CN112207857A - Offline teaching system based on binocular vision system - Google Patents
Offline teaching system based on binocular vision system Download PDFInfo
- Publication number
- CN112207857A CN112207857A CN201910629899.6A CN201910629899A CN112207857A CN 112207857 A CN112207857 A CN 112207857A CN 201910629899 A CN201910629899 A CN 201910629899A CN 112207857 A CN112207857 A CN 112207857A
- Authority
- CN
- China
- Prior art keywords
- teaching
- robot
- binocular
- image acquisition
- controller
- 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
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/0081—Programme-controlled manipulators with master teach-in means
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Numerical Control (AREA)
- Manipulator (AREA)
Abstract
The invention relates to an off-line teaching system based on a binocular vision system, which consists of a robot teaching device, a controller, a binocular image acquisition device and a teaching pen, wherein the robot teaching device is arranged in a working area, the binocular image acquisition device is arranged in the working area, the binocular image acquisition device is connected with the controller, and the controller is connected with the robot teaching device. The main function of equipment in this application is just to improve the teaching efficiency of robot. According to the invention, the 3D vision technology is adopted to position and track the marker point array of the teaching pen, so that the spatial position and the attitude of the tip point of the teaching pen are calculated, and then the positions and the attitudes are converted into the path relative to the robot coordinate system, so that the robot can directly walk to the corresponding position, and the robot or the mechanical arm does not need to move in the real teaching process.
Description
Technical Field
The invention relates to the field of industrial machine application, in particular to an offline teaching system based on a binocular vision system.
Background
The industrial robot is used for realizing automatic production, replacing laborers to engage in complicated and repeated labor, and is widely applied in the field of machine manufacturing. Industrial robots need to be taught before use. In the field of industrial machine applications, teaching robots are a necessary but inefficient task. The robot teaching is usually realized by combining an offline program with a demonstrator, and the motion trail of the robot meets the processing requirement under manual intervention. However, the track is optimized by using the demonstrator, so that the requirement on the skill level of an operator is high, the time and the energy spent on manual teaching are large, the manual teaching is only carried out by visual observation and experience, and the teaching precision is low.
The teaching robot mainly finishes work by telling the working path of the robot, and the current common mode is to send a robot instruction to the robot through a TPU (thermoplastic polyurethane) demonstrator and gradually move to a specified position for teaching. Or the mechanical arm is manually dragged to a specified teaching position, and then the current position is recorded through the teaching device. Both of these methods are inefficient, especially for workpieces with complex structures, where many positions need to be taught and where collision events can occur inadvertently. Especially when the workpiece is particularly large, the drag teaching is not feasible.
Disclosure of Invention
The invention mainly aims to provide an off-line teaching system based on a binocular vision system, which is characterized by comprising a robot teaching device, a controller, a binocular image acquisition device and a teaching pen, wherein the robot teaching device is arranged in a working area, the binocular image acquisition device is arranged in the working area, the binocular image acquisition device is connected with the controller, and the controller is connected with the robot teaching device.
The off-line teaching system based on the binocular vision system comprises the following use methods:
1. the teaching pen collects signals at the sampling point position in the working area, the teaching pen is held by hand to the sampling point position, and a collection button on the teaching pen is pressed to trigger collection signals;
2. after receiving the acquisition signal, the binocular image acquisition device transmits the acquired signal to the controller, and simultaneously identifies the teaching pen with unique posture in the space by using the binocular reconstruction system and the controller, the binocular image acquisition device can reconstruct the space position of each led lamp and match the point cloud of the identified lamp bead with the point cloud during registration, so that the position and the posture of the point are calculated; if the point cloud obtained during working is Tc, a conversion relation F from Rc to Tc can be obtained through a matching algorithm, and the relation is also suitable for the point, so that the working point position Tv can be calculated through F and Rv, and the posture of the point is obtained through the same steps;
3. and then the controller converts the position and the posture of the sharp point calculated in the steps into robot coordinates and generates a robot walking path, only one point and posture can be obtained by triggering or collecting each time, one path is composed of a plurality of points and postures, the number of the points depends on the requirements of a user, when the user needs to collect the plurality of points, the points in the collection path need to be selected to be continuously triggered, the collection of the path is finished after the collection of the plurality of points is finished, and then the path is transmitted to the robot demonstrator.
4. When in use, the robot demonstrator is used.
An LED lamp bead array is arranged on the upper side of the teaching pen.
The binocular image acquisition device utilizes a 3D vision technology.
Binocular image acquisition device is by mounting bracket, mounting panel, camera device, shifting chute, fixing bolt, the mounting panel is installed to the mounting bracket upside, the shifting chute has been seted up on the mounting panel, install two camera devices in the shifting chute, the camera device downside passes through fixing bolt to be fixed on the mounting panel.
The invention has the beneficial effects that: the main function of equipment in this application is just to improve the teaching efficiency of robot. According to the invention, the 3D vision technology is adopted to position and track the marker point array of the teaching pen, so that the spatial position and the attitude of the tip point of the teaching pen are calculated, and then the positions and the attitudes are converted into the path relative to the robot coordinate system, so that the robot can directly walk to the corresponding position, and the robot or the mechanical arm does not need to move in the real teaching process. The application is useful for optimizing off-line taught paths, rather than creating off-line taught paths.
The invention relates to a teaching pen for recognizing gesture uniqueness in space by using a binocular image acquisition device. The teaching pen is provided with led lamp bead arrays, the arrays are not symmetrical in x, y and z projection planes in a three-dimensional space, and uniqueness of a spatial point cloud direction is kept. The binocular image acquisition device can reconstruct the spatial position of each LED lamp, and the point cloud of the identified lamp bead is matched with the point cloud during registration, so that the position and the posture of a point are calculated.
The present application does not require the machine to move, nor does it require knowledge of the approximate path the robot is to move when in use. When the system is used, the system is relatively independent from the robot, and the system can be arranged on any side of the robot as long as the working area of the robot can be seen. During the use, the hand eye calibration process of robot and demonstrator is advanced, then is using same gesture of robot tool and teaching pen teaching, just afterwards can normal use this application. The application supports various teaching pens, any teaching pen meeting requirements can be registered through a vision system, and next loading can be carried out only by calling in software.
Drawings
FIG. 1 is a schematic view of the structure of the present invention.
FIG. 2 is a flow chart of the present invention.
Fig. 3 is a schematic structural view of the binocular image acquisition device of the present invention.
Detailed Description
The present application is illustrated below, in accordance with test examples:
example 1
The invention relates to an off-line teaching system based on a binocular vision system, which consists of a robot teaching device, a controller, a binocular image acquisition device and a teaching pen, and is arranged in a working area, wherein the binocular image acquisition device is arranged in the working area, the binocular image acquisition device is connected with the controller, and the controller is connected with the robot teaching device. An LED lamp bead array is arranged on the upper side of the teaching pen. The binocular image acquisition device utilizes a 3D vision technique. Binocular image acquisition device is by mounting bracket, mounting panel, camera device, shifting chute, fixing bolt, the mounting panel is installed to the mounting bracket upside, the shifting chute has been seted up on the mounting panel, install two camera devices in the shifting chute, the camera device downside passes through fixing bolt to be fixed on the mounting panel.
Example 2
The off-line teaching system based on the binocular vision system comprises the following use methods:
1. the teaching pen collects signals at the sampling point position in the working area, the teaching pen is held by hand to the sampling point position, and a collection button on the teaching pen is pressed to trigger collection signals;
2. after receiving the acquisition signal, the binocular image acquisition device transmits the acquired signal to the controller, and simultaneously identifies the teaching pen with unique posture in the space by using the binocular reconstruction system and the controller, the binocular image acquisition device can reconstruct the space position of each led lamp and match the point cloud of the identified lamp bead with the point cloud during registration, so that the position and the posture of the point are calculated; if the point cloud obtained during working is Tc, a conversion relation F from Rc to Tc can be obtained through a matching algorithm, and the relation is also suitable for the point, so that the working point position Tv can be calculated through F and Rv, and the posture of the point is obtained through the same steps;
3. and then the controller converts the position and the posture of the sharp point calculated in the steps into robot coordinates and generates a robot walking path, only one point and posture can be obtained by triggering or collecting each time, one path is composed of a plurality of points and postures, the number of the points depends on the requirements of a user, when the user needs to collect the plurality of points, the points in the collection path need to be selected to be continuously triggered, the collection of the path is finished after the collection of the plurality of points is finished, and then the path is transmitted to the robot demonstrator.
4. In the teaching process, the off-line teaching system and the robot are relatively independent, and the off-line teaching system can be arranged on any side of the robot as long as the working area of the robot can be seen. When the system is used, the hand-eye calibration process of a robot and a teaching instrument is firstly carried out, then the same gesture is taught by a robot tool and a teaching pen, and then the system can be normally used.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (5)
1. The utility model provides an off-line teaching system based on binocular vision system, its characterized in that comprises robot demonstrator, controller, binocular image acquisition device, teaching pen, the setting is in the workspace, install binocular image acquisition device in the workspace, binocular image acquisition device and controller are connected, controller and robot demonstrator connect.
2. The off-line teaching system based on the binocular vision system comprises the following use methods:
firstly, acquiring signals at a sampling point position of a teaching pen in a working area, holding the teaching pen by a worker to the sampling point position, and pressing an acquisition button on the teaching pen to trigger acquisition of the signals;
secondly, after receiving the acquisition signal, the binocular image acquisition device transmits the acquired signal to the controller, and meanwhile, the binocular image acquisition device identifies the teaching pen with unique posture in the space by using a binocular reconstruction system and the controller, reconstructs the spatial position of each led lamp, and matches the point cloud of the identified lamp bead with the point cloud during registration, so that the position and the posture of a point are calculated; if the point cloud obtained during working is Tc, a conversion relation F from Rc to Tc can be obtained through a matching algorithm, and the relation is also suitable for the point, so that the working point position Tv can be calculated through F and Rv, and the posture of the point is obtained through the same steps;
and thirdly, the controller converts the position and the gesture of the sharp point calculated in the previous step into robot coordinates and generates a robot walking path, only one point and gesture can be obtained by triggering or acquiring each time, one path is composed of a plurality of points and gestures, the number of the points depends on the requirements of a user, when the user needs to acquire the plurality of points, the points in the path need to be continuously triggered and acquired, the acquisition of the path is finished after the acquisition of the plurality of points is finished, and then the path is transmitted to the robot demonstrator.
3. The binocular vision system-based off-line teaching system of claim 1, wherein an led lamp bead array is arranged on the upper side of the teaching pen.
4. The binocular vision system-based off-line teaching system of claim 1, wherein the binocular image capturing device utilizes a 3D vision technique.
5. The binocular vision system-based off-line teaching system of claim 1, wherein the binocular image acquisition device comprises an installation frame, an installation plate, a camera device, a moving groove and a fixing bolt, the installation plate is installed on the upper side of the installation frame, the moving groove is formed in the installation plate, two camera devices are installed in the moving groove, and the lower side of each camera device is fixed on the installation plate through the fixing bolt.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910629899.6A CN112207857A (en) | 2019-07-12 | 2019-07-12 | Offline teaching system based on binocular vision system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910629899.6A CN112207857A (en) | 2019-07-12 | 2019-07-12 | Offline teaching system based on binocular vision system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112207857A true CN112207857A (en) | 2021-01-12 |
Family
ID=74047234
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910629899.6A Pending CN112207857A (en) | 2019-07-12 | 2019-07-12 | Offline teaching system based on binocular vision system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112207857A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS61182106A (en) * | 1985-02-07 | 1986-08-14 | Matsushita Electric Ind Co Ltd | Teaching device |
| CN103921265A (en) * | 2013-01-16 | 2014-07-16 | 株式会社安川电机 | Robot Teaching System And Robot Teaching Method |
| CN106041937A (en) * | 2016-08-16 | 2016-10-26 | 河南埃尔森智能科技有限公司 | Control method of manipulator grabbing control system based on binocular stereoscopic vision |
| CN106891326A (en) * | 2017-03-22 | 2017-06-27 | 南京航空航天大学 | A kind of robot teaching method |
| CN107309882A (en) * | 2017-08-14 | 2017-11-03 | 青岛理工大学 | A kind of robot teaching programming system and method |
| CN107756408A (en) * | 2017-11-22 | 2018-03-06 | 浙江优迈德智能装备有限公司 | A kind of robot trajectory's teaching apparatus and method based on active infrared binocular vision |
| CN109318232A (en) * | 2018-10-22 | 2019-02-12 | 佛山智能装备技术研究院 | A kind of polynary sensory perceptual system of industrial robot |
-
2019
- 2019-07-12 CN CN201910629899.6A patent/CN112207857A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS61182106A (en) * | 1985-02-07 | 1986-08-14 | Matsushita Electric Ind Co Ltd | Teaching device |
| CN103921265A (en) * | 2013-01-16 | 2014-07-16 | 株式会社安川电机 | Robot Teaching System And Robot Teaching Method |
| CN106041937A (en) * | 2016-08-16 | 2016-10-26 | 河南埃尔森智能科技有限公司 | Control method of manipulator grabbing control system based on binocular stereoscopic vision |
| CN106891326A (en) * | 2017-03-22 | 2017-06-27 | 南京航空航天大学 | A kind of robot teaching method |
| CN107309882A (en) * | 2017-08-14 | 2017-11-03 | 青岛理工大学 | A kind of robot teaching programming system and method |
| CN107756408A (en) * | 2017-11-22 | 2018-03-06 | 浙江优迈德智能装备有限公司 | A kind of robot trajectory's teaching apparatus and method based on active infrared binocular vision |
| CN109318232A (en) * | 2018-10-22 | 2019-02-12 | 佛山智能装备技术研究院 | A kind of polynary sensory perceptual system of industrial robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107756408B (en) | Robot track teaching device and method based on active infrared binocular vision | |
| Zhao et al. | Dual-arm robot design and testing for harvesting tomato in greenhouse | |
| US20190036337A1 (en) | System for robotic 3d printing | |
| CN204997657U (en) | Biomimetic mechanical hand with imitate function | |
| CN110170995B (en) | Robot rapid teaching method based on stereoscopic vision | |
| CN106584093A (en) | Self-assembly system and method for industrial robots | |
| CN107856014B (en) | Mechanical arm pose control method based on gesture recognition | |
| CN110171009B (en) | Robot handheld teaching device based on stereoscopic vision | |
| US20170270631A1 (en) | Automated guidance system and method for a coordinated movement machine | |
| CN106041927A (en) | Hybrid vision servo system and method combining eye-to-hand and eye-in-hand structures | |
| CN113146620B (en) | Binocular vision-based double-arm cooperative robot system and control method | |
| CN109848964B (en) | Teaching robot data collector system based on optical motion capture | |
| CN107150032A (en) | A kind of workpiece identification based on many image acquisition equipments and sorting equipment and method | |
| CN104180753A (en) | Rapid calibration method of robot visual system | |
| CN110170996B (en) | Robot rapid teaching system based on stereoscopic vision | |
| CN108748152B (en) | Robot teaching method and system | |
| CN113119077A (en) | Industrial robot handheld teaching device and teaching method | |
| CN109407111A (en) | A kind of tunnel three-dimensional scanner feature knowledge method for distinguishing | |
| CN108582031A (en) | A kind of hot line robot branch based on force feedback master ＆ slave control connects gage lap method | |
| CN107671838B (en) | Robot teaching recording system, teaching process steps and algorithm flow thereof | |
| CN102608969A (en) | Cascade robot hand and eye registration control method based on infrared optical alignment | |
| CN112207857A (en) | Offline teaching system based on binocular vision system | |
| CN204036474U (en) | Industrial robot sorting system | |
| CN112958974A (en) | Interactive automatic welding system based on three-dimensional vision | |
| CN110421565B (en) | Robot global positioning and measuring system and method for practical training |
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 |