CN102419178B - Mobile robot positioning system and method based on infrared road sign - Google Patents
Mobile robot positioning system and method based on infrared road sign Download PDFInfo
- Publication number
- CN102419178B CN102419178B CN201110260388.5A CN201110260388A CN102419178B CN 102419178 B CN102419178 B CN 102419178B CN 201110260388 A CN201110260388 A CN 201110260388A CN 102419178 B CN102419178 B CN 102419178B
- Authority
- CN
- China
- Prior art keywords
- road sign
- infrared
- mobile robot
- video camera
- homography matrix
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims description 45
- 239000011159 matrix material Substances 0.000 claims abstract description 72
- 238000004364 calculation method Methods 0.000 claims abstract description 13
- 230000033001 locomotion Effects 0.000 claims description 22
- 230000004807 localization Effects 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 10
- 238000003384 imaging method Methods 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 4
- 238000010191 image analysis Methods 0.000 abstract 1
- 230000008569 process Effects 0.000 description 9
- 238000013519 translation Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 230000000007 visual effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 239000013598 vector Substances 0.000 description 5
- 238000006073 displacement reaction Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 241000283080 Proboscidea <mammal> Species 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- NBIIXXVUZAFLBC-UHFFFAOYSA-N Phosphoric acid Chemical compound OP(O)(O)=O NBIIXXVUZAFLBC-UHFFFAOYSA-N 0.000 description 1
- 206010034960 Photophobia Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000003796 beauty Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 208000013469 light sensitivity Diseases 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 238000013341 scale-up Methods 0.000 description 1
- 238000005476 soldering Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Landscapes
- Length Measuring Devices By Optical Means (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a mobile robot indoor positioning system based on an infrared road sign. The system is structurally characterized in that: a dot matrix road sign is manufactured by using an infrared emitting diode and is adhered to an indoor ceiling; a wide-angle infrared camera is fixed on the body of a mobile robot to shoot the infrared road sign upwards; and a computer on the body of the robot performs image analysis and calculates out the position and pose of the robot in real time. The positioning system disclosed by the invention can be used for the positioning of the mobile robot at indoor places with a relatively large range, and has the characteristics of fast calculation speed, high positioning accuracy and strong anti-interference performance.
Description
Technical field
The present invention relates to the infrared imagery technique field, relate to particularly the mobile robot visual field of locating technology.
Background technology
Along with the develop rapidly of computer technology, very large scale integration technology, network technology, artificial intelligence technology etc., Robotics has also obtained the development of advancing by leaps and bounds.The kind of robot is more and more, and range of application is also more and more wider.2007, the president Bill Gates of Microsoft foretold in " Scientific Beauty compatriots " magazine: PC the same the enter huge numbers of families of robot before will be with 30 years.The Korea S Samsung institute for economic research once predicted, arrived the year two thousand twenty, and world robot market scale will be to reaching 1.4 trillion dollars, and Seoul's Information and Communication Ministry was even once drawn up the surprising target that there is a robot in the every family of the year two thousand twenty.For intelligent mobile robot, in order to walk and arrive efficiently destination from environment, and make it judge it self position according to some features that in environment, oneself knows, Here it is mobile robot's orientation problem.Robot wants in circumstances not known, automatically to walk, and location is the most basic problem.
The many researchists of recent domestic use multiple sensors, and mobile robot's self-align problem is conducted in-depth research, and have proposed many method for self-locating.Method for self-locating comprises: topological representation method, dead reckoning, Kalman Filter Estimation, Grid Method, probabilistic method, location and chartography etc. simultaneously.Sensor for location comprises: vision sensor, laser, infrared, ultrasonic, code-disc, gyroscope, accelerometer etc.Code-disc, gyroscope, accelerometer are the aiding sensors for local positioning.Infrared, sonac is limit by precision, is generally used for and promptly keeps away barrier.The laser sensor cost is higher, is not suitable for civilian popularization.The environmental information that vision sensor obtains is the abundantest, the development space maximum.The researchist lays particular emphasis on the robotic vision Position Research at present.
Vision location general minute natural landmark and two kinds of patterns of artificial landmark of mobile robot.Natural landmark refers to that utilizing in environment original scene to serve as a mark positions navigation.Although natural landmark is not destroyed original environment, universality is good, and calculation of complex, robustness are not strong, poor practicability.Artificial landmark refers to that the specific road sign of artificial design is arranged in environment, although artificial landmark changes to some extent to environment, calculating is simple, feature is stable, practical.Mostly the artificial landmark that the researchist adopts at present is the pattern of design special color information or texture structure information, also comprises numeral, letter and two-dimensional bar code etc.These patterns are all generally to use scraps of paper printing and making, by ambient light illumination, make the video camera photosensitive imaging, the impact that therefore changed by ambient lighting, thereby less stable.
Summary of the invention
The objective of the invention is, for avoiding the existing weak point of above-mentioned prior art, provides a kind of mobile robot visual positioning system and method based on infrared road sign, realize for the mobile robot accurately, fast, the location of robust.
Mobile robot's indoor locating system based on infrared road sign of the present invention comprises: dot matrix active infrared road sign, be attached on indoor ceiling, and be 3 * 3 type dot matrixs, the world coordinates value of infrared road sign is determined in advance; The wide-angle thermal camera, be fixed on it the mobile robot, and for catching infrared image, the internal reference of wide-angle imaging machine and distortion parameter are demarcated in advance, its initial homography matrix H
0also be determined in advance; Computer unit, for from the wide-angle thermal camera, receiving described infrared image, and carry out distortion correction and image pretreatment operation to infrared image, and carry out the infrared road sign of detection and Identification according to the infrared image after processing, and then utilizes initial homography matrix H
0, adopt expansion homography matrix localization method to position calculating to the mobile robot.
The present invention also provides a kind of mobile robot's indoor orientation method based on infrared road sign, and the method comprising the steps of: the dot matrix active infrared road sign note of 3 * 3 types is invested on ceiling, determine the world coordinates value of all infrared road signs; The wide-angle thermal camera is fixed on it robot, demarcates internal reference and the distortion parameter of wide-angle imaging machine, calculate the initial homography matrix H of video camera
0; Determine mobile robot's initial pose; Catch infrared image, go forward side by side line distortion correction and image pretreatment operation; Detect and identify infrared road sign; Utilize initial homography matrix H
0, adopt expansion homography matrix localization method to position calculating.
Advantage of the present invention is as follows: the infrared road sign pattern making that the present invention proposes is simple, facilitates image detection, identification and location Calculation; The location algorithm principle is simple, calculating is quick, accurate positioning.The positioning system that the present invention proposes can be used for indoor place in a big way carry out the mobile robot fast, accurately, the location of robust.
The accompanying drawing explanation
Fig. 1 is that system of the present invention forms schematic diagram;
Fig. 2 is the infrared road sign schematic diagram in the present invention;
The process flow diagram that works offline that Fig. 3 is positioning system of the present invention;
The process flow diagram that works online that Fig. 4 is positioning system of the present invention;
Fig. 5 is the translation rotation relationship figure between true mark and virtual mark.
Embodiment
For making the purpose, technical solutions and advantages of the present invention clearer, below in conjunction with specific embodiment, and, with reference to accompanying drawing, the present invention is described in more detail.
Fig. 1 has provided the schematic diagram of the mobile robot positioning system based on infrared road sign of the present invention.
With reference to Fig. 1, this system comprises: be attached at dot matrix active infrared road signs 1 on indoor ceiling, 3 * 3 types; Be fixed on robot wide-angle thermal camera 2 with it; Computer unit 3 for graphical analysis and location Calculation.
Ceiling plane is parallel to the ground, infrared road sign 1 is attached at ceiling plane, wide-angle thermal camera 2 is fixed on robot platform top, to the infrared road sign of photographs, for the computer unit 3 of graphical analysis and location Calculation, is placed in mobile robot platform inside.The mounting distance of infrared road sign 1 need to be considered from the high integrity of ceiling in conjunction with visual field size and the video camera of video camera, so that there is not location in video camera, dead angle is as the criterion, be that video camera at least can photograph Anywhere a road sign in scene, post a plurality of infrared road signs 1 on ceiling plane.
The dot matrix of infrared road sign 1 is by the luminous realization of SMD infrared-emitting diode.The emission wavelength of infrared-emitting diode generally has two kinds of 850nm and 940nm, due to CCD, the light sensitivity of 850nm light wave is greater than the light wave of 940nm, therefore selects the infrared-emitting diode that wavelength is 850nm.The specific design pattern of infrared road sign 1 as shown in Figure 2.Two kinds of point sets are arranged, and all the other points that peripheral area is larger in the dot matrix of 3*3 at 4.Each road sign has identical four, position a little bigger, for determining the subcoordinate system of road sign, determines initial point and the XY coordinate axis of road sign dot matrix, in addition, these 4 in location algorithm for calculating homography matrix.The ID value that 5 remaining points are used for calculating road sign is to distinguish each road sign, and number of combinations is 32, can mean 32 kinds of different road signs.The calculating of ID value adopts binary-coded mode, has provided the scale-of-two code value of each point in Fig. 2, and ID value scope is 0-31.
For the orientation range that single signpost is covered road sign quantity wide as much as possible, that use is few as much as possible, video camera used must have enough large field range, so the infrared wide-angle video camera adopts the large wide-angle lens that focal length is 2.8mm or 2.5mm.The narrow bandpass filter plate that camera lens the place ahead mounting center wavelength is 850nm, thus only the light wave of 850nm (optical wavelength that road sign dot matrix infrared diode is corresponding) is carried out to photosensitive imaging.
The course of work of the mobile robot's indoor locating system based on infrared road sign of the present invention comprises off-line procedure and at line process.Wherein off-line procedure relates to the configuration of localizing environment and the calculating of various parameters.
With reference to Fig. 3, off-line procedure comprises: internal reference and the distortion parameter of demarcating the wide-angle imaging machine; Determine the world coordinates value of all infrared road signs; Determine mobile robot's initial pose; Calculate the initial homography matrix H of video camera
0.
With reference to Fig. 3, off-line procedure specifically comprises the following steps:
Step S301, first complete camera calibration work, demarcates internal reference and the distortion parameter of wide-angle imaging machine, and the mapping matrix of video camera internal reference and distortion correction is stored in to respective document T1.
Step S302, make road sign, particularly, adopts the strip circuit plate to be barricaded as sphere of movements for the elephants type shelf, locates soldering surface mounted infrared-emitting diode in point of crossing.
Step S303, be attached at ceiling plane by road sign, and video camera is arranged on to the mobile robot platform top.
After localizing environment is put up, remaining work is exactly to set up cartographic information and measure the parameter for location Calculation, cartographic information is mainly that the subcoordinate that records each road sign ties up to the position in world coordinates, calculate the world coordinates value of each road sign by step S304, and deposit respective document T2 in.The world coordinates value of each road sign determines that method is as follows: due to four anchor points being arranged on each road sign, so can utilize the homography matrix relation that the position of road sign is determined one by one.The world coordinates data of road sign are stored in a file, and form is:
0:1,0 460,0 0,460 0,460 230
1:0,0 0,0 0,0 0,0 0
2:0,0 0,0 0,0 0,0 0
… … …
… … …
… … …
31:0,0 0,0 0,0 0,0 0 (1)
The format description of each row of data is as follows:
Road sign ID: whether this road sign world coordinates is determined (is 1, no 0), the world coordinates value of anchor point 0 (between each coordinate with space-separated), the world coordinates value of anchor point 1 (between each coordinate with space-separated), the world coordinates value of anchor point 2 (between each coordinate with space-separated), the world coordinates value of anchor point 3 (between each coordinate with space-separated).
Suppose and select road sign that ID is 0 as the initial point road sign, using the subcoordinate system of No. 0 road sign as world coordinates.The process that the world coordinates of other road sign calculates is as follows: 1. detect all road signs in the shooting visual field, and identify their ID value.2. the road sign that identifies of search from road sign world coordinates document, if there is the world coordinates of certain road sign to determine (judging by sign), utilize four anchor points of this road sign to calculate the homography matrix H of present image.Utilize H to calculate other and do not determine four anchor point coordinates of the road sign of world coordinates value, then deposit data in document.3., if the road sign in the visual field does not all have to determine, the mobile robot, restart the first step.4. after the road sign that can photograph has all been determined, calculate and finish.
Next, calculate initial homography matrix H at step S305
0, and deposit result of calculation in H
0document T3.Definite method of initial homography matrix is described as follows: in the expansion homography matrix localization method based on the hypothesis of plane mechanism that the present invention adopts, with camera coordinates, be reference, homography matrix does not change, and road sign produces virtual displacement.The location Calculation of back is all carried out for initial homography matrix.Because all road signs are all unified under world coordinate system, so four points of initial homography matrix in can an optional road sign are calculated.
Definite method of homography matrix is as follows:
The projection relation that in road sign, the position of each point and video camera 3 imaging planes form is the projective rejection of plane to plane, i.e. homography matrix transformation relation, and formulae express is as shown in Equation 2.
In above formula, H is homography matrix, m
i(i=1,2 ..., 9) be the matrix element of homography matrix, s
ifor scale-up factor, (u
i, v
i) coordinate for road sign point in image, (x
i, y
i) be the world coordinates of road sign point.Formula (2) is expanded into to three equations,
By first equation, divided by the 3rd equation, second equation is divided by the 3rd equation, and s disappears
iobtain two equations:
If the n on the known object plane point, know their volume coordinate (x
i, y
i) (i=1,2 ..., n), and known their picture point coordinate (u
i, v
i) (i=1,2 ..., n), we have 2n the linear equation about the homography matrix element, below with matrix form, write out these equations:
Can make m
9=1, making equation coefficient is matrix K, and variable is M, is worth for U, and equation can be written as KM=U, and the least square solution of equation is:
M=(K
TK)
-1K
TU (6)
There are 8 unknown numbers, can pass through four pairs of some solving equations, thereby obtain each matrix element value of homography matrix.
Last completing steps S306, calculate the initial position (x of video camera photocentre
0, y
0), and deposit document T4 in.Definite method of video camera photocentre initial position is described as follows: the video camera internal reference is demarcated in advance, and the outer ginseng of video camera is that impact point is transformed into the transformed matrix of camera coordinate system from world coordinate system, comprises three rotating vectors and a translation vector.With equation expression, be:
(X
c, Y
c, Z
c) be the coordinate figure of impact point under camera coordinate system, (X
w, Y
w, Z
w) be the coordinate figure of impact point under world coordinate system.M
2for video camera is joined matrix, r outward
1, r
2, r
3for the rotating vector of outer three quadratures of joining of video camera, the translation vector that t is the outer ginseng of video camera.Select infrared road sign that ID is 31 as the initial point road sign, under road sign, select free-position to calculate homography matrix H
0, utilize on road sign 9 pairs of coplanar points to solve video camera simultaneously and join M outward
2.The location of video camera photocentre is to calculate the coordinate figure of photocentre under world coordinate system.Computing formula is as follows:
(8)
The process that works online that Fig. 4 is the mobile robot's indoor locating system based on infrared road sign of the present invention.Working online of task is mainly to utilize the various parameters that work offline and measure, and detects and identify infrared road sign, adopts expansion homography matrix localization method to carry out the location Calculation of video camera.
With reference to Fig. 4, at line process, comprise: the infrared image that video camera 2 catches on ceiling, and the image of catching is sent to computer unit 3; The image of 3 pairs of receptions of computer unit carries out distortion correction and image pretreatment operation; Computer unit 3 detects and identifies infrared road sign; Computer unit 3 utilizes initial homography matrix H
0, adopt expansion homography matrix localization method to position calculating.
With reference to Fig. 4, off-line procedure specifically comprises the following steps:
At first, at step S401, by after being arranged on video camera in robot and obtaining the road sign image on ceiling, utilize correction matrix T1 to carry out the pre-service work of image, comprise image rectification, image filtering, binaryzation, morphology processing etc.
At step S402, detect all road signs (the sphere of movements for the elephants road sign be constituted by a diode) in the visual field and select to be positioned in the middle of image road sign as the initial point road sign.
At step S403, carry out the detection of four peripheral anchor points for selected road sign.
At step S404, calculate road sign ID value.
At step S405, the initial position T3 of the road sign world coordinates value T2 that utilizes off-line to record, initial homography matrix T3 and video camera photocentre, adopt expansion homography matrix localization method to position calculating.
The prerequisite of expansion homography matrix localization method is the hypothesis of plane mechanism: 1. road sign is attached at ceiling plane, and video camera is fixed in the mobile platform top, and world coordinates XY plane is based upon on the road sign plane; 2. camera motion plane and road sign plane parallel; 3. the motion of video camera only has two kinds, parallel, and the vertical line on ground of take rotates as turning axle.The principle of expansion homography matrix localization method is: under the prerequisite of the hypothesis of plane mechanism, utilize the relativity of motion, by being fixed on video camera on the robot platform rotary flat shifting movement with respect to the road sign plane, be converted into the rotary flat shifting movement of road sign with respect to camera coordinate system; By the hypothesis constant position that calculates virtual road sign of homography matrix, the pose of being extrapolated video camera by the pose difference between virtual road sign and actual road sign changes, thereby reaches the purpose of localization for Mobile Robot.Relation between former and later two poses of the motion of video camera can use formula (9) to mean, and corresponding motion pose relation of take the gauge point that video camera is reference can use formula (10) expression.
In formula (9), P
cam, P '
cam, P "
camfor the attained pose of video camera, in formula (10), P
mark, P '
mark, P "
markvirtual pose for road sign.
In conjunction with parameter definite in off-line procedure, positioning calculation process comprises:
At first, calculate the virtual pose P of road sign "
mark.
In motion positions computation process under the hypothesis of plane mechanism, homography matrix remains unchanged, and the motion of mobile platform is equivalent to the reciprocal translation of road sign/rotation.Suppose that road sign opposite direction translation/postrotational pose is P "
mark.
In conjunction with initial homography matrix H
0, can pass through the formula of picture point coordinate solution point coordinate by derived for solving:
Wherein, m
ifor homography matrix H
0element, (x
i, y
i) be the world coordinates of object point, (u
i, v
i) be image coordinate.During in new pose, detect the road sign in image when video camera, obtain image coordinate (u
i, v
i), then in conjunction with H
0utilize formula (11) to calculate the world coordinates (x of road sign
i, y
i), due to the homography matrix adopted in the calculating homography matrix that is video camera when the initial position, so (the x calculated
i, y
i) be the world coordinates of virtual road sign, three road sign points can form virtual road sign pose P "
mark.Fig. 5 has provided the graph of a relation of original road sign and virtual road sign, p
0p
1p
23 is real road sign point, p '
0p '
1p '
2virtual road sign point when only having translation motion, p "
0p "
1p "
2for translation adds postrotational virtual road sign point.O ' is the initial position of video camera photocentre with respect to world coordinates.Utilize H
0inverse P out "
markbe corresponding p "
0p "
1p "
2.
Secondly, calculate rotational angle theta.
P
0p
1p
2with p "
0p "
1p "
2between differential seat angle be exactly rotation angle θ.θ can be by calculating two vectors
with
differential seat angle draw.Will
be normalized to (cos (θ
1), sin (θ
1)),
be normalized to (cos (θ
2), sin (θ
2)), θ=θ is arranged
1-θ
2.
Finally, need displacement calculating S.
The above has calculated rotation angle θ and p "
0p "
1p "
2, only need be by p "
0p "
1p "
2be rotated counterclockwise θ and obtain p ' centered by o '
0p '
1p '
2.Formula (12) is p "
0rotation obtains p '
0formula, other 2 are similar.
Three displacements on theory
should equate, but, owing to there being the error of calculation, can obtain by the mode be averaged the displacement S of video camera.
By the calculating of above rotational angle theta and displacement S, determined the pose of robot with respect to the initial point road sign, reached the purpose of space relative positioning.
At step S406, positioning result is carried out to the filtering processing, can adopt kalman filter method to carry out.
Above-described embodiment provides is basic structure scheme and the algorithm operating flow process of the mobile robot positioning system based on infrared road sign proposed by the invention; protection scope of the present invention is not limited to this; also comprise this organization plan of employing and location algorithm and slightly make other schemes of changing in periphery, the structure or the mobile robot platform that change m*m (m is more than or equal to 3 integer) as the dot matrix road sign into change moving vehicle platform etc. into.
Above-described specific embodiment; purpose of the present invention, technical scheme and beneficial effect are further described; institute is understood that; the foregoing is only specific embodiments of the invention; be not limited to the present invention; within the spirit and principles in the present invention all, any modification of making, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.
Claims (10)
1. the mobile robot's indoor locating system based on infrared road sign, this system comprises:
Dot matrix active infrared road sign, be attached on indoor ceiling, is m * m type dot matrix, and the world coordinates value of infrared road sign is determined in advance, and wherein m is more than or equal to 3 integer;
The wide-angle thermal camera, be fixed on it the mobile robot, and for catching infrared image, the internal reference of wide-angle imaging machine and distortion parameter are demarcated in advance, its initial homography matrix H
0also be determined in advance;
Computer unit, for from the wide-angle thermal camera, receiving described infrared image, and infrared image is carried out to distortion correction and image pretreatment operation, and carry out the infrared road sign of detection and Identification according to the infrared image after processing, then utilize initial homography matrix H0, adopt expansion homography matrix location to position calculating to the mobile robot
Wherein world coordinates XY plane is based upon on the road sign plane, camera motion plane and road sign plane parallel, the motion of video camera comprises parallel and take the vertical line on ground and rotates as turning axle, expansion homography matrix location further comprises: the relativity of utilizing motion, to be fixed on the rotary flat shifting movement of robot video camera with it with respect to the road sign plane, be converted into the rotary flat shifting movement of road sign with respect to camera coordinate system; By the hypothesis constant position that calculates virtual road sign of homography matrix, the pose of being extrapolated video camera by the pose difference between virtual road sign and actual road sign changes, thereby reaches the purpose of localization for Mobile Robot.
2. positioning system according to claim 1, is characterized in that, described dot matrix active infrared road sign is made by SMD infrared-emitting diode, and near-infrared wavelength is 850nm.
3. positioning system according to claim 2, it is characterized in that, the dot matrix of described dot matrix active infrared road sign is 3 * 3 types, by periphery, larger 4 and all the other less points form, larger 4 detections for road sign and location Calculation, all the other less points are for the ID value calculating of road sign.
4. positioning system according to claim 3, is characterized in that, described infrared wide-angle video camera adopts the large wide-angle lens that focal length is 2.8mm or 2.5mm, the narrow bandpass filter plate that camera lens the place ahead mounting center wavelength is 850nm.
5. system according to claim 4, is characterized in that, described computer unit calculates the detection and Identification road sign by identification and the ID value of a territory detection, road sign point clustering, Selecting landmarks, four anchor points.
6. the mobile robot's indoor orientation method based on infrared road sign, the method comprising the steps of:
The dot matrix active infrared road sign note of 3 * 3 types is invested on ceiling, determine the world coordinates value of all infrared road signs;
The wide-angle thermal camera is fixed on it robot, demarcates internal reference and the distortion parameter of wide-angle imaging machine, calculate the initial homography matrix H of video camera
0;
Determine mobile robot's initial pose;
Catch infrared image, go forward side by side line distortion correction and image pretreatment operation;
Detect and identify infrared road sign;
Utilize initial homography matrix H
0adopt expansion homography matrix location to position calculating, wherein world coordinates XY plane is based upon on the road sign plane, camera motion plane and road sign plane parallel, the motion of video camera comprises parallel and take the vertical line on ground and rotates as turning axle, expansion homography matrix location further comprises: the relativity of utilizing motion, to be fixed on the rotary flat shifting movement of robot video camera with it with respect to the road sign plane, be converted into the rotary flat shifting movement of road sign with respect to camera coordinate system; By the hypothesis constant position that calculates virtual road sign of homography matrix, the pose of being extrapolated video camera by the pose difference between virtual road sign and actual road sign changes, thereby reaches the purpose of localization for Mobile Robot.
7. localization method according to claim 6, is characterized in that, described dot matrix active infrared road sign is made by SMD infrared-emitting diode, and near-infrared wavelength is 850nm.
8. localization method according to claim 7, it is characterized in that, the dot matrix of described dot matrix active infrared road sign larger by periphery 4 and all the other less points form, larger 4 detections for road sign and location Calculation, and all the other less points are for the ID value calculating of road sign.
9. localization method according to claim 8, is characterized in that, described infrared wide-angle video camera adopts the large wide-angle lens that focal length is 2.8mm or 2.5mm, the narrow bandpass filter plate that camera lens the place ahead mounting center wavelength is 850nm.
10. localization method according to claim 9, is characterized in that, described computer unit calculates the detection and Identification road sign by identification and the ID value of a territory detection, road sign point clustering, Selecting landmarks, four anchor points.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201110260388.5A CN102419178B (en) | 2011-09-05 | 2011-09-05 | Mobile robot positioning system and method based on infrared road sign |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201110260388.5A CN102419178B (en) | 2011-09-05 | 2011-09-05 | Mobile robot positioning system and method based on infrared road sign |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102419178A CN102419178A (en) | 2012-04-18 |
CN102419178B true CN102419178B (en) | 2014-01-08 |
Family
ID=45943705
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201110260388.5A Active CN102419178B (en) | 2011-09-05 | 2011-09-05 | Mobile robot positioning system and method based on infrared road sign |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102419178B (en) |
Families Citing this family (62)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102749072B (en) * | 2012-06-15 | 2014-11-05 | 易程科技股份有限公司 | Indoor positioning method, indoor positioning apparatus and indoor positioning system |
CN102773862B (en) * | 2012-07-31 | 2015-01-07 | 山东大学 | Quick and accurate locating system used for indoor mobile robot and working method thereof |
CN102818568B (en) * | 2012-08-24 | 2016-12-21 | 中国科学院深圳先进技术研究院 | The position fixing and navigation system of Indoor Robot and method |
CN102829775A (en) * | 2012-08-29 | 2012-12-19 | 成都理想境界科技有限公司 | Indoor navigation method, systems and equipment |
CN103020957B (en) * | 2012-11-20 | 2015-05-20 | 北京航空航天大学 | Mobile-robot-carried camera position calibration method |
CN103063211A (en) * | 2013-01-04 | 2013-04-24 | 哈尔滨伟方智能科技开发有限责任公司 | Positioning method and device based on photoelectric induction |
CN103196440B (en) * | 2013-03-13 | 2015-07-08 | 上海交通大学 | M sequence discrete-type artificial signpost arrangement method and related mobile robot positioning method |
CN103411544B (en) * | 2013-07-15 | 2016-02-10 | 大连工业大学 | The method of the relative displacement of a kind of photodiode code-disc and measurement object thereof |
CN103528583A (en) * | 2013-10-24 | 2014-01-22 | 北京理工大学 | Embedded robot locating device |
CN103837147B (en) * | 2014-03-13 | 2017-01-18 | 北京理工大学 | Active infrared dot-matrix type artificial road sign, intelligent body locating system and intelligent body locating method |
CN104035091B (en) * | 2014-06-11 | 2016-08-24 | 江苏数字鹰科技发展有限公司 | Indoor unmanned plane alignment system |
CN104216202A (en) * | 2014-08-25 | 2014-12-17 | 太仓中科信息技术研究院 | Inertia gyroscope combined real-time visual camera positioning system and method |
CN105629199A (en) * | 2014-11-04 | 2016-06-01 | Tcl集团股份有限公司 | Indoor positioning method and system |
CN105700522B (en) * | 2014-11-11 | 2019-11-15 | 沈阳新松机器人自动化股份有限公司 | A kind of robot charging method and its charging system |
CN104656075A (en) * | 2015-01-28 | 2015-05-27 | 广州视源电子科技股份有限公司 | Indoor positioning method and system |
CN104765073B (en) * | 2015-03-24 | 2017-09-01 | 中设设计集团股份有限公司 | A kind of laser water surface floating body recognition methods |
CN104898677B (en) * | 2015-06-29 | 2017-08-29 | 厦门狄耐克物联智慧科技有限公司 | The navigation system and its method of a kind of robot |
CN104950892B (en) * | 2015-06-29 | 2017-10-31 | 厦门狄耐克物联智慧科技有限公司 | The traveling control system and method for a kind of robot |
CN105078581A (en) * | 2015-09-07 | 2015-11-25 | 四川大学 | Mobile robot-assisted surgical system having positioning function |
CN105300375B (en) * | 2015-09-29 | 2018-04-20 | 塔米智能科技(北京)有限公司 | A kind of robot indoor positioning and air navigation aid based on single vision |
CN106803261A (en) * | 2015-11-20 | 2017-06-06 | 沈阳新松机器人自动化股份有限公司 | robot relative pose estimation method |
CN105425807B (en) * | 2016-01-07 | 2018-07-03 | 朱明� | A kind of Indoor Robot air navigation aid and device based on artificial landmark |
CN105737820B (en) * | 2016-04-05 | 2018-11-09 | 芜湖哈特机器人产业技术研究院有限公司 | A kind of Indoor Robot positioning navigation method |
CN106197427A (en) * | 2016-07-04 | 2016-12-07 | 上海思依暄机器人科技股份有限公司 | Method, device and the robot of a kind of indoor positioning navigation |
CN106197404B (en) * | 2016-07-12 | 2019-06-25 | 北京泊宝机器人科技有限公司 | A kind of AGV positioning system and localization method |
CN105973240B (en) * | 2016-07-15 | 2018-11-23 | 哈尔滨工大服务机器人有限公司 | A kind of conversion method of navigation module coordinate system and robot coordinate system |
CN106289187A (en) * | 2016-07-20 | 2017-01-04 | 广东大仓机器人科技有限公司 | A kind of method realizing robot chamber inner position by image recognition |
CN105974928B (en) * | 2016-07-29 | 2018-12-07 | 哈尔滨工大服务机器人有限公司 | A kind of robot navigation's paths planning method |
CN106125733A (en) * | 2016-07-29 | 2016-11-16 | 芜湖哈特机器人产业技术研究院有限公司 | Mobile machine People's Bank of China based on infrared top mark sensor walking system |
CN106003052B (en) * | 2016-07-29 | 2018-06-12 | 哈尔滨工大服务机器人有限公司 | A kind of creation method of robot visual guidance map |
CN106092090B (en) * | 2016-08-06 | 2023-04-25 | 合肥中科星翰科技有限公司 | Infrared road sign for positioning indoor mobile robot and use method thereof |
CN106338287A (en) * | 2016-08-24 | 2017-01-18 | 杭州国辰牵星科技有限公司 | Ceiling-based indoor moving robot vision positioning method |
CN106403926B (en) * | 2016-08-30 | 2020-09-11 | 上海擎朗智能科技有限公司 | Positioning method and system |
CN106468553B (en) * | 2016-08-30 | 2019-11-12 | 上海擎朗智能科技有限公司 | A kind of localization method of the mobile object based on road sign |
CN106371463B (en) * | 2016-08-31 | 2019-04-02 | 重庆邮电大学 | More gyroplane earth stations position infrared beacon system |
CN106297551A (en) * | 2016-09-14 | 2017-01-04 | 哈工大机器人集团上海有限公司 | A kind of road sign for determining robot location and coding checkout method thereof |
CN106313119B (en) * | 2016-09-14 | 2019-05-03 | 哈工大机器人集团上海有限公司 | A kind of road sign for determining robot location, device |
CN106526580A (en) * | 2016-10-26 | 2017-03-22 | 哈工大机器人集团上海有限公司 | Road sign, apparatus, and method for determining robot position |
CN108121332A (en) * | 2016-11-28 | 2018-06-05 | 沈阳新松机器人自动化股份有限公司 | Indoor mobile robot positioner and method based on Quick Response Code |
CN106651990B (en) * | 2016-12-23 | 2020-08-11 | 芜湖哈特机器人产业技术研究院有限公司 | Indoor map construction method and indoor positioning method based on indoor map |
CN107063229A (en) * | 2017-03-06 | 2017-08-18 | 上海悦合自动化技术有限公司 | Mobile robot positioning system and method based on artificial landmark |
CN108731677B (en) * | 2017-04-17 | 2020-10-02 | 哈工大机器人集团股份有限公司 | Robot navigation road sign and identification method |
CN107450540B (en) * | 2017-08-04 | 2018-10-30 | 山东大学 | Indoor mobile robot navigation system and method based on infrared road sign |
CN107436422B (en) * | 2017-08-22 | 2019-09-03 | 杭州慧仓信息科技有限公司 | A kind of robot localization method based on infrared lamp solid array |
CN107992793A (en) * | 2017-10-20 | 2018-05-04 | 深圳华侨城卡乐技术有限公司 | A kind of indoor orientation method, device and storage medium |
CN107976196B (en) * | 2017-11-30 | 2021-04-16 | 深圳Tcl新技术有限公司 | Mobile robot, mobile robot positioning method and system |
CN108015770A (en) * | 2017-12-07 | 2018-05-11 | 王群 | Position of manipulator scaling method and system |
CN108181610B (en) * | 2017-12-22 | 2021-11-19 | 鲁东大学 | Indoor robot positioning method and system |
CN108225327B (en) * | 2017-12-31 | 2021-05-14 | 芜湖哈特机器人产业技术研究院有限公司 | Construction and positioning method of top mark map |
CN112074706A (en) * | 2018-04-28 | 2020-12-11 | 优泰机电有限公司 | Accurate positioning system |
CN109087353A (en) * | 2018-08-20 | 2018-12-25 | 四川超影科技有限公司 | Indoor occupant localization method based on machine vision |
CN109596120A (en) * | 2018-12-25 | 2019-04-09 | 芜湖哈特机器人产业技术研究院有限公司 | A kind of combined positioning and navigating sensing system |
CN109613472B (en) * | 2018-12-26 | 2023-04-28 | 芜湖哈特机器人产业技术研究院有限公司 | Infrared top mark for indoor trackless navigation and identification method thereof |
CN109855602A (en) * | 2019-01-14 | 2019-06-07 | 南通大学 | Move the monocular visual positioning method under visual field |
CN110175540A (en) * | 2019-05-11 | 2019-08-27 | 深圳市普渡科技有限公司 | Road sign map structuring system and robot |
CN110398251B (en) * | 2019-08-16 | 2021-02-09 | 北京邮电大学 | Trackless navigation AGV positioning system based on multi-sensor fusion and positioning method thereof |
CN111432113B (en) * | 2019-12-30 | 2022-04-05 | 科沃斯机器人股份有限公司 | Data calibration method, device and storage medium |
CN112180938B (en) * | 2020-10-15 | 2022-09-30 | 芜湖哈特机器人产业技术研究院有限公司 | AGV trolley positioning system and method based on infrared top mark and odometer |
CN112595318A (en) * | 2020-11-04 | 2021-04-02 | 创泽智能机器人集团股份有限公司 | Robot indoor navigation positioning system and method based on SLAM and infrared |
RU2761923C1 (en) * | 2021-03-26 | 2021-12-14 | Федеральное государственное бюджетное учреждение науки Институт автоматики и процессов управления Дальневосточного отделения Российской академии наук (ИАПУ ДВО РАН) | Manipulator control method |
RU2761924C1 (en) * | 2021-03-26 | 2021-12-14 | Федеральное государственное бюджетное учреждение науки Институт автоматики и процессов управления Дальневосточного отделения Российской академии наук (ИАПУ ДВО РАН) | Manipulator control method |
CN113237488B (en) * | 2021-05-14 | 2024-07-05 | 徕兄健康科技(威海)有限责任公司 | Navigation system and navigation method based on binocular vision and curb finding technology |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5911767A (en) * | 1994-10-04 | 1999-06-15 | Garibotto; Giovanni | Navigation system for an autonomous mobile robot |
CN101669144A (en) * | 2007-03-13 | 2010-03-10 | 浦项产业科学研究院 | Landmark for position determination of mobile robot and apparatus and method using it |
CN102135429A (en) * | 2010-12-29 | 2011-07-27 | 东南大学 | Robot indoor positioning and navigating method based on vision |
-
2011
- 2011-09-05 CN CN201110260388.5A patent/CN102419178B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5911767A (en) * | 1994-10-04 | 1999-06-15 | Garibotto; Giovanni | Navigation system for an autonomous mobile robot |
CN101669144A (en) * | 2007-03-13 | 2010-03-10 | 浦项产业科学研究院 | Landmark for position determination of mobile robot and apparatus and method using it |
CN102135429A (en) * | 2010-12-29 | 2011-07-27 | 东南大学 | Robot indoor positioning and navigating method based on vision |
Non-Patent Citations (4)
Title |
---|
《基于近红外视觉的机器人室外定位系统》;王景川等;《机器人》;20100131;第32卷(第1期);第97-103页 * |
基于视觉的室内移动机器人精确定位方法;章小兵等;《数据采集与处理》;20070630;第22卷(第2期);第196-200页 * |
王景川等.《基于近红外视觉的机器人室外定位系统》.《机器人》.2010,第32卷(第1期),第97-103页. |
章小兵等.基于视觉的室内移动机器人精确定位方法.《数据采集与处理》.2007,第22卷(第2期),第196-200页. |
Also Published As
Publication number | Publication date |
---|---|
CN102419178A (en) | 2012-04-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102419178B (en) | Mobile robot positioning system and method based on infrared road sign | |
WO2023104207A1 (en) | Collaborative three-dimensional mapping method and system | |
CN104217439B (en) | Indoor visual positioning system and method | |
CN106651953B (en) | A kind of vehicle position and orientation estimation method based on traffic sign | |
CN106272423A (en) | A kind of multirobot for large scale environment works in coordination with the method for drawing and location | |
JP4232167B1 (en) | Object identification device, object identification method, and object identification program | |
CN102435188B (en) | Monocular vision/inertia autonomous navigation method for indoor environment | |
CN103175524B (en) | A kind of position of aircraft without view-based access control model under marking environment and attitude determination method | |
Merino et al. | Vision-based multi-UAV position estimation | |
Won et al. | OmniSLAM: Omnidirectional localization and dense mapping for wide-baseline multi-camera systems | |
CN103424112B (en) | A kind of motion carrier vision navigation method auxiliary based on laser plane | |
CN108051002A (en) | Transport vehicle space-location method and system based on inertia measurement auxiliary vision | |
CN106840148A (en) | Wearable positioning and path guide method based on binocular camera under outdoor work environment | |
CN110211228A (en) | For building the data processing method and device of figure | |
CN108226938A (en) | A kind of alignment system and method for AGV trolleies | |
CN114459467B (en) | VI-SLAM-based target positioning method in unknown rescue environment | |
CN110108269A (en) | AGV localization method based on Fusion | |
CN106403926B (en) | Positioning method and system | |
Lin et al. | R $^{3} $ LIVE++: A Robust, Real-time, Radiance Reconstruction Package with a Tightly-coupled LiDAR-Inertial-Visual State Estimator | |
Avgeris et al. | Single vision-based self-localization for autonomous robotic agents | |
Mariottini et al. | An accurate and robust visual-compass algorithm for robot-mounted omnidirectional cameras | |
CN116380079A (en) | Underwater SLAM method for fusing front-view sonar and ORB-SLAM3 | |
Zhang et al. | AVP-Loc: Surround view localization and relocalization based on HD vector map for automated valet parking | |
CN105424059B (en) | Wide baseline near infrared camera position and orientation estimation method | |
CN107463871A (en) | A kind of point cloud matching method based on corner characteristics weighting |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20220128 Address after: 030000 China Resources Building, Taiyuan, Shanxi t5-1902 Patentee after: Shanxi Qirui Education Technology Co.,Ltd. Address before: 100190 No. 95 East Zhongguancun Road, Beijing, Haidian District Patentee before: INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCES |
|
TR01 | Transfer of patent right |