CN104699104A - Self-adaptive AGV (Automatic Guided Vehicle) visual navigation sight adjusting device and trace tracking method - Google Patents
Self-adaptive AGV (Automatic Guided Vehicle) visual navigation sight adjusting device and trace tracking method Download PDFInfo
- Publication number
- CN104699104A CN104699104A CN201510117835.XA CN201510117835A CN104699104A CN 104699104 A CN104699104 A CN 104699104A CN 201510117835 A CN201510117835 A CN 201510117835A CN 104699104 A CN104699104 A CN 104699104A
- Authority
- CN
- China
- Prior art keywords
- agv
- camera
- angle
- adjustment
- car body
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Abstract
The invention provides a self-adaptive AGV (Automatic Guided Vehicle) visual navigation sight adjusting device and a trace tracking method. The device comprises a camera, a rotary support, a steering engine and a support frame, wherein the support frame is fastened on an AGV body, the steering engine is fixed on the support frame and is fixedly connected with the rotary support, the camera is fixed on the rotary support and is located on a middle axis in front of the AGV body and the camera can be driven to adjust a sight gear angle by the steering engine. According to the device provided by the invention, the sight angle of the camera can be automatically adjusted according to the speed of the AGV body, the camera view is opened, and the navigation and location is precise to control, therefore the working efficiency can be improved.
Description
Technical field
The invention belongs to technical field of logistic equipment, be specifically related to a kind of self-adaptation AGV vision guided navigation sight line adjusting gear and stitching tracking.
Background technology
AGV is a kind of circuit by setting or the map of setting, and under the control of logistic dispatching system or manual command, automatic running or automatically draw body feed tank, completes the unmanned material handling vehicle of material transfer and handling.Visual guidance is owing to containing much information, line trace and Navigation Control can be realized well in complex environment, in addition, also have construction use cost low simultaneously, guiding the setting of lines and safeguard simple grade for outstanding advantages, is one of major domain of AGV fundamental research and application and development.
Existing visual guidance scheme all adopts hard-wired camera to observe AGV guide line, and setting angle is mostly chosen as vertical ground, obtains the video pictures without perspective effect, reaches the object improving vision positioning precision.For high speed AGV, when car body travelling speed is higher, because camera video frame per second is fixed as 25 frames/second or 30 frames/second usually, the displacement of inter picture likely can exceed the field range of video pictures, makes machine vision complete failure; Therefore, for ensureing the validity of machine vision work, real-time adjustment must be carried out according to the travelling speed of AGV car body to camera sight line, expanding or reduce the size in the video pictures visual field; Correspondingly, the installation form of camera also only should not be perpendicular to ground but before being tilted to, adjustable angle.
Chinese patent application publication number CN1438138A, publication date on August 27th, 2003, the name of innovation and creation is called " visual guide method of automatic guide vehicle and automatic guide vehicle thereof ", and this application case discloses disposal route and the electric motor car design proposal of a kind of intake surface running path mark line, station address code identifier and running status control identifier.Its weak point is that single camera is installed on vehicle body vertically downward, and camera view limits by body width, can only see the territory, local cell that AGV car body covers.
Chinese patent application publication No. CN102997910A, date of publication on March 27th, 2013, the name of innovation and creation is called " a kind of based on road of ground surface target location guidance system and method ", this application case utilizes light shield and corresponding light fixture to eliminate light source to pollute, and vision sensor vertically downward ground proximity is installed.Its weak point is that camera mounting distance is too low, has tunnel vision and causes quantity of information too low, and the stained ability of anti-lines is more limited.
Chinese patent application publication No. CN103529838A, date of publication on January 22nd, 2014, the name of innovation and creation is called " the multi-vision visual guiding drive unit of automatic guided vehicle and collaborative scaling method thereof ", and this application case discloses the apparatus and method that a kind of multiple camera detects guiding lines drift angle and displacement bias.Each camera is all positioned at vehicle body, and camera periphery arbitrary source throws light on, and dig-ins ground guiding lines vertically downward.
Chinese patent grant number CN102346483B, authorized announcement date on November 28th, 2012, the name of innovation and creation is called " the AGV progress control method based on passive RFID and accessorial visual ", this mandate arranges that on the ad-hoc location such as stop, turning point LED or charactron are with display and control instruction, the CCD camera that AGV vehicle body side is installed observes the pictorial symbolization on road both sides LED or digital screen, provides the image of steering order.
Chinese Patent Application No. CN102608998A, July 25 2012 Shen Qing Publication day, the name of innovation and creation is called " the visual guidance AGV system and method for embedded system ", this application case adopts a forward sight camera and a camera vertically downward simultaneously, forward sight camera collection distant view image, vertical camera is used for secondary accurate positioning.Forward sight camera and ground tilt to install at an angle, prediction is about to turn round, stop, locate before deceleration etc.; The routing information that vertical camera collection is being walked, completes stitching tracing task.Wherein the setting height(from bottom) of forward sight camera is relevant by the maximum operational speed of dolly with ground angle, and solstics, the visual field is 1 ~ 1.2 times of maximum operational speed.Its weak point is, forward sight camera is fixed angle with the setting angle of vertical camera, and fails to provide setting height(from bottom), physical relationship between ground angle and dolly maximum operational speed; Dimension between car body maximum operational speed from solstics, visual field distance is different, and chronomere is unclear, is difficult to the concrete size of clear and definite visual field far point distance AGV car body, random large; Critical weak point is also, vertical camera is close to ground, only has the less visual field, only can keep a close watch on the lines local of a very little part, large losses environmental information, is difficult to adapt to various on-the-spot local pollution, such as footprint, greasy dirt, breakage etc.
In sum, existing AGV vision guided navigation scheme also exists obvious weakness: 1, the mount scheme of camera is to be installed as master vertically downward, and camera view is narrow and small, is only limitted to light shield or the very little region of vehicle body, is difficult to adapt to AGV high-speed cruising; 2, the camera tilting to install, also to fixedly mount form, lacks the physical relationship expression formula of setting angle and car body travelling speed, navigator fix control accuracy, field range etc.; Stitching is followed the tracks of the vertical camera of main dependence and is completed; 3, the camera tilting to install is only for predicting road ahead situation, and not direct and stitching tracing task contacts.
Summary of the invention
One of the object of the invention is to provide a kind of self-adaptation AGV vision guided navigation sight line adjusting gear and stitching tracking, instant invention overcomes camera view in prior art narrow and small, the shortcoming that camera angle cannot adjust.
A kind of self-adaptation AGV vision guided navigation sight line adjusting gear provided by the invention comprises camera, runing rest, steering wheel and bracing frame, support frame as described above is anchored on AGV car body, steering wheel is fixed on bracing frame, steering wheel is fixedly connected with runing rest, camera is fixed on runing rest, described camera is positioned on AGV Vehicular body front axis, and camera is by the drive adjustable sight line gear angle of steering wheel.
Present invention also offers the stitching tracking of a kind of self-adaptation AGV vision guided navigation sight line adjustment, comprise the steps:
Put image frame sequence number i=1, accept the instruction of AGV task scheduling and advance forward with instruction speed, wheel steering angle adjustment increment initial value is set
According to the feedback data of current car body actual motion speed, adjustment camera gear angle, calculate the auxiliary parameter K of current angular inferoanterior ground guiding lines,
wherein camera angle is camera and pedal line angle;
Extract in the i-th-1 frame video pictures bottom line and center row two height and positions, number of pels per line amount between two edges on guiding lines Width, and i-th-1 to guide in frame video pictures in lines bottom separated time and picture and the horizontal sequence number of the location of pixels corresponding to two intersection points of picture central horizontal pixel column, the inclination and the position that calculate the guide wire in the threshold value of Attitude Tracking error assessment function under current gear angle and picture are departed from;
AGV wheel turning angle is set to
Check AGV car body current actual motion speed, adjustment camera gear angle, if gear angle changes, then recalculate the auxiliary parameter K of current angular inferoanterior ground guiding lines,
if gear angle is unchanged, then turn next step;
Extract in the i-th frame video pictures and to guide in lines bottom separated time and picture and the horizontal sequence number of the location of pixels corresponding to two intersection points of picture central horizontal pixel column, the inclination and the position that calculate the guide wire in picture are departed from, and calculate attitude error evaluation function and evaluation function increment further;
Judge whether evaluation function increment is less than or equal to the threshold value of Attitude Tracking error assessment function, if judge whether Attitude Tracking error assessment function J is less than or equal to the threshold value of Attitude Tracking error assessment function, otherwise turn next step.
Calculate angular setting amount
frame of video sequence number i=i+1, resets AGV wheel steering angle, wherein angular setting amount
Judge whether Attitude Tracking error assessment function J is less than or equal to the threshold value of Attitude Tracking error assessment function, if, keep wheel steering angle constant, frame of video sequence number i=i+1, return to and check the current actual motion speed of AGV car body, adjustment camera angle gear angle beta, otherwise turn next step;
Calculate angular setting amount
frame of video sequence number i=i+1, resets AGV wheel steering angle, wherein angular setting amount
Further, the gear angle that sight line adjustment is selected according to AGV current kinetic speed, makes between two continuous frames video pictures, and AGV car body displacement is no more than video pictures
breadth.
Further, the pixel quantity on lines Width between two edges in a line will be guided in real-time video picture, as transversal displacement amount Calculation Basis in the video pictures under different gear angle.
Further, according to location of pixels iMid and iBtm guiding the center line of lines and two intersection points of video pictures center pixel row and bottom pixel row in video pictures, structure AGV vehicle body attitude tracking error evaluation function J=K
2dir
2+ pos
2as the foundation adjusting AGV car body steering angle direction and size, AGV attitude is made to meet the requirement of stitching tracking accuracy, wherein dir=iMid-iBtm,
k is the constant relevant with camera sight line angle of inclination beta.
Further, AGV car body turns to adjustment mode to be realized by the mode of adjustment AGV wheel turning angle.
Further, AGV car body turns to adjustment mode to be realized by the mode that AGV wheel both sides are differential.
Beneficial effect of the present invention is, the present invention can adjust the sight angle of camera automatically according to the speed of AGV car body, camera view is open, and navigator fix controls accurately, thus can increase work efficiency.
Accompanying drawing explanation
Figure 1 shows that a kind of self-adaptation AGV vision guided navigation of the present invention sight line adjusting gear structural representation.
Figure 2 shows that a kind of self-adaptation AGV vision guided navigation of the present invention sight line adjustment stitching tracking process flow diagram.
Figure 3 shows that parameters schematic diagram in a kind of self-adaptation AGV vision guided navigation of the present invention sight line adjustment stitching tracking.
Embodiment
Hereafter will describe the present invention in detail in conjunction with specific embodiments.It should be noted that the combination of technical characteristic or the technical characteristic described in following embodiment should not be considered to isolated, they can mutually be combined thus be reached better technique effect.
As shown in Figure 1, a kind of self-adaptation AGV vision guided navigation sight line adjusting gear provided by the invention, comprise camera 1, runing rest 2, steering wheel 3 and bracing frame 4, support frame as described above 4 is anchored on AGV car body 5, steering wheel 3 is fixed on bracing frame 4, and steering wheel 3 is fixedly connected with runing rest 2, and camera 1 is fixed on runing rest 2, described camera 1 is positioned on the anterior axis 7 of AGV car body 5, and camera 1 is by the drive adjustable sight line gear angle of steering wheel 3.
The adjustment of this device sight line is completed by adjustment forward sight camera 1 gear angle, relevant with the current kinetic speed of AGV car body 5.When movement velocity is lower, less sight line gear angle is selected to obtain higher positional precision; When movement velocity is higher, select larger sight line gear angle to obtain larger visual field breadth, ensure AGV car body 5 stitching pursuit movement precision.
Camera 1 sets some gear angles, and typical gear angle has 4 gears, is respectively 30 °, 45 °, 60 ° and 75 °.
As Figure 1-3, the stitching tracking of a kind of self-adaptation AGV vision guided navigation sight line adjustment provided by the invention, comprises the steps:
Step S1: put image frame sequence number i=1, accepts the instruction of AGV task scheduling and advances forward with instruction speed, arranges wheel steering angle adjustment increment initial value
Step S2: according to the feedback data of current AGV car body 5 actual motion speed v, adjustment camera 1 gear angle beta, calculate the auxiliary parameter K of current angular inferoanterior ground guiding lines 8,
wherein camera 1 gear angle beta is camera sight line and pedal line angle.
When considering that β angle is larger, surface road only will can occupy down half picture, more than local horizon meaningless picture occupies half picture, get the transverse direction of guiding lines 8 in adjacent two frame continuous videos pictures or the change of longitudinal location of pixels, must not exceed second breadth of video pixel
preferred value is
ensure in continuous print two frame video pictures, AGV car body 5 does not have possibility to exceed the breadth size of video relative to the location variation of guiding lines 8, can correctly be caught.According to the size of current AGV car body 5 travelling speed v, adjusted the gear angle beta of camera 1 by steering wheel 3, make
be not less than vT, wherein
for the surface road length that second breadth height of video pictures is corresponding, T is the time of acquisition 1 frame picture.
The guiding lines 8 that the adjustment of camera 1 gear angle beta can make perspective effect cause compress to distort with other pictures and are among dynamic changing process, and therefore traditional image calibration technology will lose efficacy.Also completely in video pictures space, itself AGV stitching tracing control can only must be carried out as reference according to guiding lines 8.
Grey level histogram enhancing is carried out to video pictures, Laplace operator is adopted to extract two edges of guiding lines 8, utilize straight line Hough transformation to calculate straight-line segment starting point and the orientation angle at two edges about representative guiding lines in video pictures, get the vector mark of middle separated time 9 as guiding lines 8 of two edge lines.
Ground vertical interval between video pictures center pixel row and bottom pixel row is
wherein H is the height on camera 1 rotation center distance ground, and α is the visible angle of the left rotation and right rotation of camera 1, and representative value is 30 degree.In video pictures, each pixel interval in every a line is approximate can think equal.Guiding lines 8 adopt 45 ~ 50mm width criteria light tone adhesive tape as white, yellow, pink etc., are directly pasted on dark ground and form.The number of pixels that the developed width of guiding lines 8 presents in video pictures is only relevant with camera 1 gear angle beta and camera 1 screen resolution m × n, can calculate among AGV operational process in advance.
Wherein auxiliary parameter
for a constant sequence relevant with camera 1 gear angle beta, wherein d is the distance of car body front-wheel 6 apart from AGV car body 5 front end, and L is the distance of car body front-wheel 6 to trailing wheel 10.
Step S3: extract in the i-th-1 frame video pictures bottom line and center row two height and positions, number of pels per line amount between two edges on guiding lines 8 Width, and i-th-1 to guide in frame video pictures in lines bottom separated time 9 and picture and the horizontal sequence number of the location of pixels corresponding to two intersection points of picture central horizontal pixel column, the inclination and the position that calculate the guiding lines in the threshold value of Attitude Tracking error assessment function under current gear angle beta and picture are departed from;
Number of pels per line amount on line segment of guiding in certain frame picture on lines 8 Width between two edges is designated as iPixNum.
Grey level histogram enhancing is carried out to the i-th-1 frame video pictures, corrosion expansion process, take Hough transformation to extract edge line, extract on bottom line in first width picture and center row two height and positions, l between two edges on guiding lines 8 Width
0with
number of pels per line amount iPixNum on line segment
0 (i-1)with
and i-th-1 to guide in frame video pictures in lines bottom separated time 9 and picture and the horizontal sequence number iBtm and iMid of the location of pixels corresponding to two intersection points of picture central horizontal pixel column.
According to fixing certain gear angle beta, on the bottom line in certain frame picture and picture center row two height positions, calculate l on guiding lines 8 Width
0with
the every corresponding horizontal actual distance on the ground of row pixel on line segment, is designated as respectively
with
be recorded as the pixel column width constant under respective notch sight angle β.
In guiding lines bottom separated time 9 and picture and the horizontal sequence number of the location of pixels corresponding to two intersection points of picture central horizontal pixel column, be designated as iBtm and iMid respectively.The course angle θ of AGV, θ are the anterior axis 7 of AGV car body 5 and the angle of separated time 9 in guiding lines, meet:
In stitching tracing process, the two row location of pixels difference expression formulas of getting AGV course angle θ are dir=iMid-iBtm.According to the course angle accuracy requirement of θ≤2 °, the two row location of pixels difference limen values corresponding to course angle threshold value should be taken as dir≤ε
θ, wherein
In stitching tracing process, the pixel expression formula of AGV positional precision is taken as
the position accuracy demand of foundation ± 20mm, the pixel threshold corresponding to AGV positional precision is taken as pos≤ε
d, wherein ε
d=0.4iPixNum
0.
The threshold value of getting Attitude Tracking error assessment function is one less among both, both J
ε=min{ ε
θ, ε
d.
The degree of tilt of the guiding lines 8 in picture and position are departed from and are respectively:
AGV Attitude Tracking error assessment function is made to be J=K
2dir
2+ pos
2, when AGV car body 5 attitude that and if only if overlaps completely with guiding lines 8 just, tracking error J is just zero.
Step S4: AGV wheel turning angle is set to
About 10% is reduced for principle to make Attitude Tracking error assessment function J, Newton-decline method is taked to calculate AGV wheel angle adjustment amount in every frame picture, calculate with the non_derivative of the pixel change in two continuous frames picture, then the angular setting amount in the 3rd frame picture is
bracket subscript (i) wherein represents the sequence number of frame of video.Every frame picture constantly adjusts wheel steering angle between switching
until tracking error J is positioned within designated precision scope, ensure course error dir≤ε
θ, and positioning error pos≤ε
d, meet the threshold value J of Attitude Tracking error assessment function
ε=min{ ε
θ, ε
d.
Step S5: check AGV car body 5 current actual motion speed v, adjustment camera angle gear β, if gear β changes, then step S2 recalculate current angular inferoanterior ground guiding lines 8 auxiliary parameter K,
if gear β is unchanged, then turn next step.
Step S6: extract in the i-th frame video pictures and guide bottom separated time in lines 9 and picture and the horizontal sequence number of the location of pixels corresponding to two intersection points of picture central horizontal pixel column, the degree of tilt and the position that calculate the guiding lines 8 in picture are departed from, and calculate attitude error evaluation function and evaluation function increment further.
Gather the i-th frame video pictures, grey level histogram enhancing is carried out to the i-th frame picture, corrosion expansion process, take Hough straight line to convert and extract edge line, extract iBtm
(i), iMid
(i).
The degree of tilt of the guiding lines 8 in picture and position depart from for
Attitude error evaluation function and evaluation function increment are respectively:
J
(i)=K
2·dir
(i)·dir
(i)+pos
(i)·pos
(i),ΔJ
(i)=K
2·dir
(i)·Δdir
(i)+pos
(i)·Δpos
(i)。
Step S7: judge whether evaluation function increment is less than or equal to the threshold value of Attitude Tracking error assessment function, namely judge Δ J
(i)≤ J
εwhether set up, if go to step S10, otherwise turn next step.
Step S8: calculate angular setting amount
frame of video sequence number i=i+1, goes to step S5 and resets AGV wheel steering angle,
Wherein angular setting amount
Step S9: judge whether Attitude Tracking error assessment function J is less than or equal to the threshold value of Attitude Tracking error assessment function, namely judges J
(i)≤ J
εwhether set up, if so, turn next step; Otherwise go to step S11.
Step S10: keep wheel steering angle constant, namely
frame of video sequence number i=i+1, goes to step S4, due to
namely be equivalent to go to step S5 and reexamine the current actual motion speed v of AGV car body 5, adjustment camera angle gear β.
Step S11: calculate angular setting amount
frame of video sequence number i=i+1, goes to step S4 and resets AGV wheel steering angle.
Wherein angular setting amount
AGV car body 5 of the present invention turns to adjustment mode to be realize with the mode constantly adjusting AGV both sides wheel differential by constantly adjusting AGV both sides wheel turning angle.So-called differential, the wheel rotor speed being exactly car body both sides is not identical, or rotating speed is contrary; When both sides vehicle wheel rotational speed is different, car body will be turned to the rotating speed wheel direction that some or reverse direction rotate slowly.
Below in conjunction with experiment checking validity of the present invention further, experimental procedure is as follows:
Ground guide wire 8 extracting yellow standard adhesive tapes, width is 50mm, is directly pasted on dark ground.AGV car body 5 width is 380mm, wheelbase 600mm, and camera 1 is installed on axis, AGV car body 5 dead ahead 7,100mm, both d=100mm, L=600mm before being positioned at AGV front-wheel 6 axial line.Camera 1 is by steering wheel 3 Direct driver, and be in certain particular location among four fixing gear angles all the time, gear angle beta is respectively 30 °, 45 °, 60 ° and 75 °.Camera 1 setting height(from bottom) is H=300mm; Camera 1 video breadth is 640 × 480, and frame per second is 25 frames/second, and left and right angle of visibility size is α=30 °.Corresponding to different gear angles, the ground true breadth parameters value that video pictures is corresponding is in theory as shown in table 1:
Table 1: the ground that video pictures is corresponding true breadth parameters value
β | 30° | 45° | 60° | 0 |
Corresponding ground width in the middle of picture | 180mm | 220mm | 311mm | 600mm |
Corresponding ground width bottom picture | 161mm | 180mm | 220mm | 311mm |
To bottom corresponding ground height in the middle of picture | 93mm | 127mm | 220mm | 600mm |
But due to camera 1 actual left and right angle of visibility α and out of true is 30 ° and Width and short transverse size also have difference, therefore, in upper table gross data only write as algorithm in initial value reference data is set.When real data starts according to the car body 5 of AGV described in the present invention, guiding lines 8 carry out pixel counts approximately perpendicular to the original state bottom video pictures, acquiescence line thickness is 50mm, respectively the middle row pixel in video pictures frame and bottom line number of pixels are counted, be designated as the iPixNum under current gear angle
0with
AGV car body 5 is placed on guiding lines 8 time flat, guiding lines 8 to appear in camera picture near normal forward.AGV task scheduling system command request, starts AGV car body 5 and runs forward.The adjustment of camera 1 angle is carried out according to the current real-time speed feedback of AGV car body 5.For guaranteeing among AGV car body 5 operational process, the interframe displacement of guiding lines 8 is enough little, takes off 110 of half range face pixels tall, both 24 pixels, the speed stage threshold value as camera 1 angular setting:
Work as the speed of a motor vehicle
time, camera 1 gear angular setting is set to 30 °;
Work as the speed of a motor vehicle
time, camera 1 gear angular setting is set to 45 °;
Work as the speed of a motor vehicle
time, camera 1 gear angular setting is set to 60 °;
Work as the speed of a motor vehicle
time, camera 1 gear angular setting is set to 75 °.
Namely bring into operation after AGV car body 5 startup stitching trace routine, grey level histogram enhancing is carried out to video pictures frame, corrosion expansion process, take Hough transformation to extract edge line, respectively the picture between the edge line on picture middle position and bottom position is counted, obtain iPixNum
0 (0)with
try to achieve AGV Attitude Tracking error assessment function threshold further
With original speed position angle beta=30 ° and theory of correspondences value for reference, under original speed position angle beta=30 °, K=6.18,
and iPixNum
0 (0)with
reference value should be respectively
with
corresponding J
ε=min{5100,6336}=5100.
In the process of follow-up each frame picture, every frame carries out grey level histogram enhancing, corrosion expansion process, takes Hough transformation to extract edge line, calculates
With
Further Calculation Estimation function J
(i)=K
2dir
(i)dir
(i)+ pos
(i)pos
(i)with evaluation function increment Delta J
(i)=K
2dir
(i)Δ dir
(i)+ pos
(i)Δ pos
(i); If Δ J
(i)be greater than evaluation function threshold value J
ε, then the corner adjustment amount between image frame switching is
if Δ J
(i)be less than or equal to evaluation function threshold value J
ε, then the corner adjustment amount between image frame switching is
car body continues to adjust wheel steering angle in operational process
size, until evaluation function J
(i)≤ J
ε, show that car body 5 is on correct circuit, keep wheel steering angle constant, both corner adjustment amount perseverance was zero, realized continual and steady stitching and followed the tracks of.
Although give some embodiments of the present invention, it will be understood by those of skill in the art that without departing from the spirit of the invention herein, can change embodiment herein.Above-described embodiment is exemplary, should using embodiment herein as the restriction of interest field of the present invention.
Claims (7)
1. a self-adaptation AGV vision guided navigation sight line adjusting gear, it is characterized in that, comprise camera, runing rest, steering wheel and bracing frame, support frame as described above is anchored on described AGV car body, described steering wheel is fixed on support frame as described above, and described steering wheel is fixedly connected with described runing rest, and described camera is fixed on described runing rest, described camera is positioned on described AGV Vehicular body front axis, and described camera is by the drive adjustable sight line gear angle of described steering wheel.
2. a stitching tracking for self-adaptation AGV vision guided navigation sight line adjustment, is characterized in that, comprise the steps:
Put image frame sequence number i=1, accept the instruction of AGV task scheduling and advance forward with instruction speed, wheel steering angle adjustment increment initial value is set
According to the feedback data of current car body actual motion speed, adjustment camera gear angle, calculate the auxiliary parameter K of current angular inferoanterior ground guiding lines,
wherein camera angle is camera and pedal line angle;
Extract in the i-th-1 frame video pictures bottom line and center row two height and positions, number of pels per line amount between two edges on guiding lines Width, and i-th-1 to guide in frame video pictures in lines bottom separated time and picture and the horizontal sequence number of the location of pixels corresponding to two intersection points of picture central horizontal pixel column, the inclination and the position that calculate the guide wire in the threshold value of Attitude Tracking error assessment function under current gear angle and picture are departed from;
AGV wheel turning angle is set to
Check AGV car body current actual motion speed, adjustment camera gear angle, if gear angle changes, then recalculate the auxiliary parameter K of current angular inferoanterior ground guiding lines,
if gear angle is unchanged, then turn next step;
Extract in the i-th frame video pictures and to guide in lines bottom separated time and picture and the horizontal sequence number of the location of pixels corresponding to two intersection points of picture central horizontal pixel column, the inclination and the position that calculate the guide wire in picture are departed from, and calculate attitude error evaluation function and evaluation function increment further;
Judge whether evaluation function increment is less than or equal to the threshold value of Attitude Tracking error assessment function, if judge whether Attitude Tracking error assessment function J is less than or equal to the threshold value of Attitude Tracking error assessment function, otherwise turn next step;
Calculate angular setting amount
frame of video sequence number i=i+1, resets AGV wheel steering angle, wherein angular setting amount
Judge whether Attitude Tracking error assessment function J is less than or equal to the threshold value of Attitude Tracking error assessment function, if, keep wheel steering angle constant, frame of video sequence number i=i+1, return to and check the current actual motion speed of AGV car body, adjustment camera angle gear angle beta, otherwise turn next step;
Calculate angular setting amount
frame of video sequence number i=i+1, resets AGV wheel steering angle, wherein angular setting amount
3. the stitching tracking of self-adaptation AGV vision guided navigation sight line adjustment as claimed in claim 2, it is characterized in that, the gear angle that sight line adjustment is selected according to AGV current kinetic speed, make between two continuous frames video pictures, and AGV car body displacement is no more than video pictures
breadth.
4. the stitching tracking of self-adaptation AGV vision guided navigation sight line adjustment as claimed in claim 1, it is characterized in that, the pixel quantity on lines Width between two edges in a line will be guided, as transversal displacement amount Calculation Basis in the video pictures under different gear angle in real-time video picture.
5. the stitching tracking of self-adaptation AGV vision guided navigation sight line adjustment as claimed in claim 2, it is characterized in that, according to location of pixels iMid and iBtm guiding the center line of lines and two intersection points of video pictures center pixel row and bottom pixel row in video pictures, structure AGV vehicle body attitude tracking error evaluation function J=K
2dir
2+ pos
2as the foundation adjusting AGV car body steering angle direction and size, AGV attitude is made to meet the requirement of stitching tracking accuracy, wherein dir=iMid-iBtm,
k is the constant relevant with camera sight line angle of inclination beta.
6. the stitching tracking of self-adaptation AGV vision guided navigation sight line adjustment as claimed in claim 2, is characterized in that, AGV car body turns to adjustment mode to be realized by the mode of adjustment AGV wheel turning angle.
7. the stitching tracking of self-adaptation AGV vision guided navigation sight line adjustment as claimed in claim 2, it is characterized in that, AGV car body turns to adjustment mode to be realized by the mode that AGV wheel both sides are differential.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510117835.XA CN104699104B (en) | 2015-03-17 | 2015-03-17 | A kind of stitching tracking of adaptive AGV vision guided navigation sight adjusting apparatus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510117835.XA CN104699104B (en) | 2015-03-17 | 2015-03-17 | A kind of stitching tracking of adaptive AGV vision guided navigation sight adjusting apparatus |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104699104A true CN104699104A (en) | 2015-06-10 |
CN104699104B CN104699104B (en) | 2018-02-02 |
Family
ID=53346332
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510117835.XA Expired - Fee Related CN104699104B (en) | 2015-03-17 | 2015-03-17 | A kind of stitching tracking of adaptive AGV vision guided navigation sight adjusting apparatus |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104699104B (en) |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105550676A (en) * | 2016-02-03 | 2016-05-04 | 天津市乐图软件科技有限公司 | Logistics delivery vehicle trace tracking method based on linearity CCD |
CN105774861A (en) * | 2016-05-09 | 2016-07-20 | 徐洪军 | Household carrying robot |
CN106969766A (en) * | 2017-03-21 | 2017-07-21 | 北京品创智能科技有限公司 | A kind of indoor autonomous navigation method based on monocular vision and Quick Response Code road sign |
CN107390683A (en) * | 2017-07-14 | 2017-11-24 | 长沙中联消防机械有限公司 | Rail convertible car automatically tracks system, method and fire fighting truck |
CN107532913A (en) * | 2015-12-03 | 2018-01-02 | 华为技术有限公司 | A kind of air navigation aid and the equipment for navigation |
CN107544490A (en) * | 2016-06-29 | 2018-01-05 | 通用汽车环球科技运作有限责任公司 | system and method for sensor platform |
CN107632602A (en) * | 2017-09-01 | 2018-01-26 | 上海斐讯数据通信技术有限公司 | AGV trolley travelling tracks method for correcting error and system, terrestrial reference Quick Response Code acquisition device |
CN108153302A (en) * | 2017-12-08 | 2018-06-12 | 深圳市易成自动驾驶技术有限公司 | Guidance method, device and the computer readable storage medium of automatic guided vehicle |
CN108458709A (en) * | 2018-02-22 | 2018-08-28 | 北京航空航天大学 | The airborne distributed POS data fusion method and device of view-based access control model subsidiary |
CN109032125A (en) * | 2018-05-31 | 2018-12-18 | 上海工程技术大学 | A kind of air navigation aid of vision AGV |
CN109426251A (en) * | 2017-08-29 | 2019-03-05 | 杭州海康机器人技术有限公司 | A kind of travel control method and device of robot |
CN109782755A (en) * | 2018-12-27 | 2019-05-21 | 广东飞库科技有限公司 | Control AGV calibrated, the method for AGV calibrating position, computer storage medium and AGV |
CN109857103A (en) * | 2019-01-22 | 2019-06-07 | 秦皇岛天业通联重工科技有限公司 | A kind of control method of automatic driving vehicle, apparatus and system |
CN109947137A (en) * | 2019-03-19 | 2019-06-28 | 北京特种机械研究所 | A kind of PGV visual scanning head automatic tracking apparatus |
CN110030932A (en) * | 2019-05-24 | 2019-07-19 | 广东嘉腾机器人自动化有限公司 | AGV displacement measuring method and AGV offset measuring device |
CN110147096A (en) * | 2019-04-01 | 2019-08-20 | 江苏大学 | A kind of multimachine control method for coordinating that view-based access control model follows |
CN110147100A (en) * | 2019-05-06 | 2019-08-20 | 珠海达明科技有限公司 | A kind of AGV platform and air navigation aid with high-precision navigation locating function |
CN110209162A (en) * | 2019-05-06 | 2019-09-06 | 珠海达明科技有限公司 | A kind of 4 wheel driven AGV autonomous tracing in intelligent vehicle based on Ackermann steering principle |
CN111374600A (en) * | 2018-12-28 | 2020-07-07 | 珠海市一微半导体有限公司 | Self-tracing control method of sweeping robot and intelligent sweeping robot |
CN111674800A (en) * | 2020-06-03 | 2020-09-18 | 灵动科技(北京)有限公司 | Intelligent warehousing technology for automatic driving system |
WO2023077255A1 (en) * | 2021-11-02 | 2023-05-11 | 深圳市大疆创新科技有限公司 | Method and apparatus for controlling movable platform, and movable platform and storage medium |
CN116437016A (en) * | 2023-06-13 | 2023-07-14 | 武汉中观自动化科技有限公司 | Object scanning method, device, electronic equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11175147A (en) * | 1997-12-09 | 1999-07-02 | Shinko Electric Co Ltd | Positioning device for moving body |
US20060064212A1 (en) * | 2004-09-22 | 2006-03-23 | Cycle Time Corporation | Reactive automated guided vehicle vision guidance system |
CN101183265A (en) * | 2007-11-15 | 2008-05-21 | 浙江大学 | Automatic guidance system based on radio frequency identification tag and vision and method thereof |
CN102608998A (en) * | 2011-12-23 | 2012-07-25 | 南京航空航天大学 | Vision guiding AGV (Automatic Guided Vehicle) system and method of embedded system |
CN104085313A (en) * | 2014-07-18 | 2014-10-08 | 安徽中家智锐科技有限公司 | Eight-freedom-degree mechanical arm system of AGV chassis |
CN204480047U (en) * | 2015-03-17 | 2015-07-15 | 武汉纺织大学 | A kind of self-adaptation AGV vision guided navigation sight line adjusting gear |
-
2015
- 2015-03-17 CN CN201510117835.XA patent/CN104699104B/en not_active Expired - Fee Related
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11175147A (en) * | 1997-12-09 | 1999-07-02 | Shinko Electric Co Ltd | Positioning device for moving body |
US20060064212A1 (en) * | 2004-09-22 | 2006-03-23 | Cycle Time Corporation | Reactive automated guided vehicle vision guidance system |
CN101183265A (en) * | 2007-11-15 | 2008-05-21 | 浙江大学 | Automatic guidance system based on radio frequency identification tag and vision and method thereof |
CN102608998A (en) * | 2011-12-23 | 2012-07-25 | 南京航空航天大学 | Vision guiding AGV (Automatic Guided Vehicle) system and method of embedded system |
CN104085313A (en) * | 2014-07-18 | 2014-10-08 | 安徽中家智锐科技有限公司 | Eight-freedom-degree mechanical arm system of AGV chassis |
CN204480047U (en) * | 2015-03-17 | 2015-07-15 | 武汉纺织大学 | A kind of self-adaptation AGV vision guided navigation sight line adjusting gear |
Non-Patent Citations (4)
Title |
---|
任小芳: "自动导引车的视觉导航", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑(月刊)》 * |
赵玉麟: "单轮驱动/转向AGV轨迹分析及视觉导航", 《中国优秀硕士学位论文全文数据库信息科技辑(月刊)》 * |
金超: "搬运机器人AGV的智能导航研究", 《中国优秀硕士学位论文全文数据库信息科技辑(月刊)》 * |
马道明: "AGV视觉导航系统的研究", 《中国优秀硕士学位论文全文数据库信息科技辑(月刊)》 * |
Cited By (31)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107532913B (en) * | 2015-12-03 | 2020-03-27 | 华为技术有限公司 | Navigation method and equipment for navigation |
CN107532913A (en) * | 2015-12-03 | 2018-01-02 | 华为技术有限公司 | A kind of air navigation aid and the equipment for navigation |
US10823577B2 (en) | 2015-12-03 | 2020-11-03 | Huawei Technologies Co., Ltd. | Navigation method and navigation device |
CN105550676A (en) * | 2016-02-03 | 2016-05-04 | 天津市乐图软件科技有限公司 | Logistics delivery vehicle trace tracking method based on linearity CCD |
CN105774861A (en) * | 2016-05-09 | 2016-07-20 | 徐洪军 | Household carrying robot |
CN107544490A (en) * | 2016-06-29 | 2018-01-05 | 通用汽车环球科技运作有限责任公司 | system and method for sensor platform |
CN107544490B (en) * | 2016-06-29 | 2021-03-09 | 通用汽车环球科技运作有限责任公司 | System and method for sensor platform |
CN106969766A (en) * | 2017-03-21 | 2017-07-21 | 北京品创智能科技有限公司 | A kind of indoor autonomous navigation method based on monocular vision and Quick Response Code road sign |
CN107390683A (en) * | 2017-07-14 | 2017-11-24 | 长沙中联消防机械有限公司 | Rail convertible car automatically tracks system, method and fire fighting truck |
CN109426251A (en) * | 2017-08-29 | 2019-03-05 | 杭州海康机器人技术有限公司 | A kind of travel control method and device of robot |
CN107632602A (en) * | 2017-09-01 | 2018-01-26 | 上海斐讯数据通信技术有限公司 | AGV trolley travelling tracks method for correcting error and system, terrestrial reference Quick Response Code acquisition device |
CN108153302A (en) * | 2017-12-08 | 2018-06-12 | 深圳市易成自动驾驶技术有限公司 | Guidance method, device and the computer readable storage medium of automatic guided vehicle |
CN108458709A (en) * | 2018-02-22 | 2018-08-28 | 北京航空航天大学 | The airborne distributed POS data fusion method and device of view-based access control model subsidiary |
CN109032125A (en) * | 2018-05-31 | 2018-12-18 | 上海工程技术大学 | A kind of air navigation aid of vision AGV |
CN109782755B (en) * | 2018-12-27 | 2022-05-31 | 广东飞库科技有限公司 | Method for controlling AGV to calibrate and AGV to calibrate position, computer storage medium and AGV |
CN109782755A (en) * | 2018-12-27 | 2019-05-21 | 广东飞库科技有限公司 | Control AGV calibrated, the method for AGV calibrating position, computer storage medium and AGV |
CN111374600A (en) * | 2018-12-28 | 2020-07-07 | 珠海市一微半导体有限公司 | Self-tracing control method of sweeping robot and intelligent sweeping robot |
CN111374600B (en) * | 2018-12-28 | 2021-08-24 | 珠海市一微半导体有限公司 | Self-tracing control method of sweeping robot and intelligent sweeping robot |
CN109857103A (en) * | 2019-01-22 | 2019-06-07 | 秦皇岛天业通联重工科技有限公司 | A kind of control method of automatic driving vehicle, apparatus and system |
CN109947137A (en) * | 2019-03-19 | 2019-06-28 | 北京特种机械研究所 | A kind of PGV visual scanning head automatic tracking apparatus |
CN109947137B (en) * | 2019-03-19 | 2021-10-22 | 北京特种机械研究所 | Automatic following device of PGV visual scanning head |
CN110147096A (en) * | 2019-04-01 | 2019-08-20 | 江苏大学 | A kind of multimachine control method for coordinating that view-based access control model follows |
CN110147100A (en) * | 2019-05-06 | 2019-08-20 | 珠海达明科技有限公司 | A kind of AGV platform and air navigation aid with high-precision navigation locating function |
CN110209162A (en) * | 2019-05-06 | 2019-09-06 | 珠海达明科技有限公司 | A kind of 4 wheel driven AGV autonomous tracing in intelligent vehicle based on Ackermann steering principle |
CN110030932B (en) * | 2019-05-24 | 2020-12-15 | 广东嘉腾机器人自动化有限公司 | AGV deviation measurement method and AGV deviation measurement device |
CN110030932A (en) * | 2019-05-24 | 2019-07-19 | 广东嘉腾机器人自动化有限公司 | AGV displacement measuring method and AGV offset measuring device |
CN111674800A (en) * | 2020-06-03 | 2020-09-18 | 灵动科技(北京)有限公司 | Intelligent warehousing technology for automatic driving system |
US11952216B2 (en) | 2020-06-03 | 2024-04-09 | Lingdong Technology (Beijing) Co. Ltd | Warehousing system, self-driving system and method of positioning a self-driving system |
WO2023077255A1 (en) * | 2021-11-02 | 2023-05-11 | 深圳市大疆创新科技有限公司 | Method and apparatus for controlling movable platform, and movable platform and storage medium |
CN116437016A (en) * | 2023-06-13 | 2023-07-14 | 武汉中观自动化科技有限公司 | Object scanning method, device, electronic equipment and storage medium |
CN116437016B (en) * | 2023-06-13 | 2023-10-10 | 武汉中观自动化科技有限公司 | Object scanning method, device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN104699104B (en) | 2018-02-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104699104A (en) | Self-adaptive AGV (Automatic Guided Vehicle) visual navigation sight adjusting device and trace tracking method | |
CN106441319B (en) | A kind of generation system and method for automatic driving vehicle lane grade navigation map | |
CN110962843B (en) | Automatic parking control decision method and system | |
CN106774313B (en) | A kind of outdoor automatic obstacle-avoiding AGV air navigation aid based on multisensor | |
CN106092121B (en) | Automobile navigation method and device | |
CN104865578B (en) | A kind of parking garage fine map creation device and method | |
CN102661733B (en) | Front vehicle ranging method based on monocular vision | |
US20200175720A1 (en) | Vehicle, vehicle positioning system, and vehicle positioning method | |
CN105511462B (en) | A kind of AGV air navigation aids of view-based access control model | |
CN106338245A (en) | Workpiece noncontact mobile measurement method | |
CN106696961A (en) | Control system and method for automatically driving onto and off ramp of freeway | |
CN105955259A (en) | Monocular vision AGV accurate positioning method and system based on multi-window real-time range finding | |
CN105936294A (en) | Travel control apparatus for vehicle | |
CN204480047U (en) | A kind of self-adaptation AGV vision guided navigation sight line adjusting gear | |
CN105676253A (en) | Longitudinal positioning system and method based on city road marking map in automatic driving | |
CN203739885U (en) | Track control system for line marking vehicle | |
CN104504364B (en) | Stop line Real time identification and distance-finding method based on space time correlation | |
CN109849922A (en) | A method of the view-based access control model information for intelligent vehicle is merged with GIS information | |
CN108152827A (en) | A kind of omnidirectional's intelligent mobile equipment positioning and air navigation aid based on laser ranging | |
CN103625471B (en) | Method and device for drawing road reference line | |
CN105737838A (en) | AGV path tracking method | |
CN107664504A (en) | A kind of path planning apparatus | |
CN108909625A (en) | Vehicle bottom based on panoramic looking-around system ground plane display method | |
CN101852619A (en) | Navigation display method and device | |
WO2022147924A1 (en) | Method and apparatus for vehicle positioning, storage medium, and electronic device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
EXSB | Decision made by sipo to initiate substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180202 Termination date: 20210317 |