CN109591013A - A kind of flexible assembly analogue system and its implementation - Google Patents
A kind of flexible assembly analogue system and its implementation Download PDFInfo
- Publication number
- CN109591013A CN109591013A CN201811517301.6A CN201811517301A CN109591013A CN 109591013 A CN109591013 A CN 109591013A CN 201811517301 A CN201811517301 A CN 201811517301A CN 109591013 A CN109591013 A CN 109591013A
- Authority
- CN
- China
- Prior art keywords
- information
- module
- mechanical arm
- flexible assembly
- analogue system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1679—Programme controls characterised by the tasks executed
- B25J9/1687—Assembly, peg and hole, palletising, straight line, weaving pattern movement
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
- B25J9/1605—Simulation of manipulator lay-out, design, modelling of manipulator
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Manipulator (AREA)
- Image Analysis (AREA)
Abstract
Present disclose provides a kind of flexible assembly analogue system and its implementation.Wherein, a kind of flexible assembly analogue system, comprising: vision guide module, the object pose information for being used to acquire on fitter's bench and mechanical arm current location information, and it is accordingly sent to power sensing module and impedance control module respectively；Power sensing module, its contact information for being used for collection machinery arm with assembly target, and matched and corrected with by received object pose information, to increase the dimension of contact information, and then obtains contact condition and feed back to vision guide module using the guide data as assembly next time；The power sensing module is also used to the wrist of collection machinery arm by force information and is sent to impedance control module；Impedance control module, being used for mechanical arm current location information based on the received and wrist by force information is respectively that vision guide module and power sensing module provide mechanical arm position update information and control moment.
Description
Technical field
The disclosure belongs to assembly system field more particularly to a kind of flexible assembly analogue system and its implementation.
Background technique
Only there is provided background technical informations relevant to the disclosure for the statement of this part, it is not necessary to so constitute first skill
Art.
In recent years, robot technology continues to develop, and receives more and more attention, and robot also obtains in the industrial production
Extensive use is arrived, wherein assembly work occupies biggish specific gravity in production, with generation and the production standard of new process
It improves, increasingly embodies the requirement to Flexible Equipment.Traditional teaching programmed method needs programming personnel to have certain profession to know
Know, especially contain contact condition during, program is increasingly complex, and it is this dependent on pinpoint program can because
Various uncertain in operation and fail so that conventional programming techniques hinder robot in the extensive use of service industry.
Summary of the invention
According to the one aspect of one or more other embodiments of the present disclosure, a kind of flexible assembly analogue system is provided, it will
Power feels that perception, vision guide and impedance control are combined, and improves the interaction and cooperation between technical ability, compensates for respective limitation
Property, improve system assembly efficiency and stability.
A kind of flexible assembly analogue system of the disclosure, comprising:
Vision guide module, the object pose information for being used to acquire on fitter's bench and mechanical arm present bit confidence
Breath, and it is accordingly sent to power sensing module and impedance control module respectively；
Power sensing module, be used for collection machinery arm with assemble the contact information of target, and with by received object pose
Information is matched and is corrected, and to increase the dimension of contact information, and then is obtained contact condition and is fed back to vision guide module
Using the guide data as assembly next time；The power sensing module is also used to the wrist of collection machinery arm by force information and is sent to
Impedance control module；
Impedance control module, being used for mechanical arm current location information based on the received and wrist by force information is respectively to regard
Feel that guiding module and power sensing module provide mechanical arm position update information and control moment.
In one or more embodiments, in the vision guide module, the object pose on fitter's bench is acquired
The process of information includes:
The relative position that vision guide module is determined in known environment, realizes calibration；
Vision guide module records image information, subscribes to vision guide Module nodes message in a program, obtains in image
Hold；
The image of acquisition is filtered；
Index enhancing function is called to enhance the useful information of filtered image information and inhibit garbage；
Enhanced image is divided into different zones according to certain similarity criterion；
It calculates and the gradient orientation histogram of statistical picture regional area carrys out constitutive characteristic, by the presentation and shape of localized target
Shape is described by the direction Density Distribution at gradient or edge；
Pose is completed by function solver () to resolve, and obtains the spatial position of image object；
Coordinate transform is executed using function transform (), obtains assembly target in the parameter value of world coordinate system.
In one or more embodiments, in the vision guide module, using maximum variance between clusters, function is utilized
Otsu () divides an image into different zones according to certain similarity criterion.
In one or more embodiments, in the impedance control module, the mistake of mechanical arm position update information is obtained
Journey includes:
Set mechanical arm desired locations；
According to each joint control torque of Inverse Dynamics of Manipulators program solution mechanical arm；
Torque is passed into mechanical arm through prescription controller, obtains wrist stress；
Wrist stress inputs end contact force conversion function after processing, exports contact force；
Contact force makes the difference with desired contact force, obtains position correction amount through impedance control module, and then modify desired locations.
In one or more embodiments, the power sensing module is also used to:
Initialize mechanical arm pose and each joint rotation angle, the relevant parameter of statement assembly algorithm and tactful network；
Mechanical arm posture is adjusted, assembly movement is executed；
Receive the six-dimensional force or pose letter when the breaker upper and lower covers contact of the contact sensor transmission of known environment setting
Breath obtains data when contact, realizes force sensing function.
In one or more embodiments, the tactful network is deep learning network.
A kind of implementation method of flexible assembly analogue system of the disclosure, comprising:
Initialization；
Create deep learning network；
Flexible assembly environment is initialized；
Circulation scene is set up, calls function Adj_eff () to execute assembly movement in the circulating cycle, passes through serial reward ()
Function calculates the return value assembled every time；
Obtain the six-dimensional force and posture information of contact sensor acquisition in power sensing module；
Training deep learning network, designs optimizer optimizer；It is dynamic by function egreedy_action () training
Make, statement create_training_method () function realizes test, and feedback arrives robot motion；
Return value, output second leg movement are solved by evaluation system；
Adjustment posture is obtained according to Previous results, repeats assembling process.
In one or more embodiments, the implementation method of the flexible assembly analogue system further include:
Draw Q value modified-image and return value modified-image.
In one or more embodiments, operation create_Q_network () creates deep learning network.
In one or more embodiments, flexible assembly environment is reset using reset () function.
The beneficial effect of the disclosure is:
(1) power is felt that perception, vision guide and impedance control are combined in the flexible assembly analogue system of the disclosure, mentioned
Interaction and cooperation between high technical ability, compensate for respective limitation, improve system assembly efficiency and stability.
(2) the flexible assembly analogue system of the disclosure is used towards technical ability programmed method, simplifies the generation of program, is improved
Programming efficiency allows layman to carry out certain modification and maintenance.
(3) the flexible assembly analogue system independence of the disclosure is higher, being capable of less production line person works amount.
(4) simulated environment that the flexible assembly analogue system of the disclosure is established, enables researcher to test in systems
The problem of assembling effect, being likely to occur when reducing the running of actual production line and product failure, shorten research and development and test period,
The improvement of hardware facility simultaneously also plays booster action to the evaluation for improving the process.
Detailed description of the invention
The Figure of description for constituting a part of this disclosure is used to provide further understanding of the disclosure, and the disclosure is shown
Meaning property embodiment and its explanation do not constitute the improper restriction to the disclosure for explaining the disclosure.
Fig. 1 is a kind of flexible assembly analogue system structural schematic diagram of the disclosure.
Fig. 2 is the process schematic of the object pose information on vision guide module acquisition fitter's bench.
Fig. 3 is the process schematic that impedance control module obtains mechanical arm position update information.
Fig. 4 is the flexible assembly analogue system simulated environment schematic diagram of the disclosure.
Fig. 5 is the file composition and connection schematic diagram for establishing assembly simulation environment.
Fig. 6 is that process flow diagram flow chart is realized in the assembly of flexible assembly analogue system.
Fig. 7 is the flow chart for constructing learning network.
Specific embodiment
It is noted that following detailed description is all illustrative, it is intended to provide further instruction to the disclosure.Unless another
It indicates, all technical and scientific terms used herein has usual with disclosure person of an ordinary skill in the technical field
The identical meanings of understanding.
It should be noted that term used herein above is merely to describe specific embodiment, and be not intended to restricted root
According to the illustrative embodiments of the disclosure.As used herein, unless the context clearly indicates otherwise, otherwise singular
Also it is intended to include plural form, additionally, it should be understood that, when in the present specification using term "comprising" and/or " packet
Include " when, indicate existing characteristics, step, operation, device, component and/or their combination.
Fig. 1 is a kind of flexible assembly analogue system structural schematic diagram of the disclosure.
As shown in Figure 1, a kind of flexible assembly analogue system of the disclosure, comprising:
(1) vision guide module, the object pose information for being used to acquire on fitter's bench and mechanical arm current location
Information, and it is accordingly sent to power sensing module and impedance control module respectively.
As shown in Fig. 2, acquiring the process packet of the object pose information on fitter's bench in the vision guide module
It includes:
(1.1) relative position that vision guide module is determined in known environment, realizes calibration；
(1.2) vision guide module records image information, subscribes to vision guide Module nodes message in a program, obtains figure
As content；
(1.3) image of acquisition is filtered；
Such as: design filter function filter () carries out image procossing, eliminates noise；
(1.4) index enhancing function is called to enhance the useful information of filtered image information and inhibit garbage；
Such as: call index enhancing function exp_enhance () to convert information into the form more suitable for analysis processing,
Inhibit garbage, improves the use value of image；
(1.5) enhanced image is divided by different zones according to certain similarity criterion；
Such as: maximum variance between clusters are used, are divided image according to certain similarity criterion using function otsu ()
At different zones；
(1.6) it calculates and the gradient orientation histogram of statistical picture regional area carrys out constitutive characteristic, by the table of localized target
As being described with shape by the direction Density Distribution at gradient or edge；
Such as: it is calculated by hog () and the gradient orientation histogram of statistical picture regional area is come constitutive characteristic；
(1.7) pose is completed by function solver () to resolve, obtain the spatial position of image object；
(1.8) coordinate transform is executed using function transform (), obtains assembly target in the parameter of world coordinate system
Value.
(2) power sensing module, be used for collection machinery arm with assemble the contact information of target, and with by received target position
Appearance information is matched and is corrected, and to increase the dimension of contact information, and then is obtained contact condition and is fed back to vision guide mould
Guide data of the block to be assembled as next time；The power sensing module is also used to the wrist of collection machinery arm by force information and transmits
To impedance control module.
The power sensing module is also used to:
(2.1) mechanical arm pose, each joint rotation angle, the relevant parameter of statement assembly algorithm, tactful network are initialized.
(2.2) posture is adjusted, assembly movement is executed.
(2.3) contact of breaker upper and lower covers is sent by the contact sensor (Contact Sensor) that simulated environment is arranged
When six-dimensional force or the information such as pose, setting pair/contact_sensor_state topic carries out related subscription in a program, obtains
Data when contact are taken, realize the functions such as power perception.
(3) impedance control module is used for mechanical arm current location information and wrist based on the received and is distinguished by force information
Mechanical arm position update information and control moment are provided for vision guide module and power sensing module.
As shown in figure 3, in the impedance control module, the process for obtaining mechanical arm position update information includes:
(3.1) desired locations are set by iiwa.set_pose_target () method.
(3.2) according to each joint control torque of Inverse Dynamics of Manipulators program solution mechanical arm.
(3.3) torque is passed into mechanical arm through PID controller, obtains wrist stress.
(3.4) wrist stress inputs end contact force conversion function after processing, exports contact force.
(3.5) contact force makes the difference with desired contact force, obtains position correction amount through impedance controller, is superimposed with desired locations
As input quantity.
The disclosure additionally provides a kind of implementation method of flexible assembly analogue system.
As shown in figure 4, the flexible assembly analogue system of the disclosure, be provided with simulated environment, simulated environment include mechanical arm,
The physical models such as camera, fitter's bench, assembly ware, the factoid and related platform and its configuration key element of environment.Base
Simulated environment is established in ROS system, and carries out image conversion using tools such as Gazebo, RViz and shows.The system is by writing
URDF file carries out mechanical arm and describes with the model for being assembled device, for example can create hereof for mechanical arm main component each
From physical model, setting size, the information such as kinematics parameters retouch the emulation of assembly environment by the completion of SDF formatted file
It states, using launch integrating documents call relation, control program is write by related api interface.
As shown in figure 5, establishing file composition and the connection of assembly simulation environment are as follows:
Writing mechanical arm, camera and being assembled the model of device (by taking low-voltage circuit breaker as an example) and retouch by URDF file
State, the description object of URDF file include connecting rod (</link>) and joint (</joint>) two piths, it can be by corresponding
Visualization tool urdf_to_graphiz carries out image conversion and shows, defines the parameters such as inertia, pose, collision detection.
The description to assembly environment is carried out in SDF file, many aspects, the static and dynamic of object of declaration model are special
Property, illumination, landform even physics content, can further define the approach of a variety of environment, such as to light source, landform, street
It is configured.
Then multiple nodes are managed by launch file, customized certain parameters, to avoid successively opening
Terminal input instruction, the parameters such as statement simulation status, hardware interface, model, RViz state do standard for next emulation setting
It is standby, the nodes such as joint trajectories are then mapped, group node is defined, further call starting emulation (Gazebo, RViz etc.) file.
Process flow diagram flow chart is realized in a kind of assembly of flexible assembly analogue system of the disclosure, as shown in Figure 6:
Initialization；
Create deep learning network；
Flexible assembly environment is initialized；
Circulation scene is set up, calls function Adj_eff () to execute assembly movement in the circulating cycle, passes through serial reward ()
Function calculates the return value assembled every time；
Obtain the six-dimensional force and posture information of contact sensor acquisition in power sensing module；
Training deep learning network, designs optimizer optimizer；It is dynamic by function egreedy_action () training
Make, statement create_training_method () function realizes test, and feedback arrives robot motion；
Return value, output second leg movement are solved by evaluation system；
Adjustment posture is obtained according to Previous results, repeats assembling process.
Wherein, as shown in fig. 7, the program operation process of building learning network can be summarized as:
(1) operation _ _ init__ () function is initialized
(2) operation create_Q_network () creates deep learning network, including input layer, hidden layer, output layer, choosing
Take relu () as hidden layer activation primitive.
(3) simulated environment is reset using reset () function.
(4) circulation scene is set up, calls Adj_eff () to execute assembly movement in the circulating cycle, passes through serial reward () letter
Number calculates the return value assembled every time.
(5) it is obtained in Gazebo and is connect by rospy.Subscriber () subscription/contact_sensor_state message
Touch the information such as six-dimensional force, the pose of sensor acquisition.
(6) using train_Q_network () training network, including state storage, parameter updating method etc., design
Optimizer optimizer；By egreedy_action () training action, create_training_method () letter is stated
Number realizes test, and feedback arrives robot motion.
(7) modified-images such as Q value, return value are drawn.
Power is felt that perception, vision guide and impedance control are combined in the flexible assembly analogue system of the disclosure, is improved
Interaction and cooperation between technical ability compensate for respective limitation, improve system assembly efficiency and stability.
The flexible assembly analogue system of the disclosure is used towards technical ability programmed method, simplifies the generation of program, is improved and is compiled
Journey efficiency allows layman to carry out certain modification and maintenance.
The flexible assembly analogue system independence of the disclosure is higher, being capable of less production line person works amount.
The simulated environment that the flexible assembly analogue system of the disclosure is established, enables researcher's test set-up in systems
Effect reduces the problem of being likely to occur when actual production line operates and product failure, shortens research and development and test period, simultaneously
The improvement of hardware facility also plays booster action to the evaluation for improving the process.
Although above-mentioned be described in conjunction with specific embodiment of the attached drawing to the disclosure, model not is protected to the disclosure
The limitation enclosed, those skilled in the art should understand that, on the basis of the technical solution of the disclosure, those skilled in the art are not
Need to make the creative labor the various modifications or changes that can be made still within the protection scope of the disclosure.
Claims (10)
1. a kind of flexible assembly analogue system characterized by comprising
Vision guide module, the object pose information for being used to acquire on fitter's bench and mechanical arm current location information, and
It is accordingly sent to power sensing module and impedance control module respectively；
Power sensing module, be used for collection machinery arm with assemble the contact information of target, and with by received object pose information
It is matched and is corrected, to increase the dimension of contact information, and then obtained contact condition and feed back to vision guide module to make
For the guide data of assembly next time；The power sensing module is also used to the wrist of collection machinery arm by force information and is sent to impedance
Control module；
Impedance control module, being used for mechanical arm current location information based on the received and wrist by force information is respectively that vision is drawn
Guide module and power sensing module provide mechanical arm position update information and control moment.
2. a kind of flexible assembly analogue system as described in claim 1, which is characterized in that in the vision guide module,
The process of object pose information on acquisition fitter's bench includes:
The relative position that vision guide module is determined in known environment, realizes calibration；
Vision guide module records image information, subscribes to vision guide Module nodes message in a program, obtains picture material；
The image of acquisition is filtered；
Index enhancing function is called to enhance the useful information of filtered image information and inhibit garbage；
Enhanced image is divided into different zones according to certain similarity criterion；
Calculate and the gradient orientation histogram of statistical picture regional area carry out constitutive characteristic, by the presentation of localized target and shape by
Gradient or the direction Density Distribution at edge are described；
Pose is completed by function solver () to resolve, and obtains the spatial position of image object；
Coordinate transform is executed using function transform (), obtains assembly target in the parameter value of world coordinate system.
3. a kind of flexible assembly analogue system as claimed in claim 2, which is characterized in that in the vision guide module,
Using maximum variance between clusters, different zones are divided an image into according to certain similarity criterion using function otsu ().
4. a kind of flexible assembly analogue system as described in claim 1, which is characterized in that in the impedance control module,
Obtain mechanical arm position update information process include:
Set mechanical arm desired locations；
According to each joint control torque of Inverse Dynamics of Manipulators program solution mechanical arm；
Torque is passed into mechanical arm through prescription controller, obtains wrist stress；
Wrist stress inputs end contact force conversion function after processing, exports contact force；
Contact force makes the difference with desired contact force, obtains position correction amount through impedance control module, and then modify desired locations.
5. a kind of flexible assembly analogue system as described in claim 1, which is characterized in that the power sensing module is also used to:
Initialize mechanical arm pose and each joint rotation angle, the relevant parameter of statement assembly algorithm and tactful network；
Mechanical arm posture is adjusted, assembly movement is executed；
The six-dimensional force or posture information when the breaker upper and lower covers contact of the contact sensor transmission of known environment setting are received, is obtained
Data when contact are taken, realize force sensing function.
6. a kind of flexible assembly analogue system as claimed in claim 5, which is characterized in that the strategy network is deep learning
Network.
7. a kind of implementation method of such as flexible assembly analogue system of any of claims 1-6, which is characterized in that packet
It includes:
Initialization；
Create deep learning network；
Flexible assembly environment is initialized；
Circulation scene is set up, calls function Adj_eff () to execute assembly movement in the circulating cycle, passes through serial reward () function
Calculate the return value assembled every time；
Obtain the six-dimensional force and posture information of contact sensor acquisition in power sensing module；
Training deep learning network, designs optimizer optimizer；By function egreedy_action () training action, sound
Bright create_training_method () function realizes test, and feedback arrives robot motion；
Return value, output second leg movement are solved by evaluation system；
Adjustment posture is obtained according to Previous results, repeats assembling process.
8. the implementation method of flexible assembly analogue system as claimed in claim 7, which is characterized in that further include:
Draw Q value modified-image and return value modified-image.
9. the implementation method of flexible assembly analogue system as claimed in claim 7, which is characterized in that operation create_Q_
Network () creates deep learning network.
10. the implementation method of flexible assembly analogue system as claimed in claim 7, which is characterized in that use reset () function
Flexible assembly environment is reset.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811517301.6A CN109591013B (en) | 2018-12-12 | 2018-12-12 | Flexible assembly simulation system and implementation method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811517301.6A CN109591013B (en) | 2018-12-12 | 2018-12-12 | Flexible assembly simulation system and implementation method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109591013A true CN109591013A (en) | 2019-04-09 |
| CN109591013B CN109591013B (en) | 2021-02-12 |
Family
ID=65962569
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811517301.6A Active CN109591013B (en) | 2018-12-12 | 2018-12-12 | Flexible assembly simulation system and implementation method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109591013B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111354031A (en) * | 2020-03-16 | 2020-06-30 | 浙江一木智能科技有限公司 | 3D vision guidance system based on deep learning |
| CN111531531A (en) * | 2020-03-27 | 2020-08-14 | 向仲宇 | Robot key control method and system |
| CN111881772A (en) * | 2020-07-06 | 2020-11-03 | 上海交通大学 | Multi-mechanical arm cooperative assembly method and system based on deep reinforcement learning |
| CN112497236A (en) * | 2020-12-15 | 2021-03-16 | 上海机器人产业技术研究院有限公司 | Intelligent force sense sensing module and control method thereof |
| CN113298877A (en) * | 2020-07-20 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Object assembling method and device |
| CN114976802A (en) * | 2022-05-06 | 2022-08-30 | 南京航空航天大学 | Self-adaptive assembly method and system for radio frequency connector |
| CN115647796A (en) * | 2022-10-26 | 2023-01-31 | 中国工程物理研究院激光聚变研究中心 | Robot system applied to micro-part parallel assembly |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101947787A (en) * | 2009-04-30 | 2011-01-19 | 通用汽车环球科技运作公司 | Hierarchical robot control system and method for controlling selected degrees of freedom of an object with a plurality of manipulators |
| CN102292194A (en) * | 2009-08-21 | 2011-12-21 | 松下电器产业株式会社 | Control device and control method for robot arm, assembly robot, control program for robot arm, and integrated electronic circuit for controlling robot arm |
| CN105252532A (en) * | 2015-11-24 | 2016-01-20 | 山东大学 | Method of cooperative flexible attitude control for motion capture robot |
| CN106853639A (en) * | 2017-01-04 | 2017-06-16 | 河北工业大学 | A kind of battery of mobile phone automatic assembly system and its control method |
| CN106960099A (en) * | 2017-03-28 | 2017-07-18 | 清华大学 | A kind of manipulator grasp stability recognition methods based on deep learning |
| CN107186460A (en) * | 2017-07-10 | 2017-09-22 | 上海新时达电气股份有限公司 | Industrial robot carries out the method and its system of peg-in-hole assembly |
| CN206510040U (en) * | 2017-01-04 | 2017-09-22 | 河北工业大学 | The battery of mobile phone automatic assembly system of view-based access control model and impedance control |
| CN107590837A (en) * | 2017-09-06 | 2018-01-16 | 西安华航唯实机器人科技有限公司 | A kind of vision positioning intelligent precise puts together machines people and its camera vision scaling method |
| CN107639634A (en) * | 2016-07-20 | 2018-01-30 | 佳能株式会社 | Robot device, robot control method and recording medium |
| CN109048924A (en) * | 2018-10-22 | 2018-12-21 | 深圳控石智能系统有限公司 | A kind of intelligent robot flexible job devices and methods therefor based on machine learning |
-
2018
- 2018-12-12 CN CN201811517301.6A patent/CN109591013B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101947787A (en) * | 2009-04-30 | 2011-01-19 | 通用汽车环球科技运作公司 | Hierarchical robot control system and method for controlling selected degrees of freedom of an object with a plurality of manipulators |
| CN102292194A (en) * | 2009-08-21 | 2011-12-21 | 松下电器产业株式会社 | Control device and control method for robot arm, assembly robot, control program for robot arm, and integrated electronic circuit for controlling robot arm |
| CN105252532A (en) * | 2015-11-24 | 2016-01-20 | 山东大学 | Method of cooperative flexible attitude control for motion capture robot |
| CN107639634A (en) * | 2016-07-20 | 2018-01-30 | 佳能株式会社 | Robot device, robot control method and recording medium |
| CN106853639A (en) * | 2017-01-04 | 2017-06-16 | 河北工业大学 | A kind of battery of mobile phone automatic assembly system and its control method |
| CN206510040U (en) * | 2017-01-04 | 2017-09-22 | 河北工业大学 | The battery of mobile phone automatic assembly system of view-based access control model and impedance control |
| CN106960099A (en) * | 2017-03-28 | 2017-07-18 | 清华大学 | A kind of manipulator grasp stability recognition methods based on deep learning |
| CN107186460A (en) * | 2017-07-10 | 2017-09-22 | 上海新时达电气股份有限公司 | Industrial robot carries out the method and its system of peg-in-hole assembly |
| CN107590837A (en) * | 2017-09-06 | 2018-01-16 | 西安华航唯实机器人科技有限公司 | A kind of vision positioning intelligent precise puts together machines people and its camera vision scaling method |
| CN109048924A (en) * | 2018-10-22 | 2018-12-21 | 深圳控石智能系统有限公司 | A kind of intelligent robot flexible job devices and methods therefor based on machine learning |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111354031A (en) * | 2020-03-16 | 2020-06-30 | 浙江一木智能科技有限公司 | 3D vision guidance system based on deep learning |
| CN111354031B (en) * | 2020-03-16 | 2023-08-29 | 浙江一木智能科技有限公司 | 3D vision guidance system based on deep learning |
| CN111531531A (en) * | 2020-03-27 | 2020-08-14 | 向仲宇 | Robot key control method and system |
| CN111881772A (en) * | 2020-07-06 | 2020-11-03 | 上海交通大学 | Multi-mechanical arm cooperative assembly method and system based on deep reinforcement learning |
| CN111881772B (en) * | 2020-07-06 | 2023-11-07 | 上海交通大学 | Multi-mechanical arm cooperative assembly method and system based on deep reinforcement learning |
| CN113298877A (en) * | 2020-07-20 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Object assembling method and device |
| CN112497236A (en) * | 2020-12-15 | 2021-03-16 | 上海机器人产业技术研究院有限公司 | Intelligent force sense sensing module and control method thereof |
| CN114976802A (en) * | 2022-05-06 | 2022-08-30 | 南京航空航天大学 | Self-adaptive assembly method and system for radio frequency connector |
| CN114976802B (en) * | 2022-05-06 | 2023-11-03 | 南京航空航天大学 | Radio frequency connector self-adaptive assembly method and system |
| CN115647796A (en) * | 2022-10-26 | 2023-01-31 | 中国工程物理研究院激光聚变研究中心 | Robot system applied to micro-part parallel assembly |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109591013B (en) | 2021-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109591013A (en) | A kind of flexible assembly analogue system and its implementation | |
| CN110026987B (en) | Method, device and equipment for generating grabbing track of mechanical arm and storage medium | |
| CN107168537B (en) | Cooperative augmented reality wearable operation guidance method and system | |
| CN103760976B (en) | Gesture identification intelligent home furnishing control method based on Kinect and system | |
| CN106200983A (en) | A kind of combined with virtual reality and BIM realize the system of virtual reality scenario architectural design | |
| CN109079794B (en) | Robot control and teaching method based on human body posture following | |
| CN104942808A (en) | Robot motion path off-line programming method and system | |
| CN110047150A (en) | It is a kind of based on augmented reality complex device operation operate in bit emulator system | |
| CN115903541A (en) | Visual algorithm simulation data set generation and verification method based on twin scene | |
| CN109637252B (en) | Neurosurgery virtual operation training system | |
| CN109344790A (en) | A kind of human body behavior analysis method and system based on posture analysis | |
| CN107577159A (en) | Augmented reality analogue system | |
| CN110262283B (en) | Multi-scene visual robot simulation platform and method | |
| CN107967057A (en) | A kind of Virtual assemble teaching method based on Leap Motion | |
| CN112327745A (en) | PLC program design method based on testable digital twin body | |
| CN104460950A (en) | Implementation of simulation interactions between users and virtual objects by utilizing virtual reality technology | |
| Filiatrault et al. | Human arm motion imitation by a humanoid robot | |
| CN115346413A (en) | Assembly guidance method and system based on virtual-real fusion | |
| CN112847336A (en) | Action learning method, action learning device, storage medium and electronic equipment | |
| CN107643820B (en) | VR passive robot and implementation method thereof | |
| CN107972069A (en) | The design method that a kind of computer vision and Mechanical Touch are mutually mapped with the time | |
| CN110142769A (en) | The online mechanical arm teaching system of ROS platform based on human body attitude identification | |
| CN109213306A (en) | A kind of robot remote control platform and its design method | |
| CN116977506A (en) | Model action redirection method, device, electronic equipment and storage medium | |
| CN112947238B (en) | Industrial robot real-time control system based on VR technique |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |