CN110274607A - Intelligent paths planning method, device and computer readable storage medium - Google Patents
Intelligent paths planning method, device and computer readable storage medium Download PDFInfo
- Publication number
- CN110274607A CN110274607A CN201910421931.1A CN201910421931A CN110274607A CN 110274607 A CN110274607 A CN 110274607A CN 201910421931 A CN201910421931 A CN 201910421931A CN 110274607 A CN110274607 A CN 110274607A
- Authority
- CN
- China
- Prior art keywords
- random number
- loudness
- initialization
- path planning
- prediction
- 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
- 238000000034 method Methods 0.000 title claims abstract description 81
- 238000003860 storage Methods 0.000 title claims abstract description 20
- 230000004888 barrier function Effects 0.000 claims abstract description 44
- 238000004422 calculation algorithm Methods 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 21
- 230000015654 memory Effects 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 18
- 230000035772 mutation Effects 0.000 claims description 10
- 230000007797 corrosion Effects 0.000 claims description 8
- 238000005260 corrosion Methods 0.000 claims description 8
- 230000008602 contraction Effects 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 239000004744 fabric Substances 0.000 claims description 5
- 125000004122 cyclic group Chemical group 0.000 claims description 4
- 230000002708 enhancing effect Effects 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 abstract 1
- 238000009826 distribution Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012886 linear function Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
Classifications
-
- 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
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
Abstract
The present invention relates to a kind of artificial intelligence technologys, disclose a kind of intelligence paths planning method, comprising: receive the marked map picture of barrier out and initialization speed, carry out grid division simultaneously initialized location to the map picture of the marked barrier outWith final positionPulse frequency f is randomly generatedt, impulse ejection rate RtWith loudness AtAfterwards, uniform random number rand is generated, and judges the uniform random number rand and the initialization pulse emissivity RtWith loudness AtSize relation, and solve the optimal direction solution x of the initial*And local solutionAfterwards, until the local solutionWith the final positionIn same grid, optimal path finally is completed in conjunction with the local solution of each time and is exported.The present invention also proposes a kind of intelligent path planning apparatus and a kind of computer readable storage medium.Accurately intelligent path planning function may be implemented in the present invention.
Description
Technical field
The present invention relates to field of artificial intelligence more particularly to a kind of intelligent path planning sides based on map picture
Method, device and computer readable storage medium.
Background technique
Intelligent path planning algorithm belongs to emerging meta-heuristic algorithm, because of its peculiar advantage, is ground in recent years
The concern for the person of studying carefully is increasingly becoming the hot issue in intelligence computation field, and relevant scientific achievement also increasingly increases, and dispatches in FJSP
All various research achievements such as problem, function optimization, wireless sensor, cloud manufacturing supply chain increasingly emerge.However, current
The defects of optimizing accuracy existing for intelligent path planning algorithm is not high, and it is optimal to be easily trapped into partial region, precocious, and it is current
Intelligent path planning algorithm low optimization accuracy it is not high, late convergence is slow, easily fall into local optimum, although both at home and abroad it is various
Scholar has carried out different degrees of improvement, achieves achievement, but whether highest its precision is also, in path planning problem
On, it may not be optimal solution.
Summary of the invention
The present invention provides a kind of intelligent paths planning method, device and computer readable storage medium, main purpose
Be when user using path planning recommend when, show accurately path planning recommendation results to user.
To achieve the above object, a kind of intelligent paths planning method provided by the invention, comprising:
Step A: picture process layer receives the marked map picture of barrier out and initialization speed vt, wherein t is indicated
Time, and based on Grid Method to it is described it is marked go out barrier map picture carry out grid division and obtain grating map, and
The initial position in setting path in the grating mapWith final positionAnd pulse frequency f is randomly generatedt, impulse ejection
Rate RtWith loudness AtValue, by the grating map, the initialization speed vt, the pulse frequency ft, impulse ejection rate RtWith
Loudness AtValue be input to path planning layer;
Step B: the time t is updated to t+1 by the path planning layer, and is generated based on Gaussian mutation algorithm and uniformly divided
Cloth random number rand;
Step C: judge the uniform random number rand and the initialization pulse emissivity RtSize relation;
Step D: when the uniform random number rand is less than the initialization pulse emissivity RtWhen, judge described equal
The even distribution random numbers rand and loudness AtSize relation;
Step E: when the uniform random number rand is less than the loudness AtWhen, update the initialization pulse transmitting
Rate RtFor Rt+1, the loudness AtValue is At+1, and D is returned to step, when the value of the uniform random number rand is between institute
State initialization pulse emissivity RtWith loudness AtBetween, then return to step B;
Step F: when the uniform random number rand is greater than the initialization pulse emissivity RtWhen, it is changed based on newton
The optimal direction solution x in the initial is solved for method*, in conjunction with the optimal direction solution x*, predict the initial position
In the center of t+1 timeAnd predict the local solution of centerThe pulse frequency ftFor ft+1, it is described
Initialize speed vtFor vt+1;
Step G: judge the prediction centerWith the final positionWhether in same grid, work as institute
State prediction centerWith the final positionNot in same grid, then updating current location is the local solutionUpdate current PRF frequency is ft+1, update current initialization speed is vt+1, and B is returned to step, when described pre-
Measured center positionWith the final positionIn same grid, the path planning layer combines the local solution of each time
It completes optimal path and exports.
Optionally, described that grid are obtained based on map picture progress grid division of the Grid Method to the marked barrier out
Lattice map, comprising:
The picture process layer carries out unit segmentation to the map picture of the marked barrier out, obtains multiple lists
Member, the multiple unit are fixed for size, the identical square of resolution ratio;
Image pretreatment operation is carried out to the multiple unit, described image pretreatment operation includes expansion, corrosion and two
Value;
A mole wheel for field track algorithm extraction barrier is used to multiple units that described image pretreatment operation is completed
Exterior feature obtains the grating map.
Optionally, the initial position of predictionThe t+1 time center are as follows:
The local solution of the center of prediction are as follows:
The pulse frequency of prediction are as follows:
ft+1=fmin+(fmax-fmin)β
The initialization speed of prediction are as follows:
Wherein, ε is contraction factor, and β is the random number generated in [0,1], fmin, fmaxRespectively indicate the minimum of pulse frequency
Value and maximum value.
Optionally, the Newton iteration method includes solving coordinate and Iterative path;
Wherein, the solution coordinate are as follows:
The Iterative path are as follows:
Wherein, x0It is the Newton iteration method close to the coordinate value of zero point, f (x0) it is curvilinear function, f ' (x0) it is the song
The derivative function of line function.
Optionally, the initialization pulse emissivity of update are as follows:
Rt+1=Rt(1-e-γt)
The loudness updated are as follows:
At+1=α At
Wherein, the enhancing coefficient of γ impulse ejection rate, α are the attenuation coefficient of volume, and e is Infinite Cyclic irrational number.
In addition, to achieve the above object, the present invention also provides a kind of intelligent path planning apparatus, which includes storage
Device and processor are stored with the intelligent path planning program that can be run on the processor, the intelligence in the memory
It can change when path planning program is executed by the processor and realize following steps:
Step A: picture process layer receives the marked map picture of barrier out and initialization speed vt, wherein t is indicated
Time, and based on Grid Method to it is described it is marked go out barrier map picture carry out grid division and obtain grating map, and
The initial position in setting path in the grating mapWith final positionAnd pulse frequency f is randomly generatedt, impulse ejection
Rate RtWith loudness AtValue, by the grating map, the initialization speed vt, the pulse frequency ft, impulse ejection rate RtWith
Loudness AtValue be input to path planning layer;
Step B: the time t is updated to t+1 by the path planning layer, and is generated based on Gaussian mutation algorithm and uniformly divided
Cloth random number rand;
Step C: judge the uniform random number rand and the initialization pulse emissivity RtSize relation;
Step D: when the uniform random number rand is less than the initialization pulse emissivity RtWhen, judge described equal
The even distribution random numbers rand and loudness AtSize relation;
Step E: when the uniform random number rand is less than the loudness AtWhen, update the initialization pulse transmitting
Rate RtFor Rt+1, the loudness AtValue is At+1, and D is returned to step, when the value of the uniform random number rand is between institute
State initialization pulse emissivity RtWith loudness AtBetween, then return to step B;
Step F: when the uniform random number rand is greater than the initialization pulse emissivity RtWhen, it is changed based on newton
The optimal direction solution x in the initial is solved for method*, in conjunction with the optimal direction solution x*, predict the initial position
In the center of t+1 timeAnd predict the local solution of centerThe pulse frequency ftFor ft+1, it is described
Initialize speed vtFor vt+1;
Step G: judge the prediction centerWith the final positionWhether in same grid, work as institute
State prediction centerWith the final positionNot in same grid, then updating current location is the local solutionUpdate current PRF frequency is ft+1, update current initialization speed is vt+1, and B is returned to step, when described pre-
Measured center positionWith the final positionIn same grid, the path planning layer combines the local solution of each time
It completes optimal path and exports.
Optionally, described that grid are obtained based on map picture progress grid division of the Grid Method to the marked barrier out
Lattice map, comprising:
The picture process layer carries out unit segmentation to the map picture of the marked barrier out, obtains multiple lists
Member, the multiple unit are fixed for size, the identical square of resolution ratio;
Image pretreatment operation is carried out to the multiple unit, described image pretreatment operation includes expansion, corrosion and two
Value;
A mole wheel for field track algorithm extraction barrier is used to multiple units that described image pretreatment operation is completed
Exterior feature obtains the grating map.
Optionally, the initial position of predictionThe center of t+1 time be
The local solution of the center of prediction are as follows:
The pulse frequency of prediction are as follows:
ft+1=fmin+(fmax-fmin)β
The initialization speed of prediction are as follows:
Wherein, ε is contraction factor, and β is the random number generated in [0,1], fmin, fmaxRespectively indicate the minimum of pulse frequency
Value and maximum value.
Optionally, the Newton iteration method includes solving coordinate and Iterative path;
Wherein, the solution coordinate are as follows:
The Iterative path are as follows:
Wherein, x0It is the Newton iteration method close to the coordinate value of zero point, f (x0) it is curvilinear function, f ' (x0) it is the song
The derivative function of line function.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer readable storage medium
Intelligent path planning program is stored on storage medium, the intelligence path planning program can be handled by one or more
The step of device executes, intelligent paths planning method as described above with realization.
Intelligence paths planning method, device and computer readable storage medium proposed by the present invention, mainly pass through grid
Method to map is divided, and is based on the intelligent paths planning method in initial position and is started to search for, and is searched out next
The optimum position at time point, and judge whether the optimum position meets the requirements according to uniform random number, until last defeated
Optimal path planning out.The present invention has reseted the calculation method of loudness and pulse frequency, can avoid when carrying out path planning
Local optimum is fallen into, and introduces local solution concept and improves path planning accuracy rate.Therefore accurately path may be implemented in the present invention
Planning function.
Detailed description of the invention
Fig. 1 is the flow diagram for the intelligent paths planning method that one embodiment of the invention provides;
Fig. 2 is the schematic diagram of internal structure for the intelligent path planning apparatus that one embodiment of the invention provides;
The module of intelligent path planning program in the intelligent path planning apparatus that Fig. 3 provides for one embodiment of the invention
Schematic diagram.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The present invention provides a kind of intelligent paths planning method.It is the intelligence that one embodiment of the invention provides shown in referring to Fig.1
The flow diagram of paths planning method can be changed.This method can be executed by device, which can be by software and/or hard
Part is realized.
In the present embodiment, intelligent paths planning method includes:
S1, picture process layer receive the marked map picture of barrier out and initialization speed vt, when wherein t is indicated
Between, and grid division is carried out based on map picture of the Grid Method to the marked barrier out and obtains grating map, and in institute
State the initial position in setting path in grating mapWith final positionAnd pulse frequency f is randomly generatedt, impulse ejection rate
RtWith loudness AtValue, by the grating map, the initialization speed vt, the pulse frequency ft, impulse ejection rate RtAnd sound
Spend AtValue be input to path planning layer.
The preparation method of the marked map picture of barrier out includes: first to map to original map picture pixels
[0-155] marks barrier with the set of pixels in [155-200].
In present pre-ferred embodiments, the picture process layer carries out the map picture of the marked barrier out single
Member segmentation obtains multiple units, and the multiple unit fixes for size and identical square, carries out image to the multiple unit
Pretreatment operation, described image pretreatment operation include the processing such as expansion, corrosion and binaryzation.Wherein, the expansion process packet
The each pixel included in structural element and the marked map picture of barrier out using 3*3 does OR operation.It is described
Corrosion treatment includes that each pixel in structural element and the marked map picture of barrier out using 3*3 does "AND"
Operation.The binarization operation includes first given threshold, and when the pixel is less than the threshold value, the pixel value becomes 0, when
When the pixel is greater than the threshold value, the pixel value becomes 1, therefore each of in the marked map picture of barrier out
The pixel value of pixel becomes 0 or 255.
Present pre-ferred embodiments calculate multiple units that described image pretreatment operation is completed using a mole field tracking
Method extracts the profile of barrier, obtains the grating map.Described mole of field track algorithm is also referred to as oblique neighborhood algorithm, substantially
Thought is to find a black picture element, and it is defined as starting pixels.Wherein, a variety of sides can be used by positioning the starting pixels
Formula, one of method are as follows: since the lower left corner pixel of the multiple unit, scan each column pixel from bottom to top until most
Then topmost pixel starts according to the top pixel, scan each column pixel from left to right, until encountering a black
Pixel, and as starting pixels.
The time t is updated to t+1 by S2, the path planning layer, and is uniformly distributed based on the generation of Gaussian mutation algorithm
Random number rand, and judge the uniform random number rand and the initialization pulse emissivity RtSize relation.
In present pre-ferred embodiments, the Gaussian mutation algorithm is using a mean μ, the normal distribution that variance is σ 2
A random number generate the uniform random number rand.
S3, when the uniform random number rand be less than the initialization pulse emissivity RtWhen, judge described uniform
The distribution random numbers rand and loudness AtSize relation, when the value of the uniform random number rand is between described initial
Change impulse ejection rate RtWith loudness AtBetween, then it returns and executes S2.
S4, when the uniform random number rand be less than the loudness AtWhen, update the initialization pulse emissivity Rt
For Rt+1, the loudness AtValue is At+1, and return and execute S3.
Present pre-ferred embodiments update the initialization pulse emissivity R using following functionstFor Rt+1:
Rt+1=Rt(1-e-γt)
The loudness A is updated using following functionstValue is At+1:
At+1=α At
Wherein, the enhancing coefficient of γ impulse ejection rate, α are the attenuation coefficient of volume, and e is Infinite Cyclic irrational number.
S5, when the uniform random number rand be greater than the initialization pulse emissivity RtWhen, it is based on Newton iteration
Method solves the optimal direction solution x in the initial*, in conjunction with the optimal direction solution x*, predict the initial positionIn t
The center of+1 timeAnd predict the local solution of centerThe pulse frequency ftFor ft+1, described first
Beginningization speed vtFor vt+1。
Newton iteration method described in present pre-ferred embodiments includes solving coordinate and Iterative path;
Wherein, the solution coordinate are as follows:
The Iterative path are as follows:
Wherein, x0It is the Newton iteration method close to the coordinate value of zero point, f (x0) it is curvilinear function, it is traditionally arranged to be binary
Linear function, f ' (x0) be the curvilinear function derivative function.
The initial position of present pre-ferred embodiments predictionT+1 time location be
The local solution of the center of prediction are as follows:
The pulse frequency of prediction are as follows:
ft+1=fmin+(fmax-fmin)β
The initialization speed of prediction are as follows:
Wherein, ε is contraction factor, and β is the random number generated in [0,1], fmin, fmaxRespectively indicate the minimum of pulse frequency
Value and maximum value.
S6, judge the prediction centerWith the final positionWhether in same grid.
S7, when the prediction centerWith the final positionNot in same grid, then present bit is updated
It is set to the local solutionUpdate current PRF frequency is ft+1, update current initialization speed is vt+1, and return to execution
S2。
S8, when the prediction centerWith the final positionIn same grid, the path planning layer
Prediction local solution in conjunction with each time is completed optimal path and is exported.
Present pre-ferred embodiments, as the position of t time isThe local solution of t+1 timeThe office of t+n time
Portion's solutionIn conjunction with the position of institute's having time, it may be determined that the path optimum programming simultaneously exports.
Invention also provides a kind of intelligent path planning apparatus.It is the intelligence that one embodiment of the invention provides referring to shown in Fig. 2
The schematic diagram of internal structure of path planning apparatus can be changed.
In the present embodiment, the intelligent path planning apparatus 1 can be PC (Personal Computer, personal electricity
Brain) or terminal devices such as smart phone, tablet computer, portable computer, it is also possible to a kind of server etc..The intelligence
Change path planning apparatus 1 and includes at least memory 11, processor 12, communication bus 13 and network interface 14.
Wherein, memory 11 include at least a type of readable storage medium storing program for executing, the readable storage medium storing program for executing include flash memory,
Hard disk, multimedia card, card-type memory (for example, SD or DX memory etc.), magnetic storage, disk, CD etc..Memory 11
It can be the internal storage unit of intelligent path planning apparatus 1, such as intelligence path planning dress in some embodiments
Set 1 hard disk.Memory 11 is also possible to the External memory equipment of intelligent path planning apparatus 1 in further embodiments,
Such as the plug-in type hard disk being equipped on intelligent path planning apparatus 1, intelligent memory card (Smart Media Card, SMC), peace
Digital (Secure Digital, SD) card, flash card (Flash Card) etc..Further, memory 11 can also be wrapped both
The internal storage unit for including intelligent path planning apparatus 1 also includes External memory equipment.Memory 11 can be not only used for depositing
Storage is installed on the application software and Various types of data of intelligent path planning apparatus 1, such as the generation of intelligent path planning program 01
Code etc., can be also used for temporarily storing the data that has exported or will export.
Processor 12 can be in some embodiments a central processing unit (Central Processing Unit,
CPU), controller, microcontroller, microprocessor or other data processing chips, the program for being stored in run memory 11
Code or processing data, such as execute intelligent path planning program 01 etc..
Communication bus 13 is for realizing the connection communication between these components.
Network interface 14 optionally may include standard wireline interface and wireless interface (such as WI-FI interface), be commonly used in
Communication connection is established between the device 1 and other electronic equipments.
Optionally, which can also include user interface, and user interface may include display (Display), input
Unit such as keyboard (Keyboard), optional user interface can also include standard wireline interface and wireless interface.It is optional
Ground, in some embodiments, display can be light-emitting diode display, liquid crystal display, touch-control liquid crystal display and OLED
(Organic Light-Emitting Diode, Organic Light Emitting Diode) touches device etc..Wherein, display can also be appropriate
Referred to as display screen or display unit, for be shown in the information handled in intelligent path planning apparatus 1 and for show can
Depending on the user interface changed.
Fig. 2 illustrates only the intelligent path planning apparatus with component 11-14 and intelligent path planning program 01
1, it will be appreciated by persons skilled in the art that structure shown in fig. 1 does not constitute the limit to intelligent path planning apparatus 1
It is fixed, it may include perhaps combining certain components or different component layouts than illustrating less perhaps more components.
In 1 embodiment of device shown in Fig. 2, intelligent path planning program 01 is stored in memory 11;Processor
Following steps are realized when the intelligent path planning program 01 stored in 12 execution memories 11:
Step 1: picture process layer receives the marked map picture of barrier out and initialization speed vt, wherein t is indicated
Time, and based on Grid Method to it is described it is marked go out barrier map picture carry out grid division and obtain grating map, and
The initial position in setting path in the grating mapWith final positionAnd pulse frequency f is randomly generatedt, impulse ejection
Rate RtWith loudness AtValue, by the grating map, the initialization speed vt, the pulse frequency ft, impulse ejection rate RtWith
Loudness AtValue be input to path planning layer.
The preparation method of the marked map picture of barrier out includes: first to map to original map picture pixels
[0-155] marks barrier with the set of pixels in [155-200].
In present pre-ferred embodiments, the picture process layer carries out the map picture of the marked barrier out single
Member segmentation obtains multiple units, and the multiple unit fixes for size and identical square, carries out image to the multiple unit
Pretreatment operation, described image pretreatment operation include the processing such as expansion, corrosion and binaryzation.Wherein, the expansion process packet
The each pixel included in structural element and the marked map picture of barrier out using 3*3 does OR operation;It is described
Corrosion treatment includes that each pixel in structural element and the marked map picture of barrier out using 3*3 does "AND"
Operation;The binarization operation includes first given threshold, and when the pixel is less than the threshold value, the pixel value becomes 0, when
When the pixel is greater than the threshold value, the pixel value becomes 1, therefore each of in the marked map picture of barrier out
The pixel value of pixel becomes 0 or 255.
Present pre-ferred embodiments calculate multiple units that described image pretreatment operation is completed using a mole field tracking
Method extracts the profile of barrier, obtains the grating map.Described mole of field track algorithm is also referred to as oblique neighborhood algorithm, substantially
Thought is to find a black picture element, and it is defined as starting pixels.Wherein, a variety of sides can be used by positioning the starting pixels
Formula, one of method are as follows: since the lower left corner pixel of the multiple unit, scan each column pixel from bottom to top until most
Then topmost pixel starts according to the top pixel, scan each column pixel from left to right, until encountering a black
Pixel, and as starting pixels.
Step 2: the time t is updated to t+1 by the path planning layer, and is generated uniformly based on Gaussian mutation algorithm
Distribution random numbers rand, and judge the uniform random number rand and the initialization pulse emissivity RtSize close
System.
In present pre-ferred embodiments, the Gaussian mutation algorithm is using a mean μ, the normal distribution that variance is σ 2
A random number generate the uniform random number rand.
Step 3: when the uniform random number rand is less than the initialization pulse emissivity RtWhen, described in judgement
The uniform random number rand and loudness AtSize relation, when the value of the uniform random number rand is between described
Initialization pulse emissivity RtWith loudness AtBetween, then return to step two.
Step 4: when the uniform random number rand is less than the loudness AtWhen, update the initialization pulse hair
Penetrate rate RtFor Rt+1, the loudness AtValue is At+1, and return to step three.
Present pre-ferred embodiments update the initialization pulse emissivity R using following functionstFor Rt+1:
Rt+1=Rt(1-e-γt)
The loudness A is updated using following functionstValue is At+1:
At+1=α At
Wherein, the enhancing coefficient of γ impulse ejection rate, α are the attenuation coefficient of volume, and e is Infinite Cyclic irrational number.
Step 5: when the uniform random number rand is greater than the initialization pulse emissivity RtWhen, it is based on newton
Optimal direction solution x in initial described in solution by iterative method*, in conjunction with the optimal direction solution x*, predict the initial positionIn the center of t+1 timeAnd predict the local solution of centerThe pulse frequency ftFor ft+1, institute
State initialization speed vtFor vt+1。
Newton iteration method described in present pre-ferred embodiments includes solving coordinate and Iterative path;
Wherein, the solution coordinate are as follows:
The Iterative path are as follows:
Wherein, x0It is the Newton iteration method close to the coordinate value of zero point, f (x0) it is curvilinear function, it is traditionally arranged to be binary
Linear function, f ' (x0) be the curvilinear function derivative function.
The initial position of present pre-ferred embodiments predictionT+1 time location be
The local solution of the center of prediction are as follows:
The pulse frequency of prediction are as follows:
ft+1=fmin+(fmax-fmin)β
The initialization speed of prediction are as follows:
Wherein, ε is contraction factor, and β is the random number generated in [0,1], fmin, fmaxRespectively indicate the minimum of pulse frequency
Value and maximum value.
Step 6: judging the prediction centerWith the final positionWhether in same grid.
Step 7: working as the prediction centerWith the final positionNot in same grid, then updates and work as
Anteposition is set to the local solutionUpdate current PRF frequency is ft+1, update current initialization speed is vt+1, and return
Execute step 2.
Step 8: working as the prediction centerWith the final positionIn same grid, the path rule
Layer is drawn to combine the prediction local solution of each time to complete optimal path and export.
Present pre-ferred embodiments, as the position of t time isThe local solution of t+1 timeThe office of t+n time
Portion's solutionIn conjunction with the position of institute's having time, it may be determined that the path optimum programming simultaneously exports.
Optionally, in other embodiments, intelligent path planning program can also be divided into one or more mould
Block, one or more module are stored in memory 11, and (the present embodiment is processor by one or more processors
12) performed to complete the present invention, so-called module of the invention is to refer to multiple computer programs of completion specific function to refer to
Section is enabled, for describing implementation procedure of the intelligent path planning program in intelligent path planning apparatus.
For example, referring to shown in Fig. 3, for the intelligent path in intelligent one embodiment of paths planning method device of the present invention
The program module schematic diagram of planing method program, in the embodiment, the intelligence paths planning method program can be divided
Illustratively for map picture receiving module 10, pulse judgment module 20, loudness judgment module 30, path output module 40:
The map picture receiving module 10 is used for: receiving the marked map picture of barrier out and initialization speed
vt, wherein t indicates the time, and carries out grid division based on map picture of the Grid Method to the marked barrier out and obtain grid
Lattice map, and in the grating map be arranged path initial positionWith final positionAnd pulse frequency is randomly generated
ft, impulse ejection rate RtWith loudness AtValue, by the grating map, the initialization speed vt, the pulse frequency ft, pulse
Emissivity RtWith loudness AtValue be input to path planning layer.
The pulse judgment module 20 is used for: the time t being updated to t+1, and is generated based on Gaussian mutation algorithm
Even distribution random numbers rand, and judge the uniform random number rand and the initialization pulse emissivity RtSize close
System.
The loudness judgment module 30 is used for: when the uniform random number rand emits less than the initialization pulse
Rate RtWhen, further judge the uniform random number rand and the loudness AtSize relation, when it is described be uniformly distributed with
Machine number rand is less than the loudness AtWhen, update the initialization pulse emissivity RtFor Rt+1, the loudness AtValue is At+1。
The path output module 40 is used for: when the uniform random number rand emits greater than the initialization pulse
Rate RtWhen, the optimal direction solution x in the initial is solved based on Newton iteration method*, in conjunction with the optimal direction solution x*, in advance
Survey the initial positionIn the center of t+1 timeAnd predict the local solution of centerThe pulse
Frequency ftFor ft+1, the initialization speed vtFor vt+1;When the prediction centerWith the final positionDo not exist
In same grid, then updating current location is the local solutionUpdate current PRF frequency is ft+1, update current initial
Change speed is vt+1, when the prediction centerWith the final positionIn same grid, the path planning
Layer combines the local solution of each time to complete optimal path and exports.
Above-mentioned map picture receiving module 10, pulse judgment module 20, loudness judgment module 30, path output module 40 etc.
Program module is performed realized functions or operations step and is substantially the same with above-described embodiment, and details are not described herein.
In addition, the embodiment of the present invention also proposes a kind of computer readable storage medium, the computer readable storage medium
On be stored with intelligent path planning program, the intelligence path planning program can be executed by one or more processors, with
Realize following operation:
Step A: picture process layer receives the marked map picture of barrier out and initialization speed vt, wherein t is indicated
Time, and based on Grid Method to it is described it is marked go out barrier map picture carry out grid division and obtain grating map, and
The initial position in setting path in the grating mapWith final positionAnd pulse frequency f is randomly generatedt, impulse ejection
Rate RtWith loudness AtValue, by the grating map, the initialization speed vt, the pulse frequency ft, impulse ejection rate RtWith
Loudness AtValue be input to path planning layer;
Step B: the time t is updated to t+1 by the path planning layer, and is generated based on Gaussian mutation algorithm and uniformly divided
Cloth random number rand;
Step C: judge the uniform random number rand and the initialization pulse emissivity RtSize relation;
Step D: when the uniform random number rand is less than the initialization pulse emissivity RtWhen, judge described equal
The even distribution random numbers rand and loudness AtSize relation;
Step E: when the uniform random number rand is less than the loudness AtWhen, update the initialization pulse transmitting
Rate RtFor Rt+1, the loudness AtValue is At+1, and D is returned to step, when the value of the uniform random number rand is between institute
State initialization pulse emissivity RtWith loudness AtBetween, then return to step B;
Step F: when the uniform random number rand is greater than the initialization pulse emissivity RtWhen, it is changed based on newton
The optimal direction solution x in the initial is solved for method*, in conjunction with the optimal direction solution x*, predict the initial position
In the center of t+1 timeAnd predict the local solution of centerThe pulse frequency ftFor ft+1, it is described
Initialize speed vtFor vt+1;
Step G: judge the prediction centerWith the final positionWhether in same grid, work as institute
State prediction centerWith the final positionNot in same grid, then updating current location is the local solutionUpdate current PRF frequency is ft+1, update current initialization speed is vt+1, and B is returned to step, when described pre-
Measured center positionWith the final positionIn same grid, the path planning layer combines the local solution of each time
It completes optimal path and exports.
It should be noted that the serial number of the above embodiments of the invention is only for description, do not represent the advantages or disadvantages of the embodiments.And
The terms "include", "comprise" herein or any other variant thereof is intended to cover non-exclusive inclusion, so that packet
Process, device, article or the method for including multiple elements not only include those elements, but also its including being not explicitly listed
His element, or further include for this process, device, article or the intrinsic element of method.What is do not limited more
In the case of, the element that is limited by sentence " including one ... ", it is not excluded that including process, device, the article of the element
Or there is also other identical elements in method.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone,
Computer, server or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of intelligence paths planning method, which is characterized in that the described method includes:
Step A: picture process layer receives the marked map picture of barrier out and initialization speed vt, wherein t indicates the time,
And grid division is carried out based on map picture of the Grid Method to the marked barrier out and obtains grating map, and in the grid
The initial position in setting path in lattice mapWith final positionAnd pulse frequency f is randomly generatedt, impulse ejection rate RtWith
Loudness AtValue, by the grating map, the initialization speed vt, the pulse frequency ft, impulse ejection rate RtWith loudness At
Value be input to path planning layer;
Step B: the time t is updated to t+1 by the path planning layer, and based on the generation of Gaussian mutation algorithm be uniformly distributed with
Machine number rand;
Step C: judge the uniform random number rand and the initialization pulse emissivity RtSize relation;
Step D: when the uniform random number rand is less than the initialization pulse emissivity RtWhen, judge described uniform point
The cloth random number rand and loudness AtSize relation;
Step E: when the uniform random number rand is less than the loudness AtWhen, update the initialization pulse emissivity Rt
For Rt+1, the loudness AtValue is At+1, and D is returned to step, when the value of the uniform random number rand is between described
Initialization pulse emissivity RtWith loudness AtBetween, then return to step B;
Step F: when the uniform random number rand is greater than the initialization pulse emissivity RtWhen, it is based on Newton iteration method
Solve the optimal direction solution x in the initial*, in conjunction with the optimal direction solution x*, predict the initial positionIn t+1
The center of timeAnd predict the local solution of centerThe pulse frequency ftFor ft+1, the initialization
Speed vtFor vt+1;
Step G: judge the prediction centerWith the final positionWhether in same grid, when the prediction
CenterWith the final positionNot in same grid, then updating current location is the local solution
Update current PRF frequency is ft+1, update current initialization speed is vt+1, and B is returned to step, when the pre- measured center
PositionWith the final positionIn same grid, the path planning layer combines the local solution of each time to complete most
Shortest path simultaneously exports.
2. intelligence paths planning method as described in claim 1, which is characterized in that described to have been marked based on Grid Method to described
Remember that the map picture of barrier out carries out grid division and obtains grating map, comprising:
The picture process layer carries out unit segmentation to the map picture of the marked barrier out, obtains multiple units, institute
It states multiple units to fix for size, the identical square of resolution ratio;
Image pretreatment operation is carried out to the multiple unit, described image pretreatment operation includes expansion, corrosion and binaryzation;
It uses mole field track algorithm to extract a profile for barrier multiple units that described image pretreatment operation is completed, obtains
To the grating map.
3. intelligence paths planning method as described in claim 1, which is characterized in that
The initial position of predictionThe t+1 time center are as follows:
The local solution of the center of prediction are as follows:
The pulse frequency of prediction are as follows:
ft+1=fmin+(fmax-fmin)β
The initialization speed of prediction are as follows:
Wherein, ε is contraction factor, and β is the random number generated in [0,1], fmin, fmaxRespectively indicate the minimum value of pulse frequency with
Maximum value.
4. such as the intelligent paths planning method in claim 3, which is characterized in that the Newton iteration method includes solving coordinate
And Iterative path;
Wherein, the solution coordinate are as follows:
The Iterative path are as follows:
Wherein, x0It is the Newton iteration method close to the coordinate value of zero point, f (x0) it is curvilinear function, f ' (x0) it is the curve letter
Several derivative functions.
5. intelligence paths planning method as described in claim 1, it is characterised in that:
The initialization pulse emissivity updated are as follows:
Rt+1=Rt(1-e-γt)
The loudness updated are as follows:
At+1=α At
Wherein, the enhancing coefficient of γ impulse ejection rate, α are the attenuation coefficient of volume, and e is Infinite Cyclic irrational number.
6. a kind of intelligence path planning apparatus, which is characterized in that described device includes memory and processor, the memory
On be stored with the intelligent path planning program that can be run on the processor, the intelligence path planning program is described
Processor realizes following steps when executing:
Step A: picture process layer receives the marked map picture of barrier out and initialization speed vt, wherein t indicates the time,
And grid division is carried out based on map picture of the Grid Method to the marked barrier out and obtains grating map, and in the grid
The initial position in setting path in lattice mapWith final positionAnd pulse frequency f is randomly generatedt, impulse ejection rate RtWith
Loudness AtValue, by the grating map, the initialization speed vt, the pulse frequency ft, impulse ejection rate RtWith loudness At
Value be input to path planning layer;
Step B: the time t is updated to t+1 by the path planning layer, and based on the generation of Gaussian mutation algorithm be uniformly distributed with
Machine number rand;
Step C: judge the uniform random number rand and the initialization pulse emissivity RtSize relation;
Step D: when the uniform random number rand is less than the initialization pulse emissivity RtWhen, judge described uniform point
The cloth random number rand and loudness AtSize relation;
Step E: when the uniform random number rand is less than the loudness AtWhen, update the initialization pulse emissivity Rt
For Rt+1, the loudness AtValue is At+1, and D is returned to step, when the value of the uniform random number rand is between described
Initialization pulse emissivity RtWith loudness AtBetween, then return to step B;
Step F: when the uniform random number rand is greater than the initialization pulse emissivity RtWhen, it is based on Newton iteration method
Solve the optimal direction solution x in the initial*, in conjunction with the optimal direction solution x*, predict the initial positionIn t+1
The center of timeAnd predict the local solution of centerThe pulse frequency ftFor ft+1, the initialization
Speed vtFor vt+1;
Step G: judge the prediction centerWith the final positionWhether in same grid, when the prediction
CenterWith the final positionNot in same grid, then updating current location is the local solution
Update current PRF frequency is ft+1, update current initialization speed is vt+1, and B is returned to step, when the pre- measured center
PositionWith the final positionIn same grid, the path planning layer combines the local solution of each time to complete most
Shortest path simultaneously exports.
7. intelligence path planning apparatus as described in claim 1, which is characterized in that described to have been marked based on Grid Method to described
Remember that the map picture of barrier out carries out grid division and obtains grating map, comprising:
The picture process layer carries out unit segmentation to the map picture of the marked barrier out, obtains multiple units, institute
It states multiple units to fix for size, the identical square of resolution ratio;
Image pretreatment operation is carried out to the multiple unit, described image pretreatment operation includes expansion, corrosion and binaryzation;
It uses mole field track algorithm to extract a profile for barrier multiple units that described image pretreatment operation is completed, obtains
To the grating map.
8. intelligence path planning apparatus as claimed in claim 2, which is characterized in that
The initial position of predictionThe t+1 time center are as follows:
The local solution of the center of prediction are as follows:
The pulse frequency of prediction are as follows:
ft+1=fmin+(fmax-fmin)β
The initialization speed of prediction are as follows:
Wherein, ε is contraction factor, and β is the random number generated in [0,1], fmin, fmaxRespectively indicate the minimum value of pulse frequency with
Maximum value.
9. intelligence path planning apparatus as claimed in claim 3, which is characterized in that the Newton iteration method includes solving to sit
Mark and Iterative path;
Wherein, the solution coordinate are as follows:
The Iterative path are as follows:
Wherein, x0It is the Newton iteration method close to the coordinate value of zero point, f (x0) it is curvilinear function, f ' (x0) it is the curve letter
Several derivative functions.
10. a kind of computer readable storage medium, which is characterized in that be stored with intelligence on the computer readable storage medium
Path planning program, the intelligence path planning program can be executed by one or more processor, to realize as right is wanted
The step of intelligent paths planning method described in asking any one of 1 to 5.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910421931.1A CN110274607A (en) | 2019-05-21 | 2019-05-21 | Intelligent paths planning method, device and computer readable storage medium |
PCT/CN2019/121515 WO2020233063A1 (en) | 2019-05-21 | 2019-11-28 | Intelligent path planning method and device, and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910421931.1A CN110274607A (en) | 2019-05-21 | 2019-05-21 | Intelligent paths planning method, device and computer readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110274607A true CN110274607A (en) | 2019-09-24 |
Family
ID=67960146
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910421931.1A Pending CN110274607A (en) | 2019-05-21 | 2019-05-21 | Intelligent paths planning method, device and computer readable storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110274607A (en) |
WO (1) | WO2020233063A1 (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111263418A (en) * | 2020-01-16 | 2020-06-09 | 中国人民解放军陆军工程大学 | System and method for planning moving path of node in wireless self-organizing network |
WO2020233063A1 (en) * | 2019-05-21 | 2020-11-26 | 深圳壹账通智能科技有限公司 | Intelligent path planning method and device, and computer readable storage medium |
WO2020233052A1 (en) * | 2019-05-21 | 2020-11-26 | 深圳壹账通智能科技有限公司 | Intelligent path planning method, apparatus and device, and storage medium |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113093761B (en) * | 2021-04-08 | 2023-03-31 | 浙江中烟工业有限责任公司 | Warehouse robot indoor map navigation system based on laser radar |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107886157A (en) * | 2017-10-30 | 2018-04-06 | 中国地质大学(武汉) | A kind of new bat optimized algorithm system |
CN107886158A (en) * | 2017-10-30 | 2018-04-06 | 中国地质大学(武汉) | A kind of bat optimized algorithm based on Iterated Local Search and Stochastic inertia weight |
CN108694077A (en) * | 2017-04-10 | 2018-10-23 | 中国科学院声学研究所 | Based on the distributed system method for scheduling task for improving binary system bat algorithm |
CN109144102A (en) * | 2018-09-19 | 2019-01-04 | 沈阳航空航天大学 | A kind of Path Planning for UAV based on improvement bat algorithm |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105447565B (en) * | 2015-11-19 | 2018-01-02 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | A kind of NoC mapping method based on discrete bat algorithm |
CN107272705B (en) * | 2017-07-31 | 2018-02-23 | 中南大学 | A kind of multiple neural network controlling planning method of robot path under intelligent environment |
US10797807B2 (en) * | 2017-09-20 | 2020-10-06 | Commscope Technologies Llc | Methods for calibrating millimeter wave antenna arrays |
CN109543572A (en) * | 2018-11-07 | 2019-03-29 | 北京交通大学 | A kind of traveling pavement condition evaluation method |
CN110274607A (en) * | 2019-05-21 | 2019-09-24 | 深圳壹账通智能科技有限公司 | Intelligent paths planning method, device and computer readable storage medium |
-
2019
- 2019-05-21 CN CN201910421931.1A patent/CN110274607A/en active Pending
- 2019-11-28 WO PCT/CN2019/121515 patent/WO2020233063A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108694077A (en) * | 2017-04-10 | 2018-10-23 | 中国科学院声学研究所 | Based on the distributed system method for scheduling task for improving binary system bat algorithm |
CN107886157A (en) * | 2017-10-30 | 2018-04-06 | 中国地质大学(武汉) | A kind of new bat optimized algorithm system |
CN107886158A (en) * | 2017-10-30 | 2018-04-06 | 中国地质大学(武汉) | A kind of bat optimized algorithm based on Iterated Local Search and Stochastic inertia weight |
CN109144102A (en) * | 2018-09-19 | 2019-01-04 | 沈阳航空航天大学 | A kind of Path Planning for UAV based on improvement bat algorithm |
Non-Patent Citations (9)
Title |
---|
GAI-GE WANG等: "Three-dimensional path planning for UCAV using an improved bat algorithm", 《AEROSPACE SCIENCE AND TECHNOLOGY》 * |
GAI-GE WANG等: "Three-dimensional path planning for UCAV using an improved bat algorithm", 《AEROSPACE SCIENCE AND TECHNOLOGY》, vol. 49, 28 February 2016 (2016-02-28), pages 231 - 238, XP029381680, DOI: 10.1016/j.ast.2015.11.040 * |
MBLSARASWATHI 等: "Optimal Path Planning of Mobile Robot Using Hybrid Cuckoo Search-Bat Algorithm", 《PROCEDIA COMPUTER SCIENCE》 * |
MBLSARASWATHI 等: "Optimal Path Planning of Mobile Robot Using Hybrid Cuckoo Search-Bat Algorithm", 《PROCEDIA COMPUTER SCIENCE》, vol. 133, 20 July 2018 (2018-07-20), pages 510 - 517 * |
余光伟: "自主移动机器人路径规划方法研究", 中国优秀硕士学位论文全文数据库 信息科技辑, no. 03, pages 3 * |
张强: "基于遗传算法的分层路径寻优策略和路径查询系统的设计", 中国优秀硕士学位论文全文数据库 信息科技辑, no. 06, pages 3 * |
李涛: "基于遗传算法的多UAV路径规划技术研究", 中国优秀硕士学位论文全文数据库 信息科技辑, no. 04, pages 2 * |
汪相国: "基于蝙蝠算法的水下潜器航路规划方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
汪相国: "基于蝙蝠算法的水下潜器航路规划方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, no. 06, 15 June 2018 (2018-06-15), pages 6 - 8 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020233063A1 (en) * | 2019-05-21 | 2020-11-26 | 深圳壹账通智能科技有限公司 | Intelligent path planning method and device, and computer readable storage medium |
WO2020233052A1 (en) * | 2019-05-21 | 2020-11-26 | 深圳壹账通智能科技有限公司 | Intelligent path planning method, apparatus and device, and storage medium |
CN111263418A (en) * | 2020-01-16 | 2020-06-09 | 中国人民解放军陆军工程大学 | System and method for planning moving path of node in wireless self-organizing network |
Also Published As
Publication number | Publication date |
---|---|
WO2020233063A1 (en) | 2020-11-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110274607A (en) | Intelligent paths planning method, device and computer readable storage medium | |
CN109472248A (en) | A kind of pedestrian recognition methods, system and electronic equipment and storage medium again | |
CN108427698A (en) | Updating device, method and the computer readable storage medium of prediction model | |
CN105164632B (en) | Form interface switching | |
CN108984605A (en) | The system of place map application and offer place catalogue | |
CN107274543B (en) | A kind of recognition methods of bank note, device, terminal device and computer storage medium | |
CN106503269A (en) | Method, device and server that application is recommended | |
CN109509056A (en) | Method of Commodity Recommendation, electronic device and storage medium based on confrontation network | |
CN110334272A (en) | The intelligent answer method, apparatus and computer storage medium of knowledge based map | |
CN106663108A (en) | Deep links for native applications | |
CN107818492B (en) | Product recommendation apparatus, method and computer-readable storage medium | |
CN109145809A (en) | A kind of note spectrum processing method and device and computer readable storage medium | |
WO2020248365A1 (en) | Intelligent model training memory allocation method and apparatus, and computer-readable storage medium | |
CN106408628B (en) | A kind of image processing method and device | |
CN109145558A (en) | Solve lock control method and electronic device | |
CN103902519A (en) | Information processing method and electronic device | |
CN108229658A (en) | The implementation method and device of object detector based on finite sample | |
CN109213554A (en) | A kind of icon layout method, computer readable storage medium and terminal device | |
CN114781654A (en) | Federal transfer learning method, device, computer equipment and medium | |
CN107679128A (en) | Information display method and device, electronic equipment and storage medium | |
CN110458184A (en) | Optical character identification householder method, device, computer equipment and storage medium | |
CN110274608A (en) | Intelligent paths planning method, device and computer readable storage medium | |
CN110020060A (en) | Web data crawling method, device and storage medium | |
CN107679222A (en) | Image processing method, mobile terminal and computer-readable recording medium | |
CN109741420B (en) | Region filling method and device, electronic equipment and storage medium |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190924 |