CN107150343A - A kind of system that object is captured based on NAO robots - Google Patents
A kind of system that object is captured based on NAO robots Download PDFInfo
- Publication number
- CN107150343A CN107150343A CN201710218155.6A CN201710218155A CN107150343A CN 107150343 A CN107150343 A CN 107150343A CN 201710218155 A CN201710218155 A CN 201710218155A CN 107150343 A CN107150343 A CN 107150343A
- Authority
- CN
- China
- Prior art keywords
- nao
- target object
- angle
- robots
- image
- 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
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Manipulator (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of system that object is captured based on NAO robots, the system includes:The system includes:First obtains module, for obtaining first nodal point pixel coordinate;Second obtains module, for obtaining the height of head changing value of the NAO robots and the first function relation of the angle of pitch, and the 3rd obtains module, for obtaining the target object to the distance of the NAO robots and the second function relation of the angle of pitch;First acquisition module, the second center pixel point coordinates for obtaining described image;4th obtains module, for obtaining level angle of the target object relative to the NAO robots and vertical drift angle;5th obtains module, for obtaining the target object to the distance of the NAO robots;Second acquisition module, for obtaining the NAO robot ambulations route.The system for solving crawl object in the prior art has that positioning precision is high, poor real technical problem.
Description
Technical field
The present invention relates to intelligent robot technology field, more particularly to a kind of system that object is captured based on NAO robots.
Background technology
With the development of artificial intelligence technology, because NAO robots have merged automation, machinery, sensing art, calculating
The multi-subject knowledges such as machine, artificial intelligence and achievement in research, are widely used in daily life and production.
In the prior art, captured using NAO robots in article system, it usually needs to object relative to robot
Position positioned, typically using monocular visual positioning method.
Present inventor has found that at least there are the following problems in the prior art when realizing technical scheme:
Existing use monocular vision alignment system, positioning to object is simultaneously inaccurate, and application condition is big, in addition, robot
If grabbing article not successfully, it can not also be fed back.
It can be seen that, alignment system has that precision is high, poor real technical problem in the prior art.
The content of the invention
The embodiment of the present invention provides a kind of system that object is captured based on NAO robots, to solve to grab in the prior art
The system of object is taken to have that positioning precision is high, poor real technical problem.
The invention discloses a kind of system that object is captured based on NAO robots, the system includes:
First obtains module, for being found using method of the searching route set in advance based on color segmentation and recognizing mesh
Object is marked, the first nodal point pixel coordinate of the image comprising the target object and the target object is obtained;
Second obtains module, for obtaining the height of head changing value of the NAO robots and the first function of the angle of pitch
RelationWherein, Δ h is the height of head changing value of NAO robots, and β is NAO robots
The head angle of pitch,For fixed value;
3rd obtains module, for according to the first function relation, obtaining the target object to the NAO robots
Distance and the angle of pitch second function relationWherein, s is
Target object is to the distance of the NAO robots, and α is NAO robot vision central shaft and horizontal angle, is a fixation
Value, h is height of the camera away from ground when NAO robots are in original state, and r is height of the target object central point away from ground
Degree;
First acquisition module, the second center pixel point coordinates for obtaining described image, wherein imago in described second
Vegetarian refreshments coordinate is the center pixel coordinate value of described image;
4th obtains module, for according to the first nodal point pixel coordinate and the second center pixel point coordinates,
Level angle of the target object relative to the NAO robots and vertical drift angle are obtained, wherein the vertical drift angle is institute
State the angle of pitch of NAO robots;
5th obtains module, for according to the vertical drift angle and the second function relation, obtaining the target object
To the distance of the NAO robots;
Second acquisition module, for according to the distance and the level angle, obtaining the NAO robot ambulations road
Line, so that the NAO robots are based on the track route and capture the target object.
Optionally, the first acquisition module is additionally operable to:
A two field picture is obtained using robot camera and is translated into the image in hsv color space;
The target object image is obtained from the image in the hsv color space,
According to the target object image, gray level image is obtained;
Processing and binary conversion treatment are optimized to the gray level image, the image for retaining original information is obtained;
According to the image for retaining original information, the first nodal point pixel coordinate of the image of the target object is obtained.
Optionally, the first nodal point pixel coordinate is obtained using minimum enclosed rectangle frame.
Optionally, the system also includes:
Module is built, the method for taking multiple measurements averaged using same distance builds distance and pitching
The corresponding offline search table of angle.
Optionally, the data of the different interval scope set according to distance are included in the offline search table.
Optionally, the 4th acquisition module is additionally operable to:
According to formulaLevel angle is obtained, wherein, x is the first center pixel coordinate
Abscissa, 320 be the abscissa of the second center pixel;
According to formulaVertical drift angle is obtained, wherein, y is the first center pixel coordinate
Ordinate, 240 be the ordinate of the second center pixel.
Optionally, the described 4th module is obtained:
According to the level angle, obtain NAO robots horizontally rotates direction;
According to the distance, the travel distance of the NAO robots is obtained;
Horizontally rotate direction and the travel distance according to described, obtain the NAO robot ambulations route.
Optionally, second acquisition module is additionally operable to:
The NAO robot motions are to the position of the target object;
Obtain the crawl track of the NAO robot arms;
In the position of the target object, the target object is captured according to the crawl track.
Optionally, second acquisition module is additionally operable to:
Obtain the hand motor value of the NAO robots;
Judge whether the hand motor value is more than preset value;
If being more than, object is successfully captured by voice feedback;
Otherwise, the NAO robots carry out repositioning crawl, to constitute crawl feedback.
The one or more technical schemes provided in the embodiment of the present invention, have at least the following technical effects or advantages:
A kind of system that object is captured based on NAO robots that the embodiment of the present application is provided, obtains mould by first first
Block obtains the first nodal point pixel coordinate of the image comprising the target object and the target object;Second acquisition module is obtained
The NAO robots height of head changing value and the first function relation of the angle of pitch, the 3rd obtains module according to described the
One functional relation, the acquisition target object to the distance of the NAO robots and the second function relation of the angle of pitch, the
One acquisition module can obtain the second center pixel point coordinates of described image, and then obtaining module by the 4th obtains the mesh
Mark level angle of the object relative to the NAO robots and vertical drift angle, the 5th obtains module, according to the vertical drift angle and
The second function relation, obtains the target object to the distance of the NAO robots;The second last acquisition module, can be with
According to the distance and the level angle, the NAO robot ambulations route is obtained, so that the NAO robots are based on institute
State track route and capture the target object.By distance and institute of the target object to the NAO robots can be obtained in real time
State the second function relation of the angle of pitch, it is possible to achieve be accurately positioned and improve the technique effect of real-time, solve prior art
In in alignment system have that precision is high, poor real technical problem.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of specification, and in order to allow above and other objects of the present invention, feature and advantage can
Become apparent, below especially exemplified by the embodiment of the present invention.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are this hairs
Some bright embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can be with root
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is a kind of logic diagram for the system that object is captured based on NAO robots in the embodiment of the present invention;
Fig. 2 is the schematic diagram of location algorithm in the embodiment of the present invention.
Embodiment
The embodiment of the present invention provides a kind of system that object is captured based on NAO robots, to solve to grab in the prior art
The system of object is taken to have that positioning precision is high, poor real technical problem.Realize the positioning precision and reality for improving object
When property technique effect.
Technical scheme in the embodiment of the present application, general thought is as follows:
A kind of system that object is captured based on NAO robots, it is characterised in that the system includes:
First obtains module, for being found using method of the searching route set in advance based on color segmentation and recognizing target
Object, obtains the first nodal point pixel coordinate of the image comprising the target object and the target object;Second obtains module,
For obtaining the height of head changing value of the NAO robots and the first function relation of the angle of pitch
Wherein, Δ h is the height of head changing value of NAO robots, and β is the head angle of pitch of NAO robots,
For fixed value;
3rd obtains module, for according to the first function relation, obtaining the target object to the NAO robots
Distance and the angle of pitch second function relationWherein, s is
Target object is to the distance of the NAO robots, and α is NAO robot vision central shaft and horizontal angle, is a fixation
Value, h is height of the camera away from ground when NAO robots are in original state, and r is height of the target object central point away from ground
Degree;First acquisition module, the second center pixel point coordinates for obtaining described image, wherein second central pixel point is sat
It is designated as the center pixel coordinate value of described image;4th obtains module, for according to the first nodal point pixel coordinate and institute
The second center pixel point coordinates is stated, the level angle of the target object relative to the NAO robots and vertical drift angle is obtained,
Wherein described vertical drift angle is the angle of pitch of the NAO robots;5th obtains module, for according to the vertical drift angle and institute
Second function relation is stated, the target object is obtained to the distance of the NAO robots;Second acquisition module, for according to institute
Distance and the level angle are stated, the NAO robot ambulations route is obtained, so that the NAO robots are based on the walking
Route captures the target object.
In said system, because the 5th acquisition module can be obtained according to the vertical drift angle and the second function relation
The target object is obtained to the distance of the NAO robots, then the second acquisition module is inclined according to the distance and the level
Angle, obtains the NAO robot ambulations route, so that the NAO robots are based on the track route and capture the object
Body, the acquisition target object of robot can be obtained in real time to the distance of the NAO robots.Solve in the prior art
The system of crawl object has that positioning precision is high, poor real technical problem.
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
A part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Embodiment one
The present embodiment provides a kind of system that object is captured based on NAO robots, and the system includes:
First obtains module 101, for being found and being known using method of the searching route set in advance based on color segmentation
Other target object, obtains the first nodal point pixel coordinate of the image comprising the target object and the target object;
Second obtains module 102, for obtaining the height of head changing value of the NAO robots and the first letter of the angle of pitch
Number relationWherein, Δ h is the height of head changing value of NAO robots, and β is NAO machines
The head angle of pitch of people,For fixed value;
3rd obtains module 103, for according to the first function relation, obtaining the target object to the NAO machines
The distance of device people and the second function relation of the angle of pitchWherein, s
For the distance of target object to the NAO robots, α is NAO robot vision central shaft and horizontal angle, is a fixation
Value, h is height of the camera away from ground when NAO robots are in original state, and r is height of the target object central point away from ground
Degree;
First acquisition module 104, the second center pixel point coordinates for obtaining described image, wherein second center
Pixel point coordinates is the center pixel coordinate value of described image;
4th obtains module 105, for according to the first nodal point pixel coordinate and second central pixel point seat
Mark, obtains the level angle of the target object relative to the NAO robots and vertical drift angle, wherein the vertical drift angle is
The angle of pitch of the NAO robots;
5th obtains module 106, for according to the vertical drift angle and the second function relation, obtaining the object
Distance of the body to the NAO robots;
Second acquisition module 107, for according to the distance and the level angle, obtaining the NAO robot ambulations
Route, so that the NAO robots are based on the track route and capture the target object.
In said system, because the 5th acquisition module can be obtained according to the vertical drift angle and the second function relation
The target object is obtained to the distance of the NAO robots, then the second acquisition module is inclined according to the distance and the level
Angle, obtains the NAO robot ambulations route, so that the NAO robots are based on the track route and capture the object
Body, the acquisition target object of robot can be obtained in real time to the distance of the NAO robots.Solve in the prior art
The system of crawl object has that positioning precision is high, poor real technical problem.
Below, the system for capturing object based on NAO robots provided with reference to Fig. 1 the application describes in detail:
First acquisition module 101 can be found and be recognized using method of the searching route set in advance based on color segmentation
Target object, obtains the first nodal point pixel coordinate of the image comprising the target object and the target object;
Above-mentioned first acquisition module 101 is additionally operable to:
A two field picture is obtained using robot camera and is translated into the image in hsv color space;
The target object image is obtained from the image in the hsv color space,
According to the target object image, gray level image is obtained;
Processing and binary conversion treatment are optimized to the gray level image, the image for retaining original information is obtained;
According to the image for retaining original information, the first nodal point pixel coordinate of the image of the target object is obtained.
Specifically, the first nodal point pixel coordinate is obtained using minimum enclosed rectangle frame.
Specifically, above-mentioned optimization processing can be the advanced column hisgram equalization processing of gray level image to acquisition, with
Improve the contrast and definition of image, bilateral filtering processing is carried out to image, the interference etc. of noise spot is removed, to binaryzation
Image carries out burn into expansion, further can effectively remove noise spot, retains original information in image.
Then by the second acquisition module 102 obtain the NAO robots height of head changing value and the angle of pitch the
One functional relationWherein, Δ h is the height of head changing value of NAO robots, and β is NAO
The head angle of pitch of robot,For fixed value.
Due to having obtained the height of head changing value and the angle of pitch of NAO robots, at this moment module can be obtained by the 3rd
103, according to the first function relation, the target object is obtained to the distance and the angle of pitch of the NAO robots
Second function relationWherein, s is target object to the NAO machines
The distance of device people, α is NAO robot vision central shaft and horizontal angle, is a fixed value, and h is that NAO robots are in just
Height of the camera away from ground during beginning state, r is height of the target object central point away from ground;
Specifically, visual field center is remained at using target object when target is positioned, facilitates robot to position thing in real time
Body, also complies with the custom that the mankind capture object.When being changed in view of the angle of pitch of robot head, its robot head is taken the photograph
As the height of head is also constantly changing.The embodiment of the present invention derives it according to the hardware configuration of robot head referring to Fig. 2
The relation of height change value and luffing angle;The height of head camera is expressed as the function (i.e. on the angle of pitch
One functional relation), and using hooking in stock location algorithm, the location algorithm (i.e. second function relation) of available object has
Improve positioning precision to effect.
First acquisition module 104 can obtain the second center pixel point coordinates of described image, wherein second center
Pixel point coordinates is the center pixel coordinate value of described image.
Specifically, described image is the image obtained using robot camera, and described image includes object and its
His background.
4th, which obtains module 105, to be sat according to the first nodal point pixel coordinate and second central pixel point
Mark, obtains the level angle of the target object relative to the NAO robots and vertical drift angle, wherein the vertical drift angle is
The angle of pitch of the NAO robots.
Specifically, the 4th acquisition module 105 is additionally operable to:
According to formulaLevel angle is obtained, wherein, x is the first center pixel coordinate
Abscissa, 320 be the abscissa of the second center pixel;
According to formulaVertical drift angle is obtained, wherein, y is the first center pixel coordinate
Ordinate, 240 be the ordinate of the second center pixel.
Specifically, (x, y) is the first center pixel coordinate, and (320,240) are the second center pixel coordinate,
The pixel of image be 640*480,60.9 ° of angle, 47.64 ° be robot camera hardware value.
5th, which obtains module 106, to obtain the object according to the vertical drift angle and the second function relation
Distance of the body to the NAO robots;
Specifically, the 5th acquisition module 106 is additionally operable to:
According to the level angle, obtain NAO robots horizontally rotates direction;
According to the distance, the travel distance of the NAO robots is obtained;
Horizontally rotate direction and the travel distance according to described, obtain the NAO robot ambulations route.
Finally by the second acquisition module 107, according to the distance and the level angle, the NAO robots are obtained
Track route, so that the NAO robots are based on the track route and capture the target object.
In second acquisition module 107, the NAO robots are based on the track route and capture the target object, specifically
Including:
The NAO robot motions are to the position of the target object;
Obtain the crawl track of the NAO robot arms;
In the position of the target object, the target object is captured according to the crawl track.
Alternatively, the system provided in an embodiment of the present invention for capturing object based on NAO robots also includes building module, institute
State structure module be used for according to the first function relation, obtain the target object to the distance of the NAO robots and
The second function relation of the angle of pitchAfterwards, in addition to:
The method that averaged is taken multiple measurements using same distance, build distance it is corresponding with luffing angle from
Line inquiry table.
Alternatively, in the system provided in an embodiment of the present invention that object is captured based on NAO robots, the offline search table
In include according to distance set different interval scope data.
Specifically, using second function relation, and by taking multiple measurements the side of averaged to same distance
Method, can build the distance offline search table corresponding with angle.Due to recognizing positioning precision because distance is different
Also different, object distance can build table, table since the angle corresponding to 20cm in front of robot foot center in inquiry table
At intervals of 1cm in the range of middle 20cm-70cm, 70cm-150cm is at intervals of 2cm, at intervals of 5cm in the range of 150cm-450cm,
Object robot outside 450cm can not be accurately identified.Specific interval can be set according to actual conditions, so that further
Improve positioning precision.
Alternatively, the second acquisition module 107 is additionally operable to:
Obtain the hand motor value of the NAO robots;
Judge whether the hand motor value is more than preset value;
If being more than, object is successfully captured by voice feedback;
Otherwise, the NAO robots carry out repositioning crawl, to carry out crawl feedback.
Applicant has found that different ground is different relative to the friction factor of robot foot, machine by substantial amounts of experiment
People often occurs that step skids and causes travel distance to fail to reach specified grab during target object implementation crawl is moved towards
Take a little, ultimately result in the phenomenon of crawl failure.For the influence of this uncertainty, the embodiment of the present invention is auxiliary not by the external world
In the case of helping equipment, propose a kind of by sensor acquisition hand motor angle value and preset value (such as value is 0.25) phase
The straightforward procedure compared, robot autonomous judges whether successfully to have grabbed object to allow.If successfully captured, robot meeting
" I grasp it " are said by loudspeaker;If uncertainty shadows such as the small slips because of robot foot in walking process and ground
Ring and cause robot crawl failure, then robot can feed back the positioning crawl do not caught and independently carry out again, until grabbing
Take success.
, can be according to end effector of robot initial point position and final position (i.e. thing in specific implementation process
Body position) four key frames of insertion, for the track of planning robot's arm crawl, above-mentioned steps are completed, then passed through offline
The function positionInterpolation of NAO robot built-ins can be sent to end effector under robot coordinate system
Specified location, then implements to capture, in the process, can obtain hand by sensor by the hand motor of control machine people
The value of portion's motor, is compared with preset value, if the value obtained is more than preset value, robot has caught thing by voice feedback
Body.Otherwise, robot re-starts identification, positioning, crawl.
It should be noted that the existing alignment system based on NAO robots can not obtain the 3 d space coordinate of object,
Therefore the object height captured in the embodiment of the present invention is known to given value, i.e. object Z coordinate;In the same of previous step object ranging
When we can measure object relative to upward deviation angle immediately ahead of robot, then robot can by rotating this angle
To ensure that object is in immediately ahead of robot, i.e., coordinate of the object in robot coordinate system in Y direction is 0;So pass through
The depth coordinate X of the object measured is assured that locus (X, 0, Z) of the object relative to robot coordinate system.By NAO
The function positionInterpolation of robot built-in can be sent to end effector specifying under robot coordinate system
Position, grasping manipulation is implemented to target point.It is attached:Closed loop feedback subprogram is as follows
Captured again.
Specifically, identification, positioning of the present invention to target object provide a kind of based on the crawl of NAO robots with crawl
The system of object, said system is the system of a set of closed loop.On the positioning of target object, the present invention is according to robot head knot
The first function relation between head luffing angle and target object distance is derived in the position of structure and camera, thus the first letter
Number relation formulates offline search table according to the multiple method for determining averaged, to the robot head angle of pitch obtained every time
Degree tries to achieve the distance of corresponding target object using the method for linear interpolation, effectively improves positioning precision.To target object
Crawl on, the present invention is according to the type of the hand motors of nao robots, by the motor anglec of rotation threshold value that sets offline i.e.
For preset value, robot can independently be judged whether accurately to have grabbed target object, machine if being captured if judging to fail
Device people would be repeated for crawl, constitute the crawl reponse system of closed loop, goes for future home service humanoid robot and helps
Always, the mankind are helped to take the various aspects such as the smart homes such as object.
The one or more technical schemes provided in the embodiment of the present invention, have at least the following technical effects or advantages:
A kind of system that object is captured based on NAO robots that the embodiment of the present application is provided, obtains mould by first first
Block obtains the first nodal point pixel coordinate of the image comprising the target object and the target object;Second acquisition module is obtained
The NAO robots height of head changing value and the first function relation of the angle of pitch, the 3rd obtains module according to described the
One functional relation, the acquisition target object to the distance of the NAO robots and the second function relation of the angle of pitch, the
One acquisition module can obtain the second center pixel point coordinates of described image, and then obtaining module by the 4th obtains the mesh
Mark level angle of the object relative to the NAO robots and vertical drift angle, the 5th obtains module, according to the vertical drift angle and
The second function relation, obtains the target object to the distance of the NAO robots;The second last acquisition module, can be with
According to the distance and the level angle, the NAO robot ambulations route is obtained, so that the NAO robots are based on institute
State track route and capture the target object.By distance and institute of the target object to the NAO robots can be obtained in real time
State the second function relation of the angle of pitch, it is possible to achieve be accurately positioned and improve the technique effect of real-time, solve prior art
The system of middle crawl object has that positioning precision is high, poor real technical problem.
, but those skilled in the art once know basic creation although preferred embodiments of the present invention have been described
Property concept, then can make other change and modification to these embodiments.So, appended claims are intended to be construed to include excellent
Select embodiment and fall into having altered and changing for the scope of the invention.
Obviously, those skilled in the art can carry out various changes and modification without departing from this hair to the embodiment of the present invention
The spirit and scope of bright embodiment.So, if these modifications and variations of the embodiment of the present invention belong to the claims in the present invention
And its within the scope of equivalent technologies, then the present invention is also intended to comprising including these changes and modification.
Claims (9)
1. a kind of system that object is captured based on NAO robots, it is characterised in that the system includes:
First obtains module, for being found using method of the searching route set in advance based on color segmentation and recognizing object
Body, obtains the first nodal point pixel coordinate of the image comprising the target object and the target object;
Second obtains module, for obtaining the height of head changing value of the NAO robots and the first function relation of the angle of pitchWherein, Δ h is the height of head changing value of NAO robots, and β is the head of NAO robots
Portion's angle of pitch, For fixed value;
3rd obtains module, for according to the first function relation, obtain the target object to the NAO robots away from
From the second function relation with the angle of pitchWherein, s is target
Object is to the distance of the NAO robots, and α is NAO robot vision central shaft and horizontal angle, is a fixed value, h is
Height of the camera away from ground when NAO robots are in original state, r is height of the target object central point away from ground;
First acquisition module, the second center pixel point coordinates for obtaining described image, wherein second central pixel point
Coordinate is the center pixel coordinate value of described image;
4th obtains module, for according to the first nodal point pixel coordinate and the second center pixel point coordinates, obtaining
Level angle of the target object relative to the NAO robots and vertical drift angle, wherein the vertical drift angle is the NAO
The angle of pitch of robot;
5th obtains module, for according to the vertical drift angle and the second function relation, obtaining the target object to institute
State the distance of NAO robots;
Second acquisition module, for according to the distance and the level angle, obtaining the NAO robot ambulations route, with
The NAO robots is based on the track route and capture the target object.
2. the system as claimed in claim 1, it is characterised in that the first acquisition module is additionally operable to:
A two field picture is obtained using robot camera and is translated into the image in hsv color space;
The target object image is obtained from the image in the hsv color space,
According to the target object image, gray level image is obtained;
Processing and binary conversion treatment are optimized to the gray level image, the image for retaining original information is obtained;
According to the image for retaining original information, the first nodal point pixel coordinate of the image of the target object is obtained.
3. system as claimed in claim 2, it is characterised in that the first nodal point picture is obtained using minimum enclosed rectangle frame
Plain coordinate.
4. the system as claimed in claim 1, it is characterised in that also include:
Module is built, the method for taking multiple measurements averaged using same distance builds distance and luffing angle
Corresponding offline search table.
5. system as claimed in claim 4, it is characterised in that the difference set according to distance is included in the offline search table
The data of interval.
6. the system as claimed in claim 1, it is characterised in that the 4th acquisition module is additionally operable to:
According to formulaLevel angle is obtained, wherein, x is the horizontal seat of the first center pixel coordinate
Mark, 320 be the abscissa of the second center pixel;
According to formulaVertical drift angle is obtained, wherein, y is the vertical seat of the first center pixel coordinate
Mark, 240 be the ordinate of the second center pixel.
7. the system as claimed in claim 1, it is characterised in that the described 4th obtains module:
According to the level angle, obtain NAO robots horizontally rotates direction;
According to the distance, the travel distance of the NAO robots is obtained;
Horizontally rotate direction and the travel distance according to described, obtain the NAO robot ambulations route.
8. the system as claimed in claim 1, it is characterised in that second acquisition module is additionally operable to:
The NAO robot motions are to the position of the target object;
Obtain the crawl track of the NAO robot arms;
In the position of the target object, the target object is captured according to the crawl track.
9. system as claimed in claim 8, it is characterised in that second acquisition module is additionally operable to:
Obtain the hand motor value of the NAO robots;
Judge whether the hand motor value is more than preset value;
If being more than, object is successfully captured by voice feedback;
Otherwise, the NAO robots carry out repositioning crawl, to constitute crawl feedback.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710218155.6A CN107150343B (en) | 2017-04-05 | 2017-04-05 | A kind of system based on NAO robot crawl object |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710218155.6A CN107150343B (en) | 2017-04-05 | 2017-04-05 | A kind of system based on NAO robot crawl object |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107150343A true CN107150343A (en) | 2017-09-12 |
CN107150343B CN107150343B (en) | 2019-07-23 |
Family
ID=59793075
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710218155.6A Expired - Fee Related CN107150343B (en) | 2017-04-05 | 2017-04-05 | A kind of system based on NAO robot crawl object |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107150343B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120072022A1 (en) * | 2010-09-20 | 2012-03-22 | Samsung Electronics Co., Ltd. | Robot and control method thereof |
US20120078419A1 (en) * | 2010-09-27 | 2012-03-29 | Samsung Electronics Co., Ltd | Robot and control method thereof |
CN104217441A (en) * | 2013-08-28 | 2014-12-17 | 北京嘉恒中自图像技术有限公司 | Mechanical arm positioning fetching method based on machine vision |
CN104647390A (en) * | 2015-02-11 | 2015-05-27 | 清华大学 | Multi-camera combined initiative object tracking method for teleoperation of mechanical arm |
CN104786226A (en) * | 2015-03-26 | 2015-07-22 | 华南理工大学 | Posture and moving track positioning system and method of robot grabbing online workpiece |
-
2017
- 2017-04-05 CN CN201710218155.6A patent/CN107150343B/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120072022A1 (en) * | 2010-09-20 | 2012-03-22 | Samsung Electronics Co., Ltd. | Robot and control method thereof |
US20120078419A1 (en) * | 2010-09-27 | 2012-03-29 | Samsung Electronics Co., Ltd | Robot and control method thereof |
CN104217441A (en) * | 2013-08-28 | 2014-12-17 | 北京嘉恒中自图像技术有限公司 | Mechanical arm positioning fetching method based on machine vision |
CN104647390A (en) * | 2015-02-11 | 2015-05-27 | 清华大学 | Multi-camera combined initiative object tracking method for teleoperation of mechanical arm |
CN104786226A (en) * | 2015-03-26 | 2015-07-22 | 华南理工大学 | Posture and moving track positioning system and method of robot grabbing online workpiece |
Non-Patent Citations (1)
Title |
---|
王振等: ""NAO机器人平台的创新实验设计与实现"", 《实验室研究与探索》 * |
Also Published As
Publication number | Publication date |
---|---|
CN107150343B (en) | 2019-07-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107009357A (en) | A kind of method that object is captured based on NAO robots | |
CN107901041B (en) | Robot vision servo control method based on image mixing moment | |
CN112070818A (en) | Robot disordered grabbing method and system based on machine vision and storage medium | |
CN108637435A (en) | A kind of three-dimensional seam tracking system and method for view-based access control model and arc voltage sensing | |
KR101618030B1 (en) | Method for Recognizing Position and Controlling Movement of a Mobile Robot, and the Mobile Robot Using the same | |
CN108171748A (en) | A kind of visual identity of object manipulator intelligent grabbing application and localization method | |
CN104184932B (en) | Ball machine control method and device | |
CN112079154B (en) | Paper-plastic composite bag differential speed deviation rectifying method and system based on visual positioning | |
CN100393486C (en) | Method and apparatus for quick tracing based on object surface color | |
CN102096927A (en) | Target tracking method of independent forestry robot | |
CN111784655B (en) | Underwater robot recycling and positioning method | |
CN110509273A (en) | The robot mechanical arm of view-based access control model deep learning feature detects and grasping means | |
CN108803591A (en) | A kind of ground drawing generating method and robot | |
CN108597009A (en) | A method of objective detection is carried out based on direction angle information | |
CN108304001A (en) | A kind of Face datection tracking, ball machine head rotation control method and ball machine | |
CN108098134A (en) | A kind of new pattern laser vision weld joint tracking system and method | |
CN107336251A (en) | A kind of control method and system of robot queue | |
KR101901588B1 (en) | Object recognition method, descriptor generating method for object recognition, descriptor generating apparatus for object recognition | |
CN109164802A (en) | A kind of robot maze traveling method, device and robot | |
CN107055331A (en) | Container guides system to case | |
Hadviger et al. | Feature-based event stereo visual odometry | |
Kumar et al. | Markov random field based small obstacle discovery over images | |
CN107729906A (en) | A kind of inspection point ammeter technique for partitioning based on intelligent robot | |
CN107030690A (en) | A kind of mechanical arm barrier-avoiding method of view-based access control model | |
CN113689365A (en) | Target tracking and positioning method based on Azure Kinect |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for 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 |
Granted publication date: 20190723 Termination date: 20200405 |
|
CF01 | Termination of patent right due to non-payment of annual fee |