CN106327514A - Path-finding robot system and path-finding method based on genetic algorithm - Google Patents
Path-finding robot system and path-finding method based on genetic algorithm Download PDFInfo
- Publication number
- CN106327514A CN106327514A CN201610818275.5A CN201610818275A CN106327514A CN 106327514 A CN106327514 A CN 106327514A CN 201610818275 A CN201610818275 A CN 201610818275A CN 106327514 A CN106327514 A CN 106327514A
- Authority
- CN
- China
- Prior art keywords
- image
- unit
- signal
- path
- robot
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000002068 genetic effect Effects 0.000 title claims abstract description 37
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000006243 chemical reaction Methods 0.000 claims description 16
- 238000003709 image segmentation Methods 0.000 claims description 16
- 230000009471 action Effects 0.000 claims description 12
- 238000003707 image sharpening Methods 0.000 claims description 12
- 238000010353 genetic engineering Methods 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 10
- 230000006978 adaptation Effects 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 8
- 210000004027 cell Anatomy 0.000 claims description 5
- 230000007246 mechanism Effects 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 5
- 206010008190 Cerebrovascular accident Diseases 0.000 claims description 4
- 208000006011 Stroke Diseases 0.000 claims description 4
- 230000004888 barrier function Effects 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 4
- 210000000349 chromosome Anatomy 0.000 claims description 4
- 238000003708 edge detection Methods 0.000 claims description 4
- 230000000717 retained effect Effects 0.000 claims description 4
- 238000010187 selection method Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 claims 1
- 230000003044 adaptive effect Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/0088—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Remote Sensing (AREA)
- Biophysics (AREA)
- Theoretical Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Automation & Control Theory (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Business, Economics & Management (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Biomedical Technology (AREA)
- Electromagnetism (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
- Manipulator (AREA)
Abstract
The invention provides a path-finding robot system and a path-finding method based on a genetic algorithm, and relates to the robot field. The path-finding robot system comprises an image acquisition device used for acquiring original image information of surrounding environment; an image processor, which is in a signal connection with the image acquisition device, and is used for the image processing of the original image information; a main controller, which is in a signal connection with the image processor, and is used to control operation of a robot; a stepping motor, which is in a signal connection with the main controller, and is used to drive the moving of the robot; a path planning processor, which is in a signal connection with the main controller, and is used to plan the moving path of the robot. The path-finding robot system and the path-finding method have advantages of automatic path-finding, high efficiency, and high accuracy.
Description
Technical field
The present invention relates to robot field, particularly to a kind of pathfinding robot system based on genetic algorithm and pathfinding side
Method.
Background technology
Mobile robot path planning is an important research field of robotics, is also artificial intelligence and robotics
A binding site.Whether the mobile robot of which kind of classification, is desirable that according to a certain criterion (such as track route total length
Short, minimum power consumption etc.), in work space, walk in the path along an optimum (or suboptimum).
The typical method of path planning has graph search method, Grid Method, Artificial Potential Field Method etc., and these algorithms have certain limitation
Property, easily it is absorbed in locally optimal solution, and genetic algorithm has the good suitability in solution nonlinear problem, it has also become path is advised
A kind of more method is used in drawing.But the genetic algorithm of standard itself there is also precocity, is easily absorbed in locally optimal solution etc.
Defect, it is impossible to ensure computational efficiency on path planning and the requirement of reliability.
Solve quality and solution efficiency in order to improve path planning, propose a kind of based on preselected mechanism niche technique
Improved adaptive GA-IAGA, and be applied to the path planning of mobile robot, the two-dimensional coordinate of employingizations complexity is one-dimensional seat
Target coded system, effectively reduces the search volume of genetic algorithm;According to the walking feature of mobile robot, devise adaptive
Answer crossover operator, adaptive mutation rate, insertion operator, deletion operator, disturbing operator and inverse operators.Pass through Computer Simulation
Demonstrate the genetic algorithm after improvement and significantly improve search efficiency and convergence rate, and can guarantee that and converge to globally optimal solution,
The shortcoming overcoming standard genetic algorithm, quickly seeks the optimal path that a nothing is touched for robot.
Summary of the invention
In consideration of it, the invention provides a kind of pathfinding robot system based on genetic algorithm and method for searching, the present invention
There is automatic pathfinding, efficiency height and accuracy advantages of higher.
The technical solution used in the present invention is as follows:
A kind of pathfinding robot system based on genetic algorithm, it is characterised in that described system includes: be used for obtaining surrounding
The image collecting device of original image information;Described image collecting device signal is connected to for original image information is carried out figure
As the image processor processed;Described image processor signal is connected to control the master controller that robot runs;Described master control
Device processed signal respectively is connected to for the motor of driven machine people motion with for the path of planning robot's motion path
Planning processor.
Described image processor includes: for the image sharpening unit being sharpened image;Described image sharpening unit
Signal is connected to the image segmentation unit for splitting image;Described image segmentation unit signal is connected to for figure
As carrying out the binarization unit of binary conversion treatment;Described binarization unit signal is connected to for image is carried out threshold skirt inspection
The threshold skirt detector unit surveyed;Described threshold skirt detector unit signal is connected to master controller.
Described path planning processor includes: for setting up initial population and determining the initialization unit of genetic parameter, institute
State initialization unit signal and be connected to the fitness computing unit for calculating ideal adaptation degree;Described fitness computing unit is believed
Number it is connected to the genetic manipulation unit for carrying out genetic manipulation;Described genetic manipulation cell signal is connected to for comparing substring
The comparing unit of size is gone here and there with father.
Described master controller includes: for the power supply powered to whole system;Described power supply signal is connected to for processing
Commute the data processing unit of master controller data message;Described data processing unit signal is connected to for transmitting data letter
Number data transmission unit and for storing the memorizer of data message.
Described image collecting device includes: for obtaining the ccd video camera of original image signal;Described ccd video camera is believed
Number it is connected to the AD conversion unit for the original image signal of simulation being converted to data image signal.
The method for searching of a kind of pathfinding robot system based on genetic algorithm, it is characterised in that described method for searching bag
Include following steps:
Step 1: system start-up, system initialization;
Step 2: image collecting device starts to gather original picture signal, picture signal is sent after the process of master controller
To path planning processor;
Step 3: path planning processor carries out the action path of signal planning robot according to the image received, by planning well
Action path be sent to master controller;
Step 4: master controller, according to the action path transmitting control commands planned to motor, controls step motor drive machine
The motion of device people.
The method that described path planning processor carries out path planning comprises the following steps:
Step 1: initialize population, equidistant along beginning and end line direction choose N number of point, on these vertical lines put with
The vertical coordinate of turning point chosen by machine, and makes these turning points not in barrier;
Step 2: every generation individuality is divided into n class, each apoplexy due to endogenous wind selects the individuality that some fitness are bigger, as a class
Outstanding representative, form a population;Obtaining population scale is:;
Step 4: calculate the fitness of all individualities in population, the individual reservation best by it, then use algorithm of tournament selection method,
Select father individual, to perform to intersect operation, and check the offspring individual chromosome length of acquisition whether more than N, without
Exceed, then retain, otherwise abandon;
Step 5: newly generated offspring individual made a variation with the probability set, insert, disturbance, delete, smooth operation:;
Meanwhile, take preselected mechanism, compare substring and father goes here and there the size of fitness, if the fitness of substring is higher than the adaptation of father's string
Degree, just replaces father's string;Father is otherwise maintained to go here and there constant;
Step 6: repeated execution of steps 3 and step 4 step are until the new individual amount obtained is equal with parent Population;
Step 7: replace the individuality that in new population, fitness is worst with the previous generation optimum individual retained;
Step 8: check algorithm stop condition.Meeting, stop, otherwise jump to: step 3, algorithm proceeds.
The described image processor original image to receiving carries out the method for image procossing and comprises the following steps:
Step 1: image sharpening unit is sharpened process to the original image information received;Image after Edge contrast is sent out
Deliver to image segmentation unit;
Step 2: the image information received is split by image segmentation unit, sends the image after segmentation to binaryzation list
Unit;
Step 3: the binarization unit image to receiving carries out binary conversion treatment, sends the image after binary conversion treatment to threshold
Value edge detection unit;
Step 4: the threshold skirt detector unit image to receiving carries out threshold skirt detection, the result that threshold skirt is detected
Send to master controller.
The method that described threshold skirt detector unit carries out threshold skirt detection comprises the following steps:
Step 1: use membership function that pending image is mapped as a fuzzy matrix;
Step 2: set imageHaveIndividual gray level, image size is, fuzzy matrixElementMembership function for image is:;Parameter
F=2;WithShape relevant;
Step 3: rightCarry out nonlinear transformation, obtain:
;
Step 4: rightCarry out inverse transformation, obtain the image after enhanced fuzzy
Step 5: the edge obtaining image is:
。
Use above technical scheme, present invention produces following beneficial effect:
1, simple in construction: the robot system of the present invention, the annexation between each processor is simple, image recognition, main control
Device and path planning processor can individually produce and assemble, greatly reduces complexity, reduces cost of manufacture.
2, possess pathfinding function: the robot system of the present invention, with the addition of path planning processor, it is possible to advise for robot
Draw rational path, it is ensured that robot arrives impact point smoothly.
3, accuracy is high: the present invention uses ccd video camera to obtain original image information, the resolution of ccd video camera itself
Rate is high, and the image accuracy rate got is high.
Use above technical scheme, present invention produces following beneficial effect:
1, accuracy is high: the edge threshold detection that image is improved by the image processor of the present invention, the edge threshold of acquisition
Value testing result is more accurate.The path planning processor of the present invention have employed Revised genetic algorithum simultaneously, and this algorithm satisfies the need
The planning in footpath is more accurate.
2, operational efficiency is high: the genetic algorithm algorithm of the present invention has taken into account the rapidity of genetic evolution simultaneously and colony is many
Sample, restrained effectively the generation of " precocious " phenomenon, can search for locally optimal solution and globally optimal solution well.This algorithm exists
Can converge to optimal solution in less evolutionary generation in different environment, the execution speed of algorithm and success rate are the highest
Genetic algorithm in standard.Evolution result is had it addition, choose suitably to intersect in the different phase evolved with mutation probability
Critical impact.The edge threshold algorithm of the present invention is on the premise of ensureing accuracy simultaneously, is greatly improved system
Treatment effeciency, treatment effeciency is higher.
3, low cost, simple in construction: the robot system of the present invention, the annexation between each processor is simple, image
Identification, master controller and path planning processor can individually produce and assemble, greatly reduces complexity, reduces
Cost of manufacture..
Accompanying drawing explanation
Fig. 1 is a kind of based on genetic algorithm pathfinding robot system and the system structure signal of method for searching of the present invention
Figure.
Detailed description of the invention
All features disclosed in this specification, or disclosed all methods or during step, except mutually exclusive
Feature and/or step beyond, all can combine by any way.
Any feature disclosed in this specification (including any accessory claim, summary), unless specifically stated otherwise,
By other equivalences or there is the alternative features of similar purpose replaced.I.e., unless specifically stated otherwise, each feature is a series of
An example in equivalence or similar characteristics.
The embodiment of the present invention 1 provides a kind of pathfinding robot system based on genetic algorithm, system structure such as Fig. 1 institute
Show:
A kind of pathfinding robot system based on genetic algorithm, it is characterised in that described system includes: be used for obtaining surrounding
The image collecting device of original image information;Described image collecting device signal is connected to for original image information is carried out figure
As the image processor processed;Described image processor signal is connected to control the master controller that robot runs;Described master control
Device processed signal respectively is connected to for the motor of driven machine people motion with for the path of planning robot's motion path
Planning processor.
Described image processor includes: for the image sharpening unit being sharpened image;Described image sharpening unit
Signal is connected to the image segmentation unit for splitting image;Described image segmentation unit signal is connected to for figure
As carrying out the binarization unit of binary conversion treatment;Described binarization unit signal is connected to for image is carried out threshold skirt inspection
The threshold skirt detector unit surveyed;Described threshold skirt detector unit signal is connected to master controller.
Described path planning processor includes: for setting up initial population and determining the initialization unit of genetic parameter, institute
State initialization unit signal and be connected to the fitness computing unit for calculating ideal adaptation degree;Described fitness computing unit is believed
Number it is connected to the genetic manipulation unit for carrying out genetic manipulation;Described genetic manipulation cell signal is connected to for comparing substring
The comparing unit of size is gone here and there with father.
Described master controller includes: for the power supply powered to whole system;Described power supply signal is connected to for processing
Commute the data processing unit of master controller data message;Described data processing unit signal is connected to for transmitting data letter
Number data transmission unit and for storing the memorizer of data message.
Described image collecting device includes: for obtaining the ccd video camera of original image signal;Described ccd video camera is believed
Number it is connected to the AD conversion unit for the original image signal of simulation being converted to data image signal.
The embodiment of the present invention 2 provides the method for searching of a kind of pathfinding robot based on genetic algorithm:
A kind of method for searching of pathfinding robot system based on genetic algorithm, it is characterised in that described method for searching include with
Lower step:
Step 1: system start-up, system initialization;
Step 2: image collecting device starts to gather original picture signal, picture signal is sent after the process of master controller
To path planning processor;
Step 3: path planning processor carries out the action path of signal planning robot according to the image received, by planning well
Action path be sent to master controller;
Step 4: master controller, according to the action path transmitting control commands planned to motor, controls step motor drive machine
The motion of device people.
The method that described path planning processor carries out path planning comprises the following steps:
Step 1: initialize population, equidistant along beginning and end line direction choose N number of point, on these vertical lines put with
The vertical coordinate of turning point chosen by machine, and makes these turning points not in barrier;
Step 2: every generation individuality is divided into n class, each apoplexy due to endogenous wind selects the individuality that some fitness are bigger, as a class
Outstanding representative, form a population;Obtaining population scale is:;
Step 4: calculate the fitness of all individualities in population, the individual reservation best by it, then use algorithm of tournament selection method,
Select father individual, to perform to intersect operation, and check the offspring individual chromosome length of acquisition whether more than N, without
Exceed, then retain, otherwise abandon;
Step 5: newly generated offspring individual made a variation with the probability set, insert, disturbance, delete, smooth operation:;
Meanwhile, take preselected mechanism, compare substring and father goes here and there the size of fitness, if the fitness of substring is higher than the adaptation of father's string
Degree, just replaces father's string;Father is otherwise maintained to go here and there constant;
Step 6: repeated execution of steps 3 and step 4 step are until the new individual amount obtained is equal with parent Population;
Step 7: replace the individuality that in new population, fitness is worst with the previous generation optimum individual retained;
Step 8: check algorithm stop condition.Meeting, stop, otherwise jump to: step 3, algorithm proceeds.
The described image processor original image to receiving carries out the method for image procossing and comprises the following steps:
Step 1: image sharpening unit is sharpened process to the original image information received;Image after Edge contrast is sent out
Deliver to image segmentation unit;
Step 2: the image information received is split by image segmentation unit, sends the image after segmentation to binaryzation list
Unit;
Step 3: the binarization unit image to receiving carries out binary conversion treatment, sends the image after binary conversion treatment to threshold
Value edge detection unit;
Step 4: the threshold skirt detector unit image to receiving carries out threshold skirt detection, the result that threshold skirt is detected
Send to master controller.
The method that described threshold skirt detector unit carries out threshold skirt detection comprises the following steps:
Step 1: use membership function that pending image is mapped as a fuzzy matrix;
Step 2: set imageHaveIndividual gray level, image size is, fuzzy matrixElementMembership function for image is:;Parameter
F=2;WithShape relevant;
Step 3: rightCarry out nonlinear transformation, obtain:
;
Step 4: rightCarry out inverse transformation, obtain the image after enhanced fuzzy
Step 5: the edge obtaining image is:
。
The embodiment of the present invention 3 provides a kind of pathfinding robot system based on genetic algorithm and method for searching, system
Structure chart is as shown in Figure 1:
A kind of pathfinding robot system based on genetic algorithm, it is characterised in that described system includes: be used for obtaining surrounding
The image collecting device of original image information;Described image collecting device signal is connected to for original image information is carried out figure
As the image processor processed;Described image processor signal is connected to control the master controller that robot runs;Described master control
Device processed signal respectively is connected to for the motor of driven machine people motion with for the path of planning robot's motion path
Planning processor.
Described image processor includes: for the image sharpening unit being sharpened image;Described image sharpening unit
Signal is connected to the image segmentation unit for splitting image;Described image segmentation unit signal is connected to for figure
As carrying out the binarization unit of binary conversion treatment;Described binarization unit signal is connected to for image is carried out threshold skirt inspection
The threshold skirt detector unit surveyed;Described threshold skirt detector unit signal is connected to master controller.
Described path planning processor includes: for setting up initial population and determining the initialization unit of genetic parameter, institute
State initialization unit signal and be connected to the fitness computing unit for calculating ideal adaptation degree;Described fitness computing unit is believed
Number it is connected to the genetic manipulation unit for carrying out genetic manipulation;Described genetic manipulation cell signal is connected to for comparing substring
The comparing unit of size is gone here and there with father.
Described master controller includes: for the power supply powered to whole system;Described power supply signal is connected to for processing
Commute the data processing unit of master controller data message;Described data processing unit signal is connected to for transmitting data letter
Number data transmission unit and for storing the memorizer of data message.
Described image collecting device includes: for obtaining the ccd video camera of original image signal;Described ccd video camera is believed
Number it is connected to the AD conversion unit for the original image signal of simulation being converted to data image signal.
The method for searching of a kind of pathfinding robot system based on genetic algorithm, it is characterised in that described method for searching bag
Include following steps:
Step 1: system start-up, system initialization;
Step 2: image collecting device starts to gather original picture signal, picture signal is sent after the process of master controller
To path planning processor;
Step 3: path planning processor carries out the action path of signal planning robot according to the image received, by planning well
Action path be sent to master controller;
Step 4: master controller, according to the action path transmitting control commands planned to motor, controls step motor drive machine
The motion of device people.
The method that described path planning processor carries out path planning comprises the following steps:
Step 1: initialize population, equidistant along beginning and end line direction choose N number of point, on these vertical lines put with
The vertical coordinate of turning point chosen by machine, and makes these turning points not in barrier;
Step 2: every generation individuality is divided into n class, each apoplexy due to endogenous wind selects the individuality that some fitness are bigger, as a class
Outstanding representative, form a population;Obtaining population scale is:;
Step 4: calculate the fitness of all individualities in population, the individual reservation best by it, then use algorithm of tournament selection method,
Select father individual, to perform to intersect operation, and check the offspring individual chromosome length of acquisition whether more than N, without
Exceed, then retain, otherwise abandon;
Step 5: newly generated offspring individual made a variation with the probability set, insert, disturbance, delete, smooth operation:;
Meanwhile, take preselected mechanism, compare substring and father goes here and there the size of fitness, if the fitness of substring is higher than the adaptation of father's string
Degree, just replaces father's string;Father is otherwise maintained to go here and there constant;
Step 6: repeated execution of steps 3 and step 4 step are until the new individual amount obtained is equal with parent Population;
Step 7: replace the individuality that in new population, fitness is worst with the previous generation optimum individual retained;
Step 8: check algorithm stop condition.Meeting, stop, otherwise jump to: step 3, algorithm proceeds.
The described image processor original image to receiving carries out the method for image procossing and comprises the following steps:
Step 1: image sharpening unit is sharpened process to the original image information received;Image after Edge contrast is sent out
Deliver to image segmentation unit;
Step 2: the image information received is split by image segmentation unit, sends the image after segmentation to binaryzation list
Unit;
Step 3: the binarization unit image to receiving carries out binary conversion treatment, sends the image after binary conversion treatment to threshold
Value edge detection unit;
Step 4: the threshold skirt detector unit image to receiving carries out threshold skirt detection, the result that threshold skirt is detected
Send to master controller.
The method that described threshold skirt detector unit carries out threshold skirt detection comprises the following steps:
Step 1: use membership function that pending image is mapped as a fuzzy matrix;
Step 2: set imageHaveIndividual gray level, image size is, fuzzy matrixElementMembership function for image is:;Parameter
F=2;WithShape relevant;
Step 3: rightCarry out nonlinear transformation, obtain:
;
Step 4: rightCarry out inverse transformation, obtain the image after enhanced fuzzy
Step 5: the edge obtaining image is:
。。
The invention is not limited in aforesaid detailed description of the invention.The present invention expands to any disclose in this manual
New feature or any new combination, and the arbitrary new method that discloses or the step of process or any new combination.
Claims (10)
1. a pathfinding robot system based on genetic algorithm, it is characterised in that described system includes: be used for obtaining ring around
The image collecting device of border original image information;Described image collecting device signal is connected to for carrying out original image information
The image processor of image procossing;Described image processor signal is connected to control the master controller that robot runs;Described master
Controller signal respectively is connected to for the motor of driven machine people motion with for the road of planning robot's motion path
Footpath planning processor.
2. pathfinding robot system based on genetic algorithm as claimed in claim 1, it is characterised in that described image processor
Including: for the image sharpening unit that image is sharpened;Described image sharpening cell signal is connected to for entering image
The image segmentation unit of row segmentation;Described image segmentation unit signal is connected to the two-value for image carries out binary conversion treatment
Change unit;Described binarization unit signal is connected to the threshold skirt detector unit for image carries out threshold skirt detection;
Described threshold skirt detector unit signal is connected to master controller.
3. pathfinding robot system based on genetic algorithm as claimed in claim 2, it is characterised in that at described path planning
Reason device includes: for setting up initial population and determining that the initialization unit of genetic parameter, described initialization unit signal are connected to
For calculating the fitness computing unit of ideal adaptation degree;Described fitness computing unit signal is connected to for carrying out heredity behaviour
The genetic manipulation unit made;Described genetic manipulation cell signal is connected to for comparing substring and father goes here and there the comparing unit of size.
4. pathfinding robot system based on genetic algorithm as claimed in claim 3, it is characterised in that described master controller bag
Include: for the power supply powered to whole system;Described power supply signal is connected to commute master controller data message for process
Data processing unit;Described data processing unit signal be connected to the data transmission unit for transmitting data signal and for
The memorizer of storage data message.
5. pathfinding robot system based on genetic algorithm as claimed in claim 4, it is characterised in that described image collector
Put and include: for obtaining the ccd video camera of original image signal;Described ccd video camera signal is connected to for former by simulate
Beginning picture signal is converted to the AD conversion unit of data image signal.
6. a method for searching based on the pathfinding robot system based on genetic algorithm one of claim 1 to 5 Suo Shu, its
Being characterised by, described method for searching comprises the following steps:
Step 1: system start-up, system initialization;
Step 2: image collecting device starts to gather original picture signal, picture signal is sent after the process of master controller
To path planning processor;
Step 3: path planning processor carries out the action path of signal planning robot according to the image received, by planning well
Action path be sent to master controller;
Step 4: master controller, according to the action path transmitting control commands planned to motor, controls step motor drive machine
The motion of device people.
7. the method for searching of pathfinding robot system based on genetic algorithm as claimed in claim 6, it is characterised in that described
Path planning processor carries out the method for path planning and comprises the following steps:
Step 1: initialize population, equidistant along beginning and end line direction choose N number of point, on these vertical lines put with
The vertical coordinate of turning point chosen by machine, and makes these turning points not in barrier;
Step 2: every generation individuality is divided into n class, each apoplexy due to endogenous wind selects the individuality that some fitness are bigger, as a class
Outstanding representative, form a population;Obtaining population scale is:;
Step 4: calculate the fitness of all individualities in population, the individual reservation best by it, then use algorithm of tournament selection method,
Select father individual, to perform to intersect operation, and check the offspring individual chromosome length of acquisition whether more than N, without
Exceed, then retain, otherwise abandon;
Step 5: newly generated offspring individual made a variation with the probability set, insert, disturbance, delete, smooth operation:;
Meanwhile, take preselected mechanism, compare substring and father goes here and there the size of fitness, if the fitness of substring is higher than the adaptation of father's string
Degree, just replaces father's string;Father is otherwise maintained to go here and there constant;
Step 6: repeated execution of steps 3 and step 4 step are until the new individual amount obtained is equal with parent Population;
Step 7: replace the individuality that in new population, fitness is worst with the previous generation optimum individual retained;
Step 8: check algorithm stop condition.
8. meeting, stop, otherwise jump to: step 3, algorithm proceeds.
9. the method for searching of pathfinding robot system based on genetic algorithm as claimed in claim 6, it is characterised in that described
The image processor original image to receiving carries out the method for image procossing and comprises the following steps:
Step 1: image sharpening unit is sharpened process to the original image information received;Image after Edge contrast is sent out
Deliver to image segmentation unit;
Step 2: the image information received is split by image segmentation unit, sends the image after segmentation to binaryzation list
Unit;
Step 3: the binarization unit image to receiving carries out binary conversion treatment, sends the image after binary conversion treatment to threshold
Value edge detection unit;
Step 4: the threshold skirt detector unit image to receiving carries out threshold skirt detection, the result that threshold skirt is detected
Send to master controller.
10. the method for searching of pathfinding robot system based on genetic algorithm as claimed in claim 8, it is characterised in that institute
State threshold skirt detector unit to carry out the method for threshold skirt detection and comprise the following steps:
Step 1: use membership function that pending image is mapped as a fuzzy matrix;
Step 2: set imageHaveIndividual gray level, image size is, fuzzy matrixElementMembership function for image is:;Parameter
F=2;WithShape relevant;
Step 3: rightCarry out nonlinear transformation, obtain:
;
Step 4: rightCarry out inverse transformation, obtain the image after enhanced fuzzy
Step 5: the edge obtaining image is:
。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610818275.5A CN106327514A (en) | 2016-09-13 | 2016-09-13 | Path-finding robot system and path-finding method based on genetic algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610818275.5A CN106327514A (en) | 2016-09-13 | 2016-09-13 | Path-finding robot system and path-finding method based on genetic algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106327514A true CN106327514A (en) | 2017-01-11 |
Family
ID=57787108
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610818275.5A Withdrawn CN106327514A (en) | 2016-09-13 | 2016-09-13 | Path-finding robot system and path-finding method based on genetic algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106327514A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107219850A (en) * | 2017-05-25 | 2017-09-29 | 深圳众厉电力科技有限公司 | A kind of automatic Pathfinding system of robot based on machine vision |
CN107816999A (en) * | 2017-09-25 | 2018-03-20 | 华南理工大学 | A kind of unmanned boat navigation path contexture by self method based on ant group algorithm |
CN109324612A (en) * | 2018-09-13 | 2019-02-12 | 鲁东大学 | A kind of robot ambulation parameter optimization method, computer equipment and readable storage medium storing program for executing |
CN109359740A (en) * | 2018-11-02 | 2019-02-19 | 北京华如科技股份有限公司 | Motor-driven route optimal selection method and storage medium based on more habitat genetic algorithms |
CN116681195A (en) * | 2023-06-06 | 2023-09-01 | 深圳启示智能科技有限公司 | Robot road-finding device based on artificial intelligence |
-
2016
- 2016-09-13 CN CN201610818275.5A patent/CN106327514A/en not_active Withdrawn
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107219850A (en) * | 2017-05-25 | 2017-09-29 | 深圳众厉电力科技有限公司 | A kind of automatic Pathfinding system of robot based on machine vision |
CN107816999A (en) * | 2017-09-25 | 2018-03-20 | 华南理工大学 | A kind of unmanned boat navigation path contexture by self method based on ant group algorithm |
CN109324612A (en) * | 2018-09-13 | 2019-02-12 | 鲁东大学 | A kind of robot ambulation parameter optimization method, computer equipment and readable storage medium storing program for executing |
CN109324612B (en) * | 2018-09-13 | 2021-12-17 | 鲁东大学 | Robot walking parameter optimization method, computer equipment and readable storage medium |
CN109359740A (en) * | 2018-11-02 | 2019-02-19 | 北京华如科技股份有限公司 | Motor-driven route optimal selection method and storage medium based on more habitat genetic algorithms |
CN116681195A (en) * | 2023-06-06 | 2023-09-01 | 深圳启示智能科技有限公司 | Robot road-finding device based on artificial intelligence |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106327514A (en) | Path-finding robot system and path-finding method based on genetic algorithm | |
Dubé et al. | SegMap: 3D segment mapping using data-driven descriptors | |
WO2020091871A1 (en) | Systems and methods for few-shot transfer learning | |
CN113110482B (en) | Indoor environment robot exploration method and system based on priori information heuristic method | |
CN111445368B (en) | Garbage classification method, device and equipment based on machine vision and deep learning | |
CN109711262B (en) | Intelligent excavator pedestrian detection method based on deep convolutional neural network | |
CN110544293B (en) | Building scene recognition method through visual cooperation of multiple unmanned aerial vehicles | |
CN110321956B (en) | Grass pest control method and device based on artificial intelligence | |
Kim et al. | Tomato harvesting robotic system based on Deep-ToMaToS: Deep learning network using transformation loss for 6D pose estimation of maturity classified tomatoes with side-stem | |
Saroya et al. | Online exploration of tunnel networks leveraging topological CNN-based world predictions | |
Thomas et al. | Self-supervised learning of lidar segmentation for autonomous indoor navigation | |
Dong et al. | Robust neural routing through space partitions for camera relocalization in dynamic indoor environments | |
CN110929848A (en) | Training and tracking method based on multi-challenge perception learning model | |
Chen et al. | Lrgnet: Learnable region growing for class-agnostic point cloud segmentation | |
CN112070071B (en) | Method and device for labeling objects in video, computer equipment and storage medium | |
CN115761529B (en) | Image processing method and electronic device | |
Zeng et al. | Lookup: Vision-only real-time precise underground localisation for autonomous mining vehicles | |
CN114186112B (en) | Robot navigation method based on Bayesian optimization multiple information gain exploration strategy | |
Cummins | Probabilistic localization and mapping in appearance space | |
Kanji | Detection-by-localization: Maintenance-free change object detector | |
Pal et al. | A novel end-to-end vision-based architecture for agricultural human–robot collaboration in fruit picking operations | |
Rückin et al. | Semi-supervised active learning for semantic segmentation in unknown environments using informative path planning | |
Hanni et al. | Deep learning framework for scene based indoor location recognition | |
Mishra et al. | Gpu-accelerated rapid planar region extraction for dynamic behaviors on legged robots | |
CN106157278A (en) | Threshold image segmentation method based on improved adaptive GA-IAGA |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20170111 |