CN216372209U - Mechanical arm capable of recognizing, positioning, bearing and grabbing without damage based on machine learning - Google Patents

Mechanical arm capable of recognizing, positioning, bearing and grabbing without damage based on machine learning Download PDF

Info

Publication number
CN216372209U
CN216372209U CN202120814876.5U CN202120814876U CN216372209U CN 216372209 U CN216372209 U CN 216372209U CN 202120814876 U CN202120814876 U CN 202120814876U CN 216372209 U CN216372209 U CN 216372209U
Authority
CN
China
Prior art keywords
fixed
arm
lead screw
steering engine
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.)
Active
Application number
CN202120814876.5U
Other languages
Chinese (zh)
Inventor
杨运高
易传美
杨海生
朱世建
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.)
Guizhou University of Engineering Science
Original Assignee
Guizhou University of Engineering Science
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 Guizhou University of Engineering Science filed Critical Guizhou University of Engineering Science
Priority to CN202120814876.5U priority Critical patent/CN216372209U/en
Application granted granted Critical
Publication of CN216372209U publication Critical patent/CN216372209U/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Manipulator (AREA)

Abstract

The utility model provides a mechanical arm for recognizing, positioning, bearing and nondestructive grabbing based on machine learning, belonging to the technical field of intelligent machines, and comprising a trolley main body, wherein the top of the trolley main body is rotatably connected with a disc, and the top of the disc is fixedly provided with a fixed seat; one end of the rear arm is rotatably connected to the fixed seat through a first screw, the other end of the rear arm is provided with a movable groove, and a front arm is movably hinged between the front inner wall and the rear inner wall of the movable groove through a third screw; the fixed claw is movably hinged with the front arm through a fourth hinge shaft; the movable claw is positioned in the square groove and is movably hinged with the fixed claw and the front arm through a fifth hinge shaft; this device makes when centre gripping target object effectively combine object three-dimensional coordinate to draw and mechanical tongs steering wheel control algorithm, realizes accurate location and snatchs the function for this device uses more conveniently, and the practicality is stronger.

Description

Mechanical arm capable of recognizing, positioning, bearing and grabbing without damage based on machine learning
Technical Field
The utility model belongs to the technical field of intelligent machines, and particularly relates to a mechanical arm for recognizing, positioning, bearing and nondestructive grabbing based on machine learning.
Background
With the rapid popularization of industrial automation, the grabbing of materials by a machine instead of manual work has become a new requirement for industrial development. Moreover, the automatic grabbing trolley is also available in daily life of people, and particularly for people with mobility disabilities, the automatic grabbing trolley can replace manual grabbing and placing of articles, so that great convenience is brought to the life of the people with mobility disabilities.
But current snatch dolly still via manual operation, whether the object is snatched through the visual observation, is not controlled like this to the centre gripping dynamics of object, snatchs the shakiness for the object causes the damage easily.
SUMMERY OF THE UTILITY MODEL
The utility model aims to provide a mechanical arm for recognizing, positioning, bearing and non-destructive grabbing based on machine learning, and aims to solve the problems that a grabbing trolley in the prior art is manually operated, whether an object is grabbed or not is observed through naked eyes, the clamping force of the object is not controlled well, grabbing is unstable, and the object is easy to damage.
In order to achieve the purpose, the utility model provides the following technical scheme:
the utility model provides a based on machine learning discernment, location, bearing, harmless arm that snatchs, includes:
the trolley comprises a trolley main body, wherein the top of the trolley main body is rotatably connected with a disc, and a fixed seat is fixed at the top of the disc;
one end of the rear arm is rotatably connected to the fixed seat through a first screw, the other end of the rear arm is provided with a movable groove, and a front arm is movably hinged between the front inner wall and the rear inner wall of the movable groove through a third screw;
the fixed claw is movably hinged with the front arm through a fourth hinge shaft;
the movable claw is positioned in the square groove and is movably hinged with the fixed claw and the front arm through a fifth hinge shaft;
the driving mechanism comprises a first driving assembly, a second driving assembly and a third driving assembly, and the first driving assembly, the second driving assembly and the third driving assembly are respectively connected with the rear arm, the front arm and the fixing claw so as to realize angle adjustment of the rear arm, the front arm and the fixing claw;
the three-dimensional capturing mechanism is used for capturing the plane coordinates of the target object; and
and the two sensors are respectively fixed on the inner surfaces of the finger ends of the fixed claw and the movable claw.
As a preferable scheme of the present invention, the three-dimensional capturing device further includes an AI learning module, the AI learning module is fixedly disposed at an external mobile control end, and the mobile control end is in signal connection with the sensor, the driving mechanism and the three-dimensional capturing mechanism.
As a preferable scheme of the utility model, the first driving assembly comprises a first steering engine, a first lead screw nut and a first concave base, the first concave base is fixed at the top of the disc, the first steering engine is movably hinged on the first concave base through a first hinge shaft, one end of the first lead screw is fixed with an output shaft of the first steering engine, the other end of the first lead screw movably penetrates through one side of the rear arm and extends outwards, the first lead screw nut is in threaded connection with the circumferential surface of the first lead screw, and the outer surface of the first lead screw nut is fixed with the inner surface of the penetrating part of the rear arm.
As a preferable scheme of the utility model, the second driving assembly comprises a second steering engine, a second lead screw nut and a second concave base, the second concave base is fixed at the top of the rear arm, the second steering engine is movably hinged on the second concave base through a second hinge shaft, one end of the second lead screw is fixed with an output shaft of the second steering engine, the other end of the second lead screw movably penetrates through one side of the front arm and extends outwards, the second lead screw nut is in threaded connection with the circumferential surface of the second lead screw, and the outer surface of the second lead screw nut is fixed with the inner surface of the penetrating part of the front arm.
As a preferable scheme of the present invention, the third driving assembly includes a third steering engine, a third lead screw nut, and a third concave base, the third concave base is fixed to the top of the forearm, the third steering engine is movably hinged to the third concave base through a third hinge shaft, one end of the third lead screw is fixed to an output shaft of the third steering engine, the other end of the third lead screw movably penetrates one side of the fixed jaw and extends outward, the third lead screw nut is connected to the circumferential surface of the third lead screw in a threaded manner, and the outer surface of the third lead screw nut is fixed to the inner surface of the penetrating portion of the fixed jaw.
As a preferable scheme of the present invention, the three-dimensional capturing mechanism is composed of a top camera and a bottom camera, the top camera is fixed to an end portion of one side of the front arm close to the fixing claw, and the bottom camera is fixed to a left end of the cart body.
As a preferable scheme of the utility model, a motor groove is formed in the trolley main body, a stepping motor is fixed on the bottom wall of the motor groove, and an output shaft of the stepping motor movably penetrates through the top of the trolley main body and is fixed with the bottom end of the disc.
The trolley comprises a trolley main body, a power supply and a wheel, wherein the trolley main body is provided with a first screw, the wheel is fixedly arranged at the top right side of the trolley main body, the wheel is fixedly arranged at the four corners of the bottom of the trolley main body through second screws, and the power supply is used for supplying power to the device.
As a preferable scheme of the utility model, the top of the trolley main body is provided with an annular groove, the bottom of the disc is fixed with an annular block matched with the annular groove, and the annular block is connected in the annular groove in a sliding manner.
As a preferable scheme of the utility model, a front shovel and a chassis are respectively fixed at the left end and the right end of the trolley main body.
Compared with the prior art, the utility model has the beneficial effects that:
1. the plane coordinate of target object is caught through the top camera in this scheme, the height value of target is caught to the bottom camera, constitute three-dimensional coordinate through height value and plane coordinate, then through the first drive assembly among the actuating mechanism, second drive assembly and third drive assembly drive the postbrachium respectively, forearm and stationary dog remove, make postbrachium and forearm adjust suitable position, make the tip of stationary dog and the tip of movable claw be close to mutually, thereby with the object centre gripping, this device makes and effectively combines object three-dimensional coordinate to draw and mechanical tongs steering wheel control algorithm when centre gripping target object, realize accurate location and snatch the function, make this device use more convenient, the practicality is stronger.
2. When the fixed claw and the movable claw clamp the target object, the sensors on the fixed claw and the movable claw control the grabbing strength by whether the object and the finger ends of the fixed claw and the movable claw slide or not, so that the nondestructive grabbing function of the mechanical gripper is realized, and the object is not easily damaged.
Drawings
The accompanying drawings, which are included to provide a further understanding of the utility model and are incorporated in and constitute a part of this specification, illustrate embodiments of the utility model and together with the description serve to explain the principles of the utility model and not to limit the utility model. In the drawings:
FIG. 1 is a first perspective view of the present invention;
FIG. 2 is a second perspective view of the present invention;
FIG. 3 is a cross-sectional view of the present invention;
FIG. 4 is a third perspective view of the present invention;
fig. 5 is a partial perspective view of the present invention at the fixing jaw 15;
fig. 6 is a block diagram of the workflow of the present invention.
In the figure: 1. a trolley main body; 2. a wheel; 3. a chassis; 4. a power source; 5. a disc; 6. a fixed seat; 7. a rear arm; 8. a first steering engine; 801. a first lead screw; 802. a first lead screw nut; 803. a first concave base; 9. a second steering engine; 901. a second lead screw; 902. a second feed screw nut; 903. a second concave base; 10. a first screw; 11. a forearm; 12. a movable groove; 13. a third screw; 14. a third steering engine; 141. a third screw rod; 142. a third feed screw nut; 143. a third concave base; 15. a fixed jaw; 151. a movable jaw; 16. a top camera; 17. a sensor; 19. a bottom camera; 20. front shoveling; 21. a motor slot; 22. a ring block; 23. a stepper motor.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the 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, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
Referring to fig. 1-6, the present invention provides the following technical solutions:
the utility model provides a based on machine learning discernment, location, bearing, harmless arm that snatchs, includes:
the trolley comprises a trolley main body 1, wherein the top of the trolley main body 1 is rotatably connected with a disc 5, and a fixed seat 6 is fixed at the top of the disc 5;
one end of the rear arm 7 is rotatably connected to the fixed seat 6 through a first screw 10, the other end of the rear arm 7 is provided with a movable groove 12, and a front arm 11 is movably hinged between the front inner wall and the rear inner wall of the movable groove 12 through a third screw 13;
the fixed claw 15 is movably hinged with the front arm 11 through a fourth hinge shaft;
the top of the front arm 11 is provided with a square groove, the movable claw 151 is positioned in the square groove, and the movable claw 151 is movably hinged with the fixed claw 15 and the front arm 11 through a fifth hinge shaft;
the driving mechanism comprises a first driving assembly, a second driving assembly and a third driving assembly, and the first driving assembly, the second driving assembly and the third driving assembly are respectively connected with the rear arm 7, the front arm 11 and the fixing claw 15 to realize angle adjustment of the rear arm, the front arm and the fixing claw;
the three-dimensional capturing mechanism is used for capturing the plane coordinates of the target object; and
two sensors 17, two sensors 17 are fixed on the inner surfaces of the finger ends of the fixed jaw 15 and the movable jaw 151 respectively.
In the specific embodiment of the utility model, a car main body 1 in the device is used as a bearing base, a disc 5 is used for bearing a fixed seat 6 and a first concave base 803, so that when the disc 5 rotates, the grabbing angle can be adjusted, the fixed seat 6 fixes a rear arm 7 through a first screw 10, so that the rear arm 7 is movably connected with the fixed seat 6 and can rotate, when the device is used, firstly, power is supplied through a power supply 4, an object is searched by moving wheels 2 on the ground, the object moves to a grabbing range after being found, a target height value is given through a bottom camera 19, a target screen coordinate value is given through the top camera 16, information is transmitted to an external movement control end through the top camera 16 and the bottom camera 19, a three-dimensional coordinate is formed through a plane target and the height value, then, the first steering engine 8 and a second steering engine 9 are controlled to start, different pulse signals are received through the steering engine, the output shaft of the lead screw nut 802 and the second lead screw nut 902 are driven to rotate respectively, so that the first lead screw nut 802 and the second lead screw nut 902 do linear motion on the surface of the lead screw nut, finally the rear arm 7 and the front arm 11 are adjusted in angle, the first steering engine 8, the second steering engine 9 and the third steering engine 14 are supported and fixed respectively through the first concave base 803, the second concave base 903 and the third concave base 143, so that the lead screw nut 142 drives one end of the fixed claw 15 to move, the fixed claw 15 and the movable claw 151 are movably hinged, the fixed claw 15 and the movable claw 151 clamp the target object at the moment, the sensors 17 at the finger ends of the fixed claw 15 and the movable claw 151 are attached to the target object at the moment, whether slippage with a target object occurs or not is judged through the positioning device, information is transmitted to an external mobile control end, the rotation angle of a third steering engine 14 is controlled, the clamping force of a fixed claw 15 is controlled, and after clamping, the target object is grabbed to a specified position, namely grabbing of the target object is completed; the device effectively combines the three-dimensional coordinate extraction of the object and the steering engine control algorithm of the mechanical gripper when clamping the target object, realizes the accurate positioning and gripping function, and has more convenient use and stronger practicability; it should be noted that: the first steering engine 8, the second steering engine 9, the stepping motor 23 and the third steering engine 14 of which type are specifically used are selected by the person skilled in the art, and the signal connection mode between the external mobile control end and the device and the first steering engine 8, the second steering engine 9, the stepping motor 23 and the third steering engine 14 belong to the prior art, and are not described in detail in the scheme.
Specifically, please refer to fig. 1, further comprising an AI learning module, wherein the AI learning module is fixedly disposed at an external mobile control end, and the mobile control end is in signal connection with the sensor 17, the driving mechanism and the three-dimensional capturing mechanism.
In this embodiment: in the device, the core of an AI learning module is an exploration intelligence K210 chip; firstly, respectively collecting 1000 pictures of eggs and iron blocks under different angles and light rays as learning samples; then, a PC is used, a deep learning framework TensorFlow is adopted for model training, and a training result is transplanted to a reconnaissance K210 development board; finally, the exploration intelligent K210 development board respectively identifies the eggs and the iron blocks after being electrified; therefore, the device can better select the target object and can better grab the target object; the external mobile control end is used for controlling the operation of the first steering engine 8, the bottom camera 19, the third steering engine 14, the power supply 4 and the stepping motor 23, meanwhile, information transmitted by the top camera 16 and the bottom camera 19 can be received, the information is integrated, then the integrated instruction acts on the first steering engine 8, the bottom camera 19, the third steering engine 14, the power supply 4 and the stepping motor 23 to achieve starting or closing of the first steering engine, meanwhile, the connection relation and the circuit board are set to be common knowledge of technicians in the field, and redundant description is omitted.
Referring to fig. 1 specifically, the first driving assembly includes a first steering engine 8, a first lead screw 801, a first lead screw nut 802 and a first concave base 803, the first concave base 803 is fixed on the top of the disc 5, the first steering engine 8 is movably hinged on the first concave base 803 through a first hinge shaft, one end of the first lead screw 801 is fixed with an output shaft of the first steering engine 8, the other end of the first lead screw 801 movably penetrates through one side of the rear arm 7 and extends outward, the first lead screw nut 802 is connected to the circumferential surface of the first lead screw 801 in a threaded manner, and the outer surface of the first lead screw nut 802 is fixed with the inner surface of the penetrating position of the rear arm 7.
Specifically, referring to fig. 1, the second driving assembly includes a second steering engine 9, a second lead screw 901, a second lead screw nut 902 and a second concave base 903, the second concave base 903 is fixed on the top of the rear arm 7, the second steering engine 9 is movably hinged on the second concave base 903 through a second hinge shaft, one end of the second lead screw 901 is fixed with an output shaft of the second steering engine 9, the other end of the second lead screw 901 movably penetrates through one side of the front arm 11 and extends outward, the second lead screw nut 902 is connected to the circumferential surface of the second lead screw 901 in a threaded manner, and the outer surface of the second lead screw nut 902 is fixed with the inner surface of the penetrating position of the front arm 11.
Referring to fig. 1 specifically, the third driving assembly includes a third steering engine 14, a third lead screw 141, a third lead screw nut 142 and a third concave base 143, the third concave base 143 is fixed to the top of the front arm 11, the third steering engine 14 is movably hinged to the third concave base 143 through a third hinge shaft, one end of the third lead screw 141 is fixed to an output shaft of the third steering engine 14, the other end of the third lead screw 141 movably penetrates through one side of the fixed jaw 15 and extends outward, the third lead screw nut 142 is connected to the circumferential surface of the third lead screw 141 in a threaded manner, and the outer surface of the third lead screw nut 142 is fixed to the inner surface of the penetrating portion of the fixed jaw 15.
Specifically referring to fig. 2, the three-dimensional capturing mechanism is composed of a top camera 16 and a bottom camera 19, the top camera 16 is fixed on the end portion of the front arm 11 close to the fixing claw 15, and the bottom camera 19 is fixed on the left end of the trolley body 1.
In this embodiment: the height value and the plane coordinate value of the target object are respectively taken through the top camera 16 and the bottom camera 19, then the information of the height value and the plane coordinate value is returned, the three-dimensional coordinate of the target object can be obtained, and therefore the device can be enabled to accurately grab the target.
Referring to fig. 3, a motor groove 21 is formed in the cart body 1, a stepping motor 23 is fixed to the bottom wall of the motor groove 21, and an output shaft of the stepping motor 23 movably penetrates through the top of the cart body 1 and is fixed to the bottom end of the disc 5.
In this embodiment: motor groove 21 is used for holding step motor 23, and is preferred, and the louvre has been seted up to the bottom of motor groove 21 for the heat that step motor 23 during operation produced can spill, makes step motor 23 difficult because the high temperature causes the damage, and step motor 23 starts the back simultaneously, and its output shaft can drive disc 5 and rotate, makes disc 5 can drive back arm 7 and carries out the regulation of angle.
Specifically, please refer to fig. 1, further comprising a power source 4, wherein the power source 4 is fixed on the right side of the top of the trolley body 1, wheels 2 are fixedly mounted at four corners of the bottom of the trolley body 1 through second screws, and the power source 4 is used for providing power for the device.
In this embodiment: power 4 is located diesel engine, generates electricity after adding diesel oil for this device need not to be connected with external power source, makes its work that can more distant place, and is more convenient, makes this device can remove to the assigned position through wheel 2 simultaneously.
Specifically referring to fig. 3, the top of the trolley body 1 is provided with an annular groove, the bottom of the disc 5 is fixed with an annular block 22 matched with the annular groove, and the annular block 22 is slidably connected in the annular groove.
In this embodiment: when the disk 5 rotates, the driving ring block 22 is embedded into the ring groove and slides, so that the disk 5 is more stable when rotating.
Specifically referring to fig. 4, a front shovel 20 and a chassis 3 are fixed to the left and right ends of the cart body 1, respectively.
In this embodiment: through front shovel 20 for when this device removed, bottom camera 19 was difficult for the object contact, made bottom camera 19 not fragile, life is longer, and chassis 3 can protect the bottom of this device not fragile.
The working principle and the using process of the utility model are as follows: when the device is used, firstly, power is supplied through a power supply 4, a target is searched by moving a wheel 2 on the ground, the target is found and then moves to a range capable of being grabbed, a target height value is given through a bottom camera 19, a target screen coordinate value is given through a top camera 16, information is transmitted to an external movement control end through the top camera 16 and the bottom camera 19, a three-dimensional coordinate is formed through a plane target and a height value, then a first steering engine 8 and a second steering engine 9 are controlled to start, output shafts of the first steering engine and the second steering engine are rotated through receiving different pulse signals, so that a first lead screw 801 and a second lead screw 901 are respectively driven to rotate, a first lead screw nut 802 and a second lead screw nut 902 make linear motion on the surfaces of the first lead screw nut and the second lead screw nut, finally, a rear arm 7 and a front arm 11 are adjusted in angle, after the angle is adjusted to a proper position, a third steering engine 14 is started, an output shaft of the third screw rod 141 is driven to rotate, so that one end of the fixed claw 15 is driven to move by the third screw rod nut 142, the fixed claw 15 is movably hinged with the movable claw 151, the fixed claw 15 and the movable claw 151 clamp the target object at the moment, the sensor 17 at the finger ends of the fixed claw 15 and the movable claw 151 is attached to the target object, whether the sensor slides with the target object is judged through the sensor, information is transmitted to an external movement control end, the rotation angle of the third steering engine 14 is controlled, the clamping force of the fixed claw 15 is controlled, and after the sensor is clamped, the target object is clamped to a specified position, so that the target object is grabbed; this device makes when centre gripping target object effectively combine object three-dimensional coordinate to draw and mechanical tongs steering wheel control algorithm, realizes accurate location and snatchs the function for this device uses more conveniently, and the practicality is stronger.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the utility model. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. The utility model provides a based on machine learning discernment, location, bearing, harmless arm that snatchs which characterized in that includes:
the trolley comprises a trolley main body (1), wherein the top of the trolley main body (1) is rotatably connected with a disc (5), and a fixed seat (6) is fixed at the top of the disc (5);
one end of the rear arm (7) is rotatably connected to the fixed seat (6) through a first screw (10), the other end of the rear arm (7) is provided with a movable groove (12), and a front arm (11) is movably hinged between the front inner wall and the rear inner wall of the movable groove (12) through a third screw (13);
the fixed claw (15) is movably hinged with the front arm (11) through a fourth hinge shaft;
the top of the front arm (11) is provided with a square groove, the movable claw (151) is positioned in the square groove, and the movable claw (151) is movably hinged with the fixed claw (15) and the front arm (11) through a fifth hinge shaft;
the driving mechanism comprises a first driving assembly, a second driving assembly and a third driving assembly, and the first driving assembly, the second driving assembly and the third driving assembly are respectively connected with the rear arm (7), the front arm (11) and the fixing claw (15) to realize angle adjustment of the rear arm, the front arm and the fixing claw;
the three-dimensional capturing mechanism is used for capturing the plane coordinates of the target object; and
and the two sensors (17), and the two sensors (17) are respectively fixed on the inner surfaces of the finger ends of the fixed claw (15) and the movable claw (151).
2. The mechanical arm for recognizing, positioning, bearing and nondestructive grabbing based on machine learning of claim 1, further comprising an AI learning module, wherein the AI learning module is fixedly arranged at an external mobile control end, and the mobile control end is in signal connection with the sensor (17), the driving mechanism and the three-dimensional grabbing mechanism.
3. The machine learning-based identification, positioning, load-bearing, non-destructive gripping robot of claim 2, it is characterized in that the first driving component comprises a first steering engine (8), a first screw rod (801), a first screw rod nut (802) and a first concave base (803), the first concave base (803) is fixed on the top of the disc (5), the first steering engine (8) is movably hinged on the first concave base (803) through a first hinge shaft, one end of the first screw rod (801) is fixed with an output shaft of the first steering engine (8), and the other end of the first screw rod (801) movably penetrates through one side of the rear arm (7) and extends outwards, the first lead screw nut (802) is screwed to the circumferential surface of the first lead screw (801), and the outer surface of the first lead screw nut (802) is fixed with the inner surface of the penetrating part of the rear arm (7).
4. The machine learning-based identification, positioning, load-bearing, non-destructive gripping robot of claim 3, it is characterized in that the second driving component comprises a second steering engine (9), a second screw rod (901), a second screw rod nut (902) and a second concave base (903), the second concave base (903) is fixed at the top of the rear arm (7), the second steering engine (9) is movably hinged on the second concave base (903) through a second hinge shaft, one end of the second screw rod (901) is fixed with an output shaft of a second steering engine (9), and the other end of the second lead screw (901) movably penetrates one side of the front arm (11) and extends outwards, the second lead screw nut (902) is threadedly coupled to a circumferential surface of the second lead screw (901), and the outer surface of the second lead screw nut (902) is fixed with the inner surface of the penetration part of the front arm (11).
5. The machine learning-based identification, positioning, load-bearing, non-destructive gripping robot of claim 4, it is characterized in that the third driving component comprises a third steering engine (14), a third screw rod (141), a third screw rod nut (142) and a third concave base (143), the third concave base (143) is fixed on the top of the forearm (11), the third steering engine (14) is movably hinged on the third concave base (143) through a third hinge shaft, one end of the third screw rod (141) is fixed with an output shaft of the third steering engine (14), and the other end of the third screw rod (141) movably penetrates through one side of the fixed claw (15) and extends outwards, the third lead screw nut (142) is screw-coupled to a circumferential surface of the third lead screw (141), and the outer surface of the third screw nut (142) is fixed with the inner surface of the penetrating part of the fixed claw (15).
6. The machine learning based identification, positioning, load-bearing and nondestructive grabbing mechanical arm according to claim 5 is characterized in that the three-dimensional capturing mechanism is composed of a top camera (16) and a bottom camera (19), the top camera (16) is fixed on one side end of the front arm (11) close to the fixed claw (15), and the bottom camera (19) is fixed on the left end of the trolley body (1).
7. The mechanical arm for recognizing, positioning, bearing and lossless grabbing based on machine learning according to claim 6, characterized in that a motor groove (21) is formed in the trolley main body (1), a stepping motor (23) is fixed to the bottom wall of the motor groove (21), and an output shaft of the stepping motor (23) movably penetrates through the top of the trolley main body (1) and is fixed to the bottom end of the disc (5).
8. The machine learning identification, positioning, bearing and lossless grabbing mechanical arm based on the claim 7 is characterized by further comprising a power source (4), wherein the power source (4) is fixed on the right side of the top of the trolley body (1), wheels (2) are fixedly mounted at four corners of the bottom of the trolley body (1) through second screws, and the power source (4) is used for providing power for the device.
9. The mechanical arm for recognizing, positioning, bearing and nondestructive grabbing based on machine learning as claimed in claim 8 is characterized in that an annular groove is formed in the top of the trolley main body (1), an annular block (22) matched with the annular groove is fixed to the bottom of the disc (5), and the annular block (22) is slidably connected into the annular groove.
10. The mechanical arm for recognizing, positioning, bearing and nondestructive grabbing based on machine learning as claimed in claim 9 is characterized in that a front shovel (20) and a chassis (3) are respectively fixed at the left end and the right end of the trolley main body (1).
CN202120814876.5U 2021-04-21 2021-04-21 Mechanical arm capable of recognizing, positioning, bearing and grabbing without damage based on machine learning Active CN216372209U (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202120814876.5U CN216372209U (en) 2021-04-21 2021-04-21 Mechanical arm capable of recognizing, positioning, bearing and grabbing without damage based on machine learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202120814876.5U CN216372209U (en) 2021-04-21 2021-04-21 Mechanical arm capable of recognizing, positioning, bearing and grabbing without damage based on machine learning

Publications (1)

Publication Number Publication Date
CN216372209U true CN216372209U (en) 2022-04-26

Family

ID=81215655

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202120814876.5U Active CN216372209U (en) 2021-04-21 2021-04-21 Mechanical arm capable of recognizing, positioning, bearing and grabbing without damage based on machine learning

Country Status (1)

Country Link
CN (1) CN216372209U (en)

Similar Documents

Publication Publication Date Title
CN1846951A (en) Control device and method for intelligent mobile robot capable of picking up article automatically
CN204546103U (en) A kind of Digit Control Machine Tool charging and discharging mechanism
CN216939325U (en) Intelligent screw mounting equipment of industrial distribution box
CN216372209U (en) Mechanical arm capable of recognizing, positioning, bearing and grabbing without damage based on machine learning
CN110668164A (en) Material transfer device
CN113146653A (en) Mechanical arm capable of recognizing, positioning, bearing and grabbing without damage based on machine learning
CN2810918Y (en) Intelligent mobile robot controller capable of collecting articles automatically
CN109166444B (en) Multi-functional desktop type robot practical training workstation
CN207873399U (en) Laser processing detent mechanism and laser-processing system
CN107253144B (en) Automatic manipulator of four-station down-swinging lens polishing machine
CN213796545U (en) Clamping jaw with vision and force feedback control function
CN212331033U (en) Industrial robot coordinate system calibration module
CN210939265U (en) High-efficient production line of carrying of bent axle correct grinding manipulator
CN210616515U (en) Six-degree-of-freedom autonomous sorting mechanical arm
CN209256923U (en) A kind of teaching machine device by visual programming
CN112372657A (en) Clamping jaw with vision and force feedback control function
CN214722793U (en) Contact type material loading position three-dimensional detection device
CN216988366U (en) Dispensing and positioning device for motor bottom shell
CN211145885U (en) Edge shooting device for large-plane workpiece
CN204414126U (en) A kind of robotic gripping apparatus
CN220313373U (en) Clamp for robot
CN218137654U (en) Automatic looping device for plastic ring with notch
CN114426923B (en) Environmental virus sampling robot and method
CN212964643U (en) Three-body machine for appearance detection
CN215511060U (en) Intelligent sorting device for warehouse

Legal Events

Date Code Title Description
GR01 Patent grant
GR01 Patent grant