WO2020233063A1 - 智能化路径规划方法、装置及计算机可读存储介质 - Google Patents

智能化路径规划方法、装置及计算机可读存储介质 Download PDF

Info

Publication number
WO2020233063A1
WO2020233063A1 PCT/CN2019/121515 CN2019121515W WO2020233063A1 WO 2020233063 A1 WO2020233063 A1 WO 2020233063A1 CN 2019121515 W CN2019121515 W CN 2019121515W WO 2020233063 A1 WO2020233063 A1 WO 2020233063A1
Authority
WO
WIPO (PCT)
Prior art keywords
grid
random number
path planning
loudness
pulse
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.)
Ceased
Application number
PCT/CN2019/121515
Other languages
English (en)
French (fr)
Inventor
杜艳艳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
OneConnect Smart Technology Co Ltd
Original Assignee
OneConnect Smart Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by OneConnect Smart Technology Co Ltd filed Critical OneConnect Smart Technology Co Ltd
Publication of WO2020233063A1 publication Critical patent/WO2020233063A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

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 or using precalculated routes

Definitions

  • This application relates to the field of artificial intelligence technology, and in particular to a method, device and computer-readable storage medium for intelligent path planning based on map pictures.
  • the intelligent path planning algorithm is a new meta-heuristic algorithm. Because of its unique advantages, it has attracted the attention of researchers in recent years and has gradually become a hot issue in the field of intelligent computing. The related scientific research results are also increasing. The FJSP scheduling problem , Function optimization, wireless sensors, cloud manufacturing supply chain and many other research results are emerging.
  • the current intelligent path planning algorithm has low optimization accuracy, and it is easy to fall into the defects of partial area optimization and premature.
  • the current intelligent path planning algorithm has low optimization accuracy and slow convergence speed in the later stage, which is easy to fall into Local optimization.
  • various scholars at home and abroad have made improvements to varying degrees and achieved results, its accuracy is still not the highest, and it may not be the optimal solution for path planning.
  • This application provides an intelligent path planning method, device, and computer-readable storage medium, the main purpose of which is to present accurate path planning recommendation results to the user when the user uses path planning recommendation.
  • an intelligent path planning method includes:
  • Step A The image processing layer receives the map image of the marked obstacle and the initial speed v t , where t represents time, and performs grid division on the map image of the marked obstacle based on the grid method to obtain a grid map , And set the initial position of the path in the grid map And end position And randomly generates a pulse frequency f t, the value of the pulse emission rate R t A t and the loudness of the grid map, the initialization velocity v t, the pulse frequency f t, the emission of the pulse and loudness A t R t Enter the value of to the path planning layer;
  • Step B The path planning layer updates the time t to t+1, and generates a uniformly distributed random number rand based on the Gaussian mutation algorithm;
  • Step C Determine the relationship between the uniformly distributed random number rand and the initial pulse emission rate R t ;
  • Step D When the uniform random number rand less than the size relationship of the initialization pulse emission rate R t, determines the uniform random number rand and the loudness of A t;
  • Step E When the uniform random number rand is less than the loudness A t, said updating initialization pulse emission rate is R t R t + 1, a loudness value A t A t + 1, and returns to step D, when the initialization pulses between emissivity loudness a t R t and the rand is a uniformly distributed random number between a value, then returns to step B;
  • Step F When the uniformly distributed random number rand is greater than the initial pulse emission rate R t , the optimal direction solution x * in the initial grid is solved based on the Newton iteration method, combined with the optimal direction solution x * , Predict the initial position At the center of time t+1 And predict the local solution of the center position
  • the pulse frequency f t is f t+1
  • the initialization speed v t is v t+1 ;
  • Step G Determine the location of the prediction center With the end position Whether in the same grid, when the prediction center position With the end position Not in the same grid, update the current position as the local solution Update the current pulse frequency to f t+1 , update the current initialization speed to v t+1 , and return to step B.
  • the path planning layer combines the local solutions at each time to complete the optimal path and output it.
  • the present application also provides an intelligent path planning device, which includes a memory and a processor, and the memory stores readable instructions for intelligent path planning that can run on the processor, When the intelligent path planning readable instruction is executed by the processor, the following steps are implemented:
  • Step A The image processing layer receives the map image of the marked obstacle and the initial speed v t , where t represents time, and performs grid division on the map image of the marked obstacle based on the grid method to obtain a grid map , And set the initial position of the path in the grid map And end position And randomly generates a pulse frequency f t, the value of the pulse emission rate R t A t and the loudness of the grid map, the initialization velocity v t, the pulse frequency f t, the emission of the pulse and loudness A t R t Enter the value of to the path planning layer;
  • Step B The path planning layer updates the time t to t+1, and generates a uniformly distributed random number rand based on the Gaussian mutation algorithm;
  • Step C Determine the relationship between the uniformly distributed random number rand and the initial pulse emission rate R t ;
  • Step D When the uniform random number rand less than the size relationship of the initialization pulse emission rate R t, determines the uniform random number rand and the loudness of A t;
  • Step E When the uniform random number rand is less than the loudness A t, said updating initialization pulse emission rate is R t R t + 1, a loudness value A t A t + 1, and returns to step D, when the initialization pulses between emissivity loudness a t R t and the rand is a uniformly distributed random number between a value, then returns to step B;
  • Step F When the uniformly distributed random number rand is greater than the initial pulse emission rate R t , the optimal direction solution x * in the initial grid is solved based on the Newton iteration method, combined with the optimal direction solution x * , Predict the initial position At the center of time t+1 And predict the local solution of the center position
  • the pulse frequency f t is f t+1
  • the initialization speed v t is v t+1 ;
  • Step G Determine the location of the prediction center With the end position Whether in the same grid, when the prediction center position With the end position Not in the same grid, update the current position as the local solution Update the current pulse frequency to f t+1 , update the current initialization speed to v t+1 , and return to step B.
  • the path planning layer combines the local solutions at each time to complete the optimal path and output it.
  • the present application also provides one or more readable storage media storing intelligent path planning readable instructions, and the computer-readable storage medium stores intelligent path planning readable instructions.
  • the path planning readable instruction is executed by one or more processors, the one or more processors execute the following steps:
  • Step A The image processing layer receives the map image of the marked obstacle and the initial speed v t , where t represents time, and performs grid division on the map image of the marked obstacle based on the grid method to obtain a grid map , And set the initial position of the path in the grid map And end position And randomly generates a pulse frequency f t, the value of the pulse emission rate R t A t and the loudness of the grid map, the initialization velocity v t, the pulse frequency f t, the emission of the pulse and loudness A t R t Enter the value of to the path planning layer;
  • Step B The path planning layer updates the time t to t+1, and generates a uniformly distributed random number rand based on the Gaussian mutation algorithm;
  • Step C Determine the relationship between the uniformly distributed random number rand and the initial pulse emission rate R t ;
  • Step D When the uniform random number rand less than the size relationship of the initialization pulse emission rate R t, determines the uniform random number rand and the loudness of A t;
  • Step E When the uniform random number rand is less than the loudness A t, said updating initialization pulse emission rate is R t R t + 1, a loudness value A t A t + 1, and returns to step D, when the initialization pulses between emissivity loudness a t R t and the rand is a uniformly distributed random number between a value, then returns to step B;
  • Step F When the uniformly distributed random number rand is greater than the initial pulse emission rate R t , the optimal direction solution x * in the initial grid is solved based on the Newton iteration method, combined with the optimal direction solution x * , Predict the initial position At the center of time t+1 And predict the local solution of the center position
  • the pulse frequency f t is f t+1
  • the initialization speed v t is v t+1 ;
  • Step G Determine the location of the prediction center With the end position Whether in the same grid, when the prediction center position With the end position Not in the same grid, update the current position as the local solution Update the current pulse frequency to f t+1 , update the current initialization speed to v t+1 , and return to step B.
  • the path planning layer combines the local solutions at each time to complete the optimal path and output it.
  • this application also provides an intelligent path planning device, which includes:
  • the map picture receiving module is used to enable the picture processing layer to receive the map picture with marked obstacles and the initialization speed v t , where t represents time, and raster the map picture with marked obstacles based on the grid method Divide to obtain a grid map, and set the initial position of the path in the grid map And end position And randomly generates a pulse frequency f t, the value of the pulse emission rate R t A t and the loudness of the grid map, the initialization velocity v t, the pulse frequency f t, the emission of the pulse and loudness A t R t Enter the value of to the path planning layer;
  • the pulse judgment module is used to make the path planning layer update the time t to t+1, and generate a uniformly distributed random number rand based on the Gaussian mutation algorithm; determine the uniformly distributed random number rand and the initial pulse emission rate R t size relationship;
  • Loudness determination module configured to, when the uniformly distributed random number rand emissivity less than the reset pulse R t when determining whether the uniform random number rand magnitude relation between the loudness of A t; if the uniformly distributed random number when less than the loudness rand A t, said updating initialization pulse emission rate is R t R t + 1, a loudness value A t A t + 1;
  • the path output module is configured to solve the optimal direction solution x * in the initial grid based on the Newton iteration method when the uniformly distributed random number rand is greater than the initial pulse emission rate R t , and combine the optimal direction Solve x * , predict the initial position At the center of time t+1 And predict the local solution of the center position
  • the pulse frequency f t is f t+1
  • the initialization speed v t is v t+1
  • update the current position as the local solution Update the current pulse frequency to f t+1 , and update the current initialization speed to v t+1 ; when the predicted center position With the end position
  • the path planning layer combines the local solutions at each time to complete the optimal path and output it.
  • FIG. 1 is a schematic flowchart of an intelligent path planning method provided by an embodiment of this application
  • FIG. 2 is a schematic diagram of the internal structure of an intelligent path planning device provided by an embodiment of the application.
  • FIG. 3 is a schematic diagram of modules of readable instructions for intelligent path planning in an intelligent path planning device provided by an embodiment of the application.
  • This application provides an intelligent path planning method.
  • FIG. 1 it is a schematic flowchart of an intelligent path planning method provided by an embodiment of this application.
  • the method can be executed by a device, and the device can be implemented by software and/or hardware.
  • the intelligent path planning method includes:
  • the image processing layer receives the map image of the marked obstacle and the initialization speed v t , where t represents time, and performs grid division on the map image of the marked obstacle based on the grid method to obtain a grid map, And set the initial position of the path in the raster map And end position And randomly generates a pulse frequency f t, the value of the pulse emission rate R t A t and the loudness of the grid map, the initialization velocity v t, the pulse frequency f t, the emission of the pulse and loudness A t R t
  • the value of is input to the route planning layer.
  • the method for obtaining the map picture with marked obstacles includes: first mapping the pixels of the original map picture to [0-155], and marking the obstacle with the pixel set in [155-200].
  • the image processing layer performs unit division on the map picture with marked obstacles to obtain multiple units, and the multiple units are squares of fixed size and the same.
  • Each unit performs image preprocessing operations.
  • the image preprocessing operations include expansion, erosion, and binarization.
  • the expansion processing includes using a 3*3 structural element to perform an "OR" operation with each pixel in the map picture where the obstacle has been marked.
  • the corrosion processing includes using a 3*3 structural element and each pixel in the map picture with the obstacle marked to perform an "AND" operation.
  • the binarization operation includes first setting a threshold, when the pixel is smaller than the threshold, the pixel value becomes 0, and when the pixel is greater than the threshold, the pixel value becomes 1, so The pixel value of each pixel in the map picture where the obstacle has been marked becomes 0 or 255.
  • a Moore field tracking algorithm is used to extract the contours of obstacles on multiple units completed by the image preprocessing operation to obtain the grid map.
  • the Moore domain tracking algorithm is also called an indirect neighborhood algorithm.
  • the basic idea is to find a black pixel and define it as the starting pixel. There are many ways to locate the starting pixel, one of which is: starting from the bottom left pixel of the multiple units, scanning each column of pixels from bottom to top to the top pixel, and then according to the top Starting from the pixel, scan each column of pixels from left to right until a black pixel is encountered, and it is used as the starting pixel.
  • the path planning layer updates the time t to t+1, and generates a uniformly distributed random number rand based on the Gaussian mutation algorithm, and determines the size of the uniformly distributed random number rand and the initial pulse emission rate R t relationship.
  • the Gaussian mutation algorithm uses a normal distributed random number with a mean value ⁇ and a variance of ⁇ 2 to generate the uniformly distributed random number rand.
  • the preferred embodiment of the present application uses the following function to update the initial pulse emission rate R t to R t+1 :
  • R t+1 R t (1-e - ⁇ t )
  • the enhancement coefficient of ⁇ pulse emission rate ⁇ is the attenuation coefficient of volume, and e is an infinite loop irrational number.
  • the optimal direction solution x * in the initial grid is solved based on the Newton iteration method, combined with the optimal direction solution x * , Predict the initial position At the center of time t+1 And predict the local solution of the center position
  • the pulse frequency f t is f t+1
  • the initialization speed v t is v t+1 .
  • the Newton iteration method described in the preferred embodiment of the present application includes solving coordinates and iteration paths;
  • the iteration path is:
  • x 0 is the coordinate value of the Newton iteration method close to zero
  • f(x 0 ) is a curve function, which is generally set as a binary linear function
  • f′(x 0 ) is a derivative function of the curve function.
  • the initial position predicted by the preferred embodiment of this application The t+1 time position is
  • the predicted pulse frequency is:
  • f t+1 f min +(f max -f min ) ⁇
  • the predicted initialization speed is:
  • ⁇ is the shrinkage factor
  • ⁇ is a random number generated in [0,1]
  • f min and f max represent the minimum and maximum pulse frequency respectively.
  • the path planning layer combines the predicted local solutions at each time to complete the optimal path and output it.
  • the position at time t is Local solution at time t+1 Local solution at t+n time
  • the optimal plan of the path can be determined and output.
  • the invention also provides an intelligent path planning device.
  • FIG. 2 it is a schematic diagram of the internal structure of an intelligent path planning device provided by an embodiment of this application.
  • the intelligent path planning device 1 may be a PC (Personal Computer, personal computer), or a terminal device such as a smart phone, a tablet computer, or a portable computer, or a server.
  • the intelligent path planning device 1 at least includes a memory 11, a processor 12, a communication bus 13, and a network interface 14.
  • the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc.
  • the memory 11 may be an internal storage unit of the intelligent path planning device 1 in some embodiments, for example, the hard disk of the intelligent path planning device 1.
  • the memory 11 may also be an external storage device of the intelligent path planning device 1, for example, a plug-in hard disk equipped on the intelligent path planning device 1, a smart media card (SMC), and a secure digital (Secure Digital, SD) card, flash card (Flash Card), etc.
  • the memory 11 may also include both an internal storage unit of the intelligent path planning device 1 and an external storage device.
  • the memory 11 can be used not only to store application software and various data installed in the intelligent path planning device 1, such as the code of the intelligent path planning readable instruction 01, etc., but also to temporarily store data that has been output or will be output. .
  • the processor 12 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip, and is used to run the program code or processing stored in the memory 11 Data, for example, execute intelligent path planning readable instruction 01, etc.
  • CPU central processing unit
  • controller microcontroller
  • microprocessor microprocessor
  • the communication bus 13 is used to realize the connection and communication between these components.
  • the network interface 14 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface), and is usually used to establish a communication connection between the device 1 and other electronic devices.
  • the device 1 may also include a user interface.
  • the user interface may include a display (Display) and an input unit such as a keyboard (Keyboard).
  • the optional user interface may also include a standard wired interface and a wireless interface.
  • the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode, organic light emitting diode) touch device, etc.
  • the display can also be called a display screen or a display unit as appropriate, and is used to display the information processed in the intelligent route planning device 1 and to display a visualized user interface.
  • FIG. 2 only shows the intelligent path planning device 1 with components 11-14 and intelligent path planning readable instructions 01. Those skilled in the art can understand that the structure shown in FIG. 1 does not constitute an intelligent path
  • the definition of the planning device 1 may include fewer or more components than shown, or a combination of certain components, or different component arrangements.
  • the memory 11 stores the intelligent path planning readable instruction 01; when the processor 12 executes the intelligent path planning readable instruction 01 stored in the memory 11, the following steps are implemented:
  • Step 1 The image processing layer receives the map picture of the marked obstacle and the initial speed v t , where t represents time, and performs grid division on the map picture of the marked obstacle based on the grid method to obtain a grid map , And set the initial position of the path in the grid map And end position And randomly generates a pulse frequency f t, the value of the pulse emission rate R t A t and the loudness of the grid map, the initialization velocity v t, the pulse frequency f t, the emission of the pulse and loudness A t R t The value of is input to the route planning layer.
  • the method for obtaining the map picture with marked obstacles includes: first mapping the pixels of the original map picture to [0-155], and marking the obstacle with the pixel set in [155-200].
  • the image processing layer performs unit division on the map picture with marked obstacles to obtain multiple units, and the multiple units are squares of fixed size and the same.
  • Each unit performs image preprocessing operations.
  • the image preprocessing operations include expansion, erosion, and binarization.
  • the expansion processing includes the use of 3*3 structural elements and each pixel in the map picture where the obstacles have been marked to perform an "OR" operation;
  • the corrosion processing includes the use of 3*3 structural elements and all pixels.
  • Each pixel in the map picture where the obstacle has been marked performs an AND operation; the binarization operation includes first setting a threshold, and when the pixel is smaller than the threshold, the pixel value becomes 0, When the pixel is greater than the threshold value, the pixel value becomes 1, so the pixel value of each pixel in the map picture with the obstacle marked becomes 0 or 255.
  • a Moore field tracking algorithm is used to extract the contours of obstacles on multiple units completed by the image preprocessing operation to obtain the grid map.
  • the Moore domain tracking algorithm is also called an indirect neighborhood algorithm.
  • the basic idea is to find a black pixel and define it as the starting pixel. There are many ways to locate the starting pixel, one of which is: starting from the bottom left pixel of the multiple units, scanning each column of pixels from bottom to top to the top pixel, and then according to the top Starting from the pixel, scan each column of pixels from left to right until a black pixel is encountered, and it is used as the starting pixel.
  • Step 2 The path planning layer updates the time t to t+1, and generates a uniformly distributed random number rand based on the Gaussian mutation algorithm, and determines the difference between the uniformly distributed random number rand and the initial pulse emission rate R t Size relationship.
  • the Gaussian mutation algorithm uses a normal distributed random number with a mean value ⁇ and a variance of ⁇ 2 to generate the uniformly distributed random number rand.
  • Step three if the uniform random number rand emissivity less than the reset pulse R t when determining whether the uniform random number rand magnitude relation between the loudness of A t the value of the uniform random number rand when If it is between the initial pulse emission rate R t and the loudness A t , return to step two.
  • Step four when the uniformly distributed random number rand is less than the loudness A t, said updating initialization pulse emission rate is R t R t + 1, a loudness value A t A t + 1, and returns to step three.
  • the preferred embodiment of the present application uses the following function to update the initial pulse emission rate R t to R t+1 :
  • R t+1 R t (1-e - ⁇ t )
  • the enhancement coefficient of ⁇ pulse emission rate ⁇ is the attenuation coefficient of volume, and e is an infinite loop irrational number.
  • Step 5 When the uniformly distributed random number rand is greater than the initial pulse emission rate R t , the optimal direction solution x * in the initial grid is solved based on the Newton iteration method, combined with the optimal direction solution x * , Predict the initial position At the center of time t+1 And predict the local solution of the center position
  • the pulse frequency f t is f t+1
  • the initialization speed v t is v t+1 .
  • the Newton iteration method described in the preferred embodiment of the present application includes solving coordinates and iteration paths;
  • the iteration path is:
  • x 0 is the coordinate value of the Newton iteration method close to zero
  • f(x 0 ) is a curve function, which is generally set as a binary linear function
  • f′(x 0 ) is a derivative function of the curve function.
  • the initial position predicted by the preferred embodiment of this application The t+1 time position is
  • the predicted pulse frequency is:
  • f t+1 f min +(f max -f min ) ⁇
  • the predicted initialization speed is:
  • ⁇ is the shrinkage factor
  • ⁇ is a random number generated in [0,1]
  • f min and f max represent the minimum and maximum pulse frequency respectively.
  • Step 6 Determine the location of the prediction center With the end position Whether it is in the same grid.
  • Step 7 When the prediction center position With the end position Not in the same grid, update the current position as the local solution Update the current pulse frequency to f t+1 , update the current initialization speed to v t+1 , and return to step two.
  • Step 8 When the prediction center position With the end position In the same grid, the path planning layer combines the predicted local solutions at each time to complete the optimal path and output it.
  • the position at time t is Local solution at time t+1 Local solution at t+n time
  • the optimal plan of the path can be determined and output.
  • the intelligent path planning readable instructions can also be divided into one or more modules, and the one or more modules are stored in the memory 11 and are executed by one or more processors (this The embodiment is executed by the processor 12) to complete this application.
  • the module referred to in this application refers to multiple computer program instruction segments that can complete specific functions, and is used to describe the intelligent path planning readable instructions in the intelligent path planning device In the implementation process.
  • FIG. 3 is a schematic diagram of program modules of an intelligent path planning program in an embodiment of an intelligent path planning device of the present application
  • the intelligent path planning program can be divided into map images and received
  • the module 10, the pulse judgment module 20, the loudness judgment module 30, and the path output module 40 are exemplary:
  • the map picture receiving module 10 is configured to: receive a map picture with marked obstacles and an initialization speed v t , where t represents time, and perform grid division on the map picture with marked obstacles based on a grid method Obtain a grid map, and set the initial position of the path in the grid map And end position And randomly generates a pulse frequency f t, the value of the pulse emission rate R t A t and the loudness of the grid map, the initialization velocity v t, the pulse frequency f t, the emission of the pulse and loudness A t R t The value of is input to the route planning layer.
  • the pulse judging module 20 is configured to: update the time t to t+1, generate a uniformly distributed random number rand based on the Gaussian mutation algorithm, and determine the uniformly distributed random number rand and the initial pulse emission rate R t The size relationship.
  • the loudness determination module 30 is configured to: when the rand uniformly distributed random number is smaller than the initializing pulse when the emission rate R t, is further determined the uniformly distributed random number rand and the magnitude relation between the loudness of A t, when the when a uniformly distributed random number rand is less than the loudness A t, said updating initialization pulse emission rate is R t R t + 1, a loudness value A t A t + 1.
  • the path output module 40 is configured to: when the uniformly distributed random number rand is greater than the initial pulse emission rate R t , solve the optimal direction solution x * in the initial grid based on the Newton iteration method, in combination with the Optimal direction solution x * , predict the initial position At the center of time t+1 And predict the local solution of the center position
  • the pulse frequency f t is f t+1
  • the initialization speed v t is v t+1
  • update the current position as the local solution Update the current pulse frequency to f t+1 , update the current initialization speed to v t+1 , when the predicted center position With the end position
  • the path planning layer combines the local solutions at each time to complete the optimal path and output it.
  • the embodiment of the present application also proposes one or more readable storage media storing readable instructions for intelligent path planning, and the computer-readable storage medium stores readable instructions for intelligent path planning.
  • the readable instructions are executed by one or more processors, the one or more processors execute the following steps:
  • Step A The image processing layer receives the map image of the marked obstacle and the initial speed v t , where t represents time, and performs grid division on the map image of the marked obstacle based on the grid method to obtain a grid map , And set the initial position of the path in the grid map And end position And randomly generates a pulse frequency f t, the value of the pulse emission rate R t A t and the loudness of the grid map, the initialization velocity v t, the pulse frequency f t, the emission of the pulse and loudness A t R t Enter the value of to the path planning layer;
  • Step B The path planning layer updates the time t to t+1, and generates a uniformly distributed random number rand based on the Gaussian mutation algorithm;
  • Step C Determine the relationship between the uniformly distributed random number rand and the initial pulse emission rate R t ;
  • Step D When the uniform random number rand less than the size relationship of the initialization pulse emission rate R t, determines the uniform random number rand and the loudness of A t;
  • Step E When the uniform random number rand is less than the loudness A t, said updating initialization pulse emission rate is R t R t + 1, a loudness value A t A t + 1, and returns to step D, when the initialization pulses between emissivity loudness a t R t and the rand is a uniformly distributed random number between a value, then returns to step B;
  • Step F When the uniformly distributed random number rand is greater than the initial pulse emission rate R t , the optimal direction solution x * in the initial grid is solved based on the Newton iteration method, combined with the optimal direction solution x * , Predict the initial position At the center of time t+1 And predict the local solution of the center position
  • the pulse frequency f t is f t+1
  • the initialization speed v t is v t+1 ;
  • Step G Determine the location of the prediction center With the end position Whether in the same grid, when the prediction center position With the end position Not in the same grid, update the current position as the local solution Update the current pulse frequency to f t+1 , update the current initialization speed to v t+1 , and return to step B.
  • the path planning layer combines the local solutions at each time to complete the optimal path and output it.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Image Processing (AREA)
  • Image Analysis (AREA)

Abstract

一种人工智能技术，揭露了一种智能化路径规划方法，包括：接收已标记出障碍物的地图图片和初始化速度，对已标记出障碍物的地图图片进行栅格划分并初始化位置与终点位置，随机产生脉冲频率f t、脉冲发射率R t和响度A t（S1），产生均匀分布随机数rand，并判断均匀分布随机数rand与初始化脉冲发射率R t和响度A t的大小关系，并求解初始栅格的最优方向解和局部解后，直至局部解与终点位置在同一栅格内，最终结合各时间的局部解完成最优路径并输出，提出一种智能化路径规划装置以及一种计算机可读存储介质，能实现精准的智能路径规划功能。

Description

智能化路径规划方法、装置及计算机可读存储介质
本申请以2019年5月21日提交的申请号为201910421931.1，名称为“智能化路径规划方法、装置及计算机可读存储介质”的中国发明申请为基础，并要求其优先权。
技术领域
本申请涉及人工智能技术领域，尤其涉及一种基于地图图片的智能化路径规划方法、装置及计算机可读存储介质。
背景技术
智能化路径规划算法属于新兴的元启发式算法，因其特有的优点，近几年备受研究者的关注，逐渐成为智能计算领域的热点问题，相关的科研成果也日益增加，在FJSP调度问题、函数优化、无线传感器、云制造供应链等诸多方面的研究成果日益浮现。然而，目前的智能化路径规划算法存在的寻优准确度不高，容易陷入部分区域最优，早熟等缺陷，且当前的智能化路径规划算法寻优精度不高，后期收敛速度慢，易陷入局部最优，虽然国内外各种学者进行了不同程度的改进，取得了成果，但是其精度还是不是最高的，在路径规划问题上，可能不是最优解。
发明内容
本申请提供一种智能化路径规划方法、装置及计算机可读存储介质，其主要目的在于当用户在使用路径规划推荐时，给用户呈现出精准的路径规划推荐结果。
为实现上述目的，本申请提供的一种智能化路径规划方法，包括：
步骤A：图片处理层接收已标记出障碍物的地图图片和初始化速度v t，其中t表示时间，并基于栅格法对所述已标记出障碍物的地图图片进行栅格划分得到栅格地图，并在所述栅格地图内设置路径的初始位置
Figure PCTCN2019121515-appb-000001
与终点位置
Figure PCTCN2019121515-appb-000002
并随机产生脉冲频率f t、脉冲发射率R t和响度A t的值，将所述栅格地图、所述初始化速度v t、所述脉冲频率f t、脉冲发射率R t和响度A t的值输入至路径规划层；
步骤B：所述路径规划层将所述时间t更新至t+1，并基于高斯变异算法产生均匀分布随机数rand；
步骤C：判断所述均匀分布随机数rand与所述初始化脉冲发射率R t的大小关系；
步骤D：当所述均匀分布随机数rand小于所述初始化脉冲发射率R t时，判断所述均匀分布随机数rand与所述响度A t的大小关系；
步骤E：当所述均匀分布随机数rand小于所述响度A t时，更新所述初始化脉冲发射率R t为R t+1，所述响度A t值为A t+1，并返回执行步骤D，当所述均匀分布随机数rand的值介于所述初始化脉冲发射率R t和响度A t之间，则返回执行步骤B；
步骤F：当所述均匀分布随机数rand大于所述初始化脉冲发射率R t时，基于牛顿迭代法求解所述初始栅格内的最优方向解x *，结合所述最优方向解x *，预测所述初始位置
Figure PCTCN2019121515-appb-000003
在t+1时间的中心位置
Figure PCTCN2019121515-appb-000004
并预测中心位置的局部解
Figure PCTCN2019121515-appb-000005
所述脉冲频率f t为f t+1、所述初始化速度v t为v t+1；
步骤G：判断所述预测中心位置
Figure PCTCN2019121515-appb-000006
与所述终点位置
Figure PCTCN2019121515-appb-000007
是否在同一栅格内，当所述预测中心位置
Figure PCTCN2019121515-appb-000008
与所述终点位置
Figure PCTCN2019121515-appb-000009
不在同一栅格内，则更新当前位置为所述局部解
Figure PCTCN2019121515-appb-000010
更新当前脉冲频率为f t+1，更新当前初始化速度为v t+1，并返回执行步骤B，当所述预测中心位置
Figure PCTCN2019121515-appb-000011
与所述终点位置
Figure PCTCN2019121515-appb-000012
在同一栅格内，所述路径规划层结合各时间的局部解完成最优路径并输出。
此外，为实现上述目的，本申请还提供一种智能化路径规划装置，该装置包括存储器和处理器，所述存储器中存储有可在所述处理器上运行的智能化路径规划可读指令，所述智能化路径规划可读指令被所述处理器执行时实现如下步骤：
步骤A：图片处理层接收已标记出障碍物的地图图片和初始化速度v t，其中t表示时间，并基于栅格法对所述已标记出障碍物的地图图片进行栅格划分得到栅格地图，并在所述栅格地图内设置路径的初始位置
Figure PCTCN2019121515-appb-000013
与终点位置
Figure PCTCN2019121515-appb-000014
并随机产生脉冲频率f t、脉冲发射率R t和响度A t的值，将所述栅格地图、所述初始化速度v t、所述脉冲频率f t、脉冲发射率R t和响度A t的值输入至路径规划层；
步骤B：所述路径规划层将所述时间t更新至t+1，并基于高斯变异算法产生均匀分布随机数rand；
步骤C：判断所述均匀分布随机数rand与所述初始化脉冲发射率R t的大小关系；
步骤D：当所述均匀分布随机数rand小于所述初始化脉冲发射率R t时，判断所述均匀分布随机数rand与所述响度A t的大小关系；
步骤E：当所述均匀分布随机数rand小于所述响度A t时，更新所述初始化脉冲发射率R t为R t+1，所述响度A t值为A t+1，并返回执行步骤D，当所述均匀分布随机数rand的值介于所述初始化脉冲发射率R t和响度A t之间，则返回执行步骤B；
步骤F：当所述均匀分布随机数rand大于所述初始化脉冲发射率R t时，基于牛顿迭代法求解所述初始栅格内的最优方向解x *，结合所述最优方向解x *，预测所述初始位置
Figure PCTCN2019121515-appb-000015
在t+1时间的中心位置
Figure PCTCN2019121515-appb-000016
并预测中心位置的局部解
Figure PCTCN2019121515-appb-000017
所述脉冲频率f t为f t+1、所述初始化速度v t为v t+1；
步骤G：判断所述预测中心位置
Figure PCTCN2019121515-appb-000018
与所述终点位置
Figure PCTCN2019121515-appb-000019
是否在同一栅格内，当所述预测中心位置
Figure PCTCN2019121515-appb-000020
与所述终点位置
Figure PCTCN2019121515-appb-000021
不在同一栅格内，则更新当前位置为所述局部解
Figure PCTCN2019121515-appb-000022
更新当前脉冲频率为f t+1，更新当前初始化速度为v t+1，并返回执行步骤B，当所述预测中心位置
Figure PCTCN2019121515-appb-000023
与所述终点位置
Figure PCTCN2019121515-appb-000024
在同一栅格内，所述路径规划层结合各时间的局部解完成最优路径并输出。
此外，为实现上述目的，本申请还提供一个或多个存储有智能化路径规划可读指令的可读存储介质，所述计算机可读存储介质存储有智能化路径规划可读指令，所述智能化路径规划可读指令被一个或多个处理器执行时，使得所述一个或多个处理器执行如下步骤：
步骤A：图片处理层接收已标记出障碍物的地图图片和初始化速度v t，其中t表示时间，并基于栅格法对所述已标记出障碍物的地图图片进行栅格划分得到栅格地图，并在所述栅格地图内设置路径的初始位置
Figure PCTCN2019121515-appb-000025
与终点位置
Figure PCTCN2019121515-appb-000026
并随机产生脉冲频率f t、脉冲发射率R t和响度A t的值，将所述栅格地图、所述初始化速度v t、所述脉冲频率f t、脉冲发射率R t和响度A t的值输入至路径规划层；
步骤B：所述路径规划层将所述时间t更新至t+1，并基于高斯变异算法产生均匀分布随机数rand；
步骤C：判断所述均匀分布随机数rand与所述初始化脉冲发射率R t的大小关系；
步骤D：当所述均匀分布随机数rand小于所述初始化脉冲发射率R t时，判断所述均匀分布随机数rand与所述响度A t的大小关系；
步骤E：当所述均匀分布随机数rand小于所述响度A t时，更新所述初始化脉冲发射率R t为R t+1，所述响度A t值为A t+1，并返回执行步骤D，当所述均匀分布随机数rand的值介于所述初始化脉冲发射率R t和响度A t之间，则返回执行步骤B；
步骤F：当所述均匀分布随机数rand大于所述初始化脉冲发射率R t时，基于牛顿迭代法求解所述初始栅格内的最优方向解x *，结合所述最优方向解x *，预测所述初始位置
Figure PCTCN2019121515-appb-000027
在t+1时间的中心位置
Figure PCTCN2019121515-appb-000028
并预测中心位置的局部解
Figure PCTCN2019121515-appb-000029
所述脉冲频率f t为f t+1、所述初始化速度v t为v t+1；
步骤G：判断所述预测中心位置
Figure PCTCN2019121515-appb-000030
与所述终点位置
Figure PCTCN2019121515-appb-000031
是否在同一栅格内，当所述预 测中心位置
Figure PCTCN2019121515-appb-000032
与所述终点位置
Figure PCTCN2019121515-appb-000033
不在同一栅格内，则更新当前位置为所述局部解
Figure PCTCN2019121515-appb-000034
更新当前脉冲频率为f t+1，更新当前初始化速度为v t+1，并返回执行步骤B，当所述预测中心位置
Figure PCTCN2019121515-appb-000035
与所述终点位置
Figure PCTCN2019121515-appb-000036
在同一栅格内，所述路径规划层结合各时间的局部解完成最优路径并输出。
此外，为实现上述目的，本申请还提供一种智能化路径规划装置，所述装置包括：
地图图片接收模块，用于使图片处理层接收已标记出障碍物的地图图片和初始化速度v t，其中t表示时间，并基于栅格法对所述已标记出障碍物的地图图片进行栅格划分得到栅格地图，并在所述栅格地图内设置路径的初始位置
Figure PCTCN2019121515-appb-000037
与终点位置
Figure PCTCN2019121515-appb-000038
并随机产生脉冲频率f t、脉冲发射率R t和响度A t的值，将所述栅格地图、所述初始化速度v t、所述脉冲频率f t、脉冲发射率R t和响度A t的值输入至路径规划层；
脉冲判断模块，用于使所述路径规划层将所述时间t更新至t+1，并基于高斯变异算法产生均匀分布随机数rand；判断所述均匀分布随机数rand与所述初始化脉冲发射率R t的大小关系；
响度判断模块，用于当所述均匀分布随机数rand小于所述初始化脉冲发射率R t时，判断所述均匀分布随机数rand与所述响度A t的大小关系；当所述均匀分布随机数rand小于所述响度A t时，更新所述初始化脉冲发射率R t为R t+1，所述响度A t值为A t+1；
路径输出模块，用于当所述均匀分布随机数rand大于所述初始化脉冲发射率R t时，基于牛顿迭代法求解所述初始栅格内的最优方向解x *，结合所述最优方向解x *，预测所述初始位置
Figure PCTCN2019121515-appb-000039
在t+1时间的中心位置
Figure PCTCN2019121515-appb-000040
并预测中心位置的局部解
Figure PCTCN2019121515-appb-000041
所述脉冲频率f t为f t+1、所述初始化速度v t为v t+1；当所述预测中心位置
Figure PCTCN2019121515-appb-000042
与所述终点位置
Figure PCTCN2019121515-appb-000043
不在同一栅格内，则更新当前位置为所述局部解
Figure PCTCN2019121515-appb-000044
更新当前脉冲频率为f t+1，更新当前初始化速度为v t+1；当所述预测中心位置
Figure PCTCN2019121515-appb-000045
与所述终点位置
Figure PCTCN2019121515-appb-000046
在同一栅格内，所述路径规划层结合各时间的局部解完成最优路径并输出。
本申请的一个或多个实施例的细节在下面的附图及描述中提出。本申请的其他特征和优点将从说明书、附图以及权利要求书变得明显。
附图说明
图1为本申请一实施例提供的智能化路径规划方法的流程示意图；
图2为本申请一实施例提供的智能化路径规划装置的内部结构示意图；
图3为本申请一实施例提供的智能化路径规划装置中智能化路径规划可读指令的模块 示意图。
本申请目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
具体实施方式
应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
本申请提供一种智能化路径规划方法。参照图1所示，为本申请一实施例提供的智能化路径规划方法的流程示意图。该方法可以由一个装置执行，该装置可以由软件和/或硬件实现。
在本实施例中，智能化路径规划方法包括：
S1、图片处理层接收已标记出障碍物的地图图片和初始化速度v t，其中t表示时间，并基于栅格法对所述已标记出障碍物的地图图片进行栅格划分得到栅格地图，并在所述栅格地图内设置路径的初始位置
Figure PCTCN2019121515-appb-000047
与终点位置
Figure PCTCN2019121515-appb-000048
并随机产生脉冲频率f t、脉冲发射率R t和响度A t的值，将所述栅格地图、所述初始化速度v t、所述脉冲频率f t、脉冲发射率R t和响度A t的值输入至路径规划层。
所述已标记出障碍物的地图图片的获得方法包括：先将原始地图图片像素映射至[0-155]，用[155-200]内的像素集标记出障碍物。
本申请较佳实施例中，所述图片处理层对所述已标记出障碍物的地图图片进行单元分割，得到多个单元，所述多个单元为大小固定且相同的方块，对所述多个单元进行图像预处理操作，所述图像预处理操作包括膨胀、腐蚀与二值化等处理。其中，所述膨胀处理包括使用3*3的结构元素与所述已标记出障碍物的地图图片内的每个像素做“或”操作。所述腐蚀处理包括使用3*3的结构元素与所述已标记出障碍物的地图图片内的每个像素做“与”操作。所述二值化操作包括先设定阈值，当所述像素小于所述阈值时，所述像素值变为0，当所述像素大于所述阈值时，所述像素值变为1，故所述已标记出障碍物的地图图片内的每个像素的像素值变为0或255。
本申请较佳实施例对所述图像预处理操作完成的多个单元使用摩尔领域跟踪算法提取障碍物的轮廓，得到所述栅格地图。所述摩尔领域跟踪算法也称间接邻域算法，基本思想为找到一个黑色像素，并将它定义为起始像素。其中，定位所述起始像素可用多种方式，其中一种方法为：从所述多个单元的左下角像素开始，自下而上扫描每一列像素直至最上方像素，然后依据所述最上方像素开始，自左向右扫描每一列像素，直至遇到一个黑色的像素，并将其作为起始像素。
S2、所述路径规划层将所述时间t更新至t+1，并基于高斯变异算法产生均匀分布随机数rand，并判断所述均匀分布随机数rand与所述初始化脉冲发射率R t的大小关系。
本申请较佳实施例中，所述高斯变异算法是使用一个均值μ、方差为σ2的正态分布的一个随机数来生成所述均匀分布随机数rand。
S3、当所述均匀分布随机数rand小于所述初始化脉冲发射率R t时，判断所述均匀分布随机数rand与所述响度A t的大小关系，当所述均匀分布随机数rand的值介于所述初始化脉冲发射率R t和响度A t之间，则返回执行S2。
S4、当所述均匀分布随机数rand小于所述响度A t时，更新所述初始化脉冲发射率R t为R t+1，所述响度A t值为A t+1，并返回执行S3。
本申请较佳实施例利用下述函数更新所述初始化脉冲发射率R t为R t+1：
R t+1＝R t(1-e -γt)
利用下述函数更新所述响度A t值为A t+1：
A t+1＝αA t
其中，γ脉冲发射率的增强系数，α为音量的衰减系数，e为无限循环无理数。
S5、当所述均匀分布随机数rand大于所述初始化脉冲发射率R t时，基于牛顿迭代法求解所述初始栅格内的最优方向解x *，结合所述最优方向解x *，预测所述初始位置
Figure PCTCN2019121515-appb-000049
在t+1时间的中心位置
Figure PCTCN2019121515-appb-000050
并预测中心位置的局部解
Figure PCTCN2019121515-appb-000051
所述脉冲频率f t为f t+1，所述初始化速度v t为v t+1。
本申请较佳实施例所述牛顿迭代法包括求解坐标和迭代路径；
其中，所述求解坐标为：
Figure PCTCN2019121515-appb-000052
所述迭代路径为：
Figure PCTCN2019121515-appb-000053
其中，x 0为所述牛顿迭代法接近零点的坐标值，f(x 0)为曲线函数，一般设置为二元一次函数，f′(x 0)为所述曲线函数的导数函数。
本申请较佳实施例预测的所述初始位置
Figure PCTCN2019121515-appb-000054
的t+1时间位置为
Figure PCTCN2019121515-appb-000055
Figure PCTCN2019121515-appb-000056
预测的中心位置的局部解为：
Figure PCTCN2019121515-appb-000057
预测的所述脉冲频率为：
f t+1＝f min+(f max-f min)β
预测的所述初始化速度为：
Figure PCTCN2019121515-appb-000058
其中，ε为收缩因子，β为[0,1]内产生的随机数，f min，f max分别表示脉冲频率的最小值与最大值。
S6、判断所述预测中心位置
Figure PCTCN2019121515-appb-000059
与所述终点位置
Figure PCTCN2019121515-appb-000060
是否在同一栅格内。
S7、当所述预测中心位置
Figure PCTCN2019121515-appb-000061
与所述终点位置
Figure PCTCN2019121515-appb-000062
不在同一栅格内，则更新当前位置为所述局部解
Figure PCTCN2019121515-appb-000063
更新当前脉冲频率为f t+1，更新当前初始化速度为v t+1，并返回执行S2。
S8、当所述预测中心位置
Figure PCTCN2019121515-appb-000064
与所述终点位置
Figure PCTCN2019121515-appb-000065
在同一栅格内，所述路径规划层结合各时间的预测局部解完成最优路径并输出。
本申请较佳实施例，如t时间的位置为
Figure PCTCN2019121515-appb-000066
t+1时间的局部解
Figure PCTCN2019121515-appb-000067
t+n时间的局部解
Figure PCTCN2019121515-appb-000068
结合所有时间的位置，可确定所述路径最优规划并输出。
发明还提供一种智能化路径规划装置。参照图2所示，为本申请一实施例提供的智能化路径规划装置的内部结构示意图。
在本实施例中，所述智能化路径规划装置1可以是PC(Personal Computer，个人电脑)，或者是智能手机、平板电脑、便携计算机等终端设备，也可以是一种服务器等。该智能化路径规划装置1至少包括存储器11、处理器12，通信总线13，以及网络接口14。
其中，存储器11至少包括一种类型的可读存储介质，所述可读存储介质包括闪存、硬盘、多媒体卡、卡型存储器(例如，SD或DX存储器等)、磁性存储器、磁盘、光盘等。存储器11在一些实施例中可以是智能化路径规划装置1的内部存储单元，例如该智能化路径规划装置1的硬盘。存储器11在另一些实施例中也可以是智能化路径规划装置1的外部存储设备，例如智能化路径规划装置1上配备的插接式硬盘，智能存储卡(Smart Media Card，SMC)，安全数字(Secure Digital，SD)卡，闪存卡(Flash Card)等。进一步地，存储器11还可以既包括智能化路径规划装置1的内部存储单元也包括外部存储设备。存储器11不仅可以用于存储安装于智能化路径规划装置1的应用软件及各类数据，例如智能化路径规划可读指令01的代码等，还可以用于暂时地存储已经输出或者将要输出的数据。
处理器12在一些实施例中可以是一中央处理器(Central Processing Unit，CPU)、控制器、微控制器、微处理器或其他数据处理芯片，用于运行存储器11中存储的程序代 码或处理数据，例如执行智能化路径规划可读指令01等。
通信总线13用于实现这些组件之间的连接通信。
网络接口14可选的可以包括标准的有线接口、无线接口(如WI-FI接口)，通常用于在该装置1与其他电子设备之间建立通信连接。
可选地，该装置1还可以包括用户接口，用户接口可以包括显示器(Display)、输入单元比如键盘(Keyboard)，可选的用户接口还可以包括标准的有线接口、无线接口。可选地，在一些实施例中，显示器可以是LED显示器、液晶显示器、触控式液晶显示器以及OLED(Organic Light-Emitting Diode，有机发光二极管)触摸器等。其中，显示器也可以适当的称为显示屏或显示单元，用于显示在智能化路径规划装置1中处理的信息以及用于显示可视化的用户界面。
图2仅示出了具有组件11-14以及智能化路径规划可读指令01的智能化路径规划装置1，本领域技术人员可以理解的是，图1示出的结构并不构成对智能化路径规划装置1的限定，可以包括比图示更少或者更多的部件，或者组合某些部件，或者不同的部件布置。
在图2所示的装置1实施例中，存储器11中存储有智能化路径规划可读指令01；处理器12执行存储器11中存储的智能化路径规划可读指令01时实现如下步骤：
步骤一、图片处理层接收已标记出障碍物的地图图片和初始化速度v t，其中t表示时间，并基于栅格法对所述已标记出障碍物的地图图片进行栅格划分得到栅格地图，并在所述栅格地图内设置路径的初始位置
Figure PCTCN2019121515-appb-000069
与终点位置
Figure PCTCN2019121515-appb-000070
并随机产生脉冲频率f t、脉冲发射率R t和响度A t的值，将所述栅格地图、所述初始化速度v t、所述脉冲频率f t、脉冲发射率R t和响度A t的值输入至路径规划层。
所述已标记出障碍物的地图图片的获得方法包括：先将原始地图图片像素映射至[0-155]，用[155-200]内的像素集标记出障碍物。
本申请较佳实施例中，所述图片处理层对所述已标记出障碍物的地图图片进行单元分割，得到多个单元，所述多个单元为大小固定且相同的方块，对所述多个单元进行图像预处理操作，所述图像预处理操作包括膨胀、腐蚀与二值化等处理。其中，所述膨胀处理包括使用3*3的结构元素与所述已标记出障碍物的地图图片内的每个像素做“或”操作；所述腐蚀处理包括使用3*3的结构元素与所述已标记出障碍物的地图图片内的每个像素做“与”操作；所述二值化操作包括先设定阈值，当所述像素小于所述阈值时，所述像素值变为0，当所述像素大于所述阈值时，所述像素值变为1，故所述已标记出障碍物的地图图片内的每个像素的像素值变为0或255。
本申请较佳实施例对所述图像预处理操作完成的多个单元使用摩尔领域跟踪算法提取障碍物的轮廓，得到所述栅格地图。所述摩尔领域跟踪算法也称间接邻域算法，基本思想为找到一个黑色像素，并将它定义为起始像素。其中，定位所述起始像素可用多种方式，其中一种方法为：从所述多个单元的左下角像素开始，自下而上扫描每一列像素直至最上方像素，然后依据所述最上方像素开始，自左向右扫描每一列像素，直至遇到一个黑色的像素，并将其作为起始像素。
步骤二、所述路径规划层将所述时间t更新至t+1，并基于高斯变异算法产生均匀分布随机数rand，并判断所述均匀分布随机数rand与所述初始化脉冲发射率R t的大小关系。
本申请较佳实施例中，所述高斯变异算法是使用一个均值μ、方差为σ2的正态分布的一个随机数来生成所述均匀分布随机数rand。
步骤三、当所述均匀分布随机数rand小于所述初始化脉冲发射率R t时，判断所述均匀分布随机数rand与所述响度A t的大小关系，当所述均匀分布随机数rand的值介于所述初始化脉冲发射率R t和响度A t之间，则返回执行步骤二。
步骤四、当所述均匀分布随机数rand小于所述响度A t时，更新所述初始化脉冲发射率R t为R t+1，所述响度A t值为A t+1，并返回执行步骤三。
本申请较佳实施例利用下述函数更新所述初始化脉冲发射率R t为R t+1：
R t+1＝R t(1-e -γt)
利用下述函数更新所述响度A t值为A t+1：
A t+1＝αA t
其中，γ脉冲发射率的增强系数，α为音量的衰减系数，e为无限循环无理数。
步骤五、当所述均匀分布随机数rand大于所述初始化脉冲发射率R t时，基于牛顿迭代法求解所述初始栅格内的最优方向解x *，结合所述最优方向解x *，预测所述初始位置
Figure PCTCN2019121515-appb-000071
在t+1时间的中心位置
Figure PCTCN2019121515-appb-000072
并预测中心位置的局部解
Figure PCTCN2019121515-appb-000073
所述脉冲频率f t为f t+1，所述初始化速度v t为v t+1。
本申请较佳实施例所述牛顿迭代法包括求解坐标和迭代路径；
其中，所述求解坐标为：
Figure PCTCN2019121515-appb-000074
所述迭代路径为：
Figure PCTCN2019121515-appb-000075
其中，x 0为所述牛顿迭代法接近零点的坐标值，f(x 0)为曲线函数，一般设置为二元一 次函数，f′(x 0)为所述曲线函数的导数函数。
本申请较佳实施例预测的所述初始位置
Figure PCTCN2019121515-appb-000076
的t+1时间位置为
Figure PCTCN2019121515-appb-000077
Figure PCTCN2019121515-appb-000078
预测的中心位置的局部解为：
Figure PCTCN2019121515-appb-000079
预测的所述脉冲频率为：
f t+1＝f min+(f max-f min)β
预测的所述初始化速度为：
Figure PCTCN2019121515-appb-000080
其中，ε为收缩因子，β为[0,1]内产生的随机数，f min，f max分别表示脉冲频率的最小值与最大值。
步骤六、判断所述预测中心位置
Figure PCTCN2019121515-appb-000081
与所述终点位置
Figure PCTCN2019121515-appb-000082
是否在同一栅格内。
步骤七、当所述预测中心位置
Figure PCTCN2019121515-appb-000083
与所述终点位置
Figure PCTCN2019121515-appb-000084
不在同一栅格内，则更新当前位置为所述局部解
Figure PCTCN2019121515-appb-000085
更新当前脉冲频率为f t+1，更新当前初始化速度为v t+1，并返回执行步骤二。
步骤八、当所述预测中心位置
Figure PCTCN2019121515-appb-000086
与所述终点位置
Figure PCTCN2019121515-appb-000087
在同一栅格内，所述路径规划层结合各时间的预测局部解完成最优路径并输出。
本申请较佳实施例，如t时间的位置为
Figure PCTCN2019121515-appb-000088
t+1时间的局部解
Figure PCTCN2019121515-appb-000089
t+n时间的局部解
Figure PCTCN2019121515-appb-000090
结合所有时间的位置，可确定所述路径最优规划并输出。
可选地，在其他实施例中，智能化路径规划可读指令还可以被分割为一个或者多个模块，一个或者多个模块被存储于存储器11中，并由一个或多个处理器(本实施例为处理器12)所执行以完成本申请，本申请所称的模块是指能够完成特定功能的多个计算机程序指令段，用于描述智能化路径规划可读指令在智能化路径规划装置中的执行过程。
例如，参照图3所示，为本申请智能化路径规划装置一实施例中的智能化路径规划程序的程序模块示意图，该实施例中，所述智能化路径规划程序可以被分割为地图图片接收模块10、脉冲判断模块20、响度判断模块30、路径输出模块40示例性地：
所述地图图片接收模块10用于：接收已标记出障碍物的地图图片和初始化速度v t，其中t表示时间，并基于栅格法对所述已标记出障碍物的地图图片进行栅格划分得到栅格地图，并在所述栅格地图内设置路径的初始位置
Figure PCTCN2019121515-appb-000091
与终点位置
Figure PCTCN2019121515-appb-000092
并随机产生脉冲频率f t、 脉冲发射率R t和响度A t的值，将所述栅格地图、所述初始化速度v t、所述脉冲频率f t、脉冲发射率R t和响度A t的值输入至路径规划层。
所述脉冲判断模块20用于：将所述时间t更新至t+1，并基于高斯变异算法产生均匀分布随机数rand，并判断所述均匀分布随机数rand与所述初始化脉冲发射率R t的大小关系。
所述响度判断模块30用于：当所述均匀分布随机数rand小于所述初始化脉冲发射率R t时，进一步判断所述均匀分布随机数rand与所述响度A t的大小关系，当所述均匀分布随机数rand小于所述响度A t时，更新所述初始化脉冲发射率R t为R t+1，所述响度A t值为A t+1。
所述路径输出模块40用于：当所述均匀分布随机数rand大于所述初始化脉冲发射率R t时，基于牛顿迭代法求解所述初始栅格内的最优方向解x *，结合所述最优方向解x *，预测所述初始位置
Figure PCTCN2019121515-appb-000093
在t+1时间的中心位置
Figure PCTCN2019121515-appb-000094
并预测中心位置的局部解
Figure PCTCN2019121515-appb-000095
所述脉冲频率f t为f t+1、所述初始化速度v t为v t+1；当所述预测中心位置
Figure PCTCN2019121515-appb-000096
与所述终点位置
Figure PCTCN2019121515-appb-000097
不在同一栅格内，则更新当前位置为所述局部解
Figure PCTCN2019121515-appb-000098
更新当前脉冲频率为f t+1，更新当前初始化速度为v t+1，当所述预测中心位置
Figure PCTCN2019121515-appb-000099
与所述终点位置
Figure PCTCN2019121515-appb-000100
在同一栅格内，所述路径规划层结合各时间的局部解完成最优路径并输出。
上述地图图片接收模块10、脉冲判断模块20、响度判断模块30、路径输出模块40等程序模块被执行时所实现的功能或操作步骤与上述实施例大体相同，在此不再赘述。
此外，本申请实施例还提出一个或多个存储有智能化路径规划可读指令的可读存储介质，所述计算机可读存储介质存储有智能化路径规划可读指令，所述智能化路径规划可读指令被一个或多个处理器执行时，使得所述一个或多个处理器执行如下步骤：
步骤A：图片处理层接收已标记出障碍物的地图图片和初始化速度v t，其中t表示时间，并基于栅格法对所述已标记出障碍物的地图图片进行栅格划分得到栅格地图，并在所述栅格地图内设置路径的初始位置
Figure PCTCN2019121515-appb-000101
与终点位置
Figure PCTCN2019121515-appb-000102
并随机产生脉冲频率f t、脉冲发射率R t和响度A t的值，将所述栅格地图、所述初始化速度v t、所述脉冲频率f t、脉冲发射率R t和响度A t的值输入至路径规划层；
步骤B：所述路径规划层将所述时间t更新至t+1，并基于高斯变异算法产生均匀分布随机数rand；
步骤C：判断所述均匀分布随机数rand与所述初始化脉冲发射率R t的大小关系；
步骤D：当所述均匀分布随机数rand小于所述初始化脉冲发射率R t时，判断所述均匀 分布随机数rand与所述响度A t的大小关系；
步骤E：当所述均匀分布随机数rand小于所述响度A t时，更新所述初始化脉冲发射率R t为R t+1，所述响度A t值为A t+1，并返回执行步骤D，当所述均匀分布随机数rand的值介于所述初始化脉冲发射率R t和响度A t之间，则返回执行步骤B；
步骤F：当所述均匀分布随机数rand大于所述初始化脉冲发射率R t时，基于牛顿迭代法求解所述初始栅格内的最优方向解x *，结合所述最优方向解x *，预测所述初始位置
Figure PCTCN2019121515-appb-000103
在t+1时间的中心位置
Figure PCTCN2019121515-appb-000104
并预测中心位置的局部解
Figure PCTCN2019121515-appb-000105
所述脉冲频率f t为f t+1、所述初始化速度v t为v t+1；
步骤G：判断所述预测中心位置
Figure PCTCN2019121515-appb-000106
与所述终点位置
Figure PCTCN2019121515-appb-000107
是否在同一栅格内，当所述预测中心位置
Figure PCTCN2019121515-appb-000108
与所述终点位置
Figure PCTCN2019121515-appb-000109
不在同一栅格内，则更新当前位置为所述局部解
Figure PCTCN2019121515-appb-000110
更新当前脉冲频率为f t+1，更新当前初始化速度为v t+1，并返回执行步骤B，当所述预测中心位置
Figure PCTCN2019121515-appb-000111
与所述终点位置
Figure PCTCN2019121515-appb-000112
在同一栅格内，所述路径规划层结合各时间的局部解完成最优路径并输出。
需要说明的是，上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。并且本文中的术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括多个要素的过程、装置、物品或者方法不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、装置、物品或者方法所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、装置、物品或者方法中还存在另外的相同要素。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在如上所述的一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种智能化路径规划方法，其特征在于，所述方法包括：
    步骤A：图片处理层接收已标记出障碍物的地图图片和初始化速度v t，其中t表示时间，并基于栅格法对所述已标记出障碍物的地图图片进行栅格划分得到栅格地图，并在所述栅格地图内设置路径的初始位置
    Figure PCTCN2019121515-appb-100001
    与终点位置
    Figure PCTCN2019121515-appb-100002
    并随机产生脉冲频率f t、脉冲发射率R t和响度A t的值，将所述栅格地图、所述初始化速度v t、所述脉冲频率f t、脉冲发射率R t和响度A t的值输入至路径规划层；
    步骤B：所述路径规划层将所述时间t更新至t+1，并基于高斯变异算法产生均匀分布随机数rand；
    步骤C：判断所述均匀分布随机数rand与所述初始化脉冲发射率R t的大小关系；
    步骤D：当所述均匀分布随机数rand小于所述初始化脉冲发射率R t时，判断所述均匀分布随机数rand与所述响度A t的大小关系；
    步骤E：当所述均匀分布随机数rand小于所述响度A t时，更新所述初始化脉冲发射率R t为R t+1，所述响度A t值为A t+1，并返回执行步骤D，当所述均匀分布随机数rand的值介于所述初始化脉冲发射率R t和响度A t之间，则返回执行步骤B；
    步骤F：当所述均匀分布随机数rand大于所述初始化脉冲发射率R t时，基于牛顿迭代法求解所述初始栅格内的最优方向解x *，结合所述最优方向解x *，预测所述初始位置
    Figure PCTCN2019121515-appb-100003
    在t+1时间的中心位置
    Figure PCTCN2019121515-appb-100004
    并预测中心位置的局部解
    Figure PCTCN2019121515-appb-100005
    所述脉冲频率f t为f t+1、所述初始化速度v t为v t+1；
    步骤G：判断所述预测中心位置
    Figure PCTCN2019121515-appb-100006
    与所述终点位置
    Figure PCTCN2019121515-appb-100007
    是否在同一栅格内，当所述预测中心位置
    Figure PCTCN2019121515-appb-100008
    与所述终点位置
    Figure PCTCN2019121515-appb-100009
    不在同一栅格内，则更新当前位置为所述局部解
    Figure PCTCN2019121515-appb-100010
    更新当前脉冲频率为f t+1，更新当前初始化速度为v t+1，并返回执行步骤B，当所述预测中心位置
    Figure PCTCN2019121515-appb-100011
    与所述终点位置
    Figure PCTCN2019121515-appb-100012
    在同一栅格内，所述路径规划层结合各时间的局部解完成最优路径并输出。
  2. 如权利要求1所述的智能化路径规划方法，其特征在于，所述基于栅格法对所述已标记出障碍物的地图图片进行栅格划分得到栅格地图，包括：
    所述图片处理层对所述已标记出障碍物的地图图片进行单元分割，得到多个单元，所述多个单元为大小固定，分辨率相同的方块；
    对所述多个单元进行图像预处理操作，所述图像预处理操作包括膨胀、腐蚀与二值化；
    对所述图像预处理操作完成的多个单元使用摩尔领域跟踪算法提取障碍物的轮廓，得 到所述栅格地图。
  3. 如权利要求1所述的智能化路径规划方法，其特征在于，
    预测的所述初始位置
    Figure PCTCN2019121515-appb-100013
    的t+1时间的中心位置为：
    Figure PCTCN2019121515-appb-100014
    预测的中心位置的局部解为：
    Figure PCTCN2019121515-appb-100015
    预测的所述脉冲频率为：
    f t+1＝f min+(f max-f min)β
    预测的所述初始化速度为：
    Figure PCTCN2019121515-appb-100016
    其中，ε为收缩因子，β为[0,1]内产生的随机数，f min，f max分别表示脉冲频率的最小值与最大值。
  4. 如权利要求3中的智能化路径规划方法，其特征在于，所述牛顿迭代法包括求解坐标和迭代路径；
    其中，所述求解坐标为：
    Figure PCTCN2019121515-appb-100017
    所述迭代路径为：
    Figure PCTCN2019121515-appb-100018
    其中，x 0为所述牛顿迭代法接近零点的坐标值，f(x 0)为曲线函数，f′(x 0)为所述曲线函数的导数函数。
  5. 如权利要求1所述的智能化路径规划方法，其特征在于：
    更新的所述初始化脉冲发射率为：
    R t+1＝R t(1-e -γt)
    更新的所述响度为：
    A t+1＝αA t
    其中，γ脉冲发射率的增强系数，α为音量的衰减系数，e为无限循环无理数。
  6. 一种智能化路径规划装置，其特征在于，所述装置包括存储器和处理器，所述存储器上存储有可在所述处理器上运行的智能化路径规划可读指令，所述智能化路径规划可读指令被所述处理器执行时实现如下步骤：
    步骤A：图片处理层接收已标记出障碍物的地图图片和初始化速度v t，其中t表示时 间，并基于栅格法对所述已标记出障碍物的地图图片进行栅格划分得到栅格地图，并在所述栅格地图内设置路径的初始位置
    Figure PCTCN2019121515-appb-100019
    与终点位置
    Figure PCTCN2019121515-appb-100020
    并随机产生脉冲频率f t、脉冲发射率R t和响度A t的值，将所述栅格地图、所述初始化速度v t、所述脉冲频率f t、脉冲发射率R t和响度A t的值输入至路径规划层；
    步骤B：所述路径规划层将所述时间t更新至t+1，并基于高斯变异算法产生均匀分布随机数rand；
    步骤C：判断所述均匀分布随机数rand与所述初始化脉冲发射率R t的大小关系；
    步骤D：当所述均匀分布随机数rand小于所述初始化脉冲发射率R t时，判断所述均匀分布随机数rand与所述响度A t的大小关系；
    步骤E：当所述均匀分布随机数rand小于所述响度A t时，更新所述初始化脉冲发射率R t为R t+1，所述响度A t值为A t+1，并返回执行步骤D，当所述均匀分布随机数rand的值介于所述初始化脉冲发射率R t和响度A t之间，则返回执行步骤B；
    步骤F：当所述均匀分布随机数rand大于所述初始化脉冲发射率R t时，基于牛顿迭代法求解所述初始栅格内的最优方向解x *，结合所述最优方向解x *，预测所述初始位置
    Figure PCTCN2019121515-appb-100021
    在t+1时间的中心位置
    Figure PCTCN2019121515-appb-100022
    并预测中心位置的局部解
    Figure PCTCN2019121515-appb-100023
    所述脉冲频率f t为f t+1、所述初始化速度v t为v t+1；
    步骤G：判断所述预测中心位置
    Figure PCTCN2019121515-appb-100024
    与所述终点位置
    Figure PCTCN2019121515-appb-100025
    是否在同一栅格内，当所述预测中心位置
    Figure PCTCN2019121515-appb-100026
    与所述终点位置
    Figure PCTCN2019121515-appb-100027
    不在同一栅格内，则更新当前位置为所述局部解
    Figure PCTCN2019121515-appb-100028
    更新当前脉冲频率为f t+1，更新当前初始化速度为v t+1，并返回执行步骤B，当所述预测中心位置
    Figure PCTCN2019121515-appb-100029
    与所述终点位置
    Figure PCTCN2019121515-appb-100030
    在同一栅格内，所述路径规划层结合各时间的局部解完成最优路径并输出。
  7. 如权利要求6所述的智能化路径规划装置，其特征在于，所述基于栅格法对所述已标记出障碍物的地图图片进行栅格划分得到栅格地图，包括：
    所述图片处理层对所述已标记出障碍物的地图图片进行单元分割，得到多个单元，所述多个单元为大小固定，分辨率相同的方块；
    对所述多个单元进行图像预处理操作，所述图像预处理操作包括膨胀、腐蚀与二值化；
    对所述图像预处理操作完成的多个单元使用摩尔领域跟踪算法提取障碍物的轮廓，得到所述栅格地图。
  8. 如权利要求6所述的智能化路径规划装置，其特征在于，
    预测的所述初始位置
    Figure PCTCN2019121515-appb-100031
    的t+1时间的中心位置为：
    Figure PCTCN2019121515-appb-100032
    预测的中心位置的局部解为：
    Figure PCTCN2019121515-appb-100033
    预测的所述脉冲频率为：
    f t+1＝f min+(f max-f min)β
    预测的所述初始化速度为：
    Figure PCTCN2019121515-appb-100034
    其中，ε为收缩因子，β为[0,1]内产生的随机数，f min，f max分别表示脉冲频率的最小值与最大值。
  9. 如权利要求8所述的智能化路径规划装置，其特征在于，所述牛顿迭代法包括求解坐标和迭代路径；
    其中，所述求解坐标为：
    Figure PCTCN2019121515-appb-100035
    所述迭代路径为：
    Figure PCTCN2019121515-appb-100036
    其中，x 0为所述牛顿迭代法接近零点的坐标值，f(x 0)为曲线函数，f′(x 0)为所述曲线函数的导数函数。
  10. 如权利要求6所述的智能化路径规划装置，其特征在于：
    更新的所述初始化脉冲发射率为：
    R t+1＝R t(1-e -γt)
    更新的所述响度为：
    A t+1＝αA t
    其中，γ脉冲发射率的增强系数，α为音量的衰减系数，e为无限循环无理数。
  11. 一个或多个存储有智能化路径规划可读指令的可读存储介质，所述计算机可读存储介质存储有智能化路径规划可读指令，其特征在于，所述智能化路径规划可读指令被一个或多个处理器执行时，使得所述一个或多个处理器执行如下步骤：
    步骤A：图片处理层接收已标记出障碍物的地图图片和初始化速度v t，其中t表示时间，并基于栅格法对所述已标记出障碍物的地图图片进行栅格划分得到栅格地图，并在所述栅格地图内设置路径的初始位置
    Figure PCTCN2019121515-appb-100037
    与终点位置
    Figure PCTCN2019121515-appb-100038
    并随机产生脉冲频率f t、脉冲发射率R t和响度A t的值，将所述栅格地图、所述初始化速度v t、所述脉冲频率f t、脉冲发射率R t和 响度A t的值输入至路径规划层；
    步骤B：所述路径规划层将所述时间t更新至t+1，并基于高斯变异算法产生均匀分布随机数rand；
    步骤C：判断所述均匀分布随机数rand与所述初始化脉冲发射率R t的大小关系；
    步骤D：当所述均匀分布随机数rand小于所述初始化脉冲发射率R t时，判断所述均匀分布随机数rand与所述响度A t的大小关系；
    步骤E：当所述均匀分布随机数rand小于所述响度A t时，更新所述初始化脉冲发射率R t为R t+1，所述响度A t值为A t+1，并返回执行步骤D，当所述均匀分布随机数rand的值介于所述初始化脉冲发射率R t和响度A t之间，则返回执行步骤B；
    步骤F：当所述均匀分布随机数rand大于所述初始化脉冲发射率R t时，基于牛顿迭代法求解所述初始栅格内的最优方向解x *，结合所述最优方向解x *，预测所述初始位置
    Figure PCTCN2019121515-appb-100039
    在t+1时间的中心位置
    Figure PCTCN2019121515-appb-100040
    并预测中心位置的局部解
    Figure PCTCN2019121515-appb-100041
    所述脉冲频率f t为f t+1、所述初始化速度v t为v t+1；
    步骤G：判断所述预测中心位置
    Figure PCTCN2019121515-appb-100042
    与所述终点位置
    Figure PCTCN2019121515-appb-100043
    是否在同一栅格内，当所述预测中心位置
    Figure PCTCN2019121515-appb-100044
    与所述终点位置
    Figure PCTCN2019121515-appb-100045
    不在同一栅格内，则更新当前位置为所述局部解
    Figure PCTCN2019121515-appb-100046
    更新当前脉冲频率为f t+1，更新当前初始化速度为v t+1，并返回执行步骤B，当所述预测中心位置
    Figure PCTCN2019121515-appb-100047
    与所述终点位置
    Figure PCTCN2019121515-appb-100048
    在同一栅格内，所述路径规划层结合各时间的局部解完成最优路径并输出。
  12. 如权利要求11所述的可读存储介质，其特征在于，所述基于栅格法对所述已标记出障碍物的地图图片进行栅格划分得到栅格地图，包括：
    所述图片处理层对所述已标记出障碍物的地图图片进行单元分割，得到多个单元，所述多个单元为大小固定，分辨率相同的方块；
    对所述多个单元进行图像预处理操作，所述图像预处理操作包括膨胀、腐蚀与二值化；
    对所述图像预处理操作完成的多个单元使用摩尔领域跟踪算法提取障碍物的轮廓，得到所述栅格地图。
  13. 如权利要求11所述的可读存储介质，其特征在于，
    预测的所述初始位置
    Figure PCTCN2019121515-appb-100049
    的t+1时间的中心位置为：
    Figure PCTCN2019121515-appb-100050
    预测的中心位置的局部解为：
    Figure PCTCN2019121515-appb-100051
    预测的所述脉冲频率为：
    f t+1＝f min+(f max-f min)β
    预测的所述初始化速度为：
    Figure PCTCN2019121515-appb-100052
    其中，ε为收缩因子，β为[0,1]内产生的随机数，f min，f max分别表示脉冲频率的最小值与最大值。
  14. 如权利要求13中的可读存储介质，其特征在于，所述牛顿迭代法包括求解坐标和迭代路径；
    其中，所述求解坐标为：
    Figure PCTCN2019121515-appb-100053
    所述迭代路径为：
    Figure PCTCN2019121515-appb-100054
    其中，x 0为所述牛顿迭代法接近零点的坐标值，f(x 0)为曲线函数，f′(x 0)为所述曲线函数的导数函数。
  15. 如权利要求11所述的可读存储介质，其特征在于：
    更新的所述初始化脉冲发射率为：
    R t+1＝R t(1-e -γt)
    更新的所述响度为：
    A t+1＝αA t
    其中，γ脉冲发射率的增强系数，α为音量的衰减系数，e为无限循环无理数。
  16. 一种智能化路径规划装置，其特征在于，所述装置包括：
    地图图片接收模块，用于使图片处理层接收已标记出障碍物的地图图片和初始化速度v t，其中t表示时间，并基于栅格法对所述已标记出障碍物的地图图片进行栅格划分得到栅格地图，并在所述栅格地图内设置路径的初始位置
    Figure PCTCN2019121515-appb-100055
    与终点位置
    Figure PCTCN2019121515-appb-100056
    并随机产生脉冲频率f t、脉冲发射率R t和响度A t的值，将所述栅格地图、所述初始化速度v t、所述脉冲频率f t、脉冲发射率R t和响度A t的值输入至路径规划层；
    脉冲判断模块，用于使所述路径规划层将所述时间t更新至t+1，并基于高斯变异算法产生均匀分布随机数rand；判断所述均匀分布随机数rand与所述初始化脉冲发射率R t的大小关系；
    响度判断模块，用于当所述均匀分布随机数rand小于所述初始化脉冲发射率R t时， 判断所述均匀分布随机数rand与所述响度A t的大小关系；当所述均匀分布随机数rand小于所述响度A t时，更新所述初始化脉冲发射率R t为R t+1，所述响度A t值为A t+1；
    路径输出模块，用于当所述均匀分布随机数rand大于所述初始化脉冲发射率R t时，基于牛顿迭代法求解所述初始栅格内的最优方向解x *，结合所述最优方向解x *，预测所述初始位置
    Figure PCTCN2019121515-appb-100057
    在t+1时间的中心位置
    Figure PCTCN2019121515-appb-100058
    并预测中心位置的局部解
    Figure PCTCN2019121515-appb-100059
    所述脉冲频率f t为f t+1、所述初始化速度v t为v t+1；当所述预测中心位置
    Figure PCTCN2019121515-appb-100060
    与所述终点位置
    Figure PCTCN2019121515-appb-100061
    不在同一栅格内，则更新当前位置为所述局部解
    Figure PCTCN2019121515-appb-100062
    更新当前脉冲频率为f t+1，更新当前初始化速度为v t+1；当所述预测中心位置
    Figure PCTCN2019121515-appb-100063
    与所述终点位置
    Figure PCTCN2019121515-appb-100064
    在同一栅格内，所述路径规划层结合各时间的局部解完成最优路径并输出。
  17. 如权利要求16所述的智能化路径规划装置，其特征在于，所述基于栅格法对所述已标记出障碍物的地图图片进行栅格划分得到栅格地图，包括：
    所述图片处理层对所述已标记出障碍物的地图图片进行单元分割，得到多个单元，所述多个单元为大小固定，分辨率相同的方块；
    对所述多个单元进行图像预处理操作，所述图像预处理操作包括膨胀、腐蚀与二值化；
    对所述图像预处理操作完成的多个单元使用摩尔领域跟踪算法提取障碍物的轮廓，得到所述栅格地图。
  18. 如权利要求16所述的智能化路径规划装置，其特征在于，
    预测的所述初始位置
    Figure PCTCN2019121515-appb-100065
    的t+1时间的中心位置为：
    Figure PCTCN2019121515-appb-100066
    预测的中心位置的局部解为：
    Figure PCTCN2019121515-appb-100067
    预测的所述脉冲频率为：
    f t+1＝f min+(f max-f min)β
    预测的所述初始化速度为：
    Figure PCTCN2019121515-appb-100068
    其中，ε为收缩因子，β为[0,1]内产生的随机数，f min，f max分别表示脉冲频率的最小值与最大值。
  19. 如权利要求18中的智能化路径规划装置，其特征在于，所述牛顿迭代法包括求解坐标和迭代路径；
    其中，所述求解坐标为：
    Figure PCTCN2019121515-appb-100069
    所述迭代路径为：
    Figure PCTCN2019121515-appb-100070
    其中，x 0为所述牛顿迭代法接近零点的坐标值，f(x 0)为曲线函数，f′(x 0)为所述曲线函数的导数函数。
  20. 如权利要求16所述的智能化路径规划装置，其特征在于：
    更新的所述初始化脉冲发射率为：
    R t+1＝R t(1-e -γt)
    更新的所述响度为：
    A t+1＝αA t
    其中，γ脉冲发射率的增强系数，α为音量的衰减系数，e为无限循环无理数。
PCT/CN2019/121515 2019-05-21 2019-11-28 智能化路径规划方法、装置及计算机可读存储介质 Ceased WO2020233063A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910421931.1A CN110274607A (zh) 2019-05-21 2019-05-21 智能化路径规划方法、装置及计算机可读存储介质
CN201910421931.1 2019-05-21

Publications (1)

Publication Number Publication Date
WO2020233063A1 true WO2020233063A1 (zh) 2020-11-26

Family

ID=67960146

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/121515 Ceased WO2020233063A1 (zh) 2019-05-21 2019-11-28 智能化路径规划方法、装置及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN110274607A (zh)
WO (1) WO2020233063A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113093761A (zh) * 2021-04-08 2021-07-09 浙江中烟工业有限责任公司 一种基于激光雷达的仓储机器人室内建图导航系统
CN120008615A (zh) * 2025-04-18 2025-05-16 长春理工大学 一种路径规划方法

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110274607A (zh) * 2019-05-21 2019-09-24 深圳壹账通智能科技有限公司 智能化路径规划方法、装置及计算机可读存储介质
CN110274608A (zh) * 2019-05-21 2019-09-24 深圳壹账通智能科技有限公司 智能化路径规划方法、装置及计算机可读存储介质
CN111263418B (zh) * 2020-01-16 2022-04-15 中国人民解放军陆军工程大学 无线自组织网络中节点的移动路径规划系统及其方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105447565A (zh) * 2015-11-19 2016-03-30 广东顺德中山大学卡内基梅隆大学国际联合研究院 一种基于离散蝙蝠算法的片上网络映射方法
CN107272705A (zh) * 2017-07-31 2017-10-20 中南大学 一种智能环境下机器人路径的多神经网络控制规划方法
WO2019060287A1 (en) * 2017-09-20 2019-03-28 Commscope Technologies Llc METHODS OF CALIBRATION OF MILLIMETER WAVE ANTENNA ARRAYS
CN109543572A (zh) * 2018-11-07 2019-03-29 北京交通大学 一种行驶路况评价方法
CN110274607A (zh) * 2019-05-21 2019-09-24 深圳壹账通智能科技有限公司 智能化路径规划方法、装置及计算机可读存储介质

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108694077B (zh) * 2017-04-10 2022-02-01 郑州芯兰德网络科技有限公司 基于改进二进制蝙蝠算法的分布式系统任务调度方法
CN107886157A (zh) * 2017-10-30 2018-04-06 中国地质大学（武汉） 一种新型蝙蝠优化算法系统
CN107886158A (zh) * 2017-10-30 2018-04-06 中国地质大学（武汉） 一种基于迭代局部搜索和随机惯性权重的蝙蝠优化算法
CN109144102B (zh) * 2018-09-19 2021-08-20 沈阳航空航天大学 一种基于改进蝙蝠算法的无人机航路规划方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105447565A (zh) * 2015-11-19 2016-03-30 广东顺德中山大学卡内基梅隆大学国际联合研究院 一种基于离散蝙蝠算法的片上网络映射方法
CN107272705A (zh) * 2017-07-31 2017-10-20 中南大学 一种智能环境下机器人路径的多神经网络控制规划方法
WO2019060287A1 (en) * 2017-09-20 2019-03-28 Commscope Technologies Llc METHODS OF CALIBRATION OF MILLIMETER WAVE ANTENNA ARRAYS
CN109543572A (zh) * 2018-11-07 2019-03-29 北京交通大学 一种行驶路况评价方法
CN110274607A (zh) * 2019-05-21 2019-09-24 深圳壹账通智能科技有限公司 智能化路径规划方法、装置及计算机可读存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
WANG, XIANGGUO: "Research on underwater vehicle route planning based on bat algorithm", SCIENCE-ENGINEERING (B), CHINA MASTER’S THESES FULL-TEXT DATABASE, vol. 6, no. 6, 15 June 2018 (2018-06-15), ISSN: 1274-0246 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113093761A (zh) * 2021-04-08 2021-07-09 浙江中烟工业有限责任公司 一种基于激光雷达的仓储机器人室内建图导航系统
CN113093761B (zh) * 2021-04-08 2023-03-31 浙江中烟工业有限责任公司 一种基于激光雷达的仓储机器人室内建图导航系统
CN120008615A (zh) * 2025-04-18 2025-05-16 长春理工大学 一种路径规划方法

Also Published As

Publication number Publication date
CN110274607A (zh) 2019-09-24

Similar Documents

Publication Publication Date Title
WO2020233063A1 (zh) 智能化路径规划方法、装置及计算机可读存储介质
US9342998B2 (en) Techniques to annotate street view images with contextual information
US20190050045A1 (en) Method for displaying content and electronic device thereof
US9582932B2 (en) Identifying and parameterizing roof types in map data
US10346996B2 (en) Image depth inference from semantic labels
WO2022110640A1 (zh) 一种模型优化方法、装置、计算机设备及存储介质
AU2016201908A1 (en) Joint depth estimation and semantic labeling of a single image
CN109035370A (zh) 一种图片标注方法与系统
WO2020248365A1 (zh) 智能分配模型训练内存方法、装置及计算机可读存储介质
US9818219B2 (en) View direction determination
CN107818290A (zh) 基于深度图的启发式手指检测方法
WO2023206904A1 (zh) 一种行人轨迹跟踪方法、系统及相关装置
US9996961B2 (en) Method and apparatus for generating a composite image based on an ambient occlusion
WO2020001024A1 (zh) 视图错层显示方法、电子设备及存储介质
WO2023142607A1 (zh) 图像渲染方法、装置、设备和介质
CN109242941B (zh) 三维对象合成通过使用视觉引导作为二维数字图像的一部分
WO2020125062A1 (zh) 一种图像融合方法及相关装置
CN107447992A (zh) 建筑板材安装方法及系统
US20160117379A1 (en) Taxonomy-Based System for Discovering and Annotating Geofences from Geo-Referenced Data
CN119250201A (zh) 气象信息确定方法、装置、电子设备以及存储介质
CN113742485B (zh) 一种处理文本的方法和装置
CN103714184B (zh) 一种遥感影像快速并行处理方法及装置
CN114898390A (zh) 表格生成方法、装置、电子设备及存储介质
CN114328783A (zh) 地图数据输出方法、地图数据处理方法、装置和电子设备
CN114937180B (zh) 对抗样本的生成方法、装置及电子设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19929652

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 01/03/2022)

122 Ep: pct application non-entry in european phase

Ref document number: 19929652

Country of ref document: EP

Kind code of ref document: A1