CN109079788A - A kind of playing chess method and anthropomorphic robot based on anthropomorphic robot - Google Patents
A kind of playing chess method and anthropomorphic robot based on anthropomorphic robot Download PDFInfo
- Publication number
- CN109079788A CN109079788A CN201810961056.1A CN201810961056A CN109079788A CN 109079788 A CN109079788 A CN 109079788A CN 201810961056 A CN201810961056 A CN 201810961056A CN 109079788 A CN109079788 A CN 109079788A
- Authority
- CN
- China
- Prior art keywords
- chessboard
- image
- chess
- anthropomorphic robot
- angle point
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- 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
-
- 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
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
- B25J9/161—Hardware, e.g. neural networks, fuzzy logic, interfaces, processor
-
- 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
- B25J9/1612—Programme controls characterised by the hand, wrist, grip control
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Orthopedic Medicine & Surgery (AREA)
- Manipulator (AREA)
Abstract
The invention discloses a kind of playing chess method and anthropomorphic robot based on anthropomorphic robot.Wherein, the described method includes: anthropomorphic robot carries out image procossing to the image for the chessboard that the camera obtains, obtain the location of pixels of chessboard angle point, and then according to the location of pixels of the obtained chessboard angle point, one target position is set, and then according to the target position of the setting, using monocular ranging calculation, the physical location of the chessboard angle point is calculated, and then according to the physical location of the chessboard angle point being calculated, the crawl international chess piece from chessboard is accurately controlled using kinematics to play chess to the target position of chessboard.It plays chess by the above-mentioned means, can be realized anthropomorphic robot and can grab international chess piece from chessboard automatically to the designated position of chessboard.
Description
Technical field
The present invention relates to anthropomorphic robot technical field more particularly to a kind of playing chess based on anthropomorphic robot
Method and anthropomorphic robot.
Background technique
2007, at home and abroad having started one research anthropomorphic robot NAO, (Aldebaran Robotics company developed
A artificial intelligence robot) upsurge, the appearance of anthropomorphic robot NAO becomes standard platform instead of Sony's robot dog.
In anthropomorphic robot field, American-European some colleges and universities are in study frontier, and many other scholars learn him in succession
Algorithm and creative thinking.The research angle of scholars is various, and some scholars focus on research algorithm, such as image is known
Not, location algorithm, speech processes etc., other scholars are keen to study the exercise bionics of anthropomorphic robot, many to grind
Study carefully to take in competition, and other are then to further improve research work.
In the country of China, start to walk evening to the research in anthropomorphic robot field, until 2010, China only has less than 5
Colleges and universities or research unit have used anthropomorphic robot in the course of the research, and achievement is also less.Comparatively, Chinese science skill
Art university, Xi'an Communications University and Tongji University etc. are more forward in this respect, and wherein the Xue Feng etc. of Chinese University of Science and Technology also takes
No small achievement was obtained, he mainly studies the movement correlation engine of anthropomorphic robot.
Although the country of China starts to walk late to the research in anthropomorphic robot field, but its development speed is very swift and violent, directly
By 2013, most " 985 ", " 211 " colleges and universities carried out at home for the related scientific research work of anthropomorphic robot.Meanwhile
The country has also held many contests about anthropomorphic robot, to carry out further exchange study.In addition to this, with humanoid
The associated image procossing of device people and location algorithm field, the scholar in China also achieve many achievements, the figure including some colleges and universities
As Processing Algorithm and location algorithm.Therefore, it although although the country of China starts to walk late to the research in anthropomorphic robot field, learns
Persons and scientific research personnel are still in continuous study and exploration anthropomorphic robot.But the research approach of existing anthropomorphic robot
Also cannot achieve anthropomorphic robot can automatically from chessboard grab international chess piece play chess to chess chess
The designated position of disk.
Summary of the invention
In view of this, it is an object of the invention to propose a kind of playing chess method based on anthropomorphic robot and people
Anthropomorphic robot, can be realized anthropomorphic robot can automatically from chessboard grab international chess piece play chess to the world
The designated position of Board of chess.
According to an aspect of the present invention, a kind of playing chess method based on anthropomorphic robot is provided, comprising:
The image for the chessboard that anthropomorphic robot obtains camera carries out image procossing, obtains chess chess
The location of pixels of disk angle point;
According to the location of pixels of the obtained chessboard angle point, a target position is set;
The chessboard is calculated using monocular ranging calculation according to the target position of the setting
The physical location of angle point;
According to the physical location of the chessboard angle point being calculated, using kinematics accurately control from
International chess piece is grabbed in chessboard to play chess to the target position of chessboard.
Wherein, the anthropomorphic robot carries out image procossing to the image of the chessboard of acquisition, obtain it is international as
The location of pixels of chess chessboard angle point, comprising:
Anthropomorphic robot carries out image using open source computer vision library mode, to the image of the chessboard of acquisition
Processing, obtains the location of pixels of chessboard angle point.
Wherein, the anthropomorphic robot is using open source computer vision library mode, to the figure of the chessboard of acquisition
As carrying out image procossing, the location of pixels of chessboard angle point is obtained, comprising:
Anthropomorphic robot carries out gray scale using open source computer vision library mode, to the image of the chessboard of acquisition
The image procossing of conversion carries out the image procossing of Harris's Corner Detection to the image after gray scale conversion, to the warp
Image after Harris's Corner Detection carries out the image procossing of image binaryzation, and through image binaryzation, treated according to described
Image obtains the location of pixels of chessboard angle point.
Wherein, the anthropomorphic robot is calculated according to the target position of the setting using monocular ranging calculation
To the physical location of the chessboard angle point, comprising:
The anthropomorphic robot demarcates camera according to the target position of the setting, obtains the interior of camera
Outer parameter establishes the model of monocular ranging calculation, and root according to the inside and outside parameter of the obtained camera
The model that monocular ranging calculation is established according to the inside and outside parameter of the obtained camera, is calculated the state
The physical location of border Board of chess angle point.
Wherein, the physical location for the chessboard angle point that the anthropomorphic robot is calculated according to,
The crawl international chess piece from chessboard is accurately controlled using kinematics to play chess to the mesh of chessboard
Cursor position, comprising:
The physical location for the chessboard angle point that anthropomorphic robot is calculated according to, using kinematics
It accurately controls right hand level to unfold, then controls the chess piece of right hand crawl chess, then control lifts right hand arm and plays chess
To the target position of chessboard.
Wherein, the image of the chessboard obtained in the anthropomorphic robot to camera carries out image procossing, obtains
To before the location of pixels of chessboard angle point, further includes:
Anthropomorphic robot obtains the image of chessboard by way of camera camera shooting.
According to another aspect of the present invention, a kind of anthropomorphic robot is provided, comprising:
Image processing module, position setup module, corner location processing module and control module of playing chess;
The image of described image processing module, the chessboard for obtaining to camera carries out image procossing, obtains
To the location of pixels of chessboard angle point;
The position setup module, the location of pixels of the chessboard angle point for being obtained according to, setting one
A target position;
The corner location processing module, for the target position according to the setting, using monocular ranging calculation,
The physical location of the chessboard angle point is calculated;
The control module of playing chess, the actual bit for the chessboard angle point being calculated according to
It sets, the crawl international chess piece from chessboard is accurately controlled using kinematics and is played chess to described in chessboard
Target position.
Wherein, described image processing module is specifically used for:
Using open source computer vision library mode, the image of gray scale conversion is carried out to the image of the chessboard of acquisition
Processing, the image procossing of Harris's Corner Detection is carried out to the image after gray scale conversion, to described through Harris's angle point
Image after detection carries out the image procossing of image binaryzation, and is obtained according to described through image binaryzation treated image
The location of pixels of chessboard angle point.
Wherein, the corner location processing module, is specifically used for:
According to the target position of the setting, camera is demarcated, the inside and outside parameter of camera is obtained, according to described
The inside and outside parameter of obtained camera establishes the model of monocular ranging calculation, and according to the obtained camera shooting
The inside and outside parameter of head establishes the model of monocular ranging calculation, and the chessboard angle point is calculated
Physical location.
Wherein, the anthropomorphic robot, further includes:
Camera, for obtaining the image of chessboard by way of camera shooting.
It can be found that above scheme, the chessboard angle point that anthropomorphic robot can be calculated according to this
Physical location accurately controls the crawl international chess piece from chessboard using kinematics and plays chess to chessboard
The target position, can be realized anthropomorphic robot can automatically from chessboard grab international chess piece play chess to
The designated position of chessboard.
Further, above scheme, anthropomorphic robot can mark camera according to the target position of the setting
It is fixed, the inside and outside parameter of camera is obtained, monocular ranging calculating is established according to the inside and outside parameter of the obtained camera
The model of mode, and the model of monocular ranging calculation is established according to the inside and outside parameter of the obtained camera,
The physical location of the chessboard angle point is calculated, can be realized the chess chess being calculated compared with high-accuracy
The physical location of disk angle point.
Further, above scheme, anthropomorphic robot can be accurately controlled using kinematics and be grabbed from chessboard
It takes international chess piece to play chess to the target position of chessboard, it is accurate by kinematics to can be realized anthropomorphic robot
Control the operation of playing chess of chess.
Further, above scheme, since the structure of the two or more anthropomorphic robots played chess of playing chess is substantially the same,
Therefore it only needs to control good time interval, avoiding two or more anthropomorphic robots from moving simultaneously leads to collision, base
This thinking is identical with the operation that separate unit anthropomorphic robot executes playing chess, can be realized two or more anthropomorphic robots
Execute the operation of operation of playing chess to play chess of chess, two or more anthropomorphic robots lower game system of playing chess can be defined as two
Platform or more the anthropomorphic robots sequentially system to complete specified step of playing chess under common operating environment.
Further, above scheme, anthropomorphic robot can obtain chessboard by way of camera camera shooting
Image can be realized the acquisition to the image of chessboard
Detailed description of the invention
Fig. 1 is the flow diagram of one embodiment of playing chess method the present invention is based on anthropomorphic robot;
Fig. 2 is that anthropomorphic robot use is opened in one embodiment of playing chess method the present invention is based on anthropomorphic robot
Source computer visual manner carries out a citing of the image processing process of Harris's Corner Detection to the image after gray scale conversion
Schematic diagram;
Fig. 3 is that anthropomorphic robot use is opened in one embodiment of playing chess method the present invention is based on anthropomorphic robot
Source computer visual manner carries out one action of the image processing process of image binaryzation to the image after Harris's Corner Detection
It illustrates and is intended to;
Fig. 4 is the original of monocular location algorithm in one embodiment of playing chess method the present invention is based on anthropomorphic robot
Manage schematic diagram;
Fig. 5 is one action of pixel coordinate system in one embodiment of playing chess method the present invention is based on anthropomorphic robot
It illustrates and is intended to;
Fig. 6 is image coordinate system and pixel in one embodiment of playing chess method the present invention is based on anthropomorphic robot
One example schematic of coordinate system relationship signal;
Fig. 7 is one of camera coordinate system in one embodiment of playing chess method the present invention is based on anthropomorphic robot
Example schematic;
Fig. 8 is to demarcate in one embodiment of playing chess method the present invention is based on anthropomorphic robot to camera
An example schematic;
Fig. 9 is the benefit of monocular location algorithm in one embodiment of playing chess method the present invention is based on anthropomorphic robot
Repay an example schematic of algorithm;
Figure 10 is monocular location algorithm in one embodiment of playing chess method the present invention is based on anthropomorphic robot
Another example schematic of backoff algorithm;
Figure 11 is chessboard in one embodiment of playing chess method the present invention is based on anthropomorphic robot
One example schematic;
Figure 12 is that double anthropomorphic robot is held in one embodiment of playing chess method the present invention is based on anthropomorphic robot
One example schematic of the operation of playing chess to play chess of row chess;
Figure 13 is the flow diagram of another embodiment of playing chess method the present invention is based on anthropomorphic robot;
Figure 14 is the structural schematic diagram of one embodiment of the present inventor's anthropomorphic robot;
Figure 15 is the structural schematic diagram of another embodiment of the present inventor's anthropomorphic robot;
Figure 16 is the structural schematic diagram of the another embodiment of the present inventor's anthropomorphic robot.
Specific embodiment
With reference to the accompanying drawings and examples, the present invention is described in further detail.It is emphasized that following implement
Example is merely to illustrate the present invention, but is not defined to the scope of the present invention.Likewise, following embodiment is only portion of the invention
Point embodiment and not all embodiments, institute obtained by those of ordinary skill in the art without making creative efforts
There are other embodiments, shall fall within the protection scope of the present invention.
The present invention provides a kind of playing chess method based on anthropomorphic robot, and can be realized anthropomorphic robot can
Automatically international chess piece is grabbed from chessboard to play chess to the designated position of chessboard.
Referring to Figure 1, Fig. 1 is that the process of one embodiment of playing chess method the present invention is based on anthropomorphic robot is shown
It is intended to.It is noted that if having substantially the same as a result, method of the invention is not limited with process sequence shown in FIG. 1.
As shown in Figure 1, this method comprises the following steps:
S101: anthropomorphic robot carries out image procossing to the image for the chessboard that camera obtains, and obtains the world
The location of pixels of Board of chess angle point.
Wherein, the image of the chessboard obtained in the anthropomorphic robot to camera carries out image procossing, obtains
Before the location of pixels of chessboard angle point, can also include:
Anthropomorphic robot obtains the image of chessboard by way of camera camera shooting.
Wherein, which carries out image procossing to the image of the chessboard of acquisition, obtains chess
The location of pixels of chessboard angle point may include:
Anthropomorphic robot is using OpenCV (Open Source Computer Vision Library, open source computer view
Feel library) mode, image procossing is carried out to the image of the chessboard of acquisition, obtains the pixel position of chessboard angle point
It sets.
Wherein, anthropomorphic robot is using open source computer vision library OpenCV mode, to the chessboard of acquisition
Image carries out image procossing, obtains the location of pixels of chessboard angle point, may include:
Anthropomorphic robot using open source computer vision library OpenCV mode, to the image of the chessboard of acquisition into
The image procossing of row gray scale conversion carries out at the image of Harris (Harris) Corner Detection the image after gray scale conversion
Reason carries out the image procossing of image binaryzation to the image after Harris's Corner Detection, and according to this through image binaryzation
Treated image, obtains the location of pixels of chessboard angle point.
In the present embodiment, the anthropomorphic robot is using open source computer vision library OpenCV mode, to the world of acquisition
The image of Board of chess carries out the image procossing of gray scale conversion, may include:
Increasing income, (call the turn one of machine word is for reading in image file by the IMREAD of computer vision library OpenCV
Data function) the various dynamics of function support, static image file format, the file format that homologous ray is supported is different, but all
It supports BMP (image file format) format, usually also supports PNG (Portable Network Graphics, portable network
Figure), JPEG (Joint Photographic Experts Group, Joint Photographic Experts Group) and TIFF (Tag Image
File Format, label image file format) format etc., the present embodiment is then utilized by taking image JPG format as an example
Cv2.cvtColor (color space conversion function) function changes image dress into BGR (Blue-Green-Red, Blue-Green-
Red three colors) format, each pixel is indicated by a three-number set, and each Integer (shaping) vector respectively indicates
One channel Blue, Green and Red, other color spaces such as HSV (Hue, Saturation, Value, color model) also with
Same mode indicates pixel, and only value range and number of active lanes are different, such as the chromatic value range of HSV color space is
0-180。
It should be noted that being a kind of YUV422 (color coding mode) image pane provided by anthropomorphic robot itself
Formula, this color space is not common, and YUV is the color coding mode that eurovision uses, and the value range of Y is in digital value 0-
255, indicate brightness, the value range of U indicates coloration, the value range of V is in digital value 0-255, table in digital value 0-255
Showing concentration, Y and other the two are to separate in YUV color space, and the sample rate of coloration is low than luma samples rate, and it
Advantage is that picture quality will not be decreased obviously, and the prototype of YUV is from RGB (Red-Green-Blue, red-green-blue
Three colors) model, it can mutually be converted by formula.
Fig. 2 is referred to, Fig. 2 is humanoid in one embodiment of playing chess method the present invention is based on anthropomorphic robot
Device people carries out the image procossing mistake of Harris's Corner Detection using open source computer vision mode to the image after gray scale conversion
One example schematic of journey.As shown in Fig. 2, the anthropomorphic robot uses open source computer vision mode, to this through gray scale conversion
Image afterwards carries out the image procossing of Harris's Corner Detection, may include:
Characteristic point detection is widely used in object matching, the application such as target following and three-dimensional reconstruction, when Target Modeling, from the warp
Extracting target from images feature after gray scale conversion, common function include color, angle point, characteristic point, profile and texture etc.;It breathes out
In this Corner Detection be characteristic point detection basis, propose that the concept of the gray scale difference value using adjacent pixel determines that it is angle
Point, edge or smooth region;The principle of Harris's Corner Detection is the gray-value variation calculated in image using moving window;
Critical workflow includes being converted to gray level image, calculating difference image, Gaussian smoothing, calculate local extremum and determine angle point etc.;Angle
The principle of point derives from the perception of mankind's angle steel joint, that is to say, that significant variation can occur for the gray value in each direction of image;
The core of the algorithm is to carry out mobile image using native window, to determine that gray level has occurred that great changes;Therefore, the window
Mouth is used to calculate the grey scale change of image, such as: [- 1,0,1;- 1,0,1;- 1,0,1], [- 1, -1, -1;0,0,0;1,1,1];
The wicket of this function is moved along all directions;As shown in Fig. 2, the gray scale of window inner region has changed a lot, it is believed that
Corner point is encountered inside window, the gray level of the image in window does not change, and does not have corner in window;If window is at certain
It is moved on a direction, the gray level of image changes very greatly in window, and does not change in some directions, the image in window
It may be straightway.
Fig. 3 is referred to, Fig. 3 is humanoid in one embodiment of playing chess method the present invention is based on anthropomorphic robot
Device people carries out the image procossing of image binaryzation using open source computer vision mode to the image after Harris's Corner Detection
One example schematic of process.As shown in figure 3, the anthropomorphic robot uses open source computer vision mode, to this through Harris
Image after Corner Detection carries out the image procossing of image binaryzation, obtains the location of pixels of chessboard angle point, can be with
Include:
The binaryzation of image is to set the gray value of the point on image to 0 or 255, i.e. whole image is presented clearly black
White effect, that is to say, that select 256 intensity level gray level images to obtain two dimensional image by threshold value appropriate, still may be used
To reflect the general image and local feature of image;In Digital Image Processing, bianry image occupies very important position,
Especially in actual image procossing, there are many systems being made of binary Images Processing, the processing of binary picture and
Analysis should be first carried out;Binaryzation gray level image is to obtain binary image, in this way, scheming when image is further processed
The aggregate attribute of picture is only related with the position of pixel that pixel value is 0 or 255;The pixel does not further relate to, and class value becomes processing
It obtains simply, also very little is determined to obtain perfect bianry image commonly using closure and fillet for data processing and compression
Adopted Non-overlapping Domain;The all pixels that its gray level is greater than or equal to threshold value are confirmed as belonging to special object and have 255
Gray value;Otherwise, these pixels are excluded except subject area and have gray value 0, indicate background or special object
Region;If an interior of articles has unified background with unified gray value and with other gray values, can make
Compare segmentation effect with threshold method to obtain;If it is for example different that the difference between object and background is not reflected in gray value
In texture, then this difference characteristic can be converted to gray difference, then image is split using threshold value selection technique, moved
State adjusts threshold value to realize the particular result of its segmented image of bianry image dynamic observation;Therefore, available chess
The location of pixels of chessboard angle point.
S102: a target position is arranged according to the location of pixels of the obtained chessboard angle point in anthropomorphic robot
It sets.
S103: the state is calculated using monocular ranging calculation according to the target position of the setting in anthropomorphic robot
The physical location of border Board of chess angle point.
Wherein, which is calculated this using monocular ranging calculation according to the target position of the setting
The physical location of chessboard angle point may include:
The anthropomorphic robot demarcates camera according to the target position of the setting, obtains the inside and outside ginseng of camera
Number, the model of monocular ranging calculation is established according to the inside and outside parameter of the obtained camera, and obtain according to this
To the inside and outside parameter of camera establish the model of monocular ranging calculation, the chessboard is calculated
The physical location of angle point.
In the present embodiment, binocular location algorithm, which is two, has the camera at repetition visual angle to shoot within a time, by
It is different in the spatial position of two cameras, obtained image can be corrected and be converted, identified in two images
Specified target, respectively obtains corresponding parameter, the reality of anthropomorphic robot and target position is calculated finally by mathematical derivation
Distance;The application condition of binocular location algorithm is small, but difficulty in computation is bigger, and for anthropomorphic robot, due to two
Overlapping area between camera is almost without causing binocular ranging difficulty very big.Therefore, preferential in the present embodiment to use
Monocular location algorithm.
Fig. 4 is referred to, Fig. 4 is that monocular is surveyed in one embodiment of playing chess method the present invention is based on anthropomorphic robot
Schematic illustration away from algorithm.As shown in figure 4, x, y are the relative position information of camera, f is the focus information of camera, letter
Single says, exactly seeks middle distance Z by two similar triangles, but finds that so error done can compare in practical calculating
Greatly, ranging model is established at this moment to obtain more accurate distance measurement result;In the present embodiment, by being taken the photograph to anthropomorphic robot
As head progress Zhang Zhengyou algorithm calibration, the inner parameter and external parameter of camera are obtained, it is empty to obtain two dimension in this way
Between image and three-dimension space image conversion.
In the present embodiment, the essence camera of anthropomorphic robot demarcated be exactly establish three-dimensional coordinate image and
Relationship between two dimensional image coordinate can be crossed as long as this relationship can establish and seek middle three-dimensional information by two dimensional image,
In the coordinate system that is related to have pixel coordinate system, image coordinate system, world coordinate system, camera coordinates system, carry out related seat below
Mark the description and interpretation of system.
Fig. 5 is referred to, Fig. 5 is that pixel is sat in one embodiment of playing chess method the present invention is based on anthropomorphic robot
Mark an example schematic of system.As shown in figure 5, it is figure respectively that the origin of pixel coordinate system u-v, which is O0, abscissa u and ordinate v,
As the row and column at place, in open source computer vision library OpenCV, u corresponds to x, and v corresponds to y, the unit of abscissa and ordinate
It is image pixel.
Fig. 6 is referred to, Fig. 6 is that image is sat in one embodiment of playing chess method the present invention is based on anthropomorphic robot
One example schematic of the system and pixel coordinate system relationship of marking signal.As shown in fig. 6, the origin of image coordinate system x-y is O1, it is picture
The midpoint of plain coordinate system, it is assumed that (u0, v0) represents coordinate of the O1 under u-v coordinate system, and dx and dy respectively indicate each pixel and exist
The physical size of horizontal axis x and longitudinal axis y.
Fig. 7 is referred to, Fig. 7 is camera in one embodiment of playing chess method the present invention is based on anthropomorphic robot
One example schematic of coordinate system.As shown in fig. 7, O is the optical center of camera, Zc is that the optical axis of camera and the plane of delineation hang down
Directly, OO1 is the focal length of camera.
In the present embodiment, it may be incorporated into world coordinate system, world coordinate system is the position in order to describe camera
And introduce, the rotation of any dimension can be expressed as the product of coordinate vector Yu suitable square matrix, and translation vector is first seat
The offset for marking origin and second coordinate origin, under world coordinate system, there are three important parameters: spin matrix R, translation
Vector T and projection matrix M, spin matrix R is only related to the internal structure of camera itself to translation vector T, so these are joined
Number is known as the inner parameter of camera;The internal structure of projection matrix M and camera itself is not related, therefore projection matrix M
It is the external parameter of camera, this process for obtaining the inner parameter and external parameter is called to the calibration of camera.
Fig. 8 is referred to, Fig. 8 is in one embodiment of playing chess method the present invention is based on anthropomorphic robot to camera shooting
The example schematic that head is demarcated.As shown in figure 8, shooting obtains by adjusting the different shooting angles of camera
Then the photo of the scaling board of different directions obtains corresponding angle point with correlated characteristic point function from image, to obtain camera shooting
The inner parameter and external parameter of head.As shown in figure 8, can be generally designated by minimum 6 known points come solution matrix,
Tens known points can be obtained on scaling board, the number of unknown number is far smaller than equation number, in the present embodiment using most
Small square law reduces bring error.
After the chessboard of adjustment calibration and the relative position of anthropomorphic robot, the camera shooting of anthropomorphic robot is used
Head shoots the chessboard of the chess of the calibration, and shooting obtains the image of different angle, and then therefrom selection is predetermined opens
For several images such as 10 images as calibration maps, the similarity of the image is smaller;By the calibration mode above to camera it
Afterwards, the inner parameter and external parameter of camera have successfully been got.
In the present embodiment, due in practical operation may focal length f for camera obtain that there are bigger mistakes
Difference, secondly, the primary optical axis of camera is not fully horizontal, and for convenience's sake, so in the present embodiment, it is preferential to select
Select the calculation of another similar compensation monocular ranging.
Fig. 9 and Figure 10 are referred to, Fig. 9 is in one embodiment of playing chess method the present invention is based on anthropomorphic robot
One example schematic of the backoff algorithm of monocular location algorithm, Figure 10 are the playing chess the present invention is based on anthropomorphic robot
Another example schematic of the backoff algorithm of monocular location algorithm in one embodiment of method.As shown in Figure 9 and Figure 10, oblique dotted line is
The primary optical axis of camera, the angle with level ground are b, and the visual angle boundary inclusion region of camera is two except above-mentioned oblique dotted line
The region that dotted line includes, area size is, for example, 47.64 °, and H is the height of anthropomorphic robot, by image recognition, can be obtained
To the approximate pixel coordinate (x, y) of target position, and image total size is 640*480, this mode is mainly according in image
The ratio of angle and the ratio of length are approximately equal, and the size of the angle of a can be obtained, and anthropomorphic robot head may also bow
Degree is faced upward, m (not marking in image) is set as, can be obtained by target position through the above way relative to robot trunk
Distance.
S104: anthropomorphic robot is according to the physical location of the chessboard angle point being calculated, using movement
Accurately control the crawl international chess piece from chessboard and play chess to the target position of chessboard.
Wherein, the anthropomorphic robot is according to the physical location of the chessboard angle point being calculated, using fortune
Dynamic accurately controls the crawl international chess piece from chessboard and plays chess to the target position of chessboard, can
To include:
Anthropomorphic robot is accurate using kinematics according to the physical location of the chessboard angle point being calculated
Control right hand level is unfolded, and then controls the chess piece of right hand crawl chess, then control lifts right hand arm and plays chess to state
The target position of border Board of chess.
In the present embodiment, a kind of Webots (emulation platform of the anthropomorphic robot) analog platform of anthropomorphic robot allows
The simulation anthropomorphic robot moved in virtual world, Webots can be provided in one before the true anthropomorphic robot of test
Simulate the analog platform of the safe and convenient of virtual anthropomorphic robot.
In the present embodiment, Webots version 7 is used exclusively for the particular version of simulation anthropomorphic robot, in its platform
It is middle that the simulated experiment of many effective controllers and the anthropomorphic robot defined in advance can be provided, comprising:
Step 1: starting dummy robot, select file > openings file and select positioned at [Webots catalogue]
Projects robots nao file nao.wbt in worlds;
Step 2: Choregraphe is connected to simulation anthropomorphic robot, start Choregraphe and is alternatively coupled to
Or click connection button;
Step 3: testing the behavior of anthropomorphic robot in webots;
Guarantee that computer has been successfully connected to anthropomorphic robot first, then the program finished writing importing is entered, allows people
Anthropomorphic robot executes corresponding actions, wherein it should be noted that anthropomorphic robot will ensure that rigidity has been switched on, otherwise can lead
Cause action failure.
In the present embodiment, the process of real anthropomorphic robot is connected to by Webots, comprising:
Step 1: opening Choregraphe;
Step 2: being connected to fixing end slogan 9559 and IP (Internet Protocol, the agreement interconnected between network)
Address connection for example, 192.168.10.106;
Step 3: closing autonomous mode, stand up (standing) module is constructed, control anthropomorphic robot is stood.
1, Figure 11 is international in one embodiment of playing chess method the present invention is based on anthropomorphic robot referring to Figure 1
One example schematic of Board of chess.As shown in figure 11, anthropomorphic robot can call camera to obtain chess first
Then chessboard picture obtains the location of pixels of angle point, then the position of practical angle point is obtained by monocular location algorithm, due to each
The size of grid is fixed, as long as therefore obtaining the position of 1 angle point and can be obtained by the physical location of possessive case subcenter.
In the present embodiment, the anthropomorphic robot is according to the actual bit of the chessboard angle point being calculated
It sets, the crawl international chess piece from chessboard is accurately controlled using kinematics and is played chess to the mesh of chessboard
Cursor position may include:
Step 1: the right hand level of control humanoid robot is unfolded, it is ensured that the right hand arm Bu Bei of anthropomorphic robot is international
The chessboard of Chinese chess is encountered, and the movement of anthropomorphic robot is influenced;
Step 2: the right hand of control anthropomorphic robot grabs chess piece, wherein the radian value of right finger joint needs son
Otherwise fine control may cause crawl failure this is because the scrambling of chess causes;
Step 3: control anthropomorphic robot lifts right hand arm, wherein it needs to control the height lifted, this is because if
Raising height is excessively high, may result in chess piece and falls, and leads to procedure failure of playing chess;
Step 4: control anthropomorphic robot executes the movement played chess, wherein which lower position can be adjusted as needed
Section, however since the size of chess piece is substantially equivalent to the size of checker-wise, along with the slightly error of algorithm, may lead
Chess piece fraction is caused to fall in other positions, but most of region of chess piece can fall in designated position.
In the present embodiment, the design of operation of playing chess to play chess that double anthropomorphic robot executes chess can also be set,
Double anthropomorphic robot lower game system of playing chess can be defined as two anthropomorphic robots under common operating environment sequentially
Come the system for completing specified step of playing chess.
2, Figure 12 is double in one embodiment of playing chess method the present invention is based on anthropomorphic robot referring to Figure 1
Anthropomorphic robot executes an example schematic of the operation of playing chess to play chess of chess.As shown in figure 12, since two are played chess to play chess
The structure of anthropomorphic robot be substantially the same, therefore only need to control good time interval, avoid two anthropomorphic robots
Movement simultaneously leads to collision, and basic ideas are identical with the operation that above-mentioned separate unit anthropomorphic robot executes playing chess.
It can be found that in the present embodiment, the chessboard angle that anthropomorphic robot can be calculated according to this
The physical location of point accurately controls the crawl international chess piece from chessboard using kinematics and plays chess to chess
The target position of chessboard, can be realized anthropomorphic robot can grab under international chess piece from chessboard automatically
Chess is to the designated position of chessboard.
Further, in the present embodiment, anthropomorphic robot can carry out camera according to the target position of the setting
Calibration, obtains the inside and outside parameter of camera, monocular range-viewfinder is established according to the inside and outside parameter of the obtained camera
The model of calculation mode, and establish according to the inside and outside parameter of the obtained camera mould of monocular ranging calculation
The physical location of the chessboard angle point is calculated in type, can be realized be calculated the world compared with high-accuracy as
The physical location of chess chessboard angle point.
Further, in the present embodiment, anthropomorphic robot can be accurately controlled using kinematics from chessboard
Middle crawl international chess piece is played chess to the target position of chessboard, be can be realized anthropomorphic robot and is passed through kinematics
Accurately control the operation of playing chess of chess.
Further, in the present embodiment, since the structure of the two or more anthropomorphic robots played chess of playing chess is all basic
It is identical, therefore only need to control good time interval, it avoids two or more anthropomorphic robots while movement leads to collision i.e.
Can, the operation that basic ideas and separate unit anthropomorphic robot execute playing chess is identical, can be realized two or more it is humanoid
Robot executes the operation of operation of playing chess to play chess of chess, and two or more anthropomorphic robots lower game system of playing chess can be determined
Justice sequentially system to complete specified step of playing chess under common operating environment for two or more anthropomorphic robots.
3, Figure 13 is the stream of another embodiment of playing chess method the present invention is based on anthropomorphic robot referring to Figure 1
Journey schematic diagram.In the present embodiment, method includes the following steps:
S1301: anthropomorphic robot obtains the image of chessboard by way of camera camera shooting.
S1302: anthropomorphic robot carries out image procossing to the image for the chessboard that the camera obtains, and obtains state
The location of pixels of border Board of chess angle point.
Can be as above described in S101, therefore not to repeat here.
S1303: a target position is arranged according to the location of pixels of the obtained chessboard angle point in anthropomorphic robot
It sets.
S1304: this is calculated using monocular ranging calculation according to the target position of the setting in anthropomorphic robot
The physical location of chessboard angle point.
Can be as above described in S103, therefore not to repeat here.
S1305: anthropomorphic robot is according to the physical location of the chessboard angle point being calculated, using movement
Accurately control the crawl international chess piece from chessboard and play chess to the target position of chessboard.
Can be as above described in S103, therefore not to repeat here.
It can be found that in the present embodiment, anthropomorphic robot can obtain chess chess by way of camera camera shooting
The image of disk can be realized the acquisition to the image of chessboard.
The present invention also provides a kind of anthropomorphic robots, and can be realized anthropomorphic robot can be automatically from chessboard
Crawl international chess piece is played chess to the designated position of chessboard.
Figure 14 is please referred to, Figure 14 is the structural schematic diagram of one embodiment of the present inventor's anthropomorphic robot.In the present embodiment, the people
Anthropomorphic robot 140 is the anthropomorphic robot in above-described embodiment, which includes image processing module 141, position
Setup module 142, corner location processing module 143, control module of playing chess 144.
The image of the image processing module 141, the chessboard for obtaining to camera carries out image procossing, obtains
To the location of pixels of chessboard angle point.
The position setup module 142, the location of pixels of the chessboard angle point for being obtained according to this are arranged one
Target position.
The corner location processing module 143, for the target position according to the setting, using monocular ranging calculation,
The physical location of the chessboard angle point is calculated.
The control module 144 of playing chess is adopted for the physical location according to the chessboard angle point being calculated
The crawl international chess piece from chessboard is accurately controlled with kinematics to play chess to the target position of chessboard
It sets.
Optionally, the image processing module 141, can be specifically used for:
Using open source computer vision library mode, image procossing is carried out to the image of the chessboard of acquisition, is obtained
The location of pixels of chessboard angle point.
Optionally, the image processing module 141, can be specifically used for:
Using open source computer vision library mode, the image of gray scale conversion is carried out to the image of the chessboard of acquisition
Processing, the image procossing of Harris's Corner Detection is carried out to the image after gray scale conversion, to this through Harris's Corner Detection
Rear image carries out the image procossing of image binaryzation, and according to this through image binaryzation treated image, obtain it is international as
The location of pixels of chess chessboard angle point.
Optionally, the corner location processing module 143, can be specifically used for:
According to the target position of the setting, camera is demarcated, the inside and outside parameter of camera is obtained, is obtained according to this
The inside and outside parameter of camera establish the model of monocular ranging calculation, and according in the obtained camera
Portion and external parameter establish the model of monocular ranging calculation, and the actual bit of the chessboard angle point is calculated
It sets.
Optionally, the control module 144 of playing chess, can be specifically used for:
According to the physical location of the chessboard angle point being calculated, right hand water is accurately controlled using kinematics
It is flat to unfold, the chess piece of right hand crawl chess is then controlled, then control lifts right hand arm and plays chess to chessboard
The target position.
5, Figure 15 is the structural schematic diagram of another embodiment of the present inventor's anthropomorphic robot referring to Figure 1.It is real to be different from one
Example is applied, anthropomorphic robot 150 described in the present embodiment further include: camera 151.
The camera 151, for obtaining the image of chessboard by way of camera shooting.
Each unit module of the anthropomorphic robot 140/150 can execute respectively corresponds to step in above method embodiment,
Therefore each unit module is not repeated herein, refer to the explanation of the above corresponding step.
6, Figure 16 is the structural schematic diagram of the another embodiment of the present inventor's anthropomorphic robot referring to Figure 1.The anthropomorphic robot
Each unit module can execute respectively and correspond to step in above method embodiment.Related content refers in the above method
It is described in detail, it is no longer superfluous herein to chat.
In the present embodiment, which includes: processor 161, the memory coupled with processor 161 162, setting
Device 163 and controller 164.
The processor 161, for obtaining the image of chessboard by way of camera shooting.
The processor 161 is also used to carry out image procossing to the image of the chessboard of the acquisition, obtain it is international as
The location of pixels of chess chessboard angle point.
The memory 162, the instruction etc. executed for storage program area and the processor 161.
A target position is arranged in the setter 163, the location of pixels of the chessboard angle point for being obtained according to this
It sets.
The processor 161, is also used to the target position according to the setting, using monocular ranging calculation, is calculated
The physical location of the chessboard angle point.
The controller 164, for the physical location according to the chessboard angle point being calculated, using movement
Accurately control the crawl international chess piece from chessboard and play chess to the target position of chessboard.
Optionally, the processor 161, can be specifically used for:
Using open source computer vision library mode, image procossing is carried out to the image of the chessboard of acquisition, is obtained
The location of pixels of chessboard angle point.
Optionally, the processor 161, can be specifically used for:
Using open source computer vision library mode, the image of gray scale conversion is carried out to the image of the chessboard of acquisition
Processing, the image procossing of Harris's Corner Detection is carried out to the image after gray scale conversion, to this through Harris's Corner Detection
Rear image carries out the image procossing of image binaryzation, and according to this through image binaryzation treated image, obtain it is international as
The location of pixels of chess chessboard angle point.
Optionally, the setter 163, can be specifically used for:
According to the target position of the setting, camera is demarcated, the inside and outside parameter of camera is obtained, is obtained according to this
The inside and outside parameter of camera establish the model of monocular ranging calculation, and according in the obtained camera
Portion and external parameter establish the model of monocular ranging calculation, and the actual bit of the chessboard angle point is calculated
It sets.
Optionally, the controller 164, can be specifically used for:
According to the physical location of the chessboard angle point being calculated, right hand water is accurately controlled using kinematics
It is flat to unfold, the chess piece of right hand crawl chess is then controlled, then control lifts right hand arm and plays chess to chessboard
The target position.
It can be found that above scheme, the chessboard angle point that anthropomorphic robot can be calculated according to this
Physical location accurately controls the crawl international chess piece from chessboard using kinematics and plays chess to chessboard
The target position, can be realized anthropomorphic robot can automatically from chessboard grab international chess piece play chess to
The designated position of chessboard.
Further, above scheme, anthropomorphic robot can mark camera according to the target position of the setting
It is fixed, the inside and outside parameter of camera is obtained, monocular ranging calculating is established according to the inside and outside parameter of the obtained camera
The model of mode, and the model of monocular ranging calculation is established according to the inside and outside parameter of the obtained camera,
The physical location of the chessboard angle point is calculated, can be realized the chess chess being calculated compared with high-accuracy
The physical location of disk angle point.
Further, above scheme, anthropomorphic robot can be accurately controlled using kinematics and be grabbed from chessboard
It takes international chess piece to play chess to the target position of chessboard, it is accurate by kinematics to can be realized anthropomorphic robot
Control the operation of playing chess of chess.
Further, above scheme, since the structure of the two or more anthropomorphic robots played chess of playing chess is substantially the same,
Therefore it only needs to control good time interval, avoiding two or more anthropomorphic robots from moving simultaneously leads to collision, base
This thinking is identical with the operation that separate unit anthropomorphic robot executes playing chess, can be realized two or more anthropomorphic robots
Execute the operation of operation of playing chess to play chess of chess, two or more anthropomorphic robots lower game system of playing chess can be defined as two
Platform or more the anthropomorphic robots sequentially system to complete specified step of playing chess under common operating environment.
Further, above scheme, anthropomorphic robot can obtain chessboard by way of camera camera shooting
Image can be realized the acquisition to the image of chessboard.
In several embodiments provided by the present invention, it should be understood that disclosed system, device and method can
To realize by another way.For example, device embodiments described above are only schematical, for example, module or
The division of unit, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units
Or component can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, institute
Display or the mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, device or unit
Indirect coupling or communication connection can be electrical property, mechanical or other forms.
Unit may or may not be physically separated as illustrated by the separation member, shown as a unit
Component may or may not be physical unit, it can and it is in one place, or may be distributed over multiple networks
On unit.It can select some or all of unit therein according to the actual needs to realize the mesh of present embodiment scheme
's.
In addition, each functional unit in each embodiment of the present invention can integrate in one processing unit, it can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units.It is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.
It, can if integrated unit is realized in the form of SFU software functional unit and when sold or used as an independent product
To be stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention substantially or
Say that all or part of the part that contributes to existing technology or the technical solution can embody in the form of software products
Out, which is stored in a storage medium, including some instructions are used so that a computer equipment
(can be personal computer, server or the network equipment etc.) or processor (processor) execute each implementation of the present invention
The all or part of the steps of methods.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (ROM,
Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. it is various
It can store the medium of program code.
The foregoing is merely section Examples of the invention, are not intended to limit protection scope of the present invention, all utilizations
Equivalent device made by description of the invention and accompanying drawing content or equivalent process transformation are applied directly or indirectly in other correlations
Technical field, be included within the scope of the present invention.
Claims (10)
1. a kind of playing chess method based on anthropomorphic robot characterized by comprising
The image for the chessboard that anthropomorphic robot obtains camera carries out image procossing, obtains chessboard angle
The location of pixels of point;
According to the location of pixels of the obtained chessboard angle point, a target position is set;
The chessboard angle point is calculated using monocular ranging calculation according to the target position of the setting
Physical location;
According to the physical location of the chessboard angle point being calculated, accurately controlled using kinematics from the world
International chess piece is grabbed in Board of chess to play chess to the target position of chessboard.
2. the playing chess method based on anthropomorphic robot as described in claim 1, which is characterized in that the humanoid
Device people carries out image procossing to the image of the chessboard of acquisition, obtains the location of pixels of chessboard angle point, wraps
It includes:
Anthropomorphic robot carries out at image the image of the chessboard of acquisition using open source computer vision library mode
Reason, obtains the location of pixels of chessboard angle point.
3. the playing chess method based on anthropomorphic robot as claimed in claim 2, which is characterized in that the humanoid
Device people carries out image procossing using open source computer vision library mode, to the image of the chessboard of acquisition, obtains the world
The location of pixels of Board of chess angle point, comprising:
Anthropomorphic robot carries out gray scale conversion using open source computer vision library mode, to the image of the chessboard of acquisition
Image procossing, the image procossing of Harris's Corner Detection is carried out to the image after gray scale conversion, to described through Harry
Image after this Corner Detection carries out the image procossing of image binaryzation, and according to described through image binaryzation treated figure
Picture obtains the location of pixels of chessboard angle point.
4. the playing chess method based on anthropomorphic robot as described in claim 1, which is characterized in that the humanoid
The chessboard angle point is calculated using monocular ranging calculation according to the target position of the setting in device people
Physical location, comprising:
The anthropomorphic robot demarcates camera according to the target position of the setting, obtains the inside and outside ginseng of camera
Number, the model of monocular ranging calculation is established according to the inside and outside parameter of the obtained camera, and according to institute
The inside and outside parameter for the camera stated establishes the model of monocular ranging calculation, be calculated it is described it is international as
The physical location of chess chessboard angle point.
5. the playing chess method based on anthropomorphic robot as described in claim 1, which is characterized in that the humanoid
Device people is accurately controlled using kinematics from the world according to the physical location of the chessboard angle point being calculated
International chess piece is grabbed in Board of chess to play chess to the target position of chessboard, comprising:
The physical location for the chessboard angle point that anthropomorphic robot is calculated according to, it is accurate using kinematics
Control right hand level is unfolded, and then controls the chess piece of right hand crawl chess, then control lifts right hand arm and plays chess to state
The target position of border Board of chess.
6. the playing chess method based on anthropomorphic robot as described in claim 1 to 5 any one, feature exist
In, the chessboard that the anthropomorphic robot obtains camera image carry out image procossing, obtain chess
Before the location of pixels of chessboard angle point, further includes:
Anthropomorphic robot obtains the image of chessboard by way of camera camera shooting.
7. a kind of anthropomorphic robot characterized by comprising
Image processing module, position setup module, corner location processing module and control module of playing chess;
The image of described image processing module, the chessboard for obtaining to camera carries out image procossing, obtains state
The location of pixels of border Board of chess angle point;
A mesh is arranged in the position setup module, the location of pixels of the chessboard angle point for obtaining according to
Cursor position;
The corner location processing module is calculated for the target position according to the setting using monocular ranging calculation
Obtain the physical location of the chessboard angle point;
The control module of playing chess is adopted for the physical location for the chessboard angle point being calculated according to
The crawl international chess piece from chessboard is accurately controlled with kinematics to play chess to the target of chessboard
Position.
8. anthropomorphic robot as claimed in claim 7, which is characterized in that described image processing module is specifically used for:
Using open source computer vision library mode, the image of the chessboard of acquisition is carried out at the image of gray scale conversion
Reason, the image procossing of Harris's Corner Detection is carried out to the image after gray scale conversion, is examined to described through Harris's angle point
Image after survey carries out the image procossing of image binaryzation, and obtains state through image binaryzation treated image according to described
The location of pixels of border Board of chess angle point.
9. anthropomorphic robot as claimed in claim 7, which is characterized in that the corner location processing module is specifically used for:
According to the target position of the setting, camera is demarcated, obtains the inside and outside parameter of camera, is obtained according to described
The inside and outside parameter of camera establish the model of monocular ranging calculation, and according to the obtained camera
Inside and outside parameter establishes the model of monocular ranging calculation, and the reality of the chessboard angle point is calculated
Position.
10. the anthropomorphic robot as described in claim 7 to 9 any one, which is characterized in that the anthropomorphic robot also wraps
It includes:
Camera, for obtaining the image of chessboard by way of camera shooting.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810961056.1A CN109079788B (en) | 2018-08-22 | 2018-08-22 | Chess playing method based on humanoid robot and humanoid robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810961056.1A CN109079788B (en) | 2018-08-22 | 2018-08-22 | Chess playing method based on humanoid robot and humanoid robot |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109079788A true CN109079788A (en) | 2018-12-25 |
CN109079788B CN109079788B (en) | 2020-04-14 |
Family
ID=64794341
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810961056.1A Expired - Fee Related CN109079788B (en) | 2018-08-22 | 2018-08-22 | Chess playing method based on humanoid robot and humanoid robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109079788B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110238851A (en) * | 2019-06-14 | 2019-09-17 | 苏州大学 | A kind of mobile robot and its quick calibrating method and system |
CN110909727A (en) * | 2019-11-20 | 2020-03-24 | 北京工业大学 | Image recognition-based go recognition method and program interface |
CN111150992A (en) * | 2019-12-13 | 2020-05-15 | 重庆智能机器人研究院 | Chess playing device and method |
CN111590583A (en) * | 2020-05-27 | 2020-08-28 | 太原理工大学 | Intelligent chess playing method based on big data |
CN112338908A (en) * | 2019-08-09 | 2021-02-09 | 科沃斯机器人股份有限公司 | Autonomous mobile device |
TWI763181B (en) * | 2020-12-16 | 2022-05-01 | 國立東華大學 | Chess playing robot and automatic chess playing method |
TWI834153B (en) * | 2022-04-22 | 2024-03-01 | 龍華科技大學 | Method for chess playing recognition based on humanoid robot |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS57164079A (en) * | 1981-01-05 | 1982-10-08 | Karifuorunia Aaru Ando Dei Cen | Computer chess device |
CN1686681A (en) * | 2005-05-20 | 2005-10-26 | 长沙市雅礼中学 | Chess gaming robot |
CN101295403A (en) * | 2008-06-05 | 2008-10-29 | 北京中星微电子有限公司 | Equipment calibration method and system, confirmation method and system of control point corresponding relation |
CN102128617A (en) * | 2010-12-08 | 2011-07-20 | 中国科学院自动化研究所 | Vision real-time measuring method based on color code block |
CN104346829A (en) * | 2013-07-29 | 2015-02-11 | 中国农业机械化科学研究院 | Three-dimensional color reconstruction system and method based on PMD (photonic mixer device) cameras and photographing head |
-
2018
- 2018-08-22 CN CN201810961056.1A patent/CN109079788B/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS57164079A (en) * | 1981-01-05 | 1982-10-08 | Karifuorunia Aaru Ando Dei Cen | Computer chess device |
CN1686681A (en) * | 2005-05-20 | 2005-10-26 | 长沙市雅礼中学 | Chess gaming robot |
CN101295403A (en) * | 2008-06-05 | 2008-10-29 | 北京中星微电子有限公司 | Equipment calibration method and system, confirmation method and system of control point corresponding relation |
CN102128617A (en) * | 2010-12-08 | 2011-07-20 | 中国科学院自动化研究所 | Vision real-time measuring method based on color code block |
CN104346829A (en) * | 2013-07-29 | 2015-02-11 | 中国农业机械化科学研究院 | Three-dimensional color reconstruction system and method based on PMD (photonic mixer device) cameras and photographing head |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110238851A (en) * | 2019-06-14 | 2019-09-17 | 苏州大学 | A kind of mobile robot and its quick calibrating method and system |
CN112338908A (en) * | 2019-08-09 | 2021-02-09 | 科沃斯机器人股份有限公司 | Autonomous mobile device |
CN110909727A (en) * | 2019-11-20 | 2020-03-24 | 北京工业大学 | Image recognition-based go recognition method and program interface |
CN111150992A (en) * | 2019-12-13 | 2020-05-15 | 重庆智能机器人研究院 | Chess playing device and method |
CN111150992B (en) * | 2019-12-13 | 2023-12-29 | 重庆智能机器人研究院 | Chess playing device and method |
CN111590583A (en) * | 2020-05-27 | 2020-08-28 | 太原理工大学 | Intelligent chess playing method based on big data |
TWI763181B (en) * | 2020-12-16 | 2022-05-01 | 國立東華大學 | Chess playing robot and automatic chess playing method |
TWI834153B (en) * | 2022-04-22 | 2024-03-01 | 龍華科技大學 | Method for chess playing recognition based on humanoid robot |
Also Published As
Publication number | Publication date |
---|---|
CN109079788B (en) | 2020-04-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109079788A (en) | A kind of playing chess method and anthropomorphic robot based on anthropomorphic robot | |
CN111738261B (en) | Single-image robot unordered target grabbing method based on pose estimation and correction | |
CN112150575B (en) | Scene data acquisition method, model training method and device and computer equipment | |
CN110084304B (en) | Target detection method based on synthetic data set | |
US9595108B2 (en) | System and method for object extraction | |
CN111126304A (en) | Augmented reality navigation method based on indoor natural scene image deep learning | |
CN109558832A (en) | A kind of human body attitude detection method, device, equipment and storage medium | |
CN108830150A (en) | One kind being based on 3 D human body Attitude estimation method and device | |
CN106355147A (en) | Acquiring method and detecting method of live face head pose detection regression apparatus | |
CN108510583A (en) | The generation method of facial image and the generating means of facial image | |
CN109045676B (en) | Chinese chess recognition learning algorithm and robot intelligent system and method based on algorithm | |
CN108154551A (en) | The method and system of real-time dynamic reconstruction three-dimensional (3 D) manikin | |
WO2023138062A1 (en) | Image processing method and apparatus | |
CN110399888B (en) | Weiqi judging system based on MLP neural network and computer vision | |
CN113723385B (en) | Video processing method and device and neural network training method and device | |
CN109752855A (en) | A kind of method of hot spot emitter and detection geometry hot spot | |
Manovich | The automation of sight: from photography to computer vision | |
CN104794748A (en) | Three-dimensional space map construction method based on Kinect vision technology | |
WO2021048985A1 (en) | Image processing device, image processing method, and program | |
CN112418171B (en) | Zebra fish spatial attitude and heart position estimation method based on deep learning | |
WO2020156836A1 (en) | Dense 6-dof pose object detector | |
US10885708B2 (en) | Automated costume augmentation using shape estimation | |
CN109318227B (en) | Dice-throwing method based on humanoid robot and humanoid robot | |
CN110349225A (en) | A kind of BIM model exterior contour rapid extracting method | |
CN110110603A (en) | A kind of multi-modal labiomaney method based on facial physiologic information |
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: 20200414 Termination date: 20210822 |
|
CF01 | Termination of patent right due to non-payment of annual fee |