CN210757741U - Novel mechanical arm dynamic grabbing system - Google Patents
Novel mechanical arm dynamic grabbing system Download PDFInfo
- Publication number
- CN210757741U CN210757741U CN201921258636.0U CN201921258636U CN210757741U CN 210757741 U CN210757741 U CN 210757741U CN 201921258636 U CN201921258636 U CN 201921258636U CN 210757741 U CN210757741 U CN 210757741U
- Authority
- CN
- China
- Prior art keywords
- steering engine
- module
- mechanical arm
- arm
- steering
- 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.)
- Active
Links
Images
Abstract
The utility model belongs to the technical field of industrial production and specifically relates to a novel arm developments grasping system, including degree of freedom arm module, speech recognition module, camera module, VGA display module, FPGA module, degree of freedom arm module includes six steering engines, control panel, set for steering engine one respectively with six steering engines, steering engine two, steering engine three, steering engine four, steering engine five, steering engine zero, the direction of snatching of four control arms of steering engine, steering engine five connect revolute joint and manipulator, opening and shutting of control arm, revolute joint part all sets up to the biggest turned angle, the control panel links to each other with six steering engines. The utility model discloses be different from traditional manual operation arm and snatch, but adopt FPGA to realize image recognition, the real-time intelligence of back by six degree of freedom arms snatchs the object, degree of automation promotes greatly, and work efficiency improves greatly, adopts speech recognition's mode to come opening of control system to open, and is convenient, safe more, is applicable to the arm among the industrial field and snatchs the task.
Description
Technical Field
The utility model belongs to the technical field of industrial production and specifically relates to a novel arm developments grasping system.
Background
In recent years, the manufacturing industry in China has been greatly developed under the condition of meeting the market demand, so that the technology of domestic industrial robots is continuously innovated, large-scale/ultra-large-scale integrated circuits (ASICs) and Field Programmable Gate Arrays (FPGAs) are rapidly developed, more and more powerful processing performance is provided for image processing, the application of the large-scale/ultra-large-scale integrated circuits (ASICs) and the FPGA is more and more extensive in the image field, and an image processing system is developing towards the directions of high speed, large capacity, small volume and light weight.
The traditional industrial mechanical arm is single in action route and not enough in flexibility.
SUMMERY OF THE UTILITY MODEL
In order to solve the problem, the utility model provides a combine image recognition and arm, the relevant sensor of reunion, through carry out intelligent recognition's arm developments grasping system to the image processing in certain region, can be used to the letter sorting and the collection of product, this system can regard as the upgrading module directly to upgrade the processing for the arm in the industrial production, makes the arm have intelligence and snatchs the function, improves production efficiency, reduction in production cost.
In order to achieve the above object, the present invention discloses the following technical solutions:
the utility model provides a novel arm developments snatch system, including degree of freedom arm module, speech recognition module, the camera module, VGA display module, the FPGA module, degree of freedom arm module includes six steering engines, the control panel, set for steering engine one respectively with six steering engines, steering engine two, steering engine three, steering engine four, steering engine five, steering engine zero, the direction of snatching of steering engine four control arms, steering engine five connect manipulator and rotation joint, opening and shutting of control arm, rotation joint part all sets up to the biggest turned angle, the control panel links to each other with six steering engines. After the mechanical arm module is programmed, the functions of rotation, extension, clamping and the like of the mechanical arm can be realized, and the mechanical arm module is suitable for control systems which need constantly changing angles and can be kept.
In the technical scheme, the dynamic mechanical arm grabbing system achieves an image recognition function based on the FPGA, the condition of the workbench can be shot and recorded in real time through the camera, the shot image is analyzed and processed through the FPGA to make mechanical arm action planning, and the whole system can be controlled by the voice recognition module for guaranteeing the operation safety of the mechanical arm.
The utility model discloses a further improvement, the speech recognition module volume is 3 x 4.3CM, and the inside of speech recognition module is provided with STC11 series chip, a timer, an external interruption, reserves 16 IO mouths, still reserves the serial ports with the FPGA module communication simultaneously, and the speech recognition module still is provided with 5V and 3.3V's power source. The system is controlled to be started or stopped by the voice recognition module, so that the system is more convenient, quicker and safer in the practical application of the industrial field.
The utility model discloses a further improvement, the camera module is provided with OV7670 image sensor, and the camera module links to each other with the SCCB bus.
The utility model discloses a further improvement, VGA display module includes circuit board, display, VGA interface, and the VGA interface is provided with fifteen needles, and fifteen needles divide into three rows, five holes in every row, the circuit board pass through the VGA interface with the display links to each other.
The utility model discloses a further improvement, the FPGA module includes that Artix-7 core plate, soft nuclear MicroBlaze, and Artix-7 core plate adopts XilinxAltix-7 FPGA series chip, and the inside soft nuclear MicroBlaze of embedding of Xilinx 7 series chip, this soft nuclear and other peripheral hardware IP nuclear are together, can accomplish the design of programmable system chip (SOPC). The soft core MicroBlaze processor adopts a RISC architecture and a 32-bit instruction and data bus of a Harvard structure, can execute programs stored in an on-chip memory and an external memory at full speed, and can complete the design of a programmable system chip (SOPC) together with other peripheral IP cores. When the Artix-7 core board is used as a main processor to process data, the image recognition function is realized, and the coordinates of an object can be accurately acquired through algorithms such as corrosion, expansion, centroid solving and the like of the FPGA. The soft core MicroBlaze of the FPGA realizes path planning of the six-degree-of-freedom mechanical arm, so that the mechanical arm can intelligently grab an object identified by an image.
The utility model discloses a further improvement, arm developments grasping system has adopted image binary method, corruption inflation, barycenter algorithm's method to carry out image processing.
The utility model discloses a further improvement, the angle of six degree of freedom arm steering engines adopts the dynamic programming algorithm to obtain.
The utility model has the advantages that: the utility model discloses be different from traditional manual operation arm and snatch, but adopt FPGA to realize image recognition, the real-time intelligence of back by six degree of freedom arms snatchs the object, degree of automation promotes greatly, and work efficiency improves greatly, adopts speech recognition's mode to come opening of control system to open, and is convenient, safe more, is applicable to the arm among the industrial field and snatchs the task.
Drawings
FIG. 1 is a schematic view of a robotic arm.
Fig. 2 is a schematic diagram of the operation of the present invention.
Fig. 3 is a system operation diagram of the present invention.
Fig. 4 is a process diagram of the present invention.
In the figure: the method comprises the steps of 1-a measured target, 2-OV7670 image sensors, 3-camera modules, 4-FPGA modules, 5-VGA display modules, 6-control execution, 7-light sources, 8-light source controllers, 9-freedom mechanical arm modules, 10-mechanical arms, 11-five steering engines, 12-four steering engines, 13-voice recognition modules, 14-three steering engines, 15-two steering engines, 16-one steering engines and 17-zero steering engines.
Detailed Description
In order to deepen the understanding of the present invention, the present invention will be described in further detail with reference to the accompanying drawings and embodiments, which are only used for explaining the present invention and are not limited to the protection scope of the present invention.
Example (b): as shown in fig. 1 and 2, the novel mechanical arm dynamic grabbing system comprises a degree of freedom mechanical arm module 9, a voice recognition module 13, a camera module 3, a VGA display module 5 and an FPGA module 4, wherein the degree of freedom mechanical arm module 9 comprises six steering engines and a control panel, the six steering engines are respectively set as a first steering engine 16, a second steering engine 15, a third steering engine 14, a fourth steering engine 12, a fifth steering engine 11 and a zero steering engine 17, the fourth steering engine 12 controls the grabbing direction of the mechanical arm, the fifth steering engine 11 is connected with a rotary joint and a mechanical arm, the opening and closing of the mechanical arm are controlled, all the other steering engines are rotary joint parts, the rotary joint parts are set to be the maximum rotary angle, and the control panel 17 is. After the mechanical arm module 9 is programmed, the functions of rotation, extension, clamping and the like of the mechanical arm 10 can be realized, and the mechanical arm module is suitable for control systems which need to change angles constantly and can be kept.
In this embodiment: the volume of the voice recognition module 13 is 3 × 4.3CM, an STC11 series chip, a timer, an external interrupt, 16I/O ports and a serial port communicated with the FPGA module are arranged in the voice recognition module, and the voice recognition module is also provided with 5V and 3.3V power interfaces. The STC11 chip can process voice data, controls the start and stop of the system through the voice recognition module, and is more convenient, rapid and safe in the actual application of the industrial field.
In this embodiment: the camera module 3 is provided with an OV7670 image sensor 2, and the camera module 3 is connected with an SCCB bus.
In this embodiment: the VGA display module 5 comprises a circuit board, a display and a VGA interface, the VGA interface is provided with fifteen pins, the fifteen pins are divided into three rows, five holes are formed in each row, and the circuit board is connected with the display through the VGA interface.
In this embodiment: the FPGA module 4 comprises an Artix-7 core board and a soft core MicroBlaze, wherein the Artix-7 core board adopts a Xilinx Artix-7FPGA series chip, the soft core MicroBlaze is embedded in the Xilinx 7 series chip, and the soft core and other peripheral IP cores can complete the design of a programmable system chip (SOPC). The soft core MicroBlaze processor adopts a RISC architecture and a 32-bit instruction and data bus of a Harvard structure, can execute programs stored in an on-chip memory and an external memory at full speed, and can complete the design of a programmable system chip (SOPC) together with other peripheral IP cores.
In this embodiment: the mechanical arm dynamic grabbing system adopts an image binary method, a corrosion expansion method and a centroid algorithm method to process images.
The process of the image binary method comprises the following steps: the sequence of the video frames collected by the FPGA control panel is f (x, y, t)1),f(x,y,t2),...,f(x,y,tn) Reading a frame of image from BRAM for binarization processing, firstly converting the color image into grey-scale image, and then doing the binarization processingAnd (6) carrying out binarization processing. The common formula for converting RGB into a gray-scale map is:
Gray＝5/16*R+9/16*G+2/16*B
if floating point operation is directly adopted, a large amount of FPGA resources are consumed, and the fact that the proportion of the G component in the gray level conversion formula is the highest can be found, so that the occupied resources can be reduced by directly adopting the G component for operation.
The image binarization adopts a self-adaptive threshold value, so that the interference of the environment to a system can be effectively reduced, and the average value of the G component of one image is the binarization threshold value. The binarization sets the background to be black and the target to be white, and the formula of the binarization is as follows:
threshold is the threshold.
Corrosion and swelling processes: and calling a RAM-based Shiftregister IP core to cache the video line, and then performing erosion expansion operation on the images by using a 3-by-3 image matrix pair respectively.
The process of the centroid algorithm: the generated binary image can be regarded as a pixel coordinate system distributed in a rectangular window, the upper left corner is set as a starting point coordinate (0,0), and the lower right corner is set as an end point coordinate (m, n), then:
in the above formula, (X, Y) is a calculated value of the centroid coordinate of the target image, and m and n are the number of rows and columns of the target image, respectively (m and n are both integers greater than or equal to 2).
And simultaneously recording the coordinates of the initial pixel and the final pixel of the target object to obtain the cross-section length of the target object. The actual coordinate and the actual cross-section length can be obtained through mapping of the pixel coordinate and the actual coordinate.
In this embodiment: rudder of mechanical arm with degree of freedomThe angle of the machine is obtained by adopting a dynamic programming algorithm, the obtained coordinate point and the cross section length are obtained after entering MicroBlaze, and the corresponding angle of the steering engine of the six-degree-of-freedom mechanical arm is obtained by the dynamic programming algorithm, wherein the specific algorithm is as follows: steering engine with zero 17 rotation angle theta0The first 16 rotation angles of the steering engine are theta1The second 15 rotation angles of the steering engine are theta2The rotation angle of the steering engine III 14 is theta3The four 12 rotation angles of the steering engine are theta4The five 11 rotation angles of the steering engine are theta5。
Taking the rotation center of the base of the mechanical arm as the origin of a three-dimensional coordinate system, and according to the distance | P between the three-dimensional coordinate P (x, y, z) of the target point and the origin O (0,0,0) of the mechanical arm0I determine if p0|≤l1+l2+l3The mechanical arm can reach; if p0|＞l1+l2+l3The mechanical arm is not reachable.
The horizontal direction is completely determined by the steering engine 0, and the rotation angle is
Then, the rotation angles of 3 steering engines in the vertical direction in the X-Y plane are solved, and the mechanical arm l is determined1I.e. M (M, n). Will l2And l3Viewed as vertical disposition, increasing θ1So that the mechanical arm can reach the object, namely, the formula is satisfied
M (M, n) is known, in combination with object coordinates P' (a, b), l2And l3Each side is fixed at two points M and P', N (i, j) is a circle (x-M)2+(y-n)2＝l2 2Harmony circle (x-a)2+(y-b)2＝l3 2The intersection point of (2) is obtained as a result, and the higher point is obtained.
Thus, the method can obtain the product,
the specific working principle of this embodiment is as follows: firstly, the camera module 3 is used for collecting image information of an area needing to be monitored, RGB data of the image is buffered and stored by the FPGA4 and then is processed in parallel to generate a binary image, in order to eliminate noise and enable a target object to be highlighted, the image is respectively corroded and expanded, and the processed RGB image and the binary image can be displayed in two windows of a display screen through a VGA5 interface after being stored. Then, the actual coordinate of the object in the target area is obtained through the object centroid algorithm and the mapping between the virtual coordinate and the actual coordinate, and the maximum transverse width of the object can be simultaneously obtained so as to be convenient for the mechanical arm 9 to grab; the dynamic programming algorithm of the soft core MicroBlaze processing mechanical arm embedded in the Xilinx Artix-7FPGA chip is utilized, the rotation angle required by the mechanical arm 9 can be obtained through the coordinate 0 data and the cross-section length data, a signal is transmitted to the steering engine 15 through a sensor of the voice module, and the steering engine 15 drives the inter-plate serial port communication to control the mechanical arm 9 to grab.
The foregoing illustrates and describes the principles, general features, and advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the above embodiments, and that the foregoing embodiments and descriptions are provided only to illustrate the principles of the present invention without departing from the spirit and scope of the present invention. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (7)
1. The utility model provides a novel arm developments snatch system, a serial communication port, including degree of freedom arm module, speech recognition module, camera module, VGA display module, FPGA module, degree of freedom arm module includes six steering engines, control panel, sets for steering engine one, steering engine two, steering engine three, steering engine four, steering engine five, steering engine zero respectively with six steering engines, the direction of snatching of steering engine four control arms, steering engine five connect revolute joint and manipulator, opening and shutting of control arm, all the other steering engines are revolute joint part, revolute joint part all sets up to the biggest turned angle, the control panel links to each other with six steering engines.
2. The novel mechanical arm dynamic grabbing system of claim 1, wherein the volume of the voice recognition module is 3 x 4.3CM, an STC11 series chip, a timer, an external interrupt, 16I/O ports and a serial port for communicating with the FPGA module are arranged inside the voice recognition module, and the voice recognition module is further provided with 5V and 3.3V power interfaces.
3. The novel mechanical arm dynamic grabbing system of claim 1, wherein the camera module is provided with an OV7670 image sensor, and the camera module is connected with an SCCB bus.
4. The novel dynamic grabbing system of mechanical arm of claim 1, wherein the VGA display module comprises a circuit board, a display, and a VGA interface, the VGA interface is provided with fifteen pins, the fifteen pins are divided into three rows, each row has five holes, and the circuit board is connected to the display through the VGA interface.
5. The novel mechanical arm dynamic grabbing system of claim 1, wherein the FPGA module comprises an Artix-7 core board and a soft core MicroBlaze, the Artix-7 core board adopts Xilinx Artix-7FPGA series chips, the Xilinx 7 series chips are embedded with the soft core MicroBlaze, and the soft core MicroBlaze processor adopts 32-bit instruction and data buses of a RISC architecture and a harvard architecture.
6. The novel mechanical arm dynamic grabbing system of any one of claims 1-5, wherein the mechanical arm dynamic grabbing system adopts an image binary method, a corrosion expansion and centroid algorithm for image processing.
7. The novel mechanical arm dynamic grabbing system of any one of claims 1-5, wherein the angle of the six-DOF mechanical arm steering engine is obtained by using a dynamic programming algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201921258636.0U CN210757741U (en) | 2019-08-05 | 2019-08-05 | Novel mechanical arm dynamic grabbing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201921258636.0U CN210757741U (en) | 2019-08-05 | 2019-08-05 | Novel mechanical arm dynamic grabbing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN210757741U true CN210757741U (en) | 2020-06-16 |
Family
ID=71055995
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201921258636.0U Active CN210757741U (en) | 2019-08-05 | 2019-08-05 | Novel mechanical arm dynamic grabbing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN210757741U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110253588A (en) * | 2019-08-05 | 2019-09-20 | 江苏科技大学 | A kind of New Type of Robot Arm dynamic grasping system |
-
2019
- 2019-08-05 CN CN201921258636.0U patent/CN210757741U/en active Active
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110253588A (en) * | 2019-08-05 | 2019-09-20 | 江苏科技大学 | A kind of New Type of Robot Arm dynamic grasping system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107767423A (en) | A kind of mechanical arm target positioning grasping means based on binocular vision | |
| CN110480637B (en) | Mechanical arm part image recognition and grabbing method based on Kinect sensor | |
| CN111695562A (en) | Autonomous robot grabbing method based on convolutional neural network | |
| CN112906797B (en) | Plane grabbing detection method based on computer vision and deep learning | |
| CN105217324A (en) | A kind of novel de-stacking method and system | |
| CN103424409A (en) | Vision detecting system based on DSP | |
| CN113379849A (en) | Robot autonomous recognition intelligent grabbing method and system based on depth camera | |
| CN111347411A (en) | Two-arm cooperative robot three-dimensional visual recognition grabbing method based on deep learning | |
| CN111360821A (en) | Picking control method, device and equipment and computer scale storage medium | |
| CN109877827B (en) | Non-fixed point material visual identification and gripping device and method of connecting rod manipulator | |
| CN112926503B (en) | Automatic generation method of grabbing data set based on rectangular fitting | |
| CN210757741U (en) | Novel mechanical arm dynamic grabbing system | |
| Wan et al. | An energy-efficient quad-camera visual system for autonomous machines on fpga platform | |
| Jia et al. | Real-time color-based sorting robotic arm system | |
| Recce et al. | Vision and neural control for an orange harvesting robot | |
| Liu et al. | Direct servo control from in-sensor cnn inference with a pixel processor array | |
| CN113762159A (en) | Target grabbing detection method and system based on directional arrow model | |
| CN109903323A (en) | Training method, device, storage medium and terminal for transparent substance identification | |
| Gao et al. | An automatic assembling system for sealing rings based on machine vision | |
| CN112975970A (en) | Vision grabbing mechanical arm system | |
| Zhang et al. | Hierarchical and parallel pipelined heterogeneous SoC for embedded vision processing | |
| CN113305840A (en) | Intelligent electric power overhaul robot visual identification system based on raspberry group | |
| CN106206357B (en) | Micro-chip pin direction embedded visual automatic detection system and detection method thereof | |
| CN110253588A (en) | A kind of New Type of Robot Arm dynamic grasping system | |
| CN114565852A (en) | Industrial robot safety protection system and method based on machine vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |