CN109100744A - Object localization method and system for AGV - Google Patents
Object localization method and system for AGV Download PDFInfo
- Publication number
- CN109100744A CN109100744A CN201810847522.3A CN201810847522A CN109100744A CN 109100744 A CN109100744 A CN 109100744A CN 201810847522 A CN201810847522 A CN 201810847522A CN 109100744 A CN109100744 A CN 109100744A
- Authority
- CN
- China
- Prior art keywords
- agv
- coordinate
- point
- cloud
- obtains
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000004807 localization Effects 0.000 title claims abstract description 15
- 238000005259 measurement Methods 0.000 claims abstract description 4
- 238000013178 mathematical model Methods 0.000 claims description 41
- 230000000007 visual effect Effects 0.000 claims description 19
- 230000003287 optical effect Effects 0.000 claims description 2
- 230000011218 segmentation Effects 0.000 claims description 2
- 238000001514 detection method Methods 0.000 description 3
- 238000011897 real-time detection Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004040 coloring Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- 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
- G01S17/42—Simultaneous measurement of distance and other co-ordinates
-
- 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
- G01S7/4802—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
-
- 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
-
- 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
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
- G05D1/0248—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means in combination with a laser
-
- 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
- G05D1/0257—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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Aviation & Aerospace Engineering (AREA)
- Automation & Control Theory (AREA)
- Theoretical Computer Science (AREA)
- Optics & Photonics (AREA)
- Multimedia (AREA)
- Optical Radar Systems And Details Thereof (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The present invention provides the object localization methods and system for AGV, method includes the following steps: being primarily based on laser point cloud positioning obtains coordinate of the target point under AGV local Coordinate System, and target point is moved to according to coordinate, it is then based on TOF measurement positioning and obtains Y-axis coordinate of the AGV under world coordinate system, so that AGV keeps at a distance during being retracted into loading cabin from target point with the hatch door in loading cabin, the image at the last rear AGV of acquisition in real time, and it positions to obtain the relative coordinate between AGV and loading cabin based on image recognition, so that AGV is based on relative coordinate and exits loading cabin.This method and system enable AGV that the place of target point is accurately positioned, and are smoothly moved at target point, and then delivery/picking or other tasks are completed at target point.
Description
Technical field
The present invention relates to AGV transportation techniques fields, in particular to are used for the object localization method and system of AGV.
Background technique
AGV (Automated Guided Vehicle), i.e. automated guided vehicle, also referred to as automatic guided vehicle or carrying
Robot has transfer function, can have by goods transportation to designated place, therefore in logistics transportation industry and other industry
Certain application.
There are mainly two types of the move modes of AGV, and one is be guided AGV along paths such as the magnetic stripes for being set to ground
It advances, but such mode needs to lay magnetic stripe on ground in advance, and needs to lay magnetic again when needing to change travelling route
The consumption such as item, time cost and human cost is larger.Also one is AGV automations to advance, without laying track in advance on ground
Route, but AGV, during advancing from trend target direction, target positioning is often inaccurate, therefore safety cost is larger.
Summary of the invention
(1) goal of the invention
To overcome above-mentioned at least one defect of the existing technology, enable AGV that target is accurately positioned, and smoothly
Completion is moved to target point and then completes delivery/picking or other tasks, and the present invention provides following technical schemes.
(2) technical solution
As the first aspect of the present invention, the present invention provides a kind of object localization methods for AGV, comprising:
The coordinate for obtaining target point under AGV local Coordinate System is positioned based on laser point cloud, and mobile according to the coordinate
To target point；
The Y-axis coordinate of the AGV under world coordinate system is obtained based on TOF measurement positioning, so that AGV is from the mesh
The hatch door that punctuate is retracted into during loading cabin with the loading cabin is kept at a distance；
Acquire the image at the rear AGV in real time, and based on image recognition position to obtain the AGV and the loading cabin it
Between relative coordinate so that the AGV be based on the relative coordinate exit the loading cabin.
A specific embodiment as above-mentioned technical proposal, the AGV are generated by the laser radar itself being equipped with
Point cloud, coordinate of the target point under AGV local Coordinate System is obtained by described cloud of processing.
A specific embodiment as above-mentioned technical proposal, it is described to be existed by described cloud of processing to obtain target point
Coordinate under AGV local Coordinate System includes:
Described cloud is split by change threshold clustering algorithm, obtains satisfactory cloud；
Operation is carried out to the satisfactory cloud by RANSAC algorithm, the target point is obtained and is sat in AGV itself
Coordinate under mark system.
A specific embodiment as above-mentioned technical proposal, it is described by RANSAC algorithm to described satisfactory
Point cloud carries out operation
(1) multiple points are randomly selected in the satisfactory cloud；
(2) operation obtains and the multiple matched mathematical model of point；
(3) point unselected in the satisfactory cloud is substituted into the mathematical model, and therefrom chooses symbol
Close the point of the mathematical model；
(4) iteration executes (3) step until the first setting number, obtains and record the point for meeting the mathematical model；
(5) iteration executes above-mentioned (1)-(4) step until the second setting number, is repeatedly met the mathematical model
Point therefrom chooses the most primary points of quantity for meeting the point of the mathematical model, and then obtains the target point in AGV itself
Coordinate under coordinate system.
A specific embodiment as above-mentioned technical proposal, described according to the coordinate to be moved to target point specific
Are as follows: the AGV is controlled by pid control algorithm and is moved to target point.
A specific embodiment as above-mentioned technical proposal, the AGV obtain the AGV by TOF sensor and exist
Y-axis coordinate under world coordinate system.
A specific embodiment as above-mentioned technical proposal, loading cabin rear are preset with visual indicia object, institute
State position to obtain the relative coordinate between the AGV and the loading cabin based on image recognition include:
Identify visual indicia object described in described image；
The relative coordinate between the AGV and the loading cabin is determined based on the visual indicia object.
As a second aspect of the invention, the present invention provides a kind of object locating systems for AGV, comprising:
First locating module comprising the laser radar being set on front side of the AGV, first locating module pass through institute
It states laser radar and obtains coordinate of the target point under the AGV local Coordinate System, so that the AGV is moved to according to the coordinate
Target point；
Second locating module comprising be set to the TOF sensor of the side AGV, second locating module passes through
The TOF sensor obtains Y-axis coordinate of the AGV under world coordinate system, so that AGV is being retracted into load from the target point
Hatch door during cargo hold with the loading cabin is kept at a distance；
Third locating module comprising the camera being set on rear side of the AGV, the third locating module pass through described
Camera acquires the image at the rear AGV in real time；
First coordinate obtaining module obtains the phase between the AGV and the loading cabin for positioning based on image recognition
To coordinate, so that the AGV is based on the relative coordinate and exits the loading cabin.
A specific embodiment as above-mentioned technical proposal, first locating module further include: points cloud processing
Module, the point cloud obtained for handling the laser radar, and then obtain seat of the target point under AGV local Coordinate System
Mark.
A specific embodiment as above-mentioned technical proposal, the points cloud processing submodule include:
Point cloud segmentation unit obtains satisfactory cloud for being split by clustering algorithm to described cloud；
Second coordinate acquiring unit is obtained for carrying out operation to the satisfactory cloud by RANSAC algorithm
Coordinate of the target point under AGV local Coordinate System.
A specific embodiment as above-mentioned technical proposal, the second coordinate acquiring unit include:
First chooses subelement, for randomly selecting multiple points in the satisfactory cloud；
Operation subelement obtains and the multiple matched mathematical model of point for operation；
Second chooses subelement, for point unselected in the satisfactory cloud to be substituted into the mathematical model
In, and therefrom choose the point for meeting the mathematical model；
Subelement is recorded, setting number is chosen for making described second to choose subelement iteration, obtains and record to meet institute
State the point of mathematical model；
Coordinate obtains subelement and is repeatedly met for making aforementioned four subelement repeat the second setting number
The point of the mathematical model is therefrom chosen the most primary points of quantity for meeting the point of the mathematical model, and then is obtained described
Coordinate of the target point under AGV local Coordinate System.
A specific embodiment as above-mentioned technical proposal, loading cabin rear are preset with visual indicia object, institute
It states the first coordinate obtaining module and identifies visual indicia object described in described image, based on described in visual indicia object determination
Relative coordinate between AGV and the loading cabin.
(3) beneficial effect
Provided by the present invention for the object localization method and system of AGV, enable AGV that the institute of target point is accurately positioned
, and be smoothly moved at target point, and then delivery/picking or other tasks are completed at target point.
Detailed description of the invention
It is exemplary below with reference to the embodiment of attached drawing description, it is intended to for the explanation and illustration present invention, and cannot manage
Solution is the limitation to protection scope of the present invention.
Fig. 1 is a kind of flow diagram of embodiment of the object localization method for AGV of offer of the invention.
Fig. 2 is a kind of structural block diagram of embodiment of the object locating system for AGV of offer of the invention.
Specific embodiment
To keep the purposes, technical schemes and advantages of the invention implemented clearer, below in conjunction in the embodiment of the present invention
Attached drawing, technical solution in the embodiment of the present invention is further described in more detail.
It should be understood that in the accompanying drawings, from beginning to end same or similar label indicate same or similar element or
Element with the same or similar functions.Described embodiments are some of the embodiments of the present invention, rather than whole implementation
Example, in the absence of conflict, the features in the embodiments and the embodiments of the present application can be combined with each other.Based in the present invention
Embodiment, every other embodiment obtained by those of ordinary skill in the art without making creative efforts,
It shall fall within the protection scope of the present invention.
Herein, " first ", " second " etc. are only used for mutual differentiation, rather than indicate their significance level and sequence
Deng.
The division of module, unit or assembly herein is only a kind of division of logic function, in actual implementation may be used
To there is other division modes, such as multiple modules and/or unit can be combined or are integrated in another system.As separation
The module of part description, unit, component are also possible to indiscrete may be physically separated.It is shown as a unit
Component can be physical unit, may not be physical unit, it can is located at a specific place, may be distributed over grid
In unit.Therefore some or all of units can be selected to realize the scheme of embodiment according to actual needs.
Below with reference to the first embodiment for the object localization method for AGV that Fig. 1 detailed description of the present invention provides.This
Embodiment is mainly used in AGV, enables AGV that the place of target point is accurately positioned, and be smoothly moved at target point, in turn
Delivery/picking or other tasks are completed at target point.
Object localization method provided in this embodiment includes the following steps:
Step 100, AGV positions the coordinate for obtaining target point under AGV local Coordinate System based on laser point cloud, and according to seat
Mark is moved to target point.
By taking AGV delivery/picking as an example, before AGV does not determine target point, AGV first has to obtain target point in AGV itself
Coordinate under coordinate system, moving direction, moving distance required for target point etc. will be reached by obtaining itself, then according to target point
Coordinate it is mobile to target point, until reaching target point.
In one embodiment, for AGV equipped with laser radar, laser radar can generate point cloud data, and AGV passes through processing
The point cloud data that laser radar generates obtains coordinate of the target point under AGV local Coordinate System.
Laser radar is the radar system to emit the characteristic quantities such as the position of detecting laser beam target, speed.Its work is former
Reason is then to be compared the reflected signal of slave target received with transmitting signal to objective emission detectable signal,
After making proper treatment, so that it may obtain target for information about, such as target range, orientation, height, speed, posture, even shape
Parameter, to be detected and be identified to target.Real-time detection is carried out to ambient enviroment by laser radar, and is tied according to detection
Fruit determines the coordinate of target point.
It is waited in the holding fix of a certain setting it is understood that AGV can be, while being taken office in reception in advance
Be engaged in after signal or automatically voluntarily using the target point near laser radar real-time detection, and detect effective target point it
Afterwards, then it is mobile to coordinate where target point.It is also possible to AGV in advance along setting path loopy moving or reciprocating movement, while benefit
With in laser radar real-time detection environment, whether there is or not target points, and after detecting effective target point, coordinate is moved where to target point
It is dynamic.
Point cloud data, also referred to as point cloud, refer to that scanning data records in dots, each point includes three-dimensional coordinate,
Some may contain colouring information or Reflection intensity information.Laser radar is by generating point cloud data as in detection target point
The area of a room can make detection result more accurate full and accurate.
In one embodiment, target point is obtained under AGV local Coordinate System by processing laser radar point cloud
Coordinate the following steps are included:
Step 110, point cloud data is split by change threshold clustering algorithm, obtains satisfactory cloud.It is first
First point cloud data is split using clustering algorithm, i.e., point cloud data is first pre-processed, the not jljl in point cloud is extracted
Body, and according to attributes such as the geometries of target, some obvious undesirable set of point cloud datas are removed, are left relevant to target
Point cloud data, with wait be further processed, this is satisfactory point cloud data.
Step 120, operation is carried out to satisfactory cloud by RANSAC algorithm, obtains target point and is sat in AGV itself
Coordinate under mark system.Operation is carried out using RANSAC algorithm to the satisfactory point cloud data left, finally obtains target point
Coordinate under AGV local Coordinate System.RANSAC (Random Sample Consensus) is to include abnormal number according to one group
According to sample data set, calculate the mathematical model parameter of data, obtain the algorithm of effective sample data.
In one embodiment, step 120 by RANSAC algorithm carries out operation to satisfactory cloud, in turn
Obtain coordinate of the target point under AGV local Coordinate System the following steps are included:
Step 121, multiple points are randomly selected in satisfactory cloud, this multiple point is set as interior group.
Step 122, operation obtains and above-mentioned multiple matched mathematical models of point, the i.e. mathematical model of the suitable interior group of calculating.
Mathematical model can be a variety of simple geometric shapes such as line segment, circle, rectangle or combinations thereof.
Step 123, point unselected in satisfactory cloud is substituted into mathematical model, i.e., by the point other than interior group
It substitutes into the mathematical model established.Later, the point for meeting mathematical model is therefrom chosen.
Step 124, iteration executes step 123, until reach the first setting number, when each iteration can will all meet mathematics
The point of model is put into container, and from last iteration when do not meet mathematical model point in find out and meet the point of mathematical model and be put into
Container obtains up to iteration the first setting number and records the point for meeting mathematical model.
Step 125, iteration executes step 121- step 124 until the second setting number, i.e., repeatedly carry out random selecting point, meter
Calculation model substitutes into model, record point, finally obtains the several point sets of the second setting time, these point sets include meeting when secondary
The point for the mathematical model being calculated selects the most primary points of quantity for meeting the point of mathematical model from these point sets,
It is considered as that RANSAC algorithm operation result is optimal as a result, the point obtained by this time, finally obtains target point in AGV itself seat
Coordinate under mark system.
In one embodiment, during AGV is mobile to target point, it is mobile that AGV is controlled by pid control algorithm
To target point.
Step 200, after AGV is moved to target point, AGV needs to enter in loading cabin, has carried out delivery/picking,
During AGV is entered in cabin from the hatch door in loading cabin, AGV is based on TOF measurement positioning and is obtained from world coordinate system
Under Y-axis coordinate, wherein Y-axis is the axis perpendicular to loading cabin length direction, and AGV is able to reflect AGV in the coordinate of Y-axis
At a distance from fallback procedures between hatch door and after entering loading cabin between bulkhead, the Y-axis by controlling AGV is sat
Mark guarantees that hatch door of AGV during being retracted into loading cabin from target point always with loading cabin is kept at a distance, with loading cabin two
It moves back under the parallel posture of side hatch door to loading cabin, prevents AGV and hatch door from bumping against, also can use the method and guarantee that AGV enters load
Certain distance is remained between bulkhead after cargo hold, prevents AGV and bulkhead from bumping against.
In one embodiment, AGV obtains Y-axis coordinate of the AGV under world coordinate system by TOF sensor.TOF
(Time of flight), i.e. flight time telemetry are a kind of turnaround times by detecting optical pulses to obtain mesh
The method for marking object distance.The equipment that TOF sensor is then that by above-mentioned measurement method.
Step 300, AGV acquires the image at itself rear in real time, and positions to obtain itself and loading cabin based on image recognition
Between relative coordinate so that AGV be based on relative coordinate exit loading cabin.
After AGV completes delivery/picking in loading cabin, AGV needs to exit loading cabin, when AGV is retreated to hatch door,
Due to not having two sides compartment wall, TOF sensor is not available, and AGV can acquire in real time the figure at the rear AGV in fallback procedures at this time
Picture guarantees itself to correct side based on itself relative coordinate between loading cabin is obtained from the content identified in image
It draws back, until exiting loading cabin completely and retreating to target point.
In one embodiment, the rear in loading cabin is preset with visual indicia object, and it is specific that visual indicia object can be certain
Shape, the mark of particular color can distinguish itself with background, and step 300 positions to obtain based on image recognition
Relative coordinate between AGV and loading cabin the following steps are included:
Step 310, visual indicia object in image is identified.
After AGV collects the image at rear, the place of visual indicia object is identified from image.
Step 320, view-based access control model marker determines the relative coordinate between AGV and loading cabin.
AGV determines itself relative coordinate between visual indicia object based on the visual indicia object recognized, so that
AGV is fed back in fallback procedures, guarantees that AGV is finally retreated to target point.
Below with reference to the second embodiment for the object locating system for AGV that Fig. 2 detailed description of the present invention provides.This
The object locating system that embodiment provides is used to implement the object localization method in first embodiment.Target provided in this embodiment
Positioning system includes that the first locating module being electrically connected with AGV, the second locating module, third locating module and the first coordinate obtain
Modulus block.
First locating module includes the laser radar being set on front side of AGV, by laser radar obtain target point AGV from
Coordinate under body coordinate system, so that AGV is moved to target point according to coordinate.
Second locating module includes the TOF sensor for being set to the side AGV, obtains AGV by TOF sensor and sits in the world
Y-axis coordinate under mark system, so that AGV keeps at a distance during being retracted into loading cabin from target point with the hatch door in loading cabin.
Third locating module includes the camera being set on rear side of AGV, acquires the figure at the rear AGV in real time by camera
Picture.
First coordinate obtaining module is used to obtain the image at the rear AGV, and positions to obtain AGV and loading based on image recognition
Relative coordinate between cabin, so that AGV is based on relative coordinate and exits loading cabin.
In one embodiment, the first locating module further includes using with points cloud processing submodule, points cloud processing submodule
In the point cloud data that processing laser radar obtains, and then coordinate of the target point under AGV local Coordinate System is obtained, AGV is according to this
Coordinate is moved to target point.
In one embodiment, points cloud processing submodule includes that point cloud data cutting unit and the second coordinate obtain list
Member.
Point cloud data cutting unit is obtained for being split by the point cloud data that clustering algorithm obtains laser radar
Satisfactory point cloud data.
Second coordinate acquiring unit is satisfactory for being obtained by RANSAC algorithm to point cloud data cutting unit
Point cloud data carries out operation, obtains coordinate of the target point under AGV local Coordinate System.
In one embodiment, the second coordinate acquiring unit includes the first selection subelement, operation subelement, the second choosing
Subelement, record subelement and coordinate is taken to obtain subelement.
First selection subelement for selecting at random in the satisfactory point cloud data that point cloud data cutting unit obtains
Take multiple points.
Operation subelement is electrically connected with the first selection subelement, chooses subelement selection with first for obtaining by operation
The mathematical model that matches of multiple points.
Second selection subelement is electrically connected with operation subelement, for choosing the satisfactory of subelement selection for first
Unselected point substitutes into the mathematical model that operation subelement is established in point cloud data, and therefrom chooses and meet mathematical model
Point.
Record subelement is electrically connected with the second selection subelement, chooses setting for making described second to choose subelement iteration
Number obtains and records the point for meeting the mathematical model；
Coordinate obtains subelement and is electrically connected with the first selection subelement and record subelement, for keeping aforementioned four son single
Member repeats the second setting number, is repeatedly met the point of mathematical model, therefrom chooses the number for meeting the point of mathematical model
The at most primary point of amount, and then obtain coordinate of the target point under AGV local Coordinate System.
In one embodiment, loading cabin rear is preset with visual indicia object, and the first coordinate obtaining module identifies figure
The visual indicia object as in, view-based access control model marker determine the relative coordinate between AGV and loading cabin.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by those familiar with the art, all answers
It is included within the scope of the present invention.Therefore, protection scope of the present invention should be with the scope of protection of the claims
It is quasi-.
Claims (10)
1. a kind of object localization method for AGV characterized by comprising
The coordinate for obtaining target point under AGV local Coordinate System is positioned based on laser point cloud, and mesh is moved to according to the coordinate
Punctuate；
The Y-axis coordinate of the AGV under world coordinate system is obtained based on TOF measurement positioning, so that AGV is from the target point
The hatch door during loading cabin with the loading cabin is retracted into keep at a distance；
The image at the rear AGV is acquired in real time, and positions to obtain between the AGV and the loading cabin based on image recognition
Relative coordinate, so that the AGV is based on the relative coordinate and exits the loading cabin.
2. object localization method according to claim 1, which is characterized in that the AGV passes through the laser thunder that itself is equipped with
Up to the point cloud of generation, coordinate of the target point under AGV local Coordinate System is obtained by described cloud of processing.
3. object localization method according to claim 2, which is characterized in that described to obtain mesh by described cloud of processing
Coordinate of the punctuate under AGV local Coordinate System include:
Described cloud is split by clustering algorithm, obtains satisfactory cloud；
Operation is carried out to the satisfactory cloud by RANSAC algorithm, obtains the target point in AGV local Coordinate System
Under coordinate.
4. object localization method according to claim 3, which is characterized in that described to be met by RANSAC algorithm described
It is required that point cloud carry out operation, obtaining coordinate of the target point under AGV local Coordinate System includes:
(1) multiple points are randomly selected in the satisfactory cloud；
(2) operation obtains and the multiple matched mathematical model of point；
(3) point unselected in the satisfactory cloud is substituted into the mathematical model, and therefrom chooses and meets institute
State the point of mathematical model；
(4) iteration executes (3) step until the first setting number, obtains and record the point for meeting the mathematical model；
(5) iteration executes above-mentioned (1)-(4) step up to the second setting number, is repeatedly met the point of the mathematical model,
The most primary points of quantity for meeting the point of the mathematical model are therefrom chosen, and then obtains the target point and is sat in AGV itself
Coordinate under mark system.
5. object localization method according to claim 1, which is characterized in that loading cabin rear is preset with visual indicia
Object, it is described position to obtain the relative coordinate between the AGV and the loading cabin based on image recognition include:
Identify visual indicia object described in described image；
The relative coordinate between the AGV and the loading cabin is determined based on the visual indicia object.
6. a kind of object locating system for AGV characterized by comprising
First locating module comprising the laser radar being set on front side of the AGV, first locating module are swashed by described
Optical radar obtains coordinate of the target point under the AGV local Coordinate System, so that the AGV is moved to target according to the coordinate
Point；
Second locating module comprising be set to the TOF sensor of the side AGV, second locating module passes through described
TOF sensor obtains Y-axis coordinate of the AGV under world coordinate system, so that AGV is being retracted into loading cabin from the target point
During keep at a distance with the hatch door in the loading cabin；
Third locating module comprising the camera being set on rear side of the AGV, the third locating module pass through the camera shooting
Head acquires the image at the rear AGV in real time；
First coordinate obtaining module, for positioning to obtain the opposite seat between the AGV and the loading cabin based on image recognition
Mark, so that the AGV is based on the relative coordinate and exits the loading cabin.
7. object locating system according to claim 6, which is characterized in that first locating module further include: point cloud
Submodule is handled, the point cloud obtained for handling the laser radar, and then the target point is obtained under AGV local Coordinate System
Coordinate.
8. object locating system according to claim 7, which is characterized in that the points cloud processing submodule includes:
Point cloud segmentation unit obtains satisfactory cloud for being split by clustering algorithm to described cloud；
Second coordinate acquiring unit obtains described for carrying out operation to the satisfactory cloud by RANSAC algorithm
Coordinate of the target point under AGV local Coordinate System.
9. object locating system according to claim 8, which is characterized in that the second coordinate acquiring unit includes:
First chooses subelement, for randomly selecting multiple points in the satisfactory cloud；
Operation subelement obtains and the multiple matched mathematical model of point for operation；
Second chooses subelement, for point unselected in the satisfactory cloud to be substituted into the mathematical model,
And therefrom choose the point for meeting the mathematical model；
Subelement is recorded, setting number is chosen for making described second to choose subelement iteration, obtains and record to meet the number
Learn the point of model；
Coordinate obtains subelement, for making aforementioned four subelement repeat the second setting number, is repeatedly met described
The point of mathematical model therefrom chooses the most primary points of quantity for meeting the point of the mathematical model, and then obtains the target
Coordinate of the point under AGV local Coordinate System.
10. object locating system according to claim 6, which is characterized in that loading cabin rear is preset with vision mark
Remember object, first coordinate obtaining module identifies visual indicia object described in described image, true based on the visual indicia object
Relative coordinate between the fixed AGV and the loading cabin.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810847522.3A CN109100744B (en) | 2018-07-27 | 2018-07-27 | Target positioning method and system for AGV |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810847522.3A CN109100744B (en) | 2018-07-27 | 2018-07-27 | Target positioning method and system for AGV |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109100744A true CN109100744A (en) | 2018-12-28 |
| CN109100744B CN109100744B (en) | 2021-03-30 |
Family
ID=64847873
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810847522.3A Active CN109100744B (en) | 2018-07-27 | 2018-07-27 | Target positioning method and system for AGV |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109100744B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110260875A (en) * | 2019-06-20 | 2019-09-20 | 广州蓝胖子机器人有限公司 | A kind of method in Global motion planning path, Global motion planning device and storage medium |
| CN111533051A (en) * | 2020-05-08 | 2020-08-14 | 三一机器人科技有限公司 | Tray pose detection method and device, forklift and freight system |
| CN113284197A (en) * | 2021-07-22 | 2021-08-20 | 浙江华睿科技股份有限公司 | TOF camera external reference calibration method and device for AGV, and electronic equipment |
| WO2021249572A1 (en) * | 2020-06-12 | 2021-12-16 | 深圳市海柔创新科技有限公司 | Goods retrieval control method and system, transportation robot, and storage medium |
| CN116580098A (en) * | 2023-07-12 | 2023-08-11 | 中科领航智能科技(苏州)有限公司 | Cabin door position detection method for automatic leaning machine system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105841687A (en) * | 2015-01-14 | 2016-08-10 | 上海智乘网络科技有限公司 | Indoor location method and indoor location system |
| CN105974922A (en) * | 2016-06-29 | 2016-09-28 | 上海诺力智能科技有限公司 | Tunnel automatic guide vehicle, guide system, and operating method for guide system |
| CN106127153A (en) * | 2016-06-24 | 2016-11-16 | 南京林业大学 | The traffic sign recognition methods of Vehicle-borne Laser Scanning cloud data |
| US20160341041A1 (en) * | 2014-01-14 | 2016-11-24 | Sandvik Mining And Construction Oy | Mine vehicle and method of determining position and direction of monitored object |
| CN206671564U (en) * | 2016-12-21 | 2017-11-24 | 深圳市镭神智能系统有限公司 | Intelligent vehicle CAS based on laser radar |
| CN207148647U (en) * | 2017-04-26 | 2018-03-27 | 北京饮冰科技有限公司 | A kind of positioning of sweeping robot and navigation plotting board |
| CN108007451A (en) * | 2017-11-10 | 2018-05-08 | 未来机器人（深圳）有限公司 | Detection method, device, computer equipment and the storage medium of cargo carrying device pose |
| CN108008413A (en) * | 2018-01-15 | 2018-05-08 | 上海兰宝传感科技股份有限公司 | A kind of multi-faceted distributed electro-optical distance measurement obstacle avoidance system and method |
| CN108089574A (en) * | 2016-11-22 | 2018-05-29 | 永恒力股份公司 | For providing the method and material carrier of the position of the storage position in warehouse |
-
2018
- 2018-07-27 CN CN201810847522.3A patent/CN109100744B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160341041A1 (en) * | 2014-01-14 | 2016-11-24 | Sandvik Mining And Construction Oy | Mine vehicle and method of determining position and direction of monitored object |
| CN105841687A (en) * | 2015-01-14 | 2016-08-10 | 上海智乘网络科技有限公司 | Indoor location method and indoor location system |
| CN106127153A (en) * | 2016-06-24 | 2016-11-16 | 南京林业大学 | The traffic sign recognition methods of Vehicle-borne Laser Scanning cloud data |
| CN105974922A (en) * | 2016-06-29 | 2016-09-28 | 上海诺力智能科技有限公司 | Tunnel automatic guide vehicle, guide system, and operating method for guide system |
| CN108089574A (en) * | 2016-11-22 | 2018-05-29 | 永恒力股份公司 | For providing the method and material carrier of the position of the storage position in warehouse |
| CN206671564U (en) * | 2016-12-21 | 2017-11-24 | 深圳市镭神智能系统有限公司 | Intelligent vehicle CAS based on laser radar |
| CN207148647U (en) * | 2017-04-26 | 2018-03-27 | 北京饮冰科技有限公司 | A kind of positioning of sweeping robot and navigation plotting board |
| CN108007451A (en) * | 2017-11-10 | 2018-05-08 | 未来机器人（深圳）有限公司 | Detection method, device, computer equipment and the storage medium of cargo carrying device pose |
| CN108008413A (en) * | 2018-01-15 | 2018-05-08 | 上海兰宝传感科技股份有限公司 | A kind of multi-faceted distributed electro-optical distance measurement obstacle avoidance system and method |
Non-Patent Citations (1)
| Title |
|---|
| 钟明: "基于激光雷达构建室内三维地图关键技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110260875A (en) * | 2019-06-20 | 2019-09-20 | 广州蓝胖子机器人有限公司 | A kind of method in Global motion planning path, Global motion planning device and storage medium |
| CN111533051A (en) * | 2020-05-08 | 2020-08-14 | 三一机器人科技有限公司 | Tray pose detection method and device, forklift and freight system |
| WO2021249572A1 (en) * | 2020-06-12 | 2021-12-16 | 深圳市海柔创新科技有限公司 | Goods retrieval control method and system, transportation robot, and storage medium |
| CN113284197A (en) * | 2021-07-22 | 2021-08-20 | 浙江华睿科技股份有限公司 | TOF camera external reference calibration method and device for AGV, and electronic equipment |
| CN113284197B (en) * | 2021-07-22 | 2021-11-23 | 浙江华睿科技股份有限公司 | TOF camera external reference calibration method and device for AGV, and electronic equipment |
| CN116580098A (en) * | 2023-07-12 | 2023-08-11 | 中科领航智能科技(苏州)有限公司 | Cabin door position detection method for automatic leaning machine system |
| CN116580098B (en) * | 2023-07-12 | 2023-09-15 | 中科领航智能科技(苏州)有限公司 | Cabin door position detection method for automatic leaning machine system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109100744B (en) | 2021-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109100744A (en) | Object localization method and system for AGV | |
| EP3293669B1 (en) | Enhanced camera object detection for automated vehicles | |
| CN110673115B (en) | Combined calibration method, device, equipment and medium for radar and integrated navigation system | |
| Thrun et al. | Probabilistic Terrain Analysis For High-Speed Desert Driving. | |
| JP6843773B2 (en) | Environmental scanning and unmanned aerial vehicle tracking | |
| CN110275538A (en) | Intelligent cruise vehicle navigation method and system | |
| KR101003168B1 (en) | Multidimensional Evidence Grids and System and Methods for Applying Same | |
| EP1034440B1 (en) | A system for determining the spatial position and orientation of a body | |
| US9857178B2 (en) | Method for position and location detection by means of virtual reference images | |
| EP3220227A1 (en) | Inspection system and method for performing inspections in a storage facility | |
| JP2015006874A (en) | Systems and methods for autonomous landing using three dimensional evidence grid | |
| CN108873904B (en) | Unmanned parking method and device for mining vehicle and readable storage medium | |
| CN106990781A (en) | Automatic dock AGV localization methods based on laser radar and image information | |
| CN107738852A (en) | Localization method, positioning map construction method and robot | |
| CN108460314A (en) | Article inspection method and related Equipment | |
| Ortiz et al. | Vessel inspection: A micro-aerial vehicle-based approach | |
| CN110162066A (en) | Intelligent cruise control system | |
| CN111397609A (en) | Route planning method, mobile machine and computer readable medium | |
| EP3979032A1 (en) | Systems and methods for enabling navigation in environments with dynamic objects | |
| Armingol et al. | Landmark perception planning for mobile robot localization | |
| Lee et al. | Cyber Physical Autonomous Mobile Robot (CPAMR) framework in the context of industry 4.0 | |
| CN111380535A (en) | Navigation method and device based on visual label, mobile machine and readable medium | |
| US11348278B2 (en) | Object detection | |
| US20240078914A1 (en) | Navigation System for Unmanned Aircraft in Unknown Environments | |
| Ortiz et al. | Saliency-driven Visual Inspection of Vessels by means of a Multirotor |
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 | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: H6-2 depot of Chiwan oil base, No.2 zuobaotai Road, Nanshan District, Shenzhen, Guangdong 518000 Patentee after: Shenzhen Lan pangzi machine intelligence Co.,Ltd. Address before: H6-2 depot of Chiwan oil base, No.2 zuobaotai Road, Nanshan District, Shenzhen, Guangdong 518000 Patentee before: SHENZHEN DORABOT Inc. |
|
| CP02 | Change in the address of a patent holder | ||
| CP02 | Change in the address of a patent holder |
Address after: 523000 reservoir H6, Chiwan left battery Road, Chiwan community, merchants street, Nanshan District, Shenzhen City, Guangdong Province Patentee after: Shenzhen Lan pangzi machine intelligence Co.,Ltd. Address before: H6-2 depot of Chiwan oil base, No.2 zuobaotai Road, Nanshan District, Shenzhen, Guangdong 518000 Patentee before: Shenzhen Lan pangzi machine intelligence Co.,Ltd. |
|
| PP01 | Preservation of patent right | ||
| PP01 | Preservation of patent right |
Effective date of registration: 20240722 Granted publication date: 20210330 |