CN107443369A - A kind of robotic arm of the inverse identification of view-based access control model measurement model is without demarcation method of servo-controlling - Google Patents

A kind of robotic arm of the inverse identification of view-based access control model measurement model is without demarcation method of servo-controlling Download PDF

Info

Publication number
CN107443369A
CN107443369A CN201710490392.8A CN201710490392A CN107443369A CN 107443369 A CN107443369 A CN 107443369A CN 201710490392 A CN201710490392 A CN 201710490392A CN 107443369 A CN107443369 A CN 107443369A
Authority
CN
China
Prior art keywords
model
servo
mechanical arm
demarcation
identification
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
Application number
CN201710490392.8A
Other languages
Chinese (zh)
Inventor
鹿安
徐健
陶磊
龚迎昆
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing Academy of Metrology and Quality Inspection
Original Assignee
Chongqing Academy of Metrology and Quality Inspection
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chongqing Academy of Metrology and Quality Inspection filed Critical Chongqing Academy of Metrology and Quality Inspection
Priority to CN201710490392.8A priority Critical patent/CN107443369A/en
Publication of CN107443369A publication Critical patent/CN107443369A/en
Pending legal-status Critical Current

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
    • B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
    • B25J9/1697—Vision controlled systems
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/40—Robotics, robotics mapping to robotics vision
    • G05B2219/40005—Vision, analyse image at one station during manipulation at next station

Landscapes

  • Engineering & Computer Science (AREA)
  • Robotics (AREA)
  • Mechanical Engineering (AREA)
  • Manipulator (AREA)

Abstract

The invention discloses a kind of robotic arm of the inverse identification of view-based access control model measurement model without demarcation method of servo-controlling, belong to mechanical arm control field.For this method using the inverse identification of the measurement model based on binocular camera vision, the measurement value of feedback of acquisition is mechanical arm position information, is so easy to the optimization built with movement locus of control system.So as to realize robotic arm without demarcation Visual servoing control.

Description

A kind of robotic arm of the inverse identification of view-based access control model measurement model is without demarcation method of servo-controlling
Technical field
The invention belongs to robot system field, be related to it is a kind of based on the robotic arm of identification of inverse model without demarcation servo motion Control.
Background technology
Mechanical arm is general to be referred in industrial application, multi-joint automated machine equipment, is the modern machine occurred earliest One of device people, it can imitate the action of the mankind, efficiently complete some complex works, from the circumstances of lengthy and jumbled processing or danger In liberate mankind both hands.The research of mechanical arm is one and is related to multi-field compound subject, including control principle, mechanical structure, The machinery such as information engineering, computer technology, Principles of Microcomputers and information knowledge.Its application field is wide, such as agricultural production, the energy Exploitation, industrial loading, automated production, service trade, military project etc., will also there be more long-range development in future.
Visual servo refers to the image information that object is gathered by Optical devices or other non-contacting sensors, then will Feedback signal of the image information as servo-drive system, so as to adjust the state of controlled device or controller output, complete servo A kind of method of control.
Image feedback by video camera to working space, controller is designed to instruct mechanical arm independently to complete the control of task Method processed, while to the internal and external parameter of video camera without demarcation.Studied for the mechanical arm without demarcation Visual servoing control Last century the nineties are started from, whether image space cartesian space is transformed into according to it, based on image and base can be divided into In cartesian space without demarcation Visual servoing control.Based on image, without demarcating, Visual servoing control device is more direct, meets Human visual system, typically realize that its requirement to environment is compared with based on cartesian space using particular topology or intelligent algorithm Controller is low, but it has the problem of robustness of control method and non-optimal movement locus.
By demarcation, although Visual servoing control can be carried out accurately, there are technical requirements in calibration process, not only accurate Exactness is difficult to ensure that its migration is also bad.Without demarcation visual servo refer in whole control process, in video camera External parameter, which is not done, accurately to be asked for or need not know its exact value, and the control method of control is completed under the premise of this.Generally Versatility without demarcation visual servo is stronger, and the requirement to installation parameter and control method is severe not over the visual servo of demarcation Carve.In the working space that external environment condition is complicated or interference is larger, the application of no demarcation visual servo is more extensive.
It is then the developing direction studied at present without demarcation visual servo.For research master of the mechanical arm without demarcation visual servo Concentrate both ways：When improve image turn by increasing aided algorithm or data processing method or improve anti- Interference performance；Second, replace image turn using other intelligent algorithms.
Be controlled by intelligent algorithm, due to without using Jacobian matrix, avoid Jacobian matrix recursion it is inaccurate, The problem of operand is big.Instantly intelligent control of the mechanical arm studied without demarcation visual servo, it is mostly direct by image deviations Change control parameter and realize control.This mode lacks the direct control to manipulator motion parameter, so being difficult to its track Directly optimized.
Therefore, lack at present it is a kind of can overcome disadvantages described above without demarcation vision watch direct control method.
The content of the invention
Using binocular camera because image space is a two dimensional surface, and cartesian space is three dimensions, monocular Camera has missing on depth information, therefore uses description of the monocular-camera to three dimensions sufficiently complete.Binocular camera Certain layout type can be used, so as to mutually make up the depth information of missing, more accurately in description cartesian space Pose.The present invention is realized without demarcation Visual servoing control using the inverse identification of the measurement model based on binocular camera vision.
To reach target, the present invention proposes following technical scheme：
A kind of robotic arm based on the inverse identification of measurement model watches direct control method without demarcation vision：Comprise the following steps：
Step 1：The camera fixed position installation of binocular, its visual layout pattern is orthogonal packing；
Step 2:The movement position of mechanical arm is set, and is based on binocular camera, is obtained corresponding based on imaging plane Image features；
Step 3：Based on data above, inverse identification modeling is carried out to vision measurement model, foundation is based on image characteristics extraction Amount carries out model inversion identification with manipulator motion position；
Step 4：Inversion model is measured based on more than, builds servo-control system, is realized without demarcation SERVO CONTROL.
The technology of the present invention effect is：Based on binocular camera vision, the inverse of mechanical arm position measurement model is carried out and has distinguished Know, the measurement value of feedback for realizing acquisition is mechanical arm position information, be so easy to control system build and movement locus Optimization.
Brief description of the drawings
In order that the purpose of the present invention, technical scheme and beneficial effect are clearer, the present invention is supplied to drawings described below to enter Row explanation：
Install Fig. 1 binocular cameras fixed position
The robotic arm servo-control system of the inverse identification of Fig. 2 view-based access control models measurement model
Fig. 3 Binocular vision photogrammetry characteristic extraction procedures
Embodiment
The preferred embodiment of the present invention is carried out below in conjunction with the accompanying drawings
Because the present invention is for the identification of Binocular vision photogrammetry model inversion, to build mechanical arm servo-control system.Step 1 In be embodied as shown in Fig. 1, the installation of the camera fixed position of binocular, its visual layout pattern is orthogonal packing；
In this example, it is embodied as in step 2 shown in Fig. 2.Set one group of motion reference position xset,yset,zset, Rxset,Ryset,Rzset, the image features u of its imaging plane is obtained based on binocular measurement1,v1,θ1,u2,v2,θ2.In binocular Its measuring principle is as shown in Figure 3 in measurement process.
Mechanical arm tail end is labelled with two identification point P herein1、P2, pass through projection of the two o'clocks in two cameras To react pose of the mechanical arm tail end in cartesian space.They have projected four altogether in the plane of delineation of two video cameras Point P11、P12、P21、P22.In theory, characteristics of image s=(P are selected11,P21,P21,P22) can meet to represent mechanical arm end The requirement of pose is held, but the image feature is octuple, and dimension is higher, can carry out dimension-reduction treatment by following method.
If θ1For vector (P11,P12) angle between the plane of delineation coordinate u axles of video camera one, θ2For vector (P21,P22) With the angle between the plane of delineation coordinate u axles of video camera two.The characteristics of image of extraction can be expressed as s=(P11, P21, θ 1, θ 2).Wherein P11, P21 are coordinate points, are represented by P11=(u1, v1), P21=(u2, v2).That is 6 characteristics of image of selection For u1, v1, u2, v2, θ 1, θ 2.
xset,yset,zset,Rxset,Ryset,RzsetRespectively robotic arm is in the setting position of cartesian coordinate system and speed；
In this example, specific implementation is based on image characteristics extraction amount u in step 31,v1,θ1,u2,v2,θ2With mechanical arm Movement position information x, y, z, Rx, Ry, Rz carry out vision measurement model inversion identification.Due to the vision measurement mistake based on dual camera Journey have it is non-linear, so being all suitable for Non-linear Model Identification method.In view of neutral net in Non-linear Model Identification The powerful capability of fitting of aspect, it is as the main stream approach mainly used.In this example, specific implementation such as Fig. 2 in step 4 After the inverse identification of vision measurement model is established, the feedback control amount of control system is x, y, z, Rx, Ry, Rz, so as to realize SERVO CONTROL based on Cartesian coordinate position metrical information.
Finally illustrate, preferred embodiment above is merely illustrative of the technical solution of the present invention and unrestricted, although logical Cross above preferred embodiment the present invention is described in detail, it is to be understood by those skilled in the art that can be Various changes are made to it in form and in details, without departing from claims of the present invention limited range.

Claims (3)

1. a kind of robotic arm of the inverse identification of view-based access control model measurement model is without demarcation method of servo-controlling, it is characterised in that
Step 1：Binocular camera fixed position is installed, and its visual layout pattern is orthogonal packing；
Step 2:The movement position of mechanical arm is set, and is based on binocular camera, obtains the corresponding image based on imaging plane Characteristic parameter；
Step 3：Based on data above, inverse identification modeling is carried out to vision measurement model, establish based on image characteristics extraction amount with Manipulator motion position carries out model inversion identification；
Step 4：Inversion model is measured based on more than, builds servo-control system, is realized without demarcation SERVO CONTROL.
2. employing view-based access control model feature inversion model and Binocular vision photogrammetry, simplify based on binocular visual positioning process, realize The integrated measuring design of mechanical arm position parameter.
3. visual signature and mechanical arm position parameters relationship inversion model are established using the methods of neutral net, it is achieved thereby that mechanical The indirect measurement of arm location parameter, so as to simplify visual signature and mechanical arm position nonlinearity in parameters modeling process.
CN201710490392.8A 2017-06-25 2017-06-25 A kind of robotic arm of the inverse identification of view-based access control model measurement model is without demarcation method of servo-controlling Pending CN107443369A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710490392.8A CN107443369A (en) 2017-06-25 2017-06-25 A kind of robotic arm of the inverse identification of view-based access control model measurement model is without demarcation method of servo-controlling

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710490392.8A CN107443369A (en) 2017-06-25 2017-06-25 A kind of robotic arm of the inverse identification of view-based access control model measurement model is without demarcation method of servo-controlling

Publications (1)

Publication Number Publication Date
CN107443369A true CN107443369A (en) 2017-12-08

Family

ID=60486551

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710490392.8A Pending CN107443369A (en) 2017-06-25 2017-06-25 A kind of robotic arm of the inverse identification of view-based access control model measurement model is without demarcation method of servo-controlling

Country Status (1)

Country Link
CN (1) CN107443369A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114516055A (en) * 2022-04-07 2022-05-20 北京信息科技大学 Mechanical arm non-shutdown real-time calibration method and device based on binocular vision and deep learning
CN114946403A (en) * 2022-07-06 2022-08-30 青岛科技大学 Tea picking robot based on calibration-free visual servo and tea picking control method thereof

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050053274A1 (en) * 2003-04-21 2005-03-10 Yaron Mayer System and method for 3D photography and/or analysis of 3D images and/or display of 3D images
CN102446355A (en) * 2011-09-05 2012-05-09 西安理工大学 Method for detecting target protruding from plane based on double viewing fields without calibration
CN103630072A (en) * 2013-10-25 2014-03-12 大连理工大学 Layout optimization method for camera in binocular vision measuring system
CN104325268A (en) * 2014-11-04 2015-02-04 南京赫曼机器人自动化有限公司 Industrial robot three-dimensional space independent assembly method based on intelligent learning
CN104626206A (en) * 2014-12-17 2015-05-20 西南科技大学 Robot operation pose information measuring method under non-structural environment
CN104808490A (en) * 2015-03-10 2015-07-29 浙江工业大学 Uncalibrated visual servoing control method for estimating image Jacobian matrix based on echo state network facing mold protection
CN105082161A (en) * 2015-09-09 2015-11-25 新疆医科大学第一附属医院 Robot vision servo control device of binocular three-dimensional video camera and application method of robot vision servo control device
CN106003036A (en) * 2016-06-16 2016-10-12 哈尔滨工程大学 Object grabbing and placing system based on binocular vision guidance
CN106291278A (en) * 2016-08-03 2017-01-04 国网山东省电力公司电力科学研究院 A kind of partial discharge of switchgear automatic testing method based on many visual systemes
CN205905026U (en) * 2016-08-26 2017-01-25 沈阳工学院 Robot system based on two mesh stereovisions
CN106408609A (en) * 2016-09-13 2017-02-15 江苏大学 Parallel mechanism end motion pose detection method based on binocular vision
CN106737665A (en) * 2016-11-30 2017-05-31 天津大学 The mechanical arm control system and implementation method matched based on binocular vision and SIFT feature

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050053274A1 (en) * 2003-04-21 2005-03-10 Yaron Mayer System and method for 3D photography and/or analysis of 3D images and/or display of 3D images
CN102446355A (en) * 2011-09-05 2012-05-09 西安理工大学 Method for detecting target protruding from plane based on double viewing fields without calibration
CN103630072A (en) * 2013-10-25 2014-03-12 大连理工大学 Layout optimization method for camera in binocular vision measuring system
CN104325268A (en) * 2014-11-04 2015-02-04 南京赫曼机器人自动化有限公司 Industrial robot three-dimensional space independent assembly method based on intelligent learning
CN104626206A (en) * 2014-12-17 2015-05-20 西南科技大学 Robot operation pose information measuring method under non-structural environment
CN104808490A (en) * 2015-03-10 2015-07-29 浙江工业大学 Uncalibrated visual servoing control method for estimating image Jacobian matrix based on echo state network facing mold protection
CN105082161A (en) * 2015-09-09 2015-11-25 新疆医科大学第一附属医院 Robot vision servo control device of binocular three-dimensional video camera and application method of robot vision servo control device
CN106003036A (en) * 2016-06-16 2016-10-12 哈尔滨工程大学 Object grabbing and placing system based on binocular vision guidance
CN106291278A (en) * 2016-08-03 2017-01-04 国网山东省电力公司电力科学研究院 A kind of partial discharge of switchgear automatic testing method based on many visual systemes
CN205905026U (en) * 2016-08-26 2017-01-25 沈阳工学院 Robot system based on two mesh stereovisions
CN106408609A (en) * 2016-09-13 2017-02-15 江苏大学 Parallel mechanism end motion pose detection method based on binocular vision
CN106737665A (en) * 2016-11-30 2017-05-31 天津大学 The mechanical arm control system and implementation method matched based on binocular vision and SIFT feature

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114516055A (en) * 2022-04-07 2022-05-20 北京信息科技大学 Mechanical arm non-shutdown real-time calibration method and device based on binocular vision and deep learning
CN114516055B (en) * 2022-04-07 2023-06-06 北京信息科技大学 Real-time calibration method and device for mechanical arm without shutdown based on binocular vision and deep learning
CN114946403A (en) * 2022-07-06 2022-08-30 青岛科技大学 Tea picking robot based on calibration-free visual servo and tea picking control method thereof

Similar Documents

Publication Publication Date Title
JP7326911B2 (en) Control system and control method
CN110039542B (en) Visual servo tracking control method with speed and direction control function and robot system
CN102848389B (en) Realization method for mechanical arm calibrating and tracking system based on visual motion capture
CN104057453B (en) The manufacture method of robot device and machined object
CN107421442A (en) A kind of robot localization error online compensation method of externally measured auxiliary
CN105014667A (en) Camera and robot relative pose calibration method based on pixel space optimization
CN110815189B (en) Robot rapid teaching system and method based on mixed reality
CN102922521A (en) Mechanical arm system based on stereo visual serving and real-time calibrating method thereof
Melchiorre et al. Collison avoidance using point cloud data fusion from multiple depth sensors: a practical approach
CN114912287A (en) Robot autonomous grabbing simulation system and method based on target 6D pose estimation
CN111360821A (en) Picking control method, device and equipment and computer scale storage medium
WO2022000713A1 (en) Augmented reality self-positioning method based on aviation assembly
CN108638052A (en) A kind of closed chain formula multi-arm robot Shared control method
Gratal et al. Visual servoing on unknown objects
CN104808490A (en) Uncalibrated visual servoing control method for estimating image Jacobian matrix based on echo state network facing mold protection
CN112650217B (en) Robot trajectory tracking strategy dynamic optimization method based on evaluation function
CN114067210A (en) Mobile robot intelligent grabbing method based on monocular vision guidance
CN115446836A (en) Visual servo method based on mixing of multiple image characteristic information
CN107443369A (en) A kind of robotic arm of the inverse identification of view-based access control model measurement model is without demarcation method of servo-controlling
CN107932502A (en) A kind of SCARA method for planning track of robot based on binocular stereo vision
Ramer et al. A robot motion planner for 6-DOF industrial robots based on the cell decomposition of the workspace
Shen et al. Safe assembly motion-A novel approach for applying human-robot co-operation in hybrid assembly systems
CN109542094A (en) Mobile robot visual point stabilization without desired image
CN110722547B (en) Vision stabilization of mobile robot under model unknown dynamic scene
Xie et al. Hybrid Feature Based 6D Pose Tracking under Binocular Vision for Automated Micro-assembly

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: 20171208

RJ01 Rejection of invention patent application after publication