CN115946134A - Magic cube robot is separated to two fork arms based on image processing - Google Patents

Magic cube robot is separated to two fork arms based on image processing Download PDF

Info

Publication number
CN115946134A
CN115946134A CN202211527575.XA CN202211527575A CN115946134A CN 115946134 A CN115946134 A CN 115946134A CN 202211527575 A CN202211527575 A CN 202211527575A CN 115946134 A CN115946134 A CN 115946134A
Authority
CN
China
Prior art keywords
magic cube
fork
double
image processing
claw
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
CN202211527575.XA
Other languages
Chinese (zh)
Inventor
史尧臣
于雪莲
李庆华
尹春梅
翁静静
曹炳谦
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.)
Changchun University
Original Assignee
Changchun University
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 Changchun University filed Critical Changchun University
Priority to CN202211527575.XA priority Critical patent/CN115946134A/en
Publication of CN115946134A publication Critical patent/CN115946134A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Landscapes

  • Manipulator (AREA)

Abstract

A magic cube solving robot with double fork arms based on image processing belongs to the technical field of intelligent control. The recognition analysis control system is used for recognizing and collecting color information of each surface of the magic cube, calculating a reduction mode of the magic cube, converting the reduction mode information into action signals and sending the action signals to the double-fork-arm mechanical arm; the double-fork arm mechanical arms are identical in structure and are reversely arranged on the triangular support part of the support, claw ends are correspondingly arranged, and the opening and closing of a power supply are controlled through a switching power supply; the support is arranged on the bottom plate. The magic cube has the advantages that a filtering device is not needed, the air tightness of the device is not required, the overall structure is simple, the daily maintenance is easy, the control precision of the rotating angle is high, and the restoration of the magic cube can be completed more stably and accurately. The recognition precision is improved, and the magic cube restoring efficiency and success rate of the robot are improved. The connecting rod is driven by the steering engine to rotate, the connecting rod pulls the claw tongs to move on the sliding rail, so that the magic cube is clamped and loosened, and the magic cube grabbing device is suitable for grabbing of magic cubes with various sizes.

Description

Magic cube robot is solved to two fork arms based on image processing
Technical Field
The invention relates to a dual-fork arm magic cube solving robot based on image processing, and belongs to the technical field of intelligent control.
Background
The magic cube is a common intelligent toy, and the quick restoration of the disordered magic cube by simple groping is a difficult behavior, so that a technology of utilizing a computer to simulate and deduce an optimal restoration path appears.
At present, most magic cube robots drive the opening, closing, rotation and movement of the robot claw tongs in a pneumatic or hydraulic mode. The rotating process is the main moving process in the path of the reset or scattering of the magic cube, and no matter the magic cube is driven by hydraulic pressure or air pressure, an air pipe or an oil pipe is required to be used as a power transmission path, and leakage inevitably exists between the surfaces moving relatively, so that strict requirements are required on the sealing performance of the device, high requirements are also required on the purity of air and oil, and the air cylinder or the hydraulic cylinder and a matched filtering device cause the whole structure of the robot to be complex and the robot to be difficult to maintain.
Disclosure of Invention
In order to solve the problems in the background art, the invention provides a dual-fork arm magic cube solving robot based on image processing.
The invention adopts the following technical scheme: a magic cube solving robot with double fork arms based on image processing comprises a switching power supply, a bottom plate, a double fork arm mechanical arm and a recognition analysis control system;
the recognition analysis control system is used for recognizing and collecting color information of each surface of the magic cube, converting the information of the restoration mode into action signals and sending the action signals to the two double-fork arm mechanical arms after calculating the restoration mode of the magic cube, wherein the action signals are signals for controlling the two double-fork arm mechanical arms to perform clamping action and/or rotating action, the clamping action is used for clamping the magic cube, and the rotating action is used for driving the clamping action to rotate so as to rearrange the magic cubes;
the two double-fork arm mechanical arms are identical in structure and are reversely arranged on the triangular support part of the support, claw ends of the two double-fork arm mechanical arms are correspondingly arranged, and the two double-fork arm mechanical arms control the on-off of a power supply through a switching power supply;
the support is arranged on the bottom plate.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention adopts electric drive, does not need a filtering device, has no requirement on the air tightness of the device, realizes the free rotation of the mechanical arm and the claw clamp by utilizing the mature electric slip ring technology, has simple integral structure, is easy for routine maintenance, has high control precision of the rotation angle, and can more stably and accurately finish the restoration of the magic cube.
2. The recognition analysis control system of the invention adopts the image processing technology to quickly and accurately group the disordered magic cube arrangement modes, calculates and selects the optimal path to complete the restoration of the magic cube, improves the recognition precision, and improves the restoration efficiency and success rate of the robot to the magic cube.
3. According to the invention, the steering engine drives the connecting rod to rotate, and the connecting rod pulls the claw tongs to move on the sliding rail, so that the magic cube can be clamped and loosened, and the device is suitable for grabbing magic cubes with various sizes.
Drawings
FIG. 1 is a schematic structural view of the present invention;
FIG. 2 is a schematic view of FIG. 1 with the exception of the housing;
FIG. 3 is a rear view of FIG. 2;
FIG. 4 is a schematic diagram of a dual-wishbone robot arm;
FIG. 5 is a schematic structural view of a dual-yoke gripper;
FIG. 6 is a rear view of FIG. 5;
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments, and based on the embodiments of the present invention, all other embodiments obtained by a person skilled in the art without making creative efforts belong to the protection scope of the present invention.
Example 1:
a magic cube solving robot with double fork arms based on image processing comprises a switching power supply 4, a bottom plate 13, a double fork arm mechanical arm and a recognition analysis control system;
the recognition analysis control system is used for recognizing and collecting color information of each surface of the magic cube, converting the reduction mode information into action signals and sending the action signals to the two double-fork arm mechanical arms after calculating the reduction mode of the magic cube, wherein the action signals are signals for controlling the two double-fork arm mechanical arms to perform clamping action and/or rotation action, the clamping action is used for clamping the magic cube, and the rotation action is used for driving the clamping action to rotate so as to rearrange the magic cube;
the recognition analysis control system comprises a terminal controller 1 and a camera 7;
the camera 7 is embedded in the center of the top end part of the bracket, and the camera 7 is used for collecting color information of each surface of the magic cube and sending the color information to the terminal controller 1; the camera 7 adopts a CONRING-KL-MN02 camera.
The terminal controller 1 is internally provided with an image processing module based on a Convolutional Neural Network (CNN), compares the received color information with a magic cube reduction data set stored in the image processing module, converts reduction mode information successfully compared into action signals and sends the action signals to the two double-fork arm mechanical arms, and the terminal controller 1 is preferably an ArduinoDUE controller, but not limited to the ArduinoDUE controller.
The image processing module is used for extracting image features and selecting a restoration path; the image feature extraction uses a large number of stored data models in the previous period, 20 iterations are carried out on the training set image through a convolutional neural network, and a proper convolutional kernel is selected to complete the image feature extraction and the selection of a reduction path; the optimal corresponding restoration scheme is preset for each group of arrangement modes, a complete recognition analysis control system is established, and recognition accuracy and scheme selection speed are improved.
The terminal controller 1 further comprises a magic cube restoring program storage module, the magic cube restoring program can be stored, the magic cube restoring program can be conveniently used in the same arrangement mode next time, and the magic cube restoring process is faster through continuous learning and recording.
The two double-fork arm mechanical arms are identical in structure and are reversely arranged on the triangular support part 2 of the support, claw ends of the two double-fork arm mechanical arms are correspondingly arranged, the middle part of each double-fork arm mechanical arm is connected with the corresponding V-shaped support part 5, the two V-shaped support parts 5 are connected with the triangular support part 2, and the two double-fork arm mechanical arms control the on-off of a power supply through a switching power supply 4; the switching power supply 4 is arranged on the power supply support frame part 3;
each double-fork arm mechanical arm comprises a double-fork arm mechanical claw 9, an electric slip ring 10, a stepping motor 11 and a stepping motor servo driver 12; the stepping motor servo driver 12 is fixed on the bottom plate 13, controls the on-off of the power supply through the switching power supply 4, and is used for receiving an action signal sent by the control system and controlling the on-off of the stepping motor 11; the stepping motor 11 selects a 86 stepping motor; the output shaft of the stepping motor 11 is connected with the bottom of the double-fork-arm mechanical claw 9 through the inner ring of the electric slip ring 10, and specifically comprises the following steps: an output shaft of the stepping motor 11 is connected with one end of an optical shaft through a coupler, and the other end of the optical shaft is connected with the bottom of the double-fork-arm mechanical claw 9 through a screw; the inner ring of the electric slip ring 10 is fixedly sleeved on an optical axis and is connected with the bottom of the double-fork-arm mechanical claw 9 through a screw, the stepping motor 11 drives the inner ring of the electric slip ring 10 to synchronously rotate with the double-fork-arm mechanical claw 9, the outer ring of the electric slip ring 10 is connected with the V-shaped support part 5 of the support, and the outer ring of the electric slip ring 10 is connected with the switching power supply 4 through a wire.
The double-fork-arm mechanical claw 9 is a parallel mechanical claw. The double-fork-arm mechanical claw 9 comprises a steering engine 6, a claw clamp 15, a connecting rod 16, a connecting plate 17 and a mechanical palm 18; the palm root of the mechanical palm 18 is connected with an inner ring of the electric slip ring 10, the palm tip of the mechanical palm 18 is connected with the claw root of two symmetrically-arranged claw tongs 15 in a sliding mode through a sliding rail, the stroke of the two claw tongs 15 is 10mm-60mm, the claw root of each claw tong 15 is hinged to one end of a corresponding arc-shaped connecting rod 16 through a pin shaft, the other end of each connecting rod 16 is hinged to the corresponding end of a connecting plate 17 through a corresponding pin shaft, the middle of each connecting plate 17 is fixedly connected with an output shaft of a steering engine 6, the steering engine 6 is arranged on the mechanical palm 18, the steering engine 6 is connected with the inner ring of the electric slip ring 10 through a conducting wire, the connecting plates 17 are driven to rotate after the steering engine 6 is electrified, then the connecting rods 16 are driven to move, and the connecting rods 16 drive the two claw tongs 15 to move oppositely or back to clamp and loosen the magic cube. The switching power supply 4 provides stable voltage for the steering engine 6 to drive the claw tongs 15 to clamp and loosen the magic cube and the rotation of the stepping motor 11.
The bracket is arranged on the bottom plate 13 and comprises a triangular bracket part 2, a power supply support frame part 3, a V-shaped bracket part 5 and a top end part.
Example 2:
this example differs from example 1 in that:
the outer side of the robot is covered with a shell 14, the lower end of the shell 14 is connected with a bottom plate 13, and the shell 14 plays a role in light gathering, protection and dust prevention for the whole device.
Example 3:
this example differs from example 2 in that:
the dual-fork arm magic cube robot based on image processing of claim 7, wherein: the light filling lamp 8 that is equipped with two symmetries and sets up is inlayed to the interior top of casing 14, and the angle of illumination of two light filling lamps 8 is 135 to provide sufficient light, the camera 7 of being convenient for more clear accurate extraction magic cube color lump distribution information. When the housing 14 is provided, the camera 7 may be disposed at the center of the top end inside the housing 14.
The working process of the invention is as follows:
controlling a steering engine 6 to clamp the magic cube to be restored through a double-fork arm mechanical arm;
under the irradiation of the light supplement lamp 8, a camera 7 in the recognition analysis control system can more clearly acquire the color block arrangement mode of the current visible surface of the magic cube;
after scanning is finished, the double-fork arm mechanical arm is controlled to rotate to finish overturning, so that color block arrangement modes of six surfaces in the initial state of the magic cube are extracted and transmitted to the image processing module;
completing recognition and classification by using the early learning training grouping result, and selecting an optimal restoration path scheme;
converting the reduction path scheme into a control signal and transmitting the control signal to a stepping motor servo driver;
the stepping motor servo driver controls the rotation direction and the rotation angle of the stepping motor according to the control signal information;
the rotation of the stepping motor drives the double-fork-arm mechanical claw to rotate so as to restore the magic cube.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.

Claims (8)

1. The utility model provides a magic cube robot is solved to two fork arms based on image processing which characterized in that: the device comprises a switching power supply (4), a bottom plate (13), a double-fork arm mechanical arm and a recognition analysis control system;
the recognition analysis control system is used for recognizing and collecting color information of each surface of the magic cube, converting the information of the restoration mode into action signals and sending the action signals to the two double-fork arm mechanical arms after calculating the restoration mode of the magic cube, wherein the action signals are signals for controlling the two double-fork arm mechanical arms to perform clamping action and/or rotating action, the clamping action is used for clamping the magic cube, and the rotating action is used for driving the clamping action to rotate so as to rearrange the magic cubes;
the two double-fork-arm mechanical arms are identical in structure and are reversely arranged on the triangular support part (2) of the support, claw ends of the two double-fork-arm mechanical arms are correspondingly arranged, and the two double-fork-arm mechanical arms control the on and off of a power supply through a switching power supply (4);
the support is arranged on the bottom plate (13).
2. The dual-fork magic cube robot based on image processing of claim 1, wherein: the recognition analysis control system comprises a terminal controller (1) and a camera (7);
the camera (7) is arranged at the top end part of the bracket, and the camera (7) is used for collecting color information of each surface of the magic cube and sending the color information to the terminal controller (1);
an image processing module based on a convolutional neural network is arranged in the terminal controller (1), received color information is compared with a magic cube reduction data set stored in the terminal controller, reduction mode information which is successfully compared is converted into action signals, and the action signals are sent to the two double-fork arm mechanical arms.
3. The dual-fork arm magic cube robot based on image processing of claim 2, wherein: the image processing module is used for extracting image features and selecting a restoration path.
4. The dual-fork arm magic cube robot based on image processing of claim 3, wherein: the terminal controller (1) further comprises a magic cube restoring program storage module.
5. The dual-fork arm magic cube robot based on image processing of claim 1 or 4, wherein: each double-fork arm mechanical arm comprises a double-fork arm mechanical claw (9), an electric slip ring (10), a stepping motor (11) and a stepping motor servo driver (12); the stepping motor servo driver (12) is fixed on the bottom plate (13), controls the on-off of the power supply through the switching power supply (4), and is used for receiving an action signal sent by the control system and controlling the on-off of the stepping motor (11); an output shaft of the stepping motor (11) is connected with the bottom of the double-fork-arm mechanical claw (9) through an inner ring of the electric slip ring (10), an outer ring of the electric slip ring (10) is connected with the V-shaped support part (5) of the support, and an outer ring of the electric slip ring (10) is connected with the switching power supply (4).
6. The dual-fork magic cube robot based on image processing of claim 5, wherein: the double-fork-arm mechanical claw (9) comprises a steering engine (6), a claw clamp (15), a connecting rod (16), a connecting plate (17) and a mechanical palm (18); the palm root of machinery palm (18) is connected with the inner ring of electric slip ring (10), and the palm point portion and two claw pincers (15) sliding connection of machinery palm (18), every the claw root part of claw pincers (15) is articulated with the one end of curved connecting rod (16) that corresponds respectively, every the other end of connecting rod (16) is articulated with the corresponding end of connecting plate (17), the middle part of connecting plate (17) and the output shaft fixed connection of steering wheel (6), steering wheel (6) set up on machinery palm (18) to steering wheel (6) link to each other through the inner ring of wire and electric slip ring (10).
7. The dual-fork arm magic cube robot based on image processing of claim 4 or 6, wherein: the outer side of the robot is covered with a shell (14), and the lower end of the shell (14) is connected with a bottom plate (13).
8. The dual-fork arm magic cube robot based on image processing of claim 7, wherein: two symmetrically arranged light supplementing lamps (8) are arranged at the inner top end of the shell (14).
CN202211527575.XA 2022-11-30 2022-11-30 Magic cube robot is separated to two fork arms based on image processing Pending CN115946134A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211527575.XA CN115946134A (en) 2022-11-30 2022-11-30 Magic cube robot is separated to two fork arms based on image processing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211527575.XA CN115946134A (en) 2022-11-30 2022-11-30 Magic cube robot is separated to two fork arms based on image processing

Publications (1)

Publication Number Publication Date
CN115946134A true CN115946134A (en) 2023-04-11

Family

ID=87296285

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211527575.XA Pending CN115946134A (en) 2022-11-30 2022-11-30 Magic cube robot is separated to two fork arms based on image processing

Country Status (1)

Country Link
CN (1) CN115946134A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102699917A (en) * 2012-06-08 2012-10-03 北京工业大学 Magic cube-solving robot based on intelligent mobile phone
DE102012109040A1 (en) * 2012-09-25 2014-04-10 BIBA - Bremer Institut für Produktion und Logistik GmbH Device for performing operations on cuboidal objects, has frame, which is adapted to shape of object, where climbing device is provided, with which frame is movable on stacks of objects along in or against stacking direction
CN108647689A (en) * 2018-06-01 2018-10-12 中国科学院福建物质结构研究所 Magic square restored method and its device based on GoogLeNet neural networks
CN108748151A (en) * 2018-06-05 2018-11-06 安徽合动智能科技有限公司 A kind of finger of both arms two structure magic cube-solving robot
CN112025716A (en) * 2020-09-25 2020-12-04 上海商汤临港智能科技有限公司 Control device, data processing method, control apparatus, and computer storage medium
CN113084840A (en) * 2021-04-20 2021-07-09 唐山学院 Double-arm humanoid-hand full-automatic third-order magic cube reduction robot

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102699917A (en) * 2012-06-08 2012-10-03 北京工业大学 Magic cube-solving robot based on intelligent mobile phone
DE102012109040A1 (en) * 2012-09-25 2014-04-10 BIBA - Bremer Institut für Produktion und Logistik GmbH Device for performing operations on cuboidal objects, has frame, which is adapted to shape of object, where climbing device is provided, with which frame is movable on stacks of objects along in or against stacking direction
CN108647689A (en) * 2018-06-01 2018-10-12 中国科学院福建物质结构研究所 Magic square restored method and its device based on GoogLeNet neural networks
CN108748151A (en) * 2018-06-05 2018-11-06 安徽合动智能科技有限公司 A kind of finger of both arms two structure magic cube-solving robot
CN112025716A (en) * 2020-09-25 2020-12-04 上海商汤临港智能科技有限公司 Control device, data processing method, control apparatus, and computer storage medium
CN113084840A (en) * 2021-04-20 2021-07-09 唐山学院 Double-arm humanoid-hand full-automatic third-order magic cube reduction robot

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
中国科协青少年科技中心编: "《第二十八届全国青少年科技创新大赛获奖作品集》", 科学普及出版社, pages: 116 - 117 *

Similar Documents

Publication Publication Date Title
CN109807917B (en) Coupling manipulator capable of grabbing objects in self-adaptive mode
CN105818154B (en) A kind of guardrail handrail automatic cleaning robot
CN104552305A (en) Magic cube solving device capable of performing three-dimensional simulation
CN109648589B (en) Robot dexterous manipulator finger device based on cylinder driving
CN115946134A (en) Magic cube robot is separated to two fork arms based on image processing
CN210589303U (en) Picking robot
CN107042473A (en) Applied to the workpiece pattern recognition device and recognition methods for throwing shot blasting equipment
CN211867832U (en) Dental material identification and pickup device based on machine vision
CN112356064A (en) Grabbing device for production mechanical arm
CN210100030U (en) Double-arm magic cube robot
CN205310298U (en) Underwater manipulator with high -pressure spray wash device
CN210414551U (en) Two-arm two-finger magic cube solving robot
CN110178536A (en) Tomato-harvesting robot and its control method
CN112706150B (en) Wearable external limb auxiliary grabbing device and control method
CN205129886U (en) Imitative people underactuated manipulator based on 3D printing technique
CN211240881U (en) Miniature three-degree-of-freedom picking manipulator
CN209198899U (en) It is a kind of that vehicle is cleared up based on ZigBee gateway and the road garbage of image recognition
CN112917481A (en) Kiwi fruit picking device based on Delta mechanical arm
CN207665528U (en) Clamping type fruit picking apparatus
CN115922709A (en) Pneumatic drive type double-arm magic cube solving robot
CN207127802U (en) A kind of hinged bolt and can night illumination hydraulic tongs
CN221010887U (en) Picking robot and tail end grabbing device thereof
CN204471381U (en) A kind of solution magic square device carrying out three-dimensional artificial
CN112758562B (en) Intelligent environment-friendly robot and using method thereof
CN117697725A (en) Robot arm for flexible assembly based on industrial vision

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20230411