CN107336252A - A kind of recognition methods of robot motion's direction and device - Google Patents
A kind of recognition methods of robot motion's direction and device Download PDFInfo
- Publication number
- CN107336252A CN107336252A CN201710541410.0A CN201710541410A CN107336252A CN 107336252 A CN107336252 A CN 107336252A CN 201710541410 A CN201710541410 A CN 201710541410A CN 107336252 A CN107336252 A CN 107336252A
- Authority
- CN
- China
- Prior art keywords
- revolver
- right wheel
- object vector
- coordinate
- initial state
- 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.)
- Withdrawn
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J13/00—Controls for manipulators
- B25J13/08—Controls for manipulators by means of sensing devices, e.g. viewing or touching devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/02—Sensing devices
Abstract
The embodiment of the invention discloses a kind of recognition methods of robot motion's direction and device, the robot includes revolver and right wheel, and methods described includes:Obtain robot revolver and the respective initial state coordinate of right wheel and final states coordinate;According to the revolver and the respective initial state coordinate of right wheel and final states coordinate, the first revolver object vector, the second revolver object vector, the first right wheel object vector and the second right wheel object vector are calculated;Cross product calculating is carried out according to the first revolver object vector, the second revolver object vector, the first right wheel object vector and the second right wheel object vector, and the direction of revolver and right wheel at the final states moment is identified respectively using the result of calculation of cross product.The embodiment of the present invention, which merely with the coordinate of robot left and right wheels is entered row vector and calculated, may recognize that the motion direction of robot, it is not necessary to by external add-in equipment, reduce cost, and calculating process is simple, has saved resource.
Description
Technical field
The present embodiments relate to recognition methods and the dress of robot technology, more particularly to a kind of robot motion's direction
Put.
Background technology
With the development of robot technology, robot has been progressed among daily life, aids in people
Learnt or assist people to complete various work.
Existing robot species is various, and they can not only sing, but also can do various actions, for example advance,
Retreat, turn left, turning right, original place such as is turn-taked at the action, and the motion of robot is towards extremely important in robot control process, shadow
Ring the precision of robot control and mobile effect.
In the prior art, it usually needs the motion direction of robot is determined by auxiliary equipment, such as is imaged first-class.This
A little methods are not only expensive, cost is high, and need to carry out computing, waste of resource by the algorithm of complexity.
The content of the invention
The embodiment of the present invention provides recognition methods and the device of a kind of robot motion's direction, true in the prior art to solve
Determine robot motion's direction method is expensive and the problem of waste of resource.
In a first aspect, the embodiments of the invention provide a kind of recognition methods of robot motion's direction, the robot bag
Revolver and right wheel are included, the recognition methods includes:
Obtain robot revolver and the respective initial state coordinate of right wheel and final states coordinate;
According to the revolver and the respective initial state coordinate of right wheel and final states coordinate, the first revolver object vector, are calculated
Two revolver object vectors, the first right wheel object vector and the second right wheel object vector;
According to the first revolver object vector, the second revolver object vector, the first right wheel object vector and the second right wheel target
Vector carries out cross product calculating, and identifies the court of revolver and right wheel at the final states moment respectively using the result of calculation of cross product
To.
Optionally, it is described according to the revolver and the respective initial state coordinate of right wheel and final states coordinate, calculate the first revolver
Object vector, the second revolver object vector, the first right wheel object vector and the second right wheel object vector, including:
According to the initial state coordinate of revolver and the initial state coordinate of right wheel, the first revolver object vector is calculated;
According to the initial state coordinate of revolver and the final states coordinate of revolver, the second revolver object vector is calculated;
According to the initial state coordinate of right wheel and the final states coordinate of right wheel, the first right wheel object vector is calculated;And
According to the initial state coordinate of right wheel and the initial state coordinate of revolver, the second right wheel object vector is calculated.
Optionally, it is described according to the first revolver object vector, the second revolver object vector, the first right wheel object vector and
Two right wheel object vectors carry out cross product calculating, and identify revolver and right wheel in the final states respectively using the result of calculation of cross product
The direction at moment, including:
The cross product of the first revolver object vector and the second revolver object vector is calculated, when result of calculation is more than zero, identification
Go out revolver in the final states moment advance the puck, when result of calculation is less than zero, identify revolver the final states moment backwards
Motion;And
The cross product of the first right wheel object vector and the second right wheel object vector is calculated, when result of calculation is more than zero, identification
Go out right wheel in the final states moment advance the puck, when result of calculation is less than zero, identify right wheel the final states moment backwards
Motion.
Optionally, the initial state and final states are any two successive frames in robot kinematics.
Second aspect, the embodiment of the present invention additionally provide a kind of identification device of robot motion's direction, the robot
Including revolver and right wheel, the identification device includes:
Coordinate obtaining module, for obtaining robot revolver and the respective initial state coordinate of right wheel and final states coordinate;
Vector calculation module, for according to the revolver and the respective initial state coordinate of right wheel and final states coordinate, calculating
One revolver object vector, the second revolver object vector, the first right wheel object vector and the second right wheel object vector;
Towards identification module, for according to the first revolver object vector, the second revolver object vector, the first right wheel target to
Amount and the second right wheel object vector carry out cross product calculating, and identify revolver and right wheel in institute respectively using the result of calculation of cross product
State the direction at final states moment.
Optionally, the vector calculation module includes:
First revolver object vector computing unit, for the initial state coordinate and the initial state coordinate of right wheel according to revolver, calculate
Go out the first revolver object vector;
Second revolver object vector computing unit, for the initial state coordinate and the final states coordinate of revolver according to revolver, calculate
Go out the second revolver object vector;
First right wheel object vector computing unit, for the initial state coordinate and the final states coordinate of right wheel according to right wheel, calculate
Go out the first right wheel object vector;
Second right wheel object vector computing unit, for the initial state coordinate and the initial state coordinate of revolver according to right wheel, calculate
Go out the second right wheel object vector.
Optionally, it is described to include towards identification module:
Revolver is towards identification module, for calculating the cross product of the first revolver object vector and the second revolver object vector, when
When result of calculation is more than zero, revolver is identified in the final states moment advance the puck, when result of calculation is less than zero, identifies a left side
Wheel moves backwards at the final states moment;
Right wheel is towards identification module, for calculating the cross product of the first right wheel object vector and the second right wheel object vector, when
When result of calculation is more than zero, right wheel is identified in the final states moment advance the puck, when result of calculation is less than zero, identifies the right side
Wheel moves backwards at the final states moment.
Optionally, the initial state and final states are any two successive frames in robot kinematics.
The embodiment of the present invention calculates accordingly according to robot revolver and the respective initial state coordinate of right wheel and final states coordinate
Object vector, and using the object vector cross product motion of the result of calculation to robot towards being identified, it is not necessary to borrow
External add-in equipment is helped, reduces cost, and is calculated merely with the coordinate of robot revolver, right wheel and may recognize that machine
The motion direction of device people, calculating process is simple, has saved resource.
Brief description of the drawings
Fig. 1 is the flow chart of the recognition methods of robot motion's direction in the embodiment of the present invention one;
Fig. 2 is the flow chart of the identification device of robot motion's direction in the embodiment of the present invention two.
Embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that in order to just
Part related to the present invention rather than entire infrastructure are illustrate only in description, accompanying drawing.
Embodiment one
Fig. 1 is the flow chart of the recognition methods for robot motion's direction that the embodiment of the present invention one provides, and the present embodiment can
Suitable for direction of the identification robot motion process, this method can be held by the identification device of robot motion's direction
OK, the device can be realized by the way of software and/or hardware.
The recognition methods of robot motion's direction of the embodiment of the present invention one specifically includes:
S100, obtain robot revolver and the respective initial state coordinate of right wheel and final states coordinate.
Robot includes revolver and right wheel, but the present embodiment does not limit the quantity of wheels of robot.In a kind of embodiment party
In formula, robot can include 2 wheels, be the revolver and right wheel respectively.In another embodiment, robot can be with
Comprising 4 wheels, two wheels positioned at robot front first row are the revolver and right wheel respectively, and two of latter row
Wheel is left rear wheel and off hind wheel, due to when robot has more than 2 quantity wheels, two wheels of front first row
The direction of (i.e. revolver and right wheel) is the motion direction of robot, therefore it may only be necessary to obtain the position coordinates of the two wheels
And carry out towards identification.
Preferably, initial state and final states are any two successive frame in robot kinematics, revolver and each leisure of right wheel
The coordinate of any two successive frame is initial state coordinate and final states coordinate, exemplary, if per second include 24 frames, control machine
Each frame of device people motion is 1/24 second, i.e., is spaced 1/24 second between initial state and final states.During implementation, it may be predetermined that good coordinate
System, initial state coordinate and final states coordinate are the position coordinates under the coordinate system uniformly determined.The origin of the coordinate system can be with
Any limit is not done to the origin of coordinate system positioned at any one wheel, or the central point of revolver and right wheel line, the present embodiment
It is fixed.
S110, according to revolver and the respective initial state coordinate of right wheel and final states coordinate, calculate the first revolver object vector,
Two revolver object vectors, the first right wheel object vector and the second right wheel object vector.
S120, according to the first revolver object vector, the second revolver object vector, the first right wheel object vector and the second right wheel
Object vector carries out cross product calculating, and identifies revolver and right wheel at the final states moment respectively using the result of calculation of cross product
Direction.
According to revolver and the respective initial state coordinate of right wheel and final states coordinate, can get respectively respective two targets to
Amount is the first revolver object vector, the second revolver object vector, the first right wheel object vector and the second right wheel target respectively to
Amount.Because vector represents that size represents direction again, therefore, the motion direction of robot can be identified using vector, enters one
Step, carry out the identification of direction using the cross product result of calculation of vector.
The embodiment of the present invention need not utilize additional external equipment, only utilize robot revolver and the respective position of right wheel
Coordinate calculates corresponding object vector, and the motion direction of robot, drop are identified by vectorial cross product calculating can
Low cost, and computational methods are simple, saved resource.
Preferably, in S110, according to revolver and the respective initial state coordinate of right wheel and final states coordinate, the first revolver is calculated
Object vector, the second revolver object vector, the first right wheel object vector and the second right wheel object vector, are specifically included:
According to the initial state coordinate of revolver and the initial state coordinate of right wheel, the first revolver object vector is calculated;
According to the initial state coordinate of revolver and the final states coordinate of revolver, the second revolver object vector is calculated;
According to the initial state coordinate of right wheel and the final states coordinate of right wheel, the first right wheel object vector is calculated;And
According to the initial state coordinate of right wheel and the initial state coordinate of revolver, the second right wheel object vector is calculated.
Accordingly, in S120, according to the first revolver object vector, the second revolver object vector, the first right wheel target to
Amount and the second right wheel object vector carry out cross product calculating, and identify revolver and right wheel in institute respectively using the result of calculation of cross product
The direction at final states moment is stated, is specifically included:
The cross product of the first revolver object vector and the second revolver object vector is calculated, when result of calculation is more than zero, identification
Go out revolver in the final states moment advance the puck, when result of calculation is less than zero, identify revolver the final states moment backwards
Motion;And
The cross product of the first right wheel object vector and the second right wheel object vector is calculated, when result of calculation is more than zero, identification
Go out right wheel in the final states moment advance the puck, when result of calculation is less than zero, identify right wheel the final states moment backwards
Motion.
It should be noted that for two object vectors of revolver, whether its cross product is more than zero, represents two object vectors
Angle whether be less than 180 °, when less than 180 °, then it represents that revolver advance the puck, it is on the contrary then move backwards, accordingly, right wheel
And in this way, the motion direction of revolver and right wheel is then only identified by the position coordinates can of revolver and right wheel.
When implementing, the embodiment of the present invention can obtain robot revolver and the respective initial state coordinate of right wheel and final states in real time
Coordinate, then by performing aforesaid operations, revolver and the respective direction of right wheel are calculated in real time, so as to respectively to revolver and the right side
Wheel implements control.
In addition, in one embodiment, if identifying revolver and right wheel towards consistent (such as facing forward or equal court
Afterwards), then it can know that robot takes the air line or moved in curves with reference to the speed of revolver and right wheel, specifically, working as revolver and right wheel
When speed is equal, then illustrate that robot takes the air line, it is on the contrary then move in curves.Exemplary, revolver can be calculated respectively in initial state
The move distance of move distance and right wheel between initial state and the frame of final states two between the frame of final states two, then, according to initial state
Time between the frame of final states two can calculate revolver speed and right wheel speed, wherein, the time can be according to sampling frequency
Rate obtains.
Further, identify revolver and right wheel towards it is opposite when, such as revolver advance the puck, right wheel move backwards, or
Person's revolver moves backwards, right wheel advance the puck, then it represents that robot does circus movement.
By obtaining robot revolver and the respective motion direction of right wheel in real time, the specific motion of robot is analyzed in time
Mode, and then preferably robot is implemented to control.
Embodiment two
Fig. 2 is the structural representation of the identification device of robot motion's direction in the embodiment of the present invention two, such as Fig. 2 institutes
Show, the identification device of robot motion's direction includes:
Coordinate obtaining module 10, for obtaining robot revolver and the respective initial state coordinate of right wheel and final states coordinate;
Vector calculation module 11, for according to revolver and the respective initial state coordinate of right wheel and final states coordinate, calculating first
Revolver object vector, the second revolver object vector, the first right wheel object vector and the second right wheel object vector;
Towards identification module 12, for according to the first revolver object vector, the second revolver object vector, the first right wheel target
The second right wheel of vector sum object vector carries out cross product calculating, and identifies that revolver and right wheel exist respectively using the result of calculation of cross product
The direction at the final states moment.
Further, the vector calculation module 11 includes:
First revolver object vector computing unit, for the initial state coordinate and the initial state coordinate of right wheel according to revolver, calculate
Go out the first revolver object vector;
Second revolver object vector computing unit, for the initial state coordinate and the final states coordinate of revolver according to revolver, calculate
Go out the second revolver object vector;
First right wheel object vector computing unit, for the initial state coordinate and the final states coordinate of right wheel according to right wheel, calculate
Go out the first right wheel object vector;
Second right wheel object vector computing unit, for the initial state coordinate and the initial state coordinate of revolver according to right wheel, calculate
Go out the second right wheel object vector.
Further, it is described to include towards identification module 12:
Revolver is towards recognition unit, for calculating the cross product of the first revolver object vector and the second revolver object vector, when
When result of calculation is more than zero, revolver is identified in the final states moment advance the puck, when result of calculation is less than zero, identifies a left side
Wheel moves backwards at the final states moment;
Right wheel is towards recognition unit, for calculating the cross product of the first right wheel object vector and the second right wheel object vector, when
When result of calculation is more than zero, right wheel is identified in the final states moment advance the puck, when result of calculation is less than zero, identifies the right side
Wheel moves backwards at the final states moment.
It should be noted that above-mentioned each unit is drawn not in the drawings.
Further, the integral multiple of 1 second is differed between the initial state and final states.
The embodiment of the present invention need not utilize additional external equipment, only utilize robot revolver and the respective position of right wheel
Coordinate calculates corresponding object vector, and the motion direction of robot, drop are identified by vectorial cross product calculating can
Low cost, and computational methods are simple, saved resource.
The identification device of robot motion's direction provided in an embodiment of the present invention can perform any embodiment of the present invention and provide
Robot motion's direction recognition methods, possess the corresponding functional module of execution method and beneficial effect.
Pay attention to, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious changes,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although being carried out by above example to the present invention
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
Other more equivalent embodiments can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (8)
1. a kind of recognition methods of robot motion's direction, the robot includes revolver and right wheel, it is characterised in that the knowledge
Other method includes:
Obtain robot revolver and the respective initial state coordinate of right wheel and final states coordinate;
According to the revolver and the respective initial state coordinate of right wheel and final states coordinate, the first revolver object vector, second left side are calculated
Take turns object vector, the first right wheel object vector and the second right wheel object vector;
According to the first revolver object vector, the second revolver object vector, the first right wheel object vector and the second right wheel object vector
Cross product calculating is carried out, and the direction of revolver and right wheel at the final states moment is identified respectively using the result of calculation of cross product.
2. recognition methods according to claim 1, it is characterised in that described according to the revolver and the respective initial state of right wheel
Coordinate and final states coordinate, calculate the first revolver object vector, the second revolver object vector, the first right wheel object vector and second
Right wheel object vector, including:
According to the initial state coordinate of revolver and the initial state coordinate of right wheel, the first revolver object vector is calculated;
According to the initial state coordinate of revolver and the final states coordinate of revolver, the second revolver object vector is calculated;
According to the initial state coordinate of right wheel and the final states coordinate of right wheel, the first right wheel object vector is calculated;And
According to the initial state coordinate of right wheel and the initial state coordinate of revolver, the second right wheel object vector is calculated.
3. recognition methods according to claim 2, it is characterised in that described according to the first revolver object vector, second left side
Take turns object vector, the first right wheel object vector and the second right wheel object vector and carry out cross product calculating, and utilize the calculating knot of cross product
Fruit identifies the direction of revolver and right wheel at the final states moment respectively, including:
The cross product of the first revolver object vector and the second revolver object vector is calculated, when result of calculation is more than zero, identifies a left side
Take turns in the final states moment advance the puck, when result of calculation is less than zero, identify that revolver moves backwards at the final states moment;
And
The cross product of the first right wheel object vector and the second right wheel object vector is calculated, when result of calculation is more than zero, identifies the right side
Take turns in the final states moment advance the puck, when result of calculation is less than zero, identify that right wheel is moved backwards at the final states moment.
4. according to the recognition methods described in claim any one of 1-3, it is characterised in that the initial state and final states are robot fortune
Any two successive frame during dynamic.
5. a kind of identification device of robot motion's direction, the robot includes revolver and right wheel, it is characterised in that the knowledge
Other device includes:
Coordinate obtaining module, for obtaining robot revolver and the respective initial state coordinate of right wheel and final states coordinate;
Vector calculation module, for according to the revolver and the respective initial state coordinate of right wheel and final states coordinate, it is left to calculate first
Take turns object vector, the second revolver object vector, the first right wheel object vector and the second right wheel object vector;
Towards identification module, for according to the first revolver object vector, the second revolver object vector, the first right wheel object vector and
Second right wheel object vector carries out cross product calculating, and identifies revolver and right wheel at the end respectively using the result of calculation of cross product
The direction at state moment.
6. identification device according to claim 5, it is characterised in that the vector calculation module includes:
First revolver object vector computing unit, for the initial state coordinate and the initial state coordinate of right wheel according to revolver, calculate
One revolver object vector;
Second revolver object vector computing unit, for the initial state coordinate and the final states coordinate of revolver according to revolver, calculate
Two revolver object vectors;
First right wheel object vector computing unit, for the initial state coordinate and the final states coordinate of right wheel according to right wheel, calculate
One right wheel object vector;
Second right wheel object vector computing unit, for the initial state coordinate and the initial state coordinate of revolver according to right wheel, calculate
Two right wheel object vectors.
7. identification device according to claim 6, it is characterised in that described to include towards identification module:
Revolver, for calculating the cross product of the first revolver object vector and the second revolver object vector, works as calculating towards recognition unit
When being as a result more than zero, revolver is identified in the final states moment advance the puck, when result of calculation is less than zero, identifies that revolver exists
The final states moment moves backwards;
Right wheel, for calculating the cross product of the first right wheel object vector and the second right wheel object vector, works as calculating towards recognition unit
When being as a result more than zero, right wheel is identified in the final states moment advance the puck, when result of calculation is less than zero, identifies that right wheel exists
The final states moment moves backwards.
8. according to the identification device described in claim any one of 5-7, it is characterised in that the initial state and final states are robot fortune
Any two successive frame during dynamic.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710541410.0A CN107336252A (en) | 2017-07-05 | 2017-07-05 | A kind of recognition methods of robot motion's direction and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710541410.0A CN107336252A (en) | 2017-07-05 | 2017-07-05 | A kind of recognition methods of robot motion's direction and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107336252A true CN107336252A (en) | 2017-11-10 |
Family
ID=60219572
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710541410.0A Withdrawn CN107336252A (en) | 2017-07-05 | 2017-07-05 | A kind of recognition methods of robot motion's direction and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107336252A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07141008A (en) * | 1993-11-15 | 1995-06-02 | Nippon Telegr & Teleph Corp <Ntt> | Successive control method for sensor orienting direction |
CN101537618A (en) * | 2008-12-19 | 2009-09-23 | 北京理工大学 | Visual system for ball picking robot in stadium |
CN101561248A (en) * | 2008-04-17 | 2009-10-21 | 鸿富锦精密工业(深圳)有限公司 | Position measurement device and measuring method |
CN103307968A (en) * | 2013-06-03 | 2013-09-18 | 西北工业大学 | Method for detecting posture of robot carrying platform |
CN105716611A (en) * | 2016-01-29 | 2016-06-29 | 西安电子科技大学 | Environmental information-based indoor mobile robot and positioning method thereof |
-
2017
- 2017-07-05 CN CN201710541410.0A patent/CN107336252A/en not_active Withdrawn
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07141008A (en) * | 1993-11-15 | 1995-06-02 | Nippon Telegr & Teleph Corp <Ntt> | Successive control method for sensor orienting direction |
CN101561248A (en) * | 2008-04-17 | 2009-10-21 | 鸿富锦精密工业(深圳)有限公司 | Position measurement device and measuring method |
CN101537618A (en) * | 2008-12-19 | 2009-09-23 | 北京理工大学 | Visual system for ball picking robot in stadium |
CN103307968A (en) * | 2013-06-03 | 2013-09-18 | 西北工业大学 | Method for detecting posture of robot carrying platform |
CN105716611A (en) * | 2016-01-29 | 2016-06-29 | 西安电子科技大学 | Environmental information-based indoor mobile robot and positioning method thereof |
Non-Patent Citations (1)
Title |
---|
朱莹莹等: "基于天花板的移动机器人视觉定位方法的研究", 《现代电子技术》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106708054B (en) | Routing planning method for inspection robot by combining map grids and potential field method obstacle avoidance | |
CN107563446B (en) | Target detection method for micro-operation system | |
CN108762309B (en) | Human body target following method based on hypothesis Kalman filtering | |
Lambrecht et al. | Spatial programming for industrial robots based on gestures and augmented reality | |
Hachimura et al. | Analysis and evaluation of dancing movement based on LMA | |
CN110605711B (en) | Method, device and system for controlling cooperative robot to grab object | |
WO2020232069A1 (en) | Video 2d multi-person pose estimation using multi-frame refinement and optimization | |
CN104062972B (en) | A kind of removable housed device and people's relative position adjustment control method and its system | |
Kulecki et al. | Practical aspects of detection and grasping objects by a mobile manipulating robot | |
CN111062135A (en) | Accurate collision detection method | |
Xiao et al. | A novel visual guidance framework for robotic welding based on binocular cooperation | |
Wnuk et al. | Tracking branched deformable linear objects with structure preserved registration by branch-wise probability modification | |
CN107336252A (en) | A kind of recognition methods of robot motion's direction and device | |
KR20130038085A (en) | Converged type circuit apparatus of support vector machine | |
Li et al. | Poly-mot: A polyhedral framework for 3d multi-object tracking | |
CN105738870B (en) | A kind of multimode filtering method | |
KR102333768B1 (en) | Hand recognition augmented reality-intraction apparatus and method | |
Shao et al. | Combining rgb and points to predict grasping region for robotic bin-picking | |
CN111208785B (en) | Motion control method and device | |
CN109934155B (en) | Depth vision-based collaborative robot gesture recognition method and device | |
Kiddee et al. | A real-time and robust feature detection method using hierarchical strategy and modified Kalman filter for thick plate seam tracking | |
CN112230801A (en) | Kalman smoothing processing method, memory and equipment applied to touch trajectory | |
CN108010130B (en) | Robot operation method facing to graphs | |
Jayasurya et al. | Gesture controlled AI-robot using Kinect | |
CN108664850B (en) | Human face posture classification method and device |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20171110 |
|
WW01 | Invention patent application withdrawn after publication |