | Robot positioning method and system based on trunk clustering tracking | |
CN109583505A (en) | A kind of object correlating method, device, equipment and the medium of multisensor | |
CN106786938A (en) | A kind of crusing robot localization method and automatic recharging method | |
CN115469659A (en) | Automatic charging system of autonomous mobile robot based on V-shaped plate recognition and positioning | |
CN114782626A (en) | Transformer substation scene mapping and positioning optimization method based on laser and vision fusion | |
CN107607093A (en) | A kind of monitoring method and device of the lake dynamic storage capacity based on unmanned boat | |
CN112947441B (en) | Control method for automatic docking and charging of robot and charging seat | |
CN113675923A (en) | Charging method, charging device and robot | |
CN108536146B (en) | Intelligent control method for positioning charging base of mobile robot based on path and RSSI (received Signal Strength indicator) | |
CN113485357A (en) | Automatic pile returning and charging system and method for indoor robot | |
CN114034299A (en) | Navigation system based on active laser SLAM | |
Shen et al. | Research on 2D-SLAM of indoor mobile robot based on laser radar | |
CN115129063A (en) | Ground head steering navigation system and method for field operation robot | |
CN108762261A (en) | Mobile robot traverse path planing method based on double wireless networks | |
EP4206849A1 (en) | Autonomous mobile device and method for controlling same | |
CN106204516B (en) | Automatic charging method and device for robot |
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 |