CN107553499A - Natural the gesture motion control system and method for a kind of Multi-shaft mechanical arm - Google Patents
Natural the gesture motion control system and method for a kind of Multi-shaft mechanical arm Download PDFInfo
- Publication number
- CN107553499A CN107553499A CN201710992223.4A CN201710992223A CN107553499A CN 107553499 A CN107553499 A CN 107553499A CN 201710992223 A CN201710992223 A CN 201710992223A CN 107553499 A CN107553499 A CN 107553499A
- Authority
- CN
- China
- Prior art keywords
- arm
- signal
- mechanical arm
- module
- control
- 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.)
- Pending
Links
Landscapes
- Manipulator (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The present invention relates to a kind of system and method for Multi-shaft mechanical arm motion control, user can be moved by natural gesture and arm motion control machinery arm.The system and method is by detecting the electromyographic signal and IMU movable informations on human arm surface, identification nature gesture simultaneously resolves arm posture, by establishing arm mechanical arm physical relation model, control machinery arm reappears human arm motion, and passes through the grasping manipulation of natural gesture control machinery arm end effector.The fields such as remote operation, the teaching of mechanical arm are present invention can be widely used to, realize the intelligent control to robot, reach man-machine co-melting, intelligent interaction purpose.
Description
Technical field
The present invention relates to human-computer intellectualization field, more particularly to one kind to be parsed based on nature gesture identification and arm posture
Multi-shaft mechanical arm kinetic control system and method.
Background technology
In recent years, robot technology is widely used in industrial production and the every field of daily life, is promoting its people
Economic development, improve people's quality of life etc. and played an important role.The intelligent and good interactivity of robot
The even more main flow direction of robot future development.During the development and use of intelligent robot, how to realize and user
Natural interaction, reach man-machine co-melting purpose be always people be concerned about topic.Modern signal measure with treatment technology and
The development of raw electromechanical integration technology so that realize that human body is direct to robot by human-body biological signal and other auxiliary signals
Or indirect control is possibly realized.The Intelligent control for developing into robot of these technologies provides a practicable way
Footpath.
Multi-shaft mechanical arm inherently imitates the physiological structure of human body, one for corresponding to the different joint of human upper limb and designing
The very high mechanical device of kind flexibility ratio, it has natural similarity with human body upper arm.The motion state of human arm is direct
It is reflected in the motion control of mechanical arm, is to realize man-machine co-melting, natural interaction splendid scheme.With nature gesture control machine
Device people can intuitively embody the intention of user, be a kind of extremely convenient and natural control mode.Surface electromyogram signal
(sEMG) it is that one kind is contracted in weak biological electric signal caused by skin surface, different electromyographic signals along with human skeletal muscle
Pattern can reflect muscle activity corresponding to various human motions to a certain extent.At present, identified by surface electromyogram signal
A variety of wrist portions act and can reach higher accuracy rate, but the identification to limb action is accurate not enough.
The content of the invention
IMU (Inertial Measurement Unit) is the abbreviation of Inertial Measurement Unit, including accelerometer, magnetic force
Meter, gyroscope etc., it more can accurately reflect the motion state and spatial attitude of object, have for the motion process of limbs
Good recognition capability, inferior positions of the sEMG in limb action identification can be made up.The present invention is by the nature based on sEMG and IMU
Gesture identification and the parsing of arm posture apply in the natural contral of Multi-shaft mechanical arm, it is proposed that a kind of control of Multi-shaft mechanical arm
System and method processed, it can be widely applied to multiple fields, the teaching of such as Multi-shaft mechanical arm, remote control.
Surface electromyogram signal (sEMG) bioelectrical signals as caused by contraction of muscle as one kind, can reflect people well
Motion intention, but can not preferably reflect the posture of limbs, so as to which the identification to limb action is not accurate enough.IMU is a kind of
The conventional measuring unit that can characterize object of which movement, its measurement data can reflect the spatial attitude of object or object, generally
For navigation equipment or system.Both are combined, the invention provides a kind of natural gestural control system of Multi-shaft mechanical arm
And method, sEMG the and IMU signals gathered in real time are organically merged and parsed with more accurately identify limb action and
Posture, so as to which the motion of people or posture are passed into mechanical arm naturally, the man-machine interaction for robots such as mechanical arms provides one
The more natural approach of kind.The present invention is carried out in fact by the way that the harvester of sEMG and IMU signals is integrated in wearable device
When gather, and the signal synthesis to being collected carry out correspondingly handle and parse to obtain more accurately recognition result, so as to
Mechanical arm is controlled more naturally.The control system can also be applied to the remote of the mechanical device of similar mechanical arm with method
Process control and teaching, a kind of new approach is provided for the man-machine interaction of intelligent robot.
On the one hand, the present invention provides a kind of Multi-shaft mechanical arm kinetic control system, it is characterised in that including：Mechanical arm, bag
Include entity mechanical arm or virtual machine arm；Signal acquisition module, worn by user, be configured as collection surface electromyographic signal and be used to
Property measuring unit signal；Natural gesture identification and arm posture parsing module, are configured to, with the signal acquisition module and obtain
The surface electromyogram signal and Inertial Measurement Unit signal taken identifies nature gesture and parses arm posture；And manipulator motion
Control module, be configured as the identification and the analysis result that are obtained according to the natural gesture identification and arm posture parsing module come
The mechanical arm is controlled to realize the motion corresponding with user action；Wherein, the signal acquisition module, the natural gesture are known
Do not communicated to connect between arm posture parsing module, the manipulator motion control module and the mechanical arm.
In one embodiment of the invention, the signal acquisition module also includes surface myoelectric electrode, inertia measurement list
First signaling module, power management module, signal pre-processing module and wireless communication module, it is characterised in that：The signal is adopted
Collection module is configured as gathering multichannel electromyographic signal, and the Inertial Measurement Unit signaling module is configured to supply the acceleration of 3 axles
Degree meter, 3 axle gyroscopes and 3 axle magnetometer informations are simultaneously integrated in the signal acquisition module.
In another embodiment of the present invention, it is characterised in that the signal pre-processing module also includes preposition amplification electricity
Road, high-pass filtering circuit, low-pass filter circuit and A/D change-over circuits, wherein, the power management module is configured as producing
The voltage of different amplitudes is powered for different unit modules.
In another embodiment of the present invention, it is characterised in that：The natural gesture identification and arm posture parsing mould
Block is configured as by carrying out pattern classification to surface electromyogram signal to identify nature gesture, and by Inertial Measurement Unit
The spatial attitude and movable information of signal real-time resolving arm.
In another embodiment of the present invention, it is characterised in that：The manipulator motion control module is configured as leading to
The physical relation model established between arm and mechanical arm is crossed to obtain the natural gesture identification and arm posture parsing module
Identification and analysis result change into the control information for controlling the mechanical arm, so as to control machinery arm realize and arm motion phase
Consistent motion or the switching of mode of operation.
On the other hand, the present invention also provides a kind of Multi-shaft mechanical arm motion control method, it is characterised in that including following step
Suddenly：
S1, calibration data acquisition device；S2, obtain surface electromyogram signal and IMU information；S3, Signal Pretreatment simultaneously pass through
Wireless communication mode is sent；S4, carry out gesture identification and the parsing of arm posture；S5, establish arm-mechanical arm physical relation mould
Type, export manipulator motion controlled quentity controlled variable；S6, driving manipulator motion.
In one embodiment of the invention, it is characterised in that pretreatment bag is carried out to primary signal described in step S3
Include：Primary signal is amplified, bandpass filtering and carries out A/D conversions and digital sample.
In another embodiment of the present invention, it is characterised in that step S4 includes：
S41, data divide window to handle；S42, to dividing window data to carry out feature extraction and Feature Dimension Reduction；S43, classifier training
With test；S44, output nature gesture recognition result；S45, arm posture is resolved, derive each articulation angle and arm end
End movement.
In another embodiment of the present invention, it is characterised in that step S4 also includes：Pass through after result is identified
The mode of operation of different gesture motion switching mechanical arms.
In another embodiment of the present invention, it is characterised in that arm-mechanical arm physics is established described in step S5 and is closed
It is that model includes：I) end-of-pipe control pattern：Pass through the anti-controlled quentity controlled variable for releasing each articulation of control machinery arm of the displacement of end；
And/or ii) joint control pattern：The change equal proportion of the arm joint angle obtained in step s 4 is mapped to mechanical arm
Motion control in.
The present invention parses with sEMG and IMU information realization natures gesture identification, arm posture, and then control machinery arm is real
Motion now consistent with human arm motion and crawl task, complete and realize：
(1) acquisition of IMU data of the electromyographic signal of nature gesture with characterizing arm motion information is characterized；
(2) the natural gesture identification based on surface electromyogram signal；
(3) based on IMU information parsing human arm motion's state；
(4) physical model established between arm motion state, natural gesture and Mechanical transmission test parameter；
(5) reproduction of the mechanical arm to human arm motion is realized based on above-mentioned physical model.
By said system and method, the invention provides a kind of system and method for Multi-shaft mechanical arm motion control, make
Natural gesture and the motion of arm motion control machinery arm can be passed through by obtaining user.The system and method for the present invention is by detecting human body
The electromyographic signal and IMU movable informations of arm surface, identify nature gesture and resolve arm posture, by establishing arm-machinery
Arm physical relation model, control machinery arm reproduction human arm motion, and pass through natural gesture control machinery arm end effector
Grasping manipulation.The fields such as remote operation, the teaching of mechanical arm are present invention can be widely used to, realize the intelligence control to robot
System, reaches man-machine co-melting, intelligent interaction purpose.
Brief description of the drawings
Fig. 1 is the application schematic diagram of one embodiment of Multi-shaft mechanical arm kinetic control system in the present invention；
Fig. 2 is the structured flowchart of one embodiment of Multi-shaft mechanical arm kinetic control system in the present invention；
Fig. 3 is the flow chart of one embodiment of Multi-shaft mechanical arm motion control method in the present invention；
Fig. 4 is pattern-recognition signal processing flow schematic diagram during Multi-shaft mechanical arm motion control in the present invention；
Fig. 5 is that the flow controlled in the present invention by arm-mechanical arm physical relation model realization manipulator motion is illustrated
Figure.
Embodiment
In order to thoroughly understand the present invention, detailed step and detailed structure will be proposed in following description, so as to
Explain technical scheme proposed by the present invention.Below in conjunction with accompanying drawing, technical scheme is carried out apparent, complete
Description.Obviously, described embodiment is the embodiment of a part of the invention, rather than whole embodiments.The present invention compared with
Good embodiment is described in detail as follows, but in addition to these detailed descriptions, the present invention can also have other embodiment.It is based on
Embodiments of the invention, those skilled in the art are obtained every other on the premise of creative work is not paid
Embodiment, belong to protection scope of the present invention.
In the following description, a large amount of concrete details are given to provide more thorough understanding of the invention.So
And it is obvious to the skilled person that the present invention can be able to without one or more of these details
Implement.It should be appreciated that the present invention can be implemented in different forms, and it should not be construed as being limited to the implementation proposed here
Example.On the contrary, providing these embodiments disclosure of the invention will be made to understand and comprehensively.
The present invention is described in further detail below in conjunction with the accompanying drawings.
With reference to figure 1 and Fig. 2, the invention provides a kind of Multi-shaft mechanical arm kinetic control system, in a specific embodiment
In can be Multi-shaft mechanical arm nature gesture teaching system 000, the system includes four parts, is signal acquisition module respectively
100th, natural gesture identification and arm posture parsing module 200, manipulator motion control module 300 and mechanical arm 400, wherein
Natural gesture identification and arm posture parsing module 200 can be host computer signal handlers.
Signal acquisition module 100 can be a kind of arm band that can gather electromyographic signal and IMU information simultaneously, be collected
Multi-channel surface myoelectric signal and IMU (including accelerometer, gyroscope and magnetometer etc.) information, can be subsequent gesture
Identification and the parsing of arm posture provide data source.Signal acquisition module 100 can be worn on individually or respectively forearm and/or on
Arm, position correction can be first passed through in advance when in use, to improve the accuracy of information gathering.In a specific embodiment, believe
Number acquisition module 100 can include surface myoelectric electrode, IMU modules, power management module, signal pre-processing module and wireless
Communication module.Preferably, signal acquisition module 100 gathers 4 to 8 passage electromyographic signals, and surface myoelectric electrode is to pass through special place
The metal electrode of reason, conduction property good between skin and electrode can be kept, so as to ensure electromyographic signal quality.It is preferred that
, IMU modules use MPU-9150 modules, can provide 3 axis accelerometers, 3 axle gyroscopes and 3 axle magnetometer informations, the mould
Block can be integrated in signal acquisition module 100 (such as：Myoelectricity picker arm band) in order to signal acquisition, and complementation can be passed through
The methods of filtering, resolves human arm posture.Preferably, power management module is used to power to modules in arm band, uses
3.7V lithium battery is powered for whole signal pickup assembly, wherein preferably producing the electricity of different amplitudes by power management chip
Press and powered for single-chip microcomputer, A/D conversion chips etc..Preferably, signal pre-processing module may further include pre-amplification circuit,
High-pass filtering circuit, low-pass filter circuit and A/D change-over circuits, it is further preferred that can be removed using notch filter
Industrial frequency noise, bandpass filter frequency range is arranged to 20-450Hz, and analog quantity is converted into number using A/D change-over circuits
Word amount, in order to carry out follow-up processing or parsing to signal.Preferably, wireless communication module is used for arm band and the knowledge of natural gesture
Data transfer not between arm posture parsing module, the sEMG collected and IMU information is wirelessly transmitted to host computer
Signal handler.
In one embodiment, natural gesture identification and arm posture parsing module 200 can be operated on host computer
Pattern-recognition and attitude algorithm algorithm.Natural gesture identification can utilize signal acquisition mould with arm posture parsing module 200
The surface myoelectric data that block 100 obtains and IMU data, pattern classification is carried out to surface myoelectric data, to identify nature gesture；Root
According to IMU data calculation arm real time kinematics postures, to resolve arm tip displacement.Preferably, natural gesture identification and arm appearance
State parsing module 200 can be further divided into two parts, and a part is the processing to electromyographic signal, can be using linear discriminant point
The sorting technique such as (LDA) or SVM is analysed, identifies nature gesture；Another part is the processing to IMU information, can use posture solution
Calculate the spatial attitude and movable information of algorithm, real-time resolving object or object (such as forearm and upper arm).
In a specific embodiment, natural gesture identification can be used with arm posture parsing module 200 and is based on
Python identification and solver.Python is a kind of explanation type computer programming language of object-oriented, is had rich
Rich and powerful storehouse, and the various modules (especially C/C++) made of other language can be easily bound up on one very much
Rise, so as to have preferable portability, scalability and Residuated Lattice.
In one embodiment, manipulator motion control module 300 can include arm-mechanical arm physical relation model and
Motion-control module two parts, to realize mapping and control of the human arm motion to manipulator motion.Manipulator motion controls
Module 300 resolves obtained natural gesture recognition result and hand according to natural gesture identification and arm posture parsing module 200
The spatial attitude and movable information of arm, control machinery arm realize the motion consistent with arm motion.Preferably, manipulator motion
Control module 300 can also realize the functions such as the switching of mode of operation according to different natural gestures.Preferably, manipulator motion control
Molding block 300 can be by establishing the physical model between human arm and Multi-shaft mechanical arm, the arm posture that will resolve
Information changes into the control information of each articulation of control machinery arm.Manipulator motion control module 300 can also be according to hand
Gesture recognition result, switch the different working modes of mechanical arm, such as end-of-pipe control pattern or joint control pattern.
In a specific embodiment, manipulator motion control module 300 can use the motion control journey based on ROS
Sequence.ROS (Robot Operating System) is a kind of metaoperating system increased income suitable for robot, there is provided a kind of
The communications framework of Publish-subscribe formula is simply and rapidly building Distributed Calculation system, there is provided substantial amounts of tool combinations to
Configuration, startup, self-test, debugging, visualization, login, test, termination distributed computing system, and provide extensive library text
Part realizes the robot function based on mobility, operational control, perception.ROS also supports a kind of similar to code storage storehouse
Association system, this system can also realize the cooperation and issue of engineering.This design can make exploitation and the reality of engineering
Decision-making (not limited by ROS) is now completely independent from file system to user interface, while all engineerings can be by ROS base
Plinth instrument combines.
Mechanical arm 400 can not only include entity mechanical arm, virtual machine arm that can also be including VR/AR etc. in environment.
In a specific embodiment, mechanical arm 400 can be used to visualize in entity Multi-shaft mechanical arm or virtual scene
Virtual machine arm, so as to complete various specific operation tasks suitable for different application scenarios.
With reference to figure 1, the course of work of one embodiment of the system is described as follows：User is according to specific task or operation
It is required that control arms swing and/or the various natural gestures of completion.Control contraction of muscle signal be as electronic signals along
What spinal cord and efferent nerve were conducted, along with the contraction of muscle, this bioelectrical signals can produce electric current in skin surface
, electromyographic signal is formed, different gestures has corresponded to different myoelectricity patterns.Electromyographic signal and IMU data pass through signal acquisition
Module 100 is (such as：Arm band) obtain, and transmit to host computer, preferably pass through the wireless transmissions such as bluetooth or WiFi.
Natural gesture identification and arm posture parsing module 200 are (such as：Host computer signal handler) on the one hand electromyographic signal is carried out
Pattern-recognition, identify different types of natural gesture；On the other hand, the attitude algorithm arithmetic analysis people such as complementary filter can be passed through
The posture of body arm.It is wherein preferable, the information from multiple signal collecting devices can be resolved simultaneously, such as forearm and upper arm point
Different signal collecting devices is not worn, to obtain forearm and the respective posture of upper arm and both position relationships, so as to count
Angle information of each joint freedom degrees etc. is calculated, the control for mechanical arm.The natural gesture parsed and arm posture is defeated
Enter to manipulator motion control module 300, the module can establish mechanical arm-arm physical model, by the kinematic parameter of arm
The control parameter of mechanical arm is converted into, so as to which control machinery arm 400 moves.The control of mechanical arm 400 can have different work
Pattern, including end-of-pipe control pattern and joint control pattern, the switching between different control models can be carried out by gesture.This
Outside, gesture can complete different crawl tasks with the mechanical paw of control machinery arm end.By the above course of work, entirely
System can by it is a kind of naturally in a manner of realize control of the human body to mechanical arm.
It is a kind of one embodiment of Multi-shaft mechanical arm motion control method in the present invention with reference next to Fig. 3, including with
Lower step：
S1, calibration data acquisition device, it is preferred that wear sEMG and IMU data measurement unit (such as：Arm band), and it is right
The position and direction of wearing are calibrated, so as to the analysis or resolving of follow-up arm motion posture.
S2, obtain surface electromyogram signal and IMU information.After S1 is calibrated, user wears one or more arm bands and done
Go out action, such as any swinging arm, the movable information and myoelectricity for gathering upper arm and/or forearm in real time are believed within the specific limits
Breath, the mode of operation of mechanical arm can also be switched by different gesture motions.Preferably, in whole process holding electrode with
The close contact of skin, avoid arm that the slip of circumferential and axial occurs with relative arm, to ensure to gather the quality of signal.It is integrated
IMU units in information acquisition module can record the exercise data of human arm in real time, and the data can be to a certain degree
The posture of upper reflection arm and displacement.
S3, Signal Pretreatment are simultaneously sent by wireless communication mode.In step S2, S3, user can preset one
A little natural gestures are simultaneously trained according to certain regulation or requirement, are worn on the electromyographic signal of the arm band collection arm muscles of arm
And IMU information, the signal that collects is filtered, amplification, is transmitted through transmission means such as bluetooth/WiFi to upper after A/D conversions
Machine is handled.The harvester of sEMG and IMU signals specifically may be referred to above corresponding description.Wherein, to original letter
Number pre-process mainly includes：Primary signal is amplified, preferable multiplication factor is between 100-500；Carry out band logical
Filtering, preferable passband is 20-450Hz；Carry out A/D conversions and simultaneously carry out digital sample, it is preferred that myoelectricity sample frequency is
1000Hz, IMU data sampling frequency are 50Hz.
S4, carry out nature gesture identification and the parsing of arm posture.In step s 4, for the identification of natural gesture, entirely
Process is further divided into training and using two process.With further reference to Fig. 4, first, user according to setting pattern
(such as：A few class nature gestures being previously set) it is trained, needed in the training stage according to training characteristics collection, obtain grader
Parameter.Specifically, the data collected segmentation is carried out into a point window to handle, then to dividing window data to carry out feature extraction and feature
Dimensionality reduction, so as to obtain training sorter model to complete classifier training, it is preferred that corresponding process can be repeated and repeatedly instructed
Practice.Then, can be to carry out pattern classification to new electromyographic signal using the grader that training obtains in service stage, identification is not
With natural gesture, as user arbitrarily does defined gesture, so as to export the recognition result of corresponding gesture, and resolve arm appearance
State, each articulation angle is derived, can be with control machinery arm end so as to for switching different mechanical arm mode of operations
Hold actuator.More specifically, for IMU data, Inertial Measurement Unit can be calculated by complementary filter scheduling algorithm
Attitude angle information, so as to indirectly reflect arm motion state.
Resolving for arm posture, the IMU information obtained in calibrated collecting device can characterize human body hand
The posture and motion state of arm, arm attitude information can be obtained according to the attitude algorithm such as complementary filter algorithm.In addition, with reference to hand
The physical model of arm can extrapolate the spatial movement situation of arm.Further, can be according to hand under end-of-pipe control pattern
The change of arm posture can calculate the displacement of arm end, so as to the displacement of corresponding mechanical arm tail end；Under joint control pattern,
The change of position, direction and the arm posture that can be worn according to data acquisition module, calculate the angle in each joint of arm
Change information is spent, the information of these angle changes has corresponded to the angle change in each joint of mechanical arm.
S5, arm-mechanical arm physical relation model is established, export manipulator motion controlled quentity controlled variable.With further reference to Fig. 5,
In step S5, according to the corresponding relation between human arm and mechanical arm (such as：Joint corresponding relation, size relationship etc.), can be with
Establish physical relation model between the two.Arm-mechanical arm physical relation model includes joint control pattern and end-of-pipe control
Pattern, the motion control to mechanical arm is realized by both patterns., can be according to arm posture solution under joint control pattern
Calculate each articulation amount of control machinery arm motion, the change of the arm joint angle being such as calculated in step s 4 can be by
Certain proportion is mapped in the motion control of mechanical arm；Under end-of-pipe control pattern, it can be moved with output control mechanical arm tail end
Displacement information, tip displacement counter can release the controlled quentity controlled variable of each articulation of control machinery arm.
S6, driving manipulator motion.All kinds of control parameters drawn according to step before, such as each joint of control machinery arm
Amount of spin, driving mechanical arm are moved accordingly, are such as performed and are captured various operations.
The present invention is illustrated by above-described embodiment, but it is to be understood that, above-described embodiment is only intended to
Citing and the purpose of explanation, and be not intended to limit the invention in described scope of embodiments.In addition people in the art
Member can also make more kinds of it is understood that the invention is not limited in above-described embodiment according to the teachings of the present invention
Variants and modifications, these variants and modifications are all fallen within scope of the present invention.Protection scope of the present invention by
The appended claims and its equivalent scope are defined.
Claims (10)
- A kind of 1. Multi-shaft mechanical arm kinetic control system, it is characterised in that including：Mechanical arm, including entity mechanical arm or virtual machine arm；Signal acquisition module, worn by user, be configured as collection surface electromyographic signal and Inertial Measurement Unit signal；Natural gesture identification and arm posture parsing module, it is configured to, with the surface myoelectric that the signal acquisition module obtains Signal and Inertial Measurement Unit signal identify nature gesture and parse arm posture；AndManipulator motion control module, it is configured as the knowledge obtained according to the natural gesture identification and arm posture parsing module Not and analysis result controls the mechanical arm realization motion corresponding with user action；Wherein, the signal acquisition module, the natural gesture identification and arm posture parsing module, the manipulator motion control Communicated to connect between molding block and the mechanical arm.
- 2. system according to claim 1, the signal acquisition module also includes surface myoelectric electrode, Inertial Measurement Unit Signaling module, power management module, signal pre-processing module and wireless communication module, it is characterised in that：The signal acquisition Module is configured as gathering multichannel electromyographic signal, and the Inertial Measurement Unit signaling module is configured to supply 3 axle accelerations Meter, 3 axle gyroscopes and 3 axle magnetometer informations are simultaneously integrated in the signal acquisition module.
- 3. system according to claim 2, it is characterised in that the signal pre-processing module also include pre-amplification circuit, High-pass filtering circuit, low-pass filter circuit and A/D change-over circuits, wherein, the power management module is configured as producing not Voltage with amplitude is powered for different unit modules.
- 4. system according to claim 1, it is characterised in that：The natural gesture identification and arm posture parsing module quilt It is configured to by carrying out pattern classification to surface electromyogram signal to identify nature gesture, and it is real-time to Inertial Measurement Unit signal Resolve the spatial attitude and movable information of arm.
- 5. system according to claim 1, it is characterised in that：The manipulator motion control module is configured as by building The knowledge that vertical physical relation model between arm and mechanical arm obtains the natural gesture identification and arm posture parsing module Not and analysis result changes into the control information for controlling the mechanical arm, so as to which the realization of control machinery arm is consistent with arm motion Motion, gesture identification result can also be used for the switching of mode of operation.
- 6. a kind of Multi-shaft mechanical arm motion control method, it is characterised in that comprise the following steps：S1, calibration data acquisition device；S2, obtain surface electromyogram signal and IMU information；S3, Signal Pretreatment are simultaneously sent by wireless communication mode；S4, carry out gesture identification and the parsing of arm posture；S5, arm-mechanical arm physical relation model is established, export manipulator motion controlled quentity controlled variable；S6, driving manipulator motion.
- 7. according to the method for claim 6, it is characterised in that Signal Pretreatment includes described in step S3：To original letter Number it is amplified, bandpass filtering and carries out A/D conversions and digital sample.
- 8. according to the method for claim 6, it is characterised in that step S4 includes：S41, data divide window to handle；S42, to dividing window data to carry out feature extraction and Feature Dimension Reduction；S43, classifier training and test；S44, output nature gesture recognition result；S45, arm posture is resolved, derive each articulation angle and arm tip displacement.
- 9. according to the method for claim 6, it is characterised in that step S4 also includes：By not after result is identified The mode of operation of same gesture motion switching mechanical arm.
- 10. according to the method for claim 6, it is characterised in that arm-mechanical arm physical relation is established described in step S5 Model includes：I) end-of-pipe control pattern：Pass through the anti-controlled quentity controlled variable for releasing each articulation of control machinery arm of the displacement of end；And/orIi) joint control pattern：The change of the arm joint angle obtained in step s 4 is mapped to machinery by a certain percentage In the motion control of arm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710992223.4A CN107553499A (en) | 2017-10-23 | 2017-10-23 | Natural the gesture motion control system and method for a kind of Multi-shaft mechanical arm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710992223.4A CN107553499A (en) | 2017-10-23 | 2017-10-23 | Natural the gesture motion control system and method for a kind of Multi-shaft mechanical arm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107553499A true CN107553499A (en) | 2018-01-09 |
Family
ID=60986977
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710992223.4A Pending CN107553499A (en) | 2017-10-23 | 2017-10-23 | Natural the gesture motion control system and method for a kind of Multi-shaft mechanical arm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107553499A (en) |
Cited By (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108247617A (en) * | 2018-04-02 | 2018-07-06 | 深圳了然视觉科技有限公司 | A kind of intelligent machine arm system |
| CN108381511A (en) * | 2018-04-28 | 2018-08-10 | 刘宇栋 | Gesture control mobile platform based on induction remote control gloves |
| CN108500989A (en) * | 2018-04-07 | 2018-09-07 | 广州未名雷蒙特实验室科技有限公司 | Laboratory intelligent machine hand system and its operating method |
| CN108549490A (en) * | 2018-05-03 | 2018-09-18 | 林潼 | A kind of gesture identification interactive approach based on Leap Motion equipment |
| CN108742957A (en) * | 2018-06-22 | 2018-11-06 | 上海交通大学 | A kind of artificial limb control method of multi-sensor fusion |
| CN108748220A (en) * | 2018-05-28 | 2018-11-06 | 武汉理工大学 | A kind of foot based on Inertial Measurement Unit-machine follow-up control method and control system |
| CN108983980A (en) * | 2018-07-27 | 2018-12-11 | 河南科技大学 | A kind of mobile robot basic exercise gestural control method |
| CN109676609A (en) * | 2019-01-24 | 2019-04-26 | 深圳市工匠社科技有限公司 | Robot control system and Related product |
| CN109676615A (en) * | 2019-01-18 | 2019-04-26 | 合肥工业大学 | A kind of spray robot teaching method and device using arm electromyography signal and motion capture signal |
| CN109732613A (en) * | 2019-03-13 | 2019-05-10 | 哈尔滨若朋机器人有限责任公司 | Mechanical arm reaches particular state recruitment evaluation system |
| CN109778932A (en) * | 2019-03-22 | 2019-05-21 | 江苏徐工工程机械研究院有限公司 | A kind of contactless digging machine arm control system and control method based on arm posture |
| CN110238852A (en) * | 2019-06-17 | 2019-09-17 | 湖南大学 | A kind of robots arm's hand remote operating control method and system |
| CN110347243A (en) * | 2019-05-30 | 2019-10-18 | 深圳乐行天下科技有限公司 | A kind of working method and robot of robot |
| CN110370264A (en) * | 2018-04-13 | 2019-10-25 | 江门市印星机器人有限公司 | Mechanical arm remotely imitates control system |
| CN110434834A (en) * | 2019-08-19 | 2019-11-12 | 浙江工业大学 | A kind of man-machine collaboration mechanical arm |
| CN110919650A (en) * | 2019-11-20 | 2020-03-27 | 江苏大学 | Low-delay grabbing teleoperation system based on SVM (support vector machine) |
| CN110962146A (en) * | 2019-05-29 | 2020-04-07 | 博睿科有限公司 | Manipulation system and method of robot apparatus |
| CN111297526A (en) * | 2020-03-02 | 2020-06-19 | 苏州通和景润康复科技有限公司 | Multi-joint upper limb myoelectric artificial limb control device |
| CN111399640A (en) * | 2020-03-05 | 2020-07-10 | 南开大学 | Multi-mode man-machine interaction control method for flexible arm |
| CN111531537A (en) * | 2020-05-07 | 2020-08-14 | 金陵科技学院 | Mechanical arm control method based on multiple sensors |
| CN111700718A (en) * | 2020-07-13 | 2020-09-25 | 北京海益同展信息科技有限公司 | Holding posture identifying method, holding posture identifying device, artificial limb and readable storage medium |
| CN111730604A (en) * | 2020-08-04 | 2020-10-02 | 季华实验室 | Mechanical clamping jaw control method and device based on human body electromyographic signals and electronic equipment |
| CN112214109A (en) * | 2020-09-30 | 2021-01-12 | 深圳市润谊泰益科技有限责任公司 | Compound control method, device and system based on myoelectricity and attitude data |
| CN112405539A (en) * | 2020-11-11 | 2021-02-26 | 东南大学 | Robot natural control method based on electromyographic signals and electroencephalogram error potentials |
| CN112643658A (en) * | 2019-10-10 | 2021-04-13 | 南京邮电大学 | Calibration method for adaptive error modeling of series robot based on SIR dimension reduction DH model |
| CN113021349A (en) * | 2021-03-24 | 2021-06-25 | 季华实验室 | Remote operation control method, device, system, equipment and storage medium |
| CN113305845A (en) * | 2021-06-03 | 2021-08-27 | 广东工业大学 | Multi-mechanical arm cooperation method |
| CN113498952A (en) * | 2021-06-07 | 2021-10-15 | 西安理工大学 | Model display device with human-computer interaction function |
| CN113730190A (en) * | 2021-09-18 | 2021-12-03 | 上海交通大学 | Upper limb rehabilitation robot system with three-dimensional space motion |
| CN113805696A (en) * | 2021-09-01 | 2021-12-17 | 肩并肩智能技术(北京)有限公司 | Machine learning method based on surface electromyographic signals and dynamic capture technology |
| CH717682A1 (en) * | 2020-07-21 | 2022-01-31 | Univ St Gallen | Device for configuring robotic systems using electromyographic signals. |
| CN114083544A (en) * | 2022-01-21 | 2022-02-25 | 成都市皓煊光电新材料科技研发中心有限公司 | Method and device for controlling movement of hand-shaped equipment, hand-shaped equipment and storage medium |
| CN114986525A (en) * | 2022-07-13 | 2022-09-02 | 佛山纽欣肯智能科技有限公司 | Robot handheld teaching device and method based on multi-mode information |
| WO2023065495A1 (en) * | 2021-10-20 | 2023-04-27 | 深圳先进技术研究院 | Intracranial hematoma puncture and drainage operation system using robotic arm for puncture |
| WO2023138784A1 (en) | 2022-01-21 | 2023-07-27 | Universität St. Gallen | System and method for configuring a robot |
| CN116728406A (en) * | 2023-06-15 | 2023-09-12 | 甘肃云梯信息科技有限公司 | Manipulator somatosensory recognition control system based on support vector machine |
| CN117340931A (en) * | 2023-09-21 | 2024-01-05 | 北京三月雨文化传播有限责任公司 | All-angle autonomous adjustable multimedia real object exhibition device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104656112A (en) * | 2015-01-28 | 2015-05-27 | 重庆大学 | Personal locating method and personal locating device based on surface electromyogram signal and MEMS inertial measurement unit combination |
| CN104772756A (en) * | 2015-01-26 | 2015-07-15 | 杭州师范大学 | Mechanical arm based on inertial measurement units and control method thereof |
| CN105005383A (en) * | 2015-07-10 | 2015-10-28 | 昆山美莱来工业设备有限公司 | Wearable arm band that manipulates mobile robot by using hand gesture |
| US20150308618A1 (en) * | 2014-03-12 | 2015-10-29 | Koncept Innovators, LLC. | Vest-mounted gimbal support, and a method for its use |
| CN204790855U (en) * | 2015-07-10 | 2015-11-18 | 昆山美莱来工业设备有限公司 | Utilize gesture to control mobile robot's wearable arm ring |
| CN106326881A (en) * | 2016-09-21 | 2017-01-11 | 济南超感智能科技有限公司 | Gesture recognition method and gesture recognition device for realizing human-computer interaction |
| CN106569606A (en) * | 2016-11-08 | 2017-04-19 | 上海交通大学 | Smart home infrared control system and smart home infrared control method based on natural gesture identification |
| CN106695794A (en) * | 2017-02-20 | 2017-05-24 | 苏州晨本智能科技有限公司 | Mobile machine arm system based on surface myoelectric signal and control method of mobile machine arm system |
-
2017
- 2017-10-23 CN CN201710992223.4A patent/CN107553499A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150308618A1 (en) * | 2014-03-12 | 2015-10-29 | Koncept Innovators, LLC. | Vest-mounted gimbal support, and a method for its use |
| CN104772756A (en) * | 2015-01-26 | 2015-07-15 | 杭州师范大学 | Mechanical arm based on inertial measurement units and control method thereof |
| CN104656112A (en) * | 2015-01-28 | 2015-05-27 | 重庆大学 | Personal locating method and personal locating device based on surface electromyogram signal and MEMS inertial measurement unit combination |
| CN105005383A (en) * | 2015-07-10 | 2015-10-28 | 昆山美莱来工业设备有限公司 | Wearable arm band that manipulates mobile robot by using hand gesture |
| CN204790855U (en) * | 2015-07-10 | 2015-11-18 | 昆山美莱来工业设备有限公司 | Utilize gesture to control mobile robot's wearable arm ring |
| CN106326881A (en) * | 2016-09-21 | 2017-01-11 | 济南超感智能科技有限公司 | Gesture recognition method and gesture recognition device for realizing human-computer interaction |
| CN106569606A (en) * | 2016-11-08 | 2017-04-19 | 上海交通大学 | Smart home infrared control system and smart home infrared control method based on natural gesture identification |
| CN106695794A (en) * | 2017-02-20 | 2017-05-24 | 苏州晨本智能科技有限公司 | Mobile machine arm system based on surface myoelectric signal and control method of mobile machine arm system |
Cited By (44)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108247617A (en) * | 2018-04-02 | 2018-07-06 | 深圳了然视觉科技有限公司 | A kind of intelligent machine arm system |
| CN108500989A (en) * | 2018-04-07 | 2018-09-07 | 广州未名雷蒙特实验室科技有限公司 | Laboratory intelligent machine hand system and its operating method |
| CN110370264A (en) * | 2018-04-13 | 2019-10-25 | 江门市印星机器人有限公司 | Mechanical arm remotely imitates control system |
| CN108381511A (en) * | 2018-04-28 | 2018-08-10 | 刘宇栋 | Gesture control mobile platform based on induction remote control gloves |
| CN108549490A (en) * | 2018-05-03 | 2018-09-18 | 林潼 | A kind of gesture identification interactive approach based on Leap Motion equipment |
| CN108748220A (en) * | 2018-05-28 | 2018-11-06 | 武汉理工大学 | A kind of foot based on Inertial Measurement Unit-machine follow-up control method and control system |
| CN108742957A (en) * | 2018-06-22 | 2018-11-06 | 上海交通大学 | A kind of artificial limb control method of multi-sensor fusion |
| CN108983980A (en) * | 2018-07-27 | 2018-12-11 | 河南科技大学 | A kind of mobile robot basic exercise gestural control method |
| CN109676615A (en) * | 2019-01-18 | 2019-04-26 | 合肥工业大学 | A kind of spray robot teaching method and device using arm electromyography signal and motion capture signal |
| CN109676609A (en) * | 2019-01-24 | 2019-04-26 | 深圳市工匠社科技有限公司 | Robot control system and Related product |
| CN109732613A (en) * | 2019-03-13 | 2019-05-10 | 哈尔滨若朋机器人有限责任公司 | Mechanical arm reaches particular state recruitment evaluation system |
| CN109732613B (en) * | 2019-03-13 | 2023-08-18 | 哈尔滨市伟晨星知识产权法律服务有限公司 | Evaluation system for effect of mechanical arm reaching specific state |
| CN109778932A (en) * | 2019-03-22 | 2019-05-21 | 江苏徐工工程机械研究院有限公司 | A kind of contactless digging machine arm control system and control method based on arm posture |
| US11612999B2 (en) | 2019-05-29 | 2023-03-28 | BrainCo Inc. | System and method for manipulating robotic device |
| CN110962146A (en) * | 2019-05-29 | 2020-04-07 | 博睿科有限公司 | Manipulation system and method of robot apparatus |
| CN110347243A (en) * | 2019-05-30 | 2019-10-18 | 深圳乐行天下科技有限公司 | A kind of working method and robot of robot |
| CN110238852A (en) * | 2019-06-17 | 2019-09-17 | 湖南大学 | A kind of robots arm's hand remote operating control method and system |
| CN110434834A (en) * | 2019-08-19 | 2019-11-12 | 浙江工业大学 | A kind of man-machine collaboration mechanical arm |
| CN112643658A (en) * | 2019-10-10 | 2021-04-13 | 南京邮电大学 | Calibration method for adaptive error modeling of series robot based on SIR dimension reduction DH model |
| CN110919650A (en) * | 2019-11-20 | 2020-03-27 | 江苏大学 | Low-delay grabbing teleoperation system based on SVM (support vector machine) |
| CN111297526A (en) * | 2020-03-02 | 2020-06-19 | 苏州通和景润康复科技有限公司 | Multi-joint upper limb myoelectric artificial limb control device |
| CN111297526B (en) * | 2020-03-02 | 2022-07-08 | 苏州通和景润康复科技有限公司 | Multi-joint upper limb myoelectric artificial limb control device |
| CN111399640A (en) * | 2020-03-05 | 2020-07-10 | 南开大学 | Multi-mode man-machine interaction control method for flexible arm |
| CN111531537A (en) * | 2020-05-07 | 2020-08-14 | 金陵科技学院 | Mechanical arm control method based on multiple sensors |
| CN111531537B (en) * | 2020-05-07 | 2022-11-01 | 金陵科技学院 | Mechanical arm control method based on multiple sensors |
| CN111700718A (en) * | 2020-07-13 | 2020-09-25 | 北京海益同展信息科技有限公司 | Holding posture identifying method, holding posture identifying device, artificial limb and readable storage medium |
| CH717682A1 (en) * | 2020-07-21 | 2022-01-31 | Univ St Gallen | Device for configuring robotic systems using electromyographic signals. |
| CN111730604A (en) * | 2020-08-04 | 2020-10-02 | 季华实验室 | Mechanical clamping jaw control method and device based on human body electromyographic signals and electronic equipment |
| CN112214109A (en) * | 2020-09-30 | 2021-01-12 | 深圳市润谊泰益科技有限责任公司 | Compound control method, device and system based on myoelectricity and attitude data |
| CN112405539B (en) * | 2020-11-11 | 2022-03-04 | 东南大学 | Robot natural control method based on electromyographic signals and electroencephalogram error potentials |
| CN112405539A (en) * | 2020-11-11 | 2021-02-26 | 东南大学 | Robot natural control method based on electromyographic signals and electroencephalogram error potentials |
| CN113021349A (en) * | 2021-03-24 | 2021-06-25 | 季华实验室 | Remote operation control method, device, system, equipment and storage medium |
| CN113305845A (en) * | 2021-06-03 | 2021-08-27 | 广东工业大学 | Multi-mechanical arm cooperation method |
| CN113305845B (en) * | 2021-06-03 | 2022-11-04 | 广东工业大学 | Multi-mechanical arm cooperation method |
| CN113498952A (en) * | 2021-06-07 | 2021-10-15 | 西安理工大学 | Model display device with human-computer interaction function |
| CN113805696A (en) * | 2021-09-01 | 2021-12-17 | 肩并肩智能技术(北京)有限公司 | Machine learning method based on surface electromyographic signals and dynamic capture technology |
| CN113730190A (en) * | 2021-09-18 | 2021-12-03 | 上海交通大学 | Upper limb rehabilitation robot system with three-dimensional space motion |
| WO2023065495A1 (en) * | 2021-10-20 | 2023-04-27 | 深圳先进技术研究院 | Intracranial hematoma puncture and drainage operation system using robotic arm for puncture |
| CN114083544A (en) * | 2022-01-21 | 2022-02-25 | 成都市皓煊光电新材料科技研发中心有限公司 | Method and device for controlling movement of hand-shaped equipment, hand-shaped equipment and storage medium |
| CN114083544B (en) * | 2022-01-21 | 2022-04-12 | 成都市皓煊光电新材料科技研发中心有限公司 | Method and device for controlling movement of hand-shaped equipment, hand-shaped equipment and storage medium |
| WO2023138784A1 (en) | 2022-01-21 | 2023-07-27 | Universität St. Gallen | System and method for configuring a robot |
| CN114986525A (en) * | 2022-07-13 | 2022-09-02 | 佛山纽欣肯智能科技有限公司 | Robot handheld teaching device and method based on multi-mode information |
| CN116728406A (en) * | 2023-06-15 | 2023-09-12 | 甘肃云梯信息科技有限公司 | Manipulator somatosensory recognition control system based on support vector machine |
| CN117340931A (en) * | 2023-09-21 | 2024-01-05 | 北京三月雨文化传播有限责任公司 | All-angle autonomous adjustable multimedia real object exhibition device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107553499A (en) | Natural the gesture motion control system and method for a kind of Multi-shaft mechanical arm | |
| CN107378944B (en) | Multidimensional surface electromyographic signal artificial hand control method based on principal component analysis method | |
| Xu et al. | Advances and disturbances in sEMG-based intentions and movements recognition: A review | |
| CN101947152B (en) | Electroencephalogram-voice control system and working method of humanoid artificial limb | |
| Yang et al. | Dynamic hand motion recognition based on transient and steady-state EMG signals | |
| CN103654774A (en) | Wearable movable bracelet | |
| WO2018111138A1 (en) | Method and system for controlling an intelligent bionic limb | |
| CN104546235A (en) | Hybrid prosthetic hand | |
| CN104997581A (en) | Artificial hand control method and apparatus for driving EEG signals on the basis of facial expressions | |
| CN103815991B (en) | Virtual training system and the method for doing evil through another person of dual pathways operation perception | |
| CN105962935A (en) | Brain electrical nerve feedback training system and method for improving motor learning function | |
| CN103294192A (en) | LED lamp switch control device and control method thereof based on motor imagery | |
| CN105012057A (en) | Intelligent artificial limb based on double-arm electromyogram and attitude information acquisition and motion classifying method | |
| CN106491251A (en) | One kind is based on non-intrusion type brain-computer interface robotic arm control system and its control method | |
| CN115050104B (en) | Continuous gesture action recognition method based on multichannel surface electromyographic signals | |
| Chang et al. | A hierarchical hand motions recognition method based on IMU and sEMG sensors | |
| Zakia et al. | Deep learning technique in recognizing hand grasps using FMG signals | |
| CN109498362A (en) | A kind of hemiplegic patient's hand movement function device for healing and training and model training method | |
| CN107914273A (en) | Mechanical arm teaching system based on gesture control | |
| CN111134974A (en) | Wheelchair robot system based on augmented reality and multi-mode biological signals | |
| CN113370172B (en) | Auxiliary manipulator system based on multiple sensors and force feedback and application method thereof | |
| CN111481197B (en) | A living-machine multimode information acquisition fuses device for man-machine natural interaction | |
| CN114936574A (en) | High-flexibility manipulator system based on BCI and implementation method thereof | |
| Lin et al. | Voluntary-Redundant Hybrid Control of SuperLimb based on Redundant Muscle for On-Site Assembly Tasks | |
| CN111522435A (en) | Mechanical arm interaction method based on surface electromyogram signal |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180109 |
|
| RJ01 | Rejection of invention patent application after publication |