CN108225361A - Pick up tennis path planning system and method - Google Patents
Pick up tennis path planning system and method Download PDFInfo
- Publication number
- CN108225361A CN108225361A CN201711475345.2A CN201711475345A CN108225361A CN 108225361 A CN108225361 A CN 108225361A CN 201711475345 A CN201711475345 A CN 201711475345A CN 108225361 A CN108225361 A CN 108225361A
- Authority
- CN
- China
- Prior art keywords
- coordinate
- target
- path planning
- tennis
- mesh
- 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
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides one kind and picks up tennis path planning system and method.System includes:For obtain target point absolute coordinate in real time coordinate acquiring unit, for target point absolute coordinate to be converted to mesh generation pick up the coordinate transformation unit of the mesh vertex coordinates behind ball region, for judging whether aiming spot has ball and the path planning unit of path planning is carried out according to mesh coordinate;The path planning unit includes the message processing module of processing grid vertex information by column and output point is connected to form the path for picking up course of action diameter adjustment module;Method includes:Step 1: being pre-processed to tennis location information, mesh generation is carried out to picking up ball region using gridding method, Step 2: target actual coordinate is converted to mesh coordinate, Step 3: improving "the" shape path planning.The present invention combines target actual distribution situation on tennis court, and efficient guidance machine people completes to pick up ball process.
Description
Technical field
The present invention relates to sports goods fields more particularly to one kind to pick up tennis path planning system and method.
Background technology
The blueness that tennis at present is increasingly subject to people narrows, and more and more people receive tennis training, and after training, net
Ball distribution is innumerable and disordered, in order to mitigate the burden of sportsman, occurs various picking up tennis robot in the market.
Innumerable and disordered situation is distributed for this tennis, the cover types scanning strategy such as "the" shape and " returning " font is mesh
Preceding most commonly seen strategy, the strategy do not need to obtain target point distribution situation in advance, it is only necessary to determine then target area is pressed
According to the mode of fixed point walking, " it " word or " going back to " font cover type scanning target area are carried out, until the covering of all robots is whole
A region.The paths planning method is simple and practicable, ensures robot covering all areas, but this method efficiency is extremely low,
Suitable for small-sized place, it is not suitable for large-scale tennis court.The paths planning method does not efficiently use tennis distributed intelligence.In addition
This method is higher to the positional precision control of robot moving platform.Therefore with the development of robot technology and artificial intelligence,
This method is gradually abandoned.
At present in multi-goal path planning problem, more than the comparison of use is to improve ant group algorithm, simulated annealing
Deng according to such algorithm, presetting original state, then by successive ignition, obtain an optimal path, such algorithm is according to
Know that the coordinate of target point passes through successive ignition operation by corresponding operator, calculate optimal path, but such algorithm is to calculating
Capability Requirement is very high, and the calculating time is also different due to target distribution situation, is not suitable for the system for not carrying high-performance CPU.It should
Class method can calculate multiobjective optimization path, but for target distribution is concentrated very much on tennis court in the case of for, do not have
Good combining target distribution characteristics can not also be directed to so many target and carry out fast path calculating.
For intelligently picking up tennis robot, the path planning during ball is picked up, not only determines that the efficiency for picking up ball is same
When be also that the crucial of intelligent robot embodies.
Invention content
According to the technical issues of set forth above, and one kind is provided and picks up tennis path planning system and method.It is of the invention main
Ball region is picked up using gridding method division, target actual coordinate dress is changed to mesh coordinate, improves the steps such as "the" shape road strength planning
Suddenly, with reference to target actual distribution situation on tennis court, efficient guidance machine people completes to pick up ball process.The technology hand that the present invention uses
Section is as follows:
One kind picks up tennis path planning system, which is characterized in that the system comprises:
Coordinate acquiring unit, for obtaining target point absolute coordinate in real time;
Coordinate transformation unit, for target point absolute coordinate to be converted to the grid vertex seat after mesh generation picks up ball region
Mark;
Path planning unit, for judging whether aiming spot has ball and according to mesh coordinate progress path planning;
The path planning unit includes the message processing module of processing grid vertex information by column and by effective information
Point series connection forms the path adjustment module for picking up course of action diameter.
Further, the mesh generation, side length of element a receive ball width L with ball picking robot and meet the following formula:
Further, the coordinate transformation unit is handled target point information by the following formula, passes through rounding letter
Number, mesh vertex coordinates are converted to by target point absolute coordinate:
Xg=[Xt/a]+[(Xt/a–[Xt/a])*2];
Yg=[Yt/a]+[(Yt/a–[Yt/a])*2];
Wherein [] represents Gauss function function, (Xt,Yt) represent target point absolute coordinate, (Xg,Yg) represent that grid vertex is sat
Mark.
Further, described information processing module judges target existence by following steps:
Preserve the mesh vertex coordinates of all target points, regard grid vertex as a two-dimensional matrix G [m n], (m, n) i.e.
(Xg, Yg), G [i j] represents grid vertex nearby with the presence or absence of target, if there is target at the grid vertex of the i-th row jth row,
G [i j]=1 is then enabled, otherwise enables G [i j]=0, after obtaining all grid vertex information G [m n], handles grid vertex letter by column
Breath, step are as follows;
S1:Jth is arranged, only considers the first aim position i of this row1With the last one target location i2, i1=0, i2
=m-1;
S2:Judge G [i1J] > 0, if so, and for the first time perform, then preserve i1Value, perform S203;If so, but it is not
It performs for the first time, then performs S203;If it is not, then i1=i1+ 1, perform S203;
S3:Judge G [i2J] > 0, if so, and perform for the first time, then preserve the value of i2, perform S204;If so, but it is not
It performs for the first time, then performs S204;If it is not, then i2=i2- 1, perform S204;
S4:Judge i1< m/2, if so, performing S201;If it is not, then judge i1Or i2Whether preserve, be, exported i1
Or i2, terminate jth row flow, no, then output is sky, terminates jth row flow.
Further, adjustment module in the path judges whether there is the point of preservation and by column by the following method by preservation
Point series connection obtains "the" shape path:
If output is sky, the row currently judged are skipped;
If output is i1Or i2, it was demonstrated that when forefront only has a point, by coordinate (i1, j) or coordinate (i2, j) and it is connected in series to output
On path;
If output is i1And i2, it was demonstrated that when forefront, there are starting point i1With end point i2, first contact (i if j is even number1,
J) contact (i again2, j), otherwise first contact (i2, j) and contact (i again1,j)。
The present invention also provides one kind to pick up tennis paths planning method, and this method includes the following steps:
Step 1: being pre-processed to collected tennis location information, mesh generation is carried out to picking up ball region using gridding method;
Step 2: target actual coordinate is converted into mesh vertex coordinates;
Step 3: preserving the mesh vertex coordinates of all target points, all target points by "the" shape are connected, are picked up
Course of action diameter.
The present invention is picked up ball region, target actual coordinate is converted to mesh coordinate, improving " it " word using gridding method division
The strength planning of shape road and etc., with reference to target actual distribution situation on tennis court, efficient guidance machine people completes to pick up ball process, is based on
The above-mentioned reason present invention can be widely popularized in fields such as ball picker of tennis device people.
Description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, to embodiment or will show below
There is attached drawing needed in technology description to do simply to introduce, it should be apparent that, the accompanying drawings in the following description is this hair
Some bright embodiments, for those of ordinary skill in the art, without having to pay creative labor, can be with
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is picks up tennis path planning system module map.
Fig. 2 is picks up tennis paths planning method entire block diagram.
Fig. 3 is the geometrical relationship figure that mesh width receives ball width with ball picking robot.
Fig. 4 is that tennis is counted on specific grid vertex schematic diagram.
Fig. 5 is improves "the" shape path planning overall flow figure.
Fig. 6 is improves "the" shape path planning jth column data process chart.
Fig. 7 is improves "the" shape route programming result example.
Specific embodiment
Purpose, technical scheme and advantage to make the embodiment of the present invention are clearer, below in conjunction with the embodiment of the present invention
In attached drawing, the technical solution in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
Part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
All other embodiments obtained without making creative work shall fall within the protection scope of the present invention.
As shown in Figure 1 and Figure 2, one kind picks up tennis path planning system, the system comprises:
The coordinate acquiring unit of target point absolute coordinate is obtained in real time, target point absolute coordinate is converted into mesh generation picks up
The coordinate transformation unit of mesh vertex coordinates behind ball region judges whether aiming spot has ball and carried out according to mesh coordinate
The path planning unit of path planning;The path planning unit includes the message processing module for handling grid vertex information by column
The path for picking up course of action diameter adjustment module is formed with effective information point is connected.
After practical tennis training, tennis is distributed very intensive, about 100 target points in half of tennis court,
And it is mainly distributed on tennis field edge and two regions off the net.In order to improve ball picking-up efficiency, robot ambulation target point is reduced
Number will pick up ball region using gridding method and carry out mesh generation.
As shown in figure 3, in step 1, the mesh generation, side length of element a and ball picking robot receive ball width L meet with
Lower formula:
It can ensure no matter robot in any direction can ensure the institute that will be unified in the grid vertex by mesh point
There is target all to pick up.
After ball region progress mesh generation will be picked up, all target points is needed all to unify to closest grid vertex
On, as shown in figure 4, in step 2, all tennises in shadow region all count on the grid vertex in the region, institute
It states coordinate transformation unit to handle target point information by the following formula, by bracket function, by target point absolute coordinate
Be converted to mesh vertex coordinates:
Xg=[Xt/a]+[(Xt/a–[Xt/a])*2];
Yg=[Yt/a]+[(Yt/a–[Yt/a])*2];
Wherein [] represents Gauss function function, (Xt,Yt) represent target point absolute coordinate, (Xg,Yg) represent that grid vertex is sat
Mark.
Known all target point information all by formula are converted, obtain all grid vertex seats there are target
Mark, for calculating path.
As shown in Figure 5, Figure 6, described information processing module judges target existence by following steps:
Preserve the mesh vertex coordinates of all target points, regard grid vertex as a two-dimensional matrix G [m n], (m, n) i.e.
(Xg, Yg), G [i j] represents grid vertex nearby with the presence or absence of target, if there is target at the grid vertex of the i-th row jth row,
G [i j]=1 is then enabled, otherwise enables G [i j]=0, after obtaining all grid vertex information G [m n], handles grid vertex letter by column
Breath, step are as follows;
S1:Jth is arranged, only considers the first aim position i of this row1With the last one target location i2, i1=0, i2
=m-1,
S2:Judge G [i1J] > 0, if so, and for the first time perform, then preserve i1Value, perform S203;If so, but it is not
It performs for the first time, then performs S203;If it is not, then i1=i1+ 1, perform S203;
S3:Judge G [i2J] > 0, if so, and perform for the first time, then preserve the value of i2, perform S204;If so, but it is not
It performs for the first time, then performs S204;If it is not, then i2=i2- 1, perform S204;
S4:Judge i1< m/2, if so, performing S201;If it is not, then judge i1Or i2Whether preserve, be, exported i1
Or i2, terminate jth row flow, no, then output is sky, terminates jth row flow.
To same target point may Multiple-Scan, for jth row i1Or i2Value when performing for the first time is only preserved,
As shown in fig. 7, the path adjustment module judges whether there is the point of preservation and will preserve by column by the following method
Point connect to obtain "the" shape path:It is arranged in the case of jth,
If output is sky, the row currently judged are skipped;
If output is i1Or i2, it was demonstrated that when forefront only has a point, by coordinate (i1, j) or coordinate (i2, j) and it is connected in series to output
On path.
If output is i1And i2, it was demonstrated that when forefront, there are starting point i1With end point i2, first contact (i if j is even number1,
J) contact (i2, j) again, and otherwise first contact (i2, j) and contact (i again1,j)。
By data processing by column, each row can all export in these three results first, when all column datas processing knot
All output points according to above series connection rule are connected, form one and pick up course of action diameter by Shu Hou.The paths planning method is this hair
The improvement "the" shape paths planning method based on gridding method of bright proposition.
Finally it should be noted that:The above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations;To the greatest extent
Pipe is described in detail the present invention with reference to foregoing embodiments, it will be understood by those of ordinary skill in the art that:Its according to
Can so modify to the technical solution recorded in foregoing embodiments either to which part or all technical features into
Row equivalent replacement;And these modifications or replacement, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (6)
1. one kind picks up tennis path planning system, which is characterized in that the system comprises:
Coordinate acquiring unit, for obtaining target point absolute coordinate in real time;
Coordinate transformation unit, for target point absolute coordinate to be converted to the mesh vertex coordinates after mesh generation picks up ball region;
Path planning unit, for judging whether aiming spot has ball and according to mesh coordinate progress path planning;
The path planning unit includes the message processing module of processing grid vertex information by column and by effective information point string
Connection forms the path adjustment module for picking up course of action diameter.
2. according to claim 1 pick up tennis path planning system, which is characterized in that the mesh generation, side length of element a
Ball width L, which is received, with ball picking robot meets the following formula:
3. according to claim 2 pick up tennis path planning system, which is characterized in that the coordinate transformation unit by with
Lower formula handles target point information, and by bracket function, target point absolute coordinate is converted to mesh vertex coordinates:
Xg=[Xt/a]+[(Xt/a–[Xt/a])*2];
Yg=[Yt/a]+[(Yt/a–[Yt/a])*2];
Wherein [] represents Gauss function function, (Xt,Yt) represent target point absolute coordinate, (Xg,Yg) represent mesh vertex coordinates.
4. according to claim 3 pick up tennis path planning system, which is characterized in that described information processing module by with
Lower step judges target existence:
The mesh vertex coordinates of all target points are preserved, regard grid vertex as a two-dimensional matrix G [m n], (m, n) i.e. (Xg,
Yg), G [i j] represents grid vertex nearby with the presence or absence of target, if there is target at the grid vertex of the i-th row jth row,
G [i j]=1 is enabled, otherwise enables G [i j]=0, after obtaining all grid vertex information G [m n], handles grid vertex letter by column
Breath, is divided into following steps:
S1:Jth is arranged, only considers the first aim position i of this row1With the last one target location i2, i1=0, i2=m-
1;
S2:Judge G [i1J] > 0, if so, and for the first time perform, then preserve i1Value, perform S203;If so, but it is not first
Secondary execution, then perform S203;If it is not, then i1=i1+ 1, perform S203;
S3:Judge G [i2J] > 0, if so, and perform for the first time, then preserve the value of i2, perform S204;If so, but it is not first
Secondary execution, then perform S204;If it is not, then i2=i2- 1, perform S204;
S4:Judge i1< m/2, if so, performing S201;If it is not, then judge i1Or i2Whether preserve, be, exported i1Or i2,
Terminate jth row flow, no, then output is sky, terminates jth row flow.
5. according to claim 4 pick up tennis path planning system, which is characterized in that path adjustment module by with
Lower method judges whether there is the point of preservation and connects to obtain "the" shape path by the point of preservation by column:
If output is sky, the row currently judged are skipped;
If output is i1Or i2, it was demonstrated that when forefront only has a point, by coordinate (i1, j) or coordinate (i2, j) and it is connected in series to outgoing route
On;
If output is i1And i2, it was demonstrated that when forefront, there are starting point i1With end point i2, first contact (i if j is even number1, j) again
Contact (i2, j), otherwise first contact (i2, j) and contact (i again1,j)。
6. one kind picks up tennis paths planning method, which is characterized in that this method includes the following steps:
Step 1: being pre-processed to collected tennis location information, mesh generation is carried out to picking up ball region using gridding method;
Step 2: target actual coordinate is converted into mesh vertex coordinates;
Step 3: preserving the mesh vertex coordinates of all target points, all target points by "the" shape are connected, obtain picking up course of action
Diameter.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711475345.2A CN108225361B (en) | 2017-12-29 | 2017-12-29 | Tennis ball picking path planning system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711475345.2A CN108225361B (en) | 2017-12-29 | 2017-12-29 | Tennis ball picking path planning system and method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108225361A true CN108225361A (en) | 2018-06-29 |
CN108225361B CN108225361B (en) | 2021-06-25 |
Family
ID=62646893
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711475345.2A Expired - Fee Related CN108225361B (en) | 2017-12-29 | 2017-12-29 | Tennis ball picking path planning system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108225361B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109333549A (en) * | 2018-10-25 | 2019-02-15 | 湖南大学 | A kind of ping-pong pickup mobile robot and control method based on machine vision |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050012023A1 (en) * | 1996-02-12 | 2005-01-20 | Vock Curtis A. | Ball tracking in three-dimensions |
CN101537618A (en) * | 2008-12-19 | 2009-09-23 | 北京理工大学 | Visual system for ball picking robot in stadium |
CN102614641A (en) * | 2012-03-15 | 2012-08-01 | 上海电力学院 | Intelligent integrated tennis ball picking robot |
CN106164817A (en) * | 2014-02-28 | 2016-11-23 | 罗素商标有限责任公司 | Sporting equipment is mutual with wearable computer |
CN106483886A (en) * | 2016-11-30 | 2017-03-08 | 五邑大学 | A kind of intelligent caddie's system based on image procossing and its dispatching method |
-
2017
- 2017-12-29 CN CN201711475345.2A patent/CN108225361B/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050012023A1 (en) * | 1996-02-12 | 2005-01-20 | Vock Curtis A. | Ball tracking in three-dimensions |
CN101537618A (en) * | 2008-12-19 | 2009-09-23 | 北京理工大学 | Visual system for ball picking robot in stadium |
CN102614641A (en) * | 2012-03-15 | 2012-08-01 | 上海电力学院 | Intelligent integrated tennis ball picking robot |
CN106164817A (en) * | 2014-02-28 | 2016-11-23 | 罗素商标有限责任公司 | Sporting equipment is mutual with wearable computer |
CN106483886A (en) * | 2016-11-30 | 2017-03-08 | 五邑大学 | A kind of intelligent caddie's system based on image procossing and its dispatching method |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109333549A (en) * | 2018-10-25 | 2019-02-15 | 湖南大学 | A kind of ping-pong pickup mobile robot and control method based on machine vision |
CN109333549B (en) * | 2018-10-25 | 2022-05-27 | 湖南大学 | Table tennis ball picking mobile robot based on machine vision and control method |
Also Published As
Publication number | Publication date |
---|---|
CN108225361B (en) | 2021-06-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106843211B (en) | A kind of method for planning path for mobile robot based on improved adaptive GA-IAGA | |
CN107289950B (en) | Plant protection drone operation flight course planning method and plant protection drone | |
Ling et al. | Dual-arm cooperation and implementing for robotic harvesting tomato using binocular vision | |
Li et al. | Real-time detection of kiwifruit flower and bud simultaneously in orchard using YOLOv4 for robotic pollination | |
CN109945873A (en) | A kind of mixed path planing method for indoor mobile robot motion control | |
CN104866820B (en) | A kind of farm machinery navigation line drawing method and device based on genetic algorithm | |
CN110110763A (en) | A kind of grating map fusion method based on maximum public subgraph | |
CN108541458A (en) | A kind of Robot Fuzzy picking method | |
Comba et al. | Robot ensembles for grafting herbaceous crops | |
He et al. | Auto recognition of navigation path for harvest robot based on machine vision | |
CN106373160A (en) | Active camera target positioning method based on depth reinforcement learning | |
CN107291072A (en) | A kind of mobile robot path planning system and method | |
CN113065562A (en) | Crop ridge row extraction and leading route selection method based on semantic segmentation network | |
Jin et al. | Far-near combined positioning of picking-point based on depth data features for horizontal-trellis cultivated grape | |
CN108225361A (en) | Pick up tennis path planning system and method | |
Gao et al. | Image processing and analysis for autonomous grapevine pruning | |
JP2007185111A (en) | Agricultural material for farm work-supporting equipment, farmland using the agricultural material, and method for recognizing traveling direction of the farm work-supporting equipment in the farmland | |
CN112369208B (en) | Method for dynamically planning picking sequence of spheroidal fruits | |
Jin et al. | Intelligent tomato picking robot system based on multimodal depth feature analysis method | |
CN109472460A (en) | Operation overlay area Real-time Reconstruction method and system based on useful cross | |
CN116138036B (en) | Secondary positioning method for picking young buds of famous tea | |
CN110377033B (en) | RGBD information-based small football robot identification and tracking grabbing method | |
TWI744020B (en) | Intelligent fruit bagging machine system | |
Xu et al. | Geometric positioning and color recognition of greenhouse electric work robot based on visual processing | |
CN110807425B (en) | Intelligent weeding system and weeding method |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20201230 Address after: 350001 No.260, Wusi Road, Gulou District, Fuzhou City, Fujian Province Applicant after: Dong Mingwu Address before: Room 303, building 1, courtyard 13, cuihu'nan Ring Road, Sujiatuo Town, Haidian District, Beijing Applicant before: SIBO SAIRUI (BEIJING) TECHNOLOGY Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210625 Termination date: 20211229 |