CN108227689A - A kind of design method of Agriculture Mobile Robot independent navigation - Google Patents
A kind of design method of Agriculture Mobile Robot independent navigation Download PDFInfo
- Publication number
- CN108227689A CN108227689A CN201611155493.1A CN201611155493A CN108227689A CN 108227689 A CN108227689 A CN 108227689A CN 201611155493 A CN201611155493 A CN 201611155493A CN 108227689 A CN108227689 A CN 108227689A
- Authority
- CN
- China
- Prior art keywords
- navigation
- robot
- image
- mobile robot
- overall view
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000013461 design Methods 0.000 title claims abstract description 32
- 230000000007 visual effect Effects 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000002474 experimental method Methods 0.000 claims abstract description 10
- 238000007689 inspection Methods 0.000 claims abstract description 7
- 238000004088 simulation Methods 0.000 claims abstract description 7
- 238000003384 imaging method Methods 0.000 claims description 14
- 238000012795 verification Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 6
- 230000008901 benefit Effects 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 5
- 230000000052 comparative effect Effects 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000012938 design process Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000011160 research Methods 0.000 abstract description 4
- 238000012271 agricultural production Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Aviation & Aerospace Engineering (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Manipulator (AREA)
- Image Analysis (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a kind of design methods of Agriculture Mobile Robot independent navigation, the described method comprises the following steps：The first step, the characteristics of analyzing various NI Vision Builder for Automated Inspections；Second step designs the acquisition of crops row ambient image and the Processing Algorithm of the overall view visual system based on catadioptric principle；Third walks, and utilizes Hough transform navigation by recognition reference path；4th step designs the navigation controller of the Agriculture Mobile Robot based on fuzzy control method；5th step carries out simulation crops row Navigation Control experiment under the natural environment indoors without fixed light source irradiation.The design method of the Agriculture Mobile Robot independent navigation of the present invention, proposes to be applied to the overall view visual system based on catadioptric principle in the independent navigation of agricultural vehicle or agricultural robot；Using refractive and reflective panorama vision system as core, on existing hardware platform, research and design is directed to the guidance path recognizer of crops row environment and Navigation Control algorithm.
Description
Technical field
The present invention relates to a kind of design methods of Agriculture Mobile Robot independent navigation, belong to agricultural automation technology neck
Domain.
Background technology
With widely available, the expansion of scale of agricultural production of agricultural machinery, scientific and technical continuous development, agricultural production
Just gradually develop to agricultural modernization direction；Agricultural operation environment it is severe, job task heavy, agriculture chemical unreasonable
Utilization pollution environment and toxic object is caused to injure the main barrier for having become and having restricted agricultural development caused by human body
Hinder, more and more people wish to free from heavy agricultural production, cause the shortage of labour, this phenomena just promotees
Agricultural production is made to occur change precision agricultures, Automation of Agricultural Production, it is unmanned come into being, and to realize agriculture life
Production automation just needs the Intelligent agricultural machinery or agricultural robot that the mankind can be replaced to complete part or all of agricultural operation task；
And the agricultural population in China is numerous, per capita land resource is less, is always maintained at splat cropping pattern for a long time,
The waste of vast resources or unreasonable utilization are caused, seriously constrains the development of China's agricultural high-tech, it is particularly agriculture
Machine man-based development；With China's expanding economy, rural laborer largely shifts and the guiding role of national policy will make
China carries out the research of Automation of Agricultural Production and is possibly realized extensively.
Invention content
To solve the above problems, the present invention proposes a kind of design method of Agriculture Mobile Robot independent navigation, summarize
About the mode of agricultural vehicle independent navigation, propose by the overall view visual system based on catadioptric principle be applied to agricultural vehicle or
In the independent navigation of agricultural robot；Using refractive and reflective panorama vision system as core, on existing hardware platform, research and design
It is directed to the guidance path recognizer of crops row environment and Navigation Control algorithm.
The design method of the Agriculture Mobile Robot independent navigation of the present invention, the described method comprises the following steps：
The first step, on this basis, summarizes overall view visual system relative to tradition at the characteristics of analyzing various NI Vision Builder for Automated Inspections
The advantage of NI Vision Builder for Automated Inspection, according to the advantage and disadvantage of various modes, select the overall view visual system based on catadioptric principle as
The navigation sensor of robot, the system cost is low, image taking speed is fast, is very suitable for the occasion higher to requirement of real-time；Base
The information of robot is reflected using the convex reflecting mirror of certain face shape in the overall view visual system of catadioptric principle
It is imaged into video camera, obtains the ambient image in the range of 360 ° of level and certain angle vertical visual field；Due to convex refractive
Mirror makes object to scene environment information in the presence of compression, and there is radial deformations in video camera imaging plane so that actual scene
In some rule objects occur imaging deformation；For the imaging characteristics of the overall view visual system based on catadioptric principle, compare
The scaling method of common several overall view visual systems, and pass through experimental method a certain reality for being parallel to camera plane is put down
Scene image in face obtains the correspondence between image point into row distance and angle calibration；This method, which need not be known, to be taken the photograph
The internal and external parameter of camera and the parametric equation of mirror surface, it is relatively low to the installation requirement of system, and demarcate conveniently；
Second step designs the acquisition of crops row ambient image and the Processing Algorithm of the overall view visual system based on catadioptric principle,
A. camera image acquisition is carried out using Directshow technologies；The characteristics of for agricultural robot operating environment, to adopting
The image of collection is pre-processed, and assumes the colour cast of algorithm and white balance algorithm and diagonal calibration model to acquisition using gray world
Image carries out colour correction, the essential color of approximation reduction object；
B. gray processing processing is carried out to image using normalized excess green value 2xg-r-b on this basis, and then using most
Big Ostu method obtains the bianry image of crops row environment；
C. the impulsive noise point in image is eliminated using medium filtering, has obtained comparatively ideal agricultural robot ambient enviroment
Bianry image；
D. for panorama system imaging the characteristics of, using calibration result, to crop pixel into row distance and angular transformation,
To restore the space line feature of crops row, the convenient extraction to guidance path line；
Third walks, and navigation is calculated using Hough transform navigation by recognition reference path, and with reference to digital compass course heading information
Control parameter；On the basis of image acquisition and processing, the characteristics of imaging with reference to refractive and reflective panorama vision system, become using Hough
It has got the directional information of navigational reference path-line in return, has selected near robot central point, it is closest from imaging center
Straight line is as robot navigation's reference arm radial line；Since robot walks between two row crops, with reference to digital compass
Initial angle information, calculate Navigation Control parameter；
4th step designs the navigation controller of the Agriculture Mobile Robot based on fuzzy control method, and has carried out verification experimental verification；
The characteristics of common navigation control method in analysis robot navigation, comparative study various methods；For farmland operation environment
Feature because fuzzy control need not establish the accurate mathematical model of controlled device, and similar with the mode of thinking of people, therefore, is used
Navigation control method of the fuzzy control as the design；The design process of detailed analysis fuzzy controller, design are poor based on two-wheeled
The two-dimensional fuzzy controller of the Agriculture Mobile Robot of speed control, inputs as Navigation Control parameter, exports as robot left and right wheels
Rotating speed, and be designed and carried out experimental verification with MATLAB, the results showed that, the fuzzy controller that the present invention designs can be with
Accurate track navigation path-line；
5th step carries out simulation crops row Navigation Control experiment under the natural environment indoors without fixed light source irradiation；To agriculture
Industry mobile robot is integrally debugged, and simulation crops row is carried out under the natural environment indoors without fixed light source irradiation and is led
Navigate Control experiment, the results showed that the navigation that crops guidance path line and energy tenacious tracking identify can be recognized accurately in system
Path-line.
Further, three kinds of constituted modes of overall view visual system include the use of special optical frames in the first step
Head, the mode for splicing and adding using single camera rotary head after being imaged using multiple-camera.
Further, the Navigation Control parameter in the third step and the 4th step includes course error angle_err and horizontal stroke
To error distant_err.
The present invention compared with prior art, summarize by the design method of Agriculture Mobile Robot independent navigation of the invention
About the mode of agricultural vehicle independent navigation, propose by the overall view visual system based on catadioptric principle be applied to agricultural vehicle or
In the independent navigation of agricultural robot；Using refractive and reflective panorama vision system as core, on existing hardware platform, research and design
It is directed to the guidance path recognizer of crops row environment and Navigation Control algorithm.
Specific embodiment
The design method of the Agriculture Mobile Robot independent navigation of the present invention, the described method comprises the following steps：
The first step, on this basis, summarizes overall view visual system relative to tradition at the characteristics of analyzing various NI Vision Builder for Automated Inspections
The advantage of NI Vision Builder for Automated Inspection, according to the advantage and disadvantage of various modes, select the overall view visual system based on catadioptric principle as
The navigation sensor of robot, the system cost is low, image taking speed is fast, is very suitable for the occasion higher to requirement of real-time；Base
The information of robot is reflected using the convex reflecting mirror of certain face shape in the overall view visual system of catadioptric principle
It is imaged into video camera, obtains the ambient image in the range of 360 ° of level and certain angle vertical visual field；Due to convex refractive
Mirror makes object to scene environment information in the presence of compression, and there is radial deformations in video camera imaging plane so that actual scene
In some rule objects occur imaging deformation；For the imaging characteristics of the overall view visual system based on catadioptric principle, compare
The scaling method of common several overall view visual systems, and pass through experimental method a certain reality for being parallel to camera plane is put down
Scene image in face obtains the correspondence between image point into row distance and angle calibration；This method, which need not be known, to be taken the photograph
The internal and external parameter of camera and the parametric equation of mirror surface, it is relatively low to the installation requirement of system, and demarcate conveniently；
Second step designs the acquisition of crops row ambient image and the Processing Algorithm of the overall view visual system based on catadioptric principle,
A. camera image acquisition is carried out using Directshow technologies；The characteristics of for agricultural robot operating environment, to adopting
The image of collection is pre-processed, and assumes the colour cast of algorithm and white balance algorithm and diagonal calibration model to acquisition using gray world
Image carries out colour correction, the essential color of approximation reduction object；
B. gray processing processing is carried out to image using normalized excess green value 2xg-r-b on this basis, and then using most
Big Ostu method obtains the bianry image of crops row environment；
C. the impulsive noise point in image is eliminated using medium filtering, has obtained comparatively ideal agricultural robot ambient enviroment
Bianry image；
D. for panorama system imaging the characteristics of, using calibration result, to crop pixel into row distance and angular transformation,
To restore the space line feature of crops row, the convenient extraction to guidance path line；
Third walks, and navigation is calculated using Hough transform navigation by recognition reference path, and with reference to digital compass course heading information
Control parameter；On the basis of image acquisition and processing, the characteristics of imaging with reference to refractive and reflective panorama vision system, become using Hough
It has got the directional information of navigational reference path-line in return, has selected near robot central point, it is closest from imaging center
Straight line is as robot navigation's reference arm radial line；Since robot walks between two row crops, with reference to digital compass
Initial angle information, calculate Navigation Control parameter；
4th step designs the navigation controller of the Agriculture Mobile Robot based on fuzzy control method, and has carried out verification experimental verification；
The characteristics of common navigation control method in analysis robot navigation, comparative study various methods；For farmland operation environment
Feature because fuzzy control need not establish the accurate mathematical model of controlled device, and similar with the mode of thinking of people, therefore, is used
Navigation control method of the fuzzy control as the design；The design process of detailed analysis fuzzy controller, design are poor based on two-wheeled
The two-dimensional fuzzy controller of the Agriculture Mobile Robot of speed control, inputs as Navigation Control parameter, exports as robot left and right wheels
Rotating speed, and be designed and carried out experimental verification with MATLAB, the results showed that, the fuzzy controller that the present invention designs can be with
Accurate track navigation path-line；
5th step carries out simulation crops row Navigation Control experiment under the natural environment indoors without fixed light source irradiation；To agriculture
Industry mobile robot is integrally debugged, and simulation crops row is carried out under the natural environment indoors without fixed light source irradiation and is led
Navigate Control experiment, the results showed that the navigation that crops guidance path line and energy tenacious tracking identify can be recognized accurately in system
Path-line.
Three kinds of constituted modes of overall view visual system include the use of special optical lens, using taking the photograph more in the first step
Splice and add using single camera the mode of rotary head after camera imaging.
Navigation Control parameter in the third step and the 4th step includes course error angle_err and lateral error
distant_err。
Above-described embodiment is only the better embodiment of the present invention, therefore all structures described according to present patent application range
It makes, the equivalent change or modification that feature and principle are done, is included in the range of present patent application.
Claims (3)
1. a kind of design method of Agriculture Mobile Robot independent navigation, which is characterized in that the described method comprises the following steps：
The first step, on this basis, summarizes overall view visual system relative to tradition at the characteristics of analyzing various NI Vision Builder for Automated Inspections
The advantage of NI Vision Builder for Automated Inspection, according to the advantage and disadvantage of various modes, select the overall view visual system based on catadioptric principle as
The navigation sensor of robot；For the imaging characteristics of the overall view visual system based on catadioptric principle, compare common several
The scaling method of kind of overall view visual system, and pass through experimental method to the scene that is parallel in a certain physical plane of camera plane
Image obtains the correspondence between image point into row distance and angle calibration；
Second step designs the acquisition of crops row ambient image and the Processing Algorithm of the overall view visual system based on catadioptric principle,
A. camera image acquisition is carried out using Directshow technologies；The characteristics of for agricultural robot operating environment, to adopting
The image of collection is pre-processed, and assumes the colour cast of algorithm and white balance algorithm and diagonal calibration model to acquisition using gray world
Image carries out colour correction, the essential color of approximation reduction object；
B. gray processing processing is carried out to image using normalized excess green value 2xg-r-b on this basis, and then using most
Big Ostu method obtains the bianry image of crops row environment；
C. the impulsive noise point in image is eliminated using medium filtering, has obtained comparatively ideal agricultural robot ambient enviroment
Bianry image；
D. for panorama system imaging the characteristics of, using calibration result, to crop pixel into row distance and angular transformation,
To restore the space line feature of crops row, the convenient extraction to guidance path line；
Third walks, and navigation is calculated using Hough transform navigation by recognition reference path, and with reference to digital compass course heading information
Control parameter；On the basis of image acquisition and processing, the characteristics of imaging with reference to refractive and reflective panorama vision system, become using Hough
It has got the directional information of navigational reference path-line in return, has selected near robot central point, it is closest from imaging center
Straight line is as robot navigation's reference arm radial line；Since robot walks between two row crops, with reference to digital compass
Initial angle information, calculate Navigation Control parameter；
4th step designs the navigation controller of the Agriculture Mobile Robot based on fuzzy control method, and has carried out verification experimental verification；
The characteristics of common navigation control method in analysis robot navigation, comparative study various methods；For farmland operation environment
Feature, with navigation control method of the fuzzy control as the design；The design process of detailed analysis fuzzy controller designs base
In the two-dimensional fuzzy controller of the Agriculture Mobile Robot of two wheel guide robot control, input as Navigation Control parameter, export as machine
The rotating speed of people's left and right wheels, and experimental verification is designed and carried out with MATLAB, the results showed that, the Fuzzy Control that the present invention designs
Device processed can accurate track navigation path-line；
5th step carries out simulation crops row Navigation Control experiment under the natural environment indoors without fixed light source irradiation；To agriculture
Industry mobile robot is integrally debugged, and simulation crops row is carried out under the natural environment indoors without fixed light source irradiation and is led
Navigate Control experiment, the results showed that the navigation that crops guidance path line and energy tenacious tracking identify can be recognized accurately in system
Path-line.
2. the design method of Agriculture Mobile Robot independent navigation according to claim 1, it is characterised in that：Described first
In step three kinds of constituted modes of overall view visual system include the use of special optical lens, be imaged using multiple-camera after splicing and
Use the mode of single camera plus rotary head.
3. the design method of Agriculture Mobile Robot independent navigation according to claim 1, it is characterised in that：The third
Navigation Control parameter in step and the 4th step includes course error angle_err and lateral error distant_err.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611155493.1A CN108227689A (en) | 2016-12-14 | 2016-12-14 | A kind of design method of Agriculture Mobile Robot independent navigation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611155493.1A CN108227689A (en) | 2016-12-14 | 2016-12-14 | A kind of design method of Agriculture Mobile Robot independent navigation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108227689A true CN108227689A (en) | 2018-06-29 |
Family
ID=62651168
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611155493.1A Pending CN108227689A (en) | 2016-12-14 | 2016-12-14 | A kind of design method of Agriculture Mobile Robot independent navigation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108227689A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109792951A (en) * | 2019-02-21 | 2019-05-24 | 华南农业大学 | For the unmanned plane course line correction system of hybrid rice pollination and its bearing calibration |
| CN111578927A (en) * | 2020-04-29 | 2020-08-25 | 清华大学 | Explosion-proof mobile robot multi-sensing fusion navigation system and mobile robot |
| WO2020207017A1 (en) * | 2019-04-11 | 2020-10-15 | 上海交通大学 | Method and device for collaborative servo control of uncalibrated movement vision of robot in agricultural scene |
-
2016
- 2016-12-14 CN CN201611155493.1A patent/CN108227689A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109792951A (en) * | 2019-02-21 | 2019-05-24 | 华南农业大学 | For the unmanned plane course line correction system of hybrid rice pollination and its bearing calibration |
| WO2020207017A1 (en) * | 2019-04-11 | 2020-10-15 | 上海交通大学 | Method and device for collaborative servo control of uncalibrated movement vision of robot in agricultural scene |
| CN111578927A (en) * | 2020-04-29 | 2020-08-25 | 清华大学 | Explosion-proof mobile robot multi-sensing fusion navigation system and mobile robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108229366B (en) | Deep learning vehicle-mounted obstacle detection method based on radar and image data fusion | |
| CN110827395B (en) | Instant positioning and map construction method suitable for dynamic environment | |
| CA2950791C (en) | Binocular visual navigation system and method based on power robot | |
| CN102982557B (en) | Method for processing space hand signal gesture command based on depth camera | |
| CN111462135A (en) | Semantic mapping method based on visual S L AM and two-dimensional semantic segmentation | |
| CN111897332A (en) | Semantic intelligent substation robot humanoid inspection operation method and system | |
| CN104835173B (en) | A kind of localization method based on machine vision | |
| CN106584451B (en) | automatic transformer substation composition robot and method based on visual navigation | |
| CN109270534A (en) | A kind of intelligent vehicle laser sensor and camera online calibration method | |
| CN110082775B (en) | Vehicle positioning method and system based on laser device | |
| CN105866790A (en) | Laser radar barrier identification method and system taking laser emission intensity into consideration | |
| Wulf et al. | Colored 2D maps for robot navigation with 3D sensor data | |
| CN105243664A (en) | Vision-based wheeled mobile robot fast target tracking method | |
| CN113362247B (en) | Semantic real scene three-dimensional reconstruction method and system for laser fusion multi-view camera | |
| CN101452292B (en) | Fish glasses head omnidirectional vision aiming method based on sequence dual-color dot matrix type navigation mark | |
| CN106780631A (en) | A kind of robot closed loop detection method based on deep learning | |
| CN108227689A (en) | A kind of design method of Agriculture Mobile Robot independent navigation | |
| CN103632044A (en) | Camera topology building method and device based on geographic information system | |
| CN103759724B (en) | A kind of indoor navigation method based on lamp decoration feature and system | |
| Li et al. | A mobile robot visual SLAM system with enhanced semantics segmentation | |
| CN112729318A (en) | AGV fork truck is from moving SLAM navigation of fixed position | |
| CN116630394A (en) | Multi-mode target object attitude estimation method and system based on three-dimensional modeling constraint | |
| CN116518984A (en) | Vehicle road co-location system and method for underground coal mine auxiliary transportation robot | |
| CN106444774B (en) | Vision navigation method of mobile robot based on indoor illumination | |
| CN206832260U (en) | A kind of Navigation System for Mobile Robot of view-based access control model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180629 |