[go: up one dir, main page]

CN106182054B - Finger tip vision crest line identifies adaptive robot arm device - Google Patents

Finger tip vision crest line identifies adaptive robot arm device Download PDF

Info

Publication number
CN106182054B
CN106182054B CN201610640748.7A CN201610640748A CN106182054B CN 106182054 B CN106182054 B CN 106182054B CN 201610640748 A CN201610640748 A CN 201610640748A CN 106182054 B CN106182054 B CN 106182054B
Authority
CN
China
Prior art keywords
finger
driving wheel
joint shaft
axis
image processing
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.)
Expired - Fee Related
Application number
CN201610640748.7A
Other languages
Chinese (zh)
Other versions
CN106182054A (en
Inventor
曾宝莹
张文增
蔡基锋
梁伟东
杨沛
袁晨峰
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.)
Guangzhou Light Industry Vocational School
Original Assignee
Guangzhou Light Industry Vocational School
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 Guangzhou Light Industry Vocational School filed Critical Guangzhou Light Industry Vocational School
Priority to CN201610640748.7A priority Critical patent/CN106182054B/en
Publication of CN106182054A publication Critical patent/CN106182054A/en
Application granted granted Critical
Publication of CN106182054B publication Critical patent/CN106182054B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B25HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25JMANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J15/00Gripping heads and other end effectors
    • B25J15/02Gripping heads and other end effectors servo-actuated
    • B25J15/0206Gripping heads and other end effectors servo-actuated comprising articulated grippers
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B25HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25JMANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J15/00Gripping heads and other end effectors
    • B25J15/08Gripping heads and other end effectors having finger members
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B25HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25JMANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00Programme-controlled manipulators
    • B25J9/16Programme controls
    • B25J9/1694Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
    • B25J9/1697Vision controlled systems

Landscapes

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

Abstract

Finger tip vision crest line identifies adaptive robot arm device, belong to robot vision technique field, including pedestal, three motors, transmission mechanism, the first joint shaft, palm, two parallel holding fingers, two video cameras, image processing module and controller etc..The arrangement achieves parallel clamping functions robot crawl orientation self-adjusting and be suitable for situations such as object is not placed in the middle;The device has parallel clamping grasp mode, is treated by vision-based detection and grabs object progress crest line identification, according to the crawl orientation of the result adjust automatically palm of crest line identification and finger;And according to whether contact the visual feedback of object to be grabbed, the movement of different fingers is automatically controlled, to meet the good crawl of object not placed in the middle.

Description

Finger tip vision crest line identifies adaptive robot arm device
Technical field
The invention belongs to robot vision technique field, in particular to a kind of finger tip vision crest line identifies adaptive machine The structure of hand apparatus designs.
Background technique
Vision has been used widely as the important means of human-computer interaction, becomes current research hotspot.But by It contains much information in vision technique, the reasons such as real time handling requirement is high, Visual Feature Retrieval Process and identification difficulty, causes vision in machine There are many more untapped spaces for people's application aspect.
Robot is often required to adjust posture for object in crawl, to be conducive to stablize crawl.Exist on object Many corner angle and crest line are not appropriate for grabbing, i.e., when finger contacts corner angle or crest line, it is difficult to stablize and apply grasping force and cause Crawl failure.Traditional robot does not have the ability to corner angle or crest line automatic identification, it is difficult to make suitable adjustment.
When robot grabs object, object placement position is often unknown in advance, and there are rough crawl ranges, but do not have There is accurate placement position, also It is not necessary to require operator that the object that last process is completed is placed in reasonable position, What traditional robot often required that object is placed in accurate position, if object deviates larger, crawl is caused to fail.
Other than the specialized robots such as magnetic absorption, air pressure absorption or Electrostatic Absorption, robot mainly has two The multifingered robot hands of a or multiple fingers, including industrial clamper, under-actuated robot hand and apery type Dextrous Hand.Industry folder Holder is widely used in various manufacturing fields, is presently the most mature robot, and generally all there are two fingers for tool, right Claim arrangement, two fingers move in parallel when crawl, and referred to as clamping grasp mode, the robot are known as parallel clamping machine in parallel Manpower.Traditional robot moved in parallel is only a component, does not have the energy being well perceived to environment and object Power, partially the robot with sensing capability is mainly realized using tactile, and detects each pass using multiple sensors The position of section, to reach the stability contorting and control precision of the closed loop feedback of each joint position of finger or speed.
Visual pattern is a kind of sensing media that information content is very big, and feature angle point, straight line or song are quickly extracted from image The technology of line has been developed that, is aided with the mode of color or priori knowledge, and robot can be helped to improve in crawl work Intelligence in work.In order to preferably grab object, traditional object recognition technique needs to carry out object at complicated image Reason, including vision invariants image processing algorithm (SIFT etc.), feature angular-point detection method (Harris etc.), marginal point extraction side Method (Sobel, Canney, Robert, Prewits etc.), corrodes line detection method (least square fitting, Hough, GPI etc.) Or expansion etc..Complicated algorithm is under different light environments, and often reliability is not high, and success rate is relatively low, it is difficult to be applicable in In wider collection of objects.
Summary of the invention
The purpose of the invention is to overcome the shortcoming of prior art, it is adaptive to provide a kind of finger tip vision crest line identification Answer robot hand device.The device has parallel clamping grasp mode, treats and grabs object progress vision-based detection, according to vision-based detection As a result adjust automatically grabs orientation, and can satisfy the good parallel crawl of object not placed in the middle.
Technical scheme is as follows:
A kind of finger tip vision crest line that the present invention designs identifies adaptive robot arm device, including pedestal, first motor, First transmission mechanism, the first joint shaft, palm, the first finger and second finger;The first motor is affixed on the base, described The output shaft of first motor is connected with the input terminal of the first transmission mechanism, the output end of first transmission mechanism and the first joint Axis is connected, and first joint shaft is set in pedestal, and the palm is fixed on the first joint shaft;The palm is respectively with One finger, second finger are connected;First finger is arranged symmetrically with second finger, and symmetry axis is the center of the first joint shaft Line;First finger, second finger are respectively provided at least one translation joint;When grabbing object, first finger, second Finger is mobile respectively along the first joint shaft vertical direction, and the second finger and the first finger move toward one another;It is characterized in that: The finger tip vision crest line identifies that adaptive robot arm device further includes the first video camera, the second video camera, the first image procossing Module, the second image processing module, controller, the first drive module, the second drive module and third drive module;Described first Finger includes the first finger base, the second motor, the first finger tips segment, the first remote joint shaft and the second transmission mechanism;Institute Stating second finger includes second finger pedestal, third motor, second finger end segment, the second remote joint shaft and third driver Structure;Second motor is fixed in the first finger base, the input of the output shaft and the second transmission mechanism of second motor End is connected, and the output end of second transmission mechanism joint shaft remote with first is connected, and the first remote joint shaft is set in first In finger base, the first finger tips segment is socketed on the first remote joint shaft;First finger base is fixed in hand Palm, first video camera are mounted in the first finger tips segment, if the table that the first finger tips segment is contacted with object Face is Q1, and the camera lens optical axis of the first video camera is perpendicular to Q1;The third motor is fixed on second finger pedestal, the third The output shaft of motor is connected with the input terminal of third transmission mechanism, the output end of third transmission mechanism joint shaft remote with second It is connected, the second remote joint shaft is set on second finger pedestal, and second finger end segment is socketed in the second remote pass On nodal axisn;The second finger pedestal is fixed on palm, and second video camera is mounted in the segment of second finger end, if The surface that second finger end segment is contacted with object is Q2, and the camera lens optical axis of the second video camera is perpendicular to Q2;The controller Be connected respectively with the first image processing module, the second image processing module, the controller respectively with the first drive module, second Drive module is connected with third drive module;The signal exit of first video camera and the signal of the first image processing module Input terminal connection, the signal exit of second video camera are connect with the signal input part of the second image processing module;It is described First video camera acquires the side image of object to be grabbed, and second video camera acquires the other side image of object to be grabbed;It is described Controller executes grasping means after receiving crawl signal;The first image processing module runs the first image processing program, Second image processing module runs the second image processing program;
The first image processing routine includes that sequence executes following steps:
a1:Shooting obtains image I11, carries out Edge extraction to I11, obtains the result images I12 containing marginal point;
b1:For I12, crest line detection is carried out, the position and direction of object crest line K1 to be grabbed on the image is obtained, then carries out In next step;If not finding crest line K1 in I12, flag bit P1=0 is set, executes d1 step;
c1:When in I12 crest line K1 pass through it is preset grab region H1, set flag bit P1=1;Otherwise, flag bit is set P1=0;
d1:Calculate I11 average gray value T1, when T1 be lower than preset threshold T, then set flag bit S1=1, otherwise set Flag bit S1=0, the first image processing program terminate;
Second image processing program includes that sequence executes following steps:
a2:Shooting obtains image I21, carries out Edge extraction to I21, obtains the result images I22 containing marginal point;
b2:For I22, crest line detection is carried out, the position and direction of object crest line K2 to be grabbed on the image is obtained, then carries out In next step;If not finding crest line K2 in I22, flag bit P2=0 is set, executes d2 step;
c2:When in I22 crest line K2 pass through it is preset grab region H2, set flag bit P2=1;Otherwise, flag bit is set P2=0;
d2:Calculate I21 average gray value T2, when T2 be lower than preset threshold T, then set flag bit S2=1, otherwise set Flag bit S2=0, the second image processing program terminate;
The grasping means includes that sequence executes following steps:
a3:The first image processing program and the second image processing program are executed, P1, P2, S1 and S2 are obtained;
b3:If P1=0 and P2=0, step d3 is executed, is otherwise performed the next step;
c3:It issues order-driven first motor and rotates low-angle, return step a3;
d3:Drive first motor stalling, the second motor of driving, the rotation of third motor;
e3:If S1=1 is performed the next step, no to then follow the steps g3;
f3:Issue the stalling of the second motor of order-driven;
g3:If S2=1 is performed the next step, no to then follow the steps i3;
h3:Issue the stalling of order-driven third motor;
i3:If S1=1, S2=1, step k3 is executed, is otherwise performed the next step;
j3:Return step a3;
k3:Crawl terminates.
Finger tip vision crest line of the present invention identifies adaptive robot arm device, it is characterised in that:Described second passes Motivation structure and third transmission mechanism are the flat clamp mechanism of the wheeled straight line of bar;The flat clamp mechanism of the wheeled straight line of bar includes the first company Bar, second connecting rod, third connecting rod, first axle, the second axis, third axis, the 4th axis, the first driving wheel, the first flexible drive parts, Two driving wheels, third driving wheel, the second flexible drive parts, the 4th driving wheel;The first axle, the second axis, third axis, the 4th axis Center line joint shaft remote with first centerline parallel;In the second transmission mechanism, the first remote joint shaft is set in In three-link;In third transmission mechanism, the second remote joint shaft is set in third connecting rod;The remote joint shaft is set in In third connecting rod;The third connecting rod is socketed on the 4th axis;The output shaft of second motor is connected with first axle, and described One axle sleeve is located in palm;The first connecting rod is fixed in first axle;Second axle sleeve is located on first connecting rod, and described One end of three-link is socketed on the second axis;The third axle sleeve is located in palm, and one end of the second connecting rod is socketed in On three axis, the other end of second connecting rod is socketed on the 4th axis;4th axle sleeve is located at the middle part of third connecting rod;If first axle Center be point A, the center of the second axis is point B, and the center of the 4th axis is point C, in the second transmission mechanism, the first remote joint shaft Center be point D, in third transmission mechanism, the center of the second remote joint shaft is point D, and the center of third axis is point E, line segment BC Length, the length three of the length of line segment CD and line segment CE it is equal, 2 times of length of the length equal to line segment AB of line segment AE, The length of line segment CE is 2.5 times of the length of line segment AB;First driving wheel is socketed on third axis, first driving wheel It is fixed on palm, first flexible drive parts are separately connected the first driving wheel, the second driving wheel, first Flexible Transmission Part be in " O " font, first flexible drive parts, the first driving wheel, the second driving wheel three constitute drive connection, described second Driving wheel is socketed on the 4th axis;The third driving wheel is socketed on the 4th axis, second driving wheel and third driving wheel Affixed, second flexible drive parts are separately connected third driving wheel, the 4th driving wheel, and second flexible drive parts are in " O " Font, second flexible drive parts, third driving wheel, the 4th driving wheel three constitute drive connection, in the second transmission mechanism In, the 4th driving wheel is fixed on the first remote joint shaft, and in third transmission mechanism, the 4th driving wheel is fixed in On two remote joint shafts.
Finger tip vision crest line of the present invention identifies adaptive robot arm device, it is characterised in that:Described first is soft Property driving member use transmission belt, chain or rope, first driving wheel use belt wheel, sprocket wheel or rope sheave, second driving wheel Using belt wheel, sprocket wheel or rope sheave, first flexible drive parts, the first driving wheel, the second driving wheel three constitute belt wheel transmission Relationship, sprocket wheel drive connection or rope sheave drive connection.
Finger tip vision crest line of the present invention identifies adaptive robot arm device, it is characterised in that:Described second is soft Property driving member use transmission belt, chain or rope, the third driving wheel use belt wheel, sprocket wheel or rope sheave, the 4th driving wheel Using belt wheel, sprocket wheel or rope sheave, second flexible drive parts, third driving wheel, the 4th driving wheel three constitute belt wheel transmission Relationship, sprocket wheel drive connection or rope sheave drive connection.
Compared with prior art, the present invention having the following advantages that and high-lighting effect:
Apparatus of the present invention utilize three motors, two parallel holding fingers, two video cameras, image processing module and control The comprehensive parallel clamping function for realizing robot finger and grabbing orientation self-adjusting with being suitable for situations such as object is not placed in the middle such as device; The device has parallel clamping grasp mode, is treated by vision-based detection and grabs object progress crest line identification, according to crest line identification As a result the crawl orientation of adjust automatically palm and finger;And according to whether the visual feedback contacted, automatically controls different fingers Movement, to meet the good crawl of object not placed in the middle.
Detailed description of the invention
Fig. 1 is a kind of solid of the embodiment for the finger tip vision crest line identification adaptive robot arm device that the present invention designs Outside drawing.
Fig. 2 is the front view of embodiment illustrated in fig. 1.
Fig. 3 is the front view (being not drawn into part) of embodiment illustrated in fig. 1.
Fig. 4 is the stereo appearance figure (being not drawn into part) of embodiment illustrated in fig. 1.
Fig. 5 is the side view (being not drawn into part) of embodiment illustrated in fig. 1.
Fig. 6 is the explosive view of embodiment illustrated in fig. 1.
Fig. 7 is the single finger side appearance (being not drawn into part) of embodiment illustrated in fig. 1, shows point A, B, C, D With the position of E.
Fig. 8 is multiple link mechanism schematic diagrams of AB, BC, CD, CE shown in fig. 6 and base linkage AE, is shown actively The motion track of pivot link AB time point D, have in the track one section of straight path be exactly the present embodiment the second segment straight line it is flat The motion track of row reception step.
Fig. 9 is that embodiment illustrated in fig. 1 shows that robot opens up into the signal of maximum and closed configuration (double dot dash line) Figure.
Figure 10 is the electrical connection diagram of embodiment illustrated in fig. 1.
Figure 11 is the flow chart of the first image processing program of embodiment illustrated in fig. 1.
Figure 12 is the flow chart of the second image processing program of embodiment illustrated in fig. 1.
Figure 13 is the grasping means flow chart of embodiment illustrated in fig. 1.
Figure 14 to Figure 17 is the action process figure of the palm of embodiment illustrated in fig. 1.
Figure 18 to Figure 20 is three kinds of grasp modes of the crawl object of embodiment illustrated in fig. 1:Between two parties, to the left, to the right.
Figure 21 to Figure 23 is that the identification crest line of embodiment illustrated in fig. 1 correctly grabs the action process figure of object.
Figure 24 be embodiment illustrated in fig. 1 object can not crawl position the first video camera or the clapped figure of the second video camera As schematic diagram.
Figure 25 be embodiment illustrated in fig. 1 object can crawl position the first video camera or the second video camera shot image Schematic diagram.
In Fig. 1 into Figure 25:
1- pedestal, 11- first motor, the first transmission mechanism of 12-, the first joint shaft of 13-,
14- palm, the first finger of 2-, the first finger base of 21-, 22- the first finger tips segment,
The remote joint shaft of 23- first, the second motor of 24-, the second transmission mechanism of 25-, 211- first axle,
The second axis of 212-, 213- third axis, the 4th axis of 214-, 221- first connecting rod,
222- second connecting rod, 223- third connecting rod, the first driving wheel of 231-, the second driving wheel of 232-,
233- third driving wheel, the 4th driving wheel of 234-, the first flexible drive parts of 241-, the second flexible drive parts of 242-
3- second finger, 31- second finger pedestal, 32- second finger end segment, the remote joint shaft of 33- second,
34- third motor, the first video camera of 41-, the second video camera of 42-,
The first image processing module of 51-, the second image processing module of 52-, 6- controller, the first drive module of 71-,
The second drive module of 72-, 73- third drive module, 8- object grab region on H- image,
The crest line of K- object, J- viewing area.
Specific embodiment
The content of specific structure of the invention, working principle is described in further detail with reference to the accompanying drawings and embodiments.
A kind of embodiment for the finger tip vision crest line identification adaptive robot arm device that the present invention designs, such as Fig. 1 to Fig. 2 It is shown, including pedestal 1, first motor 11, the first transmission mechanism 12, the first joint shaft 13, palm 14, the first finger 2 and second Finger 3;The first motor 11 is fixed on pedestal 1, and the output shaft of the first motor 11 is defeated with the first transmission mechanism 12 Enter end to be connected, the output end of first transmission mechanism 12 is connected with the first joint shaft 13, and first joint shaft 13 is set in In pedestal 1, the palm 14 is fixed on the first joint shaft 13;The palm 14 respectively with the first finger 2,3 phase of second finger Even;First finger 2 is arranged symmetrically with second finger 3, and symmetry axis is the center line of the first joint shaft 13;It is described first-hand Refer to that 2, second finger 3 is respectively provided at least one translation joint;When grabbing object 8, first finger 2, second finger 3 are distinguished It is moved along 13 vertical direction of the first joint shaft, the second finger 3 and the first finger 2 move toward one another;The finger tip vision crest line Identify that adaptive robot arm device further includes the first video camera 41, the second video camera 42, the first image processing module 51, second Image processing module 52, controller 6, the first drive module 71, the second drive module 72 and third drive module 73;Described first Finger 2 includes the first finger base 21, the second motor 24, the first finger tips segment 22, the first remote joint shaft 23 and the second biography Motivation structure 25;The second finger 3 is remote including second finger pedestal 31, third motor 34, second finger end segment 32, second Joint shaft 33 and third transmission mechanism;Second motor 24 is fixed in the first finger base 21, second motor 24 Output shaft is connected with the input terminal of the second transmission mechanism 25, the output end of second transmission mechanism 25 joint shaft 23 remote with first It is connected, the first remote joint shaft 23 is set in the first finger base 21, and the first finger tips segment 22 is socketed in the On one remote joint shaft 23;First finger base 21 is fixed on palm 14, and first video camera 41 is mounted on first-hand Refer in end segment 22, if the surface that the first finger tips segment 22 is contacted with object 8 is Q1, the camera lens light of the first video camera 41 Axis is perpendicular to Q1;The third motor 34 is fixed on second finger pedestal 31, the output shaft and third of the third motor 34 The input terminal of transmission mechanism is connected, and the output end of third transmission mechanism joint shaft 33 remote with second is connected, and described second is remote Joint shaft 33 is set on second finger pedestal 31, and second finger end segment 32 is socketed on the second remote joint shaft 33; The second finger pedestal 31 is fixed on palm 14, and second video camera 42 is mounted in second finger end segment 32, If the surface that second finger end segment 32 is contacted with object 8 is Q2, the camera lens optical axis of the second video camera 42 is perpendicular to Q2;It is described Controller 6 is connected with the first image processing module 51, the second image processing module 52 respectively, as shown in Figure 10, the controller 6 It is connected respectively with the first drive module 71, the second drive module 72 and third drive module 73;The letter of first video camera 41 Number exit is connect with the signal input part of the first image processing module 51, the signal exit of second video camera 42 and The signal input part of two image processing modules 52 connects;First video camera 41 acquires the side image of object 8 to be grabbed, described Second video camera 42 acquires the other side image of object 8 to be grabbed;The controller 6 executes crawl side after receiving crawl signal Method;The first image processing module 51 runs the first image processing program, the operation of the second image processing module 52 second Image processing program;
The first image processing routine includes that sequence executes following steps:
(a1) shooting obtains image I11, carries out Edge extraction to I11, obtains the result images containing marginal point I12;
(b1) be directed to I12, carry out crest line detection, obtain the position and direction of 8 crest line K1 of object to be grabbed on the image, then into Row is in next step;If not finding crest line K1 in I12, flag bit P1=0 is set, executes (d1) step;
(c1) when in I12 crest line K1 pass through it is preset grab region H1, set flag bit P1=1;Otherwise, flag bit is set P1=0;
(d1) calculate I11 average gray value T1, when T1 be lower than preset threshold T, then set flag bit S1=1, otherwise set Determine flag bit S1=0, the first image processing program terminates;
Second image processing program includes that sequence executes following steps:
(a2) shooting obtains image I21, carries out Edge extraction to I21, obtains the result images containing marginal point I22;
(b2) be directed to I22, carry out crest line detection, obtain the position and direction of 8 crest line K2 of object to be grabbed on the image, then into Row is in next step;If not finding crest line K2 in I22, flag bit P2=0 is set, executes (d2) step;
(c2) when in I22 crest line K2 pass through it is preset grab region H2, set flag bit P2=1;Otherwise, flag bit is set P2=0;
(d2) calculate I21 average gray value T2, when T2 be lower than preset threshold T, then set flag bit S2=1, otherwise set Determine flag bit S2=0, the second image processing program terminates;
The grasping means includes that sequence executes following steps:
(a3) the first image processing program and the second image processing program are executed, P1, P2, S1 and S2 are obtained;
(b3) it if P1=0 and P2=0, executes step (d3), otherwise performs the next step;
(c3) it issues order-driven first motor 11 and rotates low-angle, return step (a3);
(d3) driving first motor 11 stalls, and the second motor 24 of driving, third motor 34 rotate;
(e3) it if S1=1, performs the next step, it is no to then follow the steps (g3);
(f3) the second motor of order-driven 24 is issued to stall;
(g3) it if S2=1, performs the next step, it is no to then follow the steps (i3);
(h3) order-driven third motor 34 is issued to stall;
(i3) it if S1=1, S2=1, executes step (k3), otherwise performs the next step;
(j3) return step (a3);
(k3) crawl terminates.
In the present embodiment, second transmission mechanism 25 and third transmission mechanism are the flat clamp mechanism of the wheeled straight line of bar;Institute Stating the flat clamp mechanism of the wheeled straight line of bar includes first connecting rod 221, second connecting rod 222, third connecting rod 223, first axle 211, the second axis 212, third axis 213, the 4th axis 214, the first driving wheel 231, the first flexible drive parts 241, the second driving wheel 232, third pass Driving wheel 233, the second flexible drive parts 242, the 4th driving wheel 234;The first axle 211, the second axis 212, third axis 213, The centerline parallel of the center line of four axis 214 joint shaft 23 remote with first;In the second transmission mechanism, the first remote joint shaft It is set in third connecting rod 223;In third transmission mechanism, the second remote joint shaft is set in third connecting rod 223;It is described Third connecting rod 223 is socketed on the 4th axis 214;The output shaft of second motor 24 is connected with first axle 211, the first axle 211 are set in palm 14;The first connecting rod 221 is fixed in first axle 211;Second axis 212 is set in the first company On bar 221, one end of the third connecting rod 223 is socketed on the second axis 212;The third axis 213 is set in palm 14, institute The one end for stating second connecting rod 222 is socketed on third axis 213, and the other end of second connecting rod 222 is socketed on the 4th axis 214;Institute State the middle part that the 4th axis 214 is set in third connecting rod 223;If the center of first axle 211 is point A, the center of the second axis 212 is point The center of B, the 4th axis 214 are point C, and in the second transmission mechanism, the center of the first remote joint shaft is point D, in third driver In structure, the center of the second remote joint shaft is point D, and the center of third axis 213 is point E, as shown in Figure 7 and Figure 8, the length of line segment BC The length three of degree, the length of line segment CD and line segment CE is equal, and 2 times of length of the length equal to line segment AB of line segment AE, line segment The length of CE is 2.5 times of the length of line segment AB;First driving wheel 231 is socketed on third axis 213, first transmission Wheel 231 is fixed on palm 14, and first flexible drive parts 241 are separately connected the first driving wheel 231, the second driving wheel 232, First flexible drive parts 241 are in " O " font, first flexible drive parts 241, the first driving wheel 231, the second driving wheel 232 threes constitute drive connection, and second driving wheel 232 is socketed on the 4th axis 214;The third driving wheel 233 is socketed On the 4th axis 214, second driving wheel 232 and third driving wheel 233 are affixed, and second flexible drive parts 242 are distinguished Third driving wheel 233, the 4th driving wheel 234 are connected, second flexible drive parts 242 are in " O " font, the described second flexible biography Moving part 242, third driving wheel 233,234 three of the 4th driving wheel constitute drive connection;In the second transmission mechanism, the described 4th Driving wheel 234 is fixed on the first remote joint shaft;In third transmission mechanism, it is remote that the 4th driving wheel 234 is fixed in second On joint shaft;As shown in Figures 3 to 8.Fig. 9 is the original state that the present embodiment clamps in parallel and final state (double dot dash line).
Finger tip vision crest line of the present invention identifies adaptive robot arm device, it is characterised in that:Described first is soft Property driving member 241 using transmission belt, chain or rope, first driving wheel 231 is using belt wheel, sprocket wheel or rope sheave, described second Driving wheel 232 is using belt wheel, sprocket wheel or rope sheave, first flexible drive parts 241, the first driving wheel 231, the second driving wheel 232 threes constitute belt wheel transmission relationship, sprocket wheel drive connection or rope sheave drive connection.In the present embodiment, the described first flexible biography Moving part 241 uses transmission belt, and first driving wheel 231 uses belt wheel, and second driving wheel 232 uses belt wheel, and described the One flexible drive parts 241, the first driving wheel 231,232 three of the second driving wheel constitute belt wheel transmission relationship.
Finger tip vision crest line of the present invention identifies adaptive robot arm device, it is characterised in that:Described second is soft Property driving member 242 using transmission belt, chain or rope, the third driving wheel 233 is using belt wheel, sprocket wheel or rope sheave, the described 4th Driving wheel 234 is using belt wheel, sprocket wheel or rope sheave, second flexible drive parts 242, third driving wheel 233, the 4th driving wheel 234 threes constitute belt wheel transmission relationship, sprocket wheel drive connection or rope sheave drive connection.In the present embodiment, the described second flexible biography Moving part 242 uses transmission belt, and the third driving wheel 233 uses belt wheel, and the 4th driving wheel 234 uses belt wheel, and described the Two flexible drive parts 242, third driving wheel 233,234 three of the 4th driving wheel constitute belt wheel transmission relationship.
Action process when the present embodiment the first joint shaft of rotation is as shown in Figure 14 to Figure 17.
The situation grabbed when object is placed on to the left, to the right or middle is as shown in Figure 18 to Figure 20.
When grasping body, crest line it is observed can capture area H when situation it is as shown in figure 21.
When grasping body, reach the orientation that can be grabbed after having rotated the first joint shaft according to crest line image recognition situation When it is as shown in figure 22, after crawl as shown in figure 23.
The working principle of the present embodiment, is described below in conjunction with attached drawing:
Object 8 to be grabbed is placed on crawl workbench, controller 6 executes the program of grasping means, such as Figure 11 to Figure 13 Shown, the first video camera 41 claps figure, feeds back to the first image processing module 51, executes the first image processing program, obtains first 2 end segment of finger corresponds to the gripping surface of object 8 with the presence or absence of crest line, and crest line and crest line, which are in, if it exists can grab region H1, then It drives first motor 11 to rotate a low-angle, then shoots image;Second video camera 42 claps figure and claps figure processing with the first video camera 41 Program is similar.Until image that the first video camera 41 and the second video camera 42 are fed back all does not grab region there are ribs respective Line then enters next link;
It respectively drives the second motor 24 and third motor 34 rotates;
First video camera 41 claps figure, feeds back to the first image processing module 51, executes the first image processing program, and detection should The average gray value T1 of image stops the second motor 24 if T1 is lower than preset threshold T;
Second video camera 42 claps figure, feeds back to the second image processing module 52, executes the second image processing program, and detection should The average gray value T2 of image stops third motor 34 if T2 is lower than preset threshold T;
If T1 is lower than preset threshold T and T2 is lower than preset threshold T, crawl terminates.
When controller 6 receives release signal, release procedure is executed, release procedure is to respectively drive the second motor 24, the Three motors 34 are inverted to initial position.
Observed region is J, as shown in Figure 1, the image photographed is as shown in Figure 24,25, wherein observe rib on image Line can capture area when it is as shown in figure 24, when crest line not can capture area when it is as shown in figure 25.
The edge extracting method uses Sobel method, is the well-known technique of robot visual field, repeats no more.
The crest line detection method uses line detection method, that is, detects in the marginal point result images that edge extracting obtains A most straight line of passing point can use well known line detection method, as Hough method or Gray Projection integrate (GPI) method, bibliography are:
The round child window multistep GPI method of the image weld seam detection such as [1] Zheng Zhewei, Zhang Wenzeng welds journal .2007, 28(8):77-80.
The gray projecting integral method Tsinghua University journal .2005,45 (11) of the straight-line detection such as [2] Zhang Wenzeng, Chen Qiang: 1446-1449.
For apparatus of the present invention only for the grasping body of uniform background environment, the object grabbed is there are crest line or is not present Crest line is applicable in.On image it is described can capture area H be to be set in advance according to parameters such as the lens focus of video camera, crawl ranges Fixed fixed area.Described image average gray value T is also preset fixed value.
Apparatus of the present invention utilize three motors, two parallel holding fingers, two video cameras, image processing module and control The comprehensive parallel clamping function for realizing robot finger and grabbing orientation self-adjusting with being suitable for situations such as object is not placed in the middle such as device; The device has parallel clamping grasp mode, is treated by vision-based detection and grabs object progress crest line identification, according to crest line identification As a result the crawl orientation of adjust automatically palm and finger;And according to whether the visual feedback contacted, automatically controls different fingers Movement, to meet the good crawl of object not placed in the middle.

Claims (4)

1. a kind of finger tip vision crest line identifies adaptive robot arm device, including pedestal, first motor, the first transmission mechanism, First joint shaft, palm, the first finger and second finger;The first motor is affixed on the base, the first motor it is defeated Shaft is connected with the input terminal of the first transmission mechanism, and the output end of first transmission mechanism is connected with the first joint shaft, described First joint shaft is set in pedestal, and the palm is fixed on the first joint shaft;The palm respectively with the first finger, second Finger is connected;First finger is arranged symmetrically with second finger, and symmetry axis is the center line of the first joint shaft;Described first Finger, second finger are respectively provided at least one translation joint;When grabbing object, first finger, second finger edge respectively The first joint shaft vertical direction it is mobile, the second finger and the first finger move toward one another;It is characterized in that:The finger tip vision Crest line identifies that adaptive robot arm device further includes the first video camera, the second video camera, the first image processing module, the second figure As processing module, controller, the first drive module, the second drive module and third drive module;First finger includes the One finger base, the second motor, the first finger tips segment, the first remote joint shaft and the second transmission mechanism;The second finger Including second finger pedestal, third motor, second finger end segment, the second remote joint shaft and third transmission mechanism;Described Two motors are fixed in the first finger base, and the output shaft of second motor is connected with the input terminal of the second transmission mechanism, institute The output end joint shaft remote with first for stating the second transmission mechanism is connected, and the first remote joint shaft is set in the first finger base On, the first finger tips segment is socketed on the first remote joint shaft;First finger base is fixed on palm, described First video camera is mounted in the first finger tips segment, if the surface that the first finger tips segment is contacted with object is Q1, the The camera lens optical axis of one video camera is perpendicular to Q1;The third motor is fixed on second finger pedestal, the third motor it is defeated Shaft is connected with the input terminal of third transmission mechanism, and the output end of third transmission mechanism joint shaft remote with second is connected, institute It states the second remote joint shaft to be set on second finger pedestal, second finger end segment is socketed on the second remote joint shaft; The second finger pedestal is fixed on palm, and second video camera is mounted in the segment of second finger end, if second-hand Refer to that the surface that end segment is contacted with object is Q2, the camera lens optical axis of the second video camera is perpendicular to Q2;The controller respectively with First image processing module, the second image processing module are connected;The controller drives mould with the first drive module, second respectively Block is connected with third drive module;The signal exit of first video camera and the signal input part of the first image processing module Connection, the signal exit of second video camera are connect with the signal input part of the second image processing module;Described first takes the photograph Camera acquires the side image of object to be grabbed, and second video camera acquires the other side image of object to be grabbed;The controller Grasping means is executed after receiving crawl signal;The first image processing module runs the first image processing program, and described the Two image processing modules run the second image processing program;
The first image processing routine includes that sequence executes following steps:
a1:Shooting obtains image I11, carries out Edge extraction to I11, obtains the result images I12 containing marginal point;
b1:For I12, crest line detection is carried out, the position and direction of object crest line K1 to be grabbed on the image is obtained, then carries out next Step;If not finding crest line K1 in I12, flag bit P1=0 is set, executes d1 step;
c1:When in I12 crest line K1 pass through it is preset grab region H1, set flag bit P1=1;Otherwise, flag bit P1=is set 0;
d1:Calculate I11 average gray value T1, when T1 be lower than preset threshold T, then set flag bit S1=1, otherwise setting mark Position S1=0, the first image processing program terminate;
Second image processing program includes that sequence executes following steps:
a2:Shooting obtains image I21, carries out Edge extraction to I21, obtains the result images I22 containing marginal point;
b2:For I22, crest line detection is carried out, the position and direction of object crest line K2 to be grabbed on the image is obtained, then carries out next Step;If not finding crest line K2 in I22, flag bit P2=0 is set, executes d2 step;
c2:When in I22 crest line K2 pass through it is preset grab region H2, set flag bit P2=1;Otherwise, flag bit P2=is set 0;
d2:Calculate I21 average gray value T2, when T2 be lower than preset threshold T, then set flag bit S2=1, otherwise setting mark Position S2=0, the second image processing program terminate;
The grasping means includes that sequence executes following steps:
a3:The first image processing program and the second image processing program are executed, P1, P2, S1 and S2 are obtained;
b3:If P1=0 and P2=0, step d3 is executed, is otherwise performed the next step;
c3:It issues order-driven first motor and rotates low-angle, return step a3;
d3:Drive first motor stalling, the second motor of driving, the rotation of third motor;
e3:If S1=1 is performed the next step, no to then follow the steps g3;
f3:Issue the stalling of the second motor of order-driven;
g3:If S2=1 is performed the next step, no to then follow the steps i3;
h3:Issue the stalling of order-driven third motor;
i3:If S1=1, S2=1, step k3 is executed, is otherwise performed the next step;
j3:Return step a3;
k3:Crawl terminates.
2. finger tip vision crest line as described in claim 1 identifies adaptive robot arm device, it is characterised in that:Described second Transmission mechanism and third transmission mechanism are the flat clamp mechanism of the wheeled straight line of bar;The flat clamp mechanism of the wheeled straight line of bar includes the first company Bar, second connecting rod, third connecting rod, first axle, the second axis, third axis, the 4th axis, the first driving wheel, the first flexible drive parts, Two driving wheels, third driving wheel, the second flexible drive parts, the 4th driving wheel;The first axle, the second axis, third axis, the 4th axis Center line joint shaft remote with first centerline parallel;In the second transmission mechanism, the first remote joint shaft is set in In three-link;In third transmission mechanism, the second remote joint shaft is set in third connecting rod;The remote joint shaft is set in In third connecting rod;The third connecting rod is socketed on the 4th axis;The output shaft of second motor is connected with first axle, and described One axle sleeve is located in palm;The first connecting rod is fixed in first axle;Second axle sleeve is located on first connecting rod, and described One end of three-link is socketed on the second axis;The third axle sleeve is located in palm, and one end of the second connecting rod is socketed in On three axis, the other end of second connecting rod is socketed on the 4th axis;4th axle sleeve is located at the middle part of third connecting rod;If first axle Center be point A, the center of the second axis is point B, and the center of the 4th axis is point C, in the second transmission mechanism, the first remote joint shaft Center be point D, in third transmission mechanism, the center of the second remote joint shaft is point D, and the center of third axis is point E, line segment BC Length, the length three of the length of line segment CD and line segment CE it is equal, 2 times of length of the length equal to line segment AB of line segment AE, The length of line segment CE is 2.5 times of the length of line segment AB;First driving wheel is socketed on third axis, first driving wheel It is fixed on palm, first flexible drive parts are separately connected the first driving wheel, the second driving wheel, first Flexible Transmission Part be in " O " font, first flexible drive parts, the first driving wheel, the second driving wheel three constitute drive connection, described second Driving wheel is socketed on the 4th axis;The third driving wheel is socketed on the 4th axis, second driving wheel and third driving wheel Affixed, second flexible drive parts are separately connected third driving wheel, the 4th driving wheel, and second flexible drive parts are in " O " Font, second flexible drive parts, third driving wheel, the 4th driving wheel three constitute drive connection, in the second transmission mechanism In, the 4th driving wheel is fixed on the first remote joint shaft, and in third transmission mechanism, the 4th driving wheel is fixed in On two remote joint shafts.
3. finger tip vision crest line as claimed in claim 2 identifies adaptive robot arm device, it is characterised in that:Described first Flexible drive parts use transmission belt, chain or rope, and first driving wheel uses belt wheel, sprocket wheel or rope sheave, second transmission Wheel uses belt wheel, sprocket wheel or rope sheave, and first flexible drive parts, the first driving wheel, the second driving wheel three constitute belt wheel and pass Dynamic relationship, sprocket wheel drive connection or rope sheave drive connection.
4. finger tip vision crest line as claimed in claim 2 identifies adaptive robot arm device, it is characterised in that:Described second Flexible drive parts use transmission belt, chain or rope, and the third driving wheel uses belt wheel, sprocket wheel or rope sheave, the 4th transmission Wheel uses belt wheel, sprocket wheel or rope sheave, and second flexible drive parts, third driving wheel, the 4th driving wheel three constitute belt wheel and pass Dynamic relationship, sprocket wheel drive connection or rope sheave drive connection.
CN201610640748.7A 2016-08-05 2016-08-05 Finger tip vision crest line identifies adaptive robot arm device Expired - Fee Related CN106182054B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610640748.7A CN106182054B (en) 2016-08-05 2016-08-05 Finger tip vision crest line identifies adaptive robot arm device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610640748.7A CN106182054B (en) 2016-08-05 2016-08-05 Finger tip vision crest line identifies adaptive robot arm device

Publications (2)

Publication Number Publication Date
CN106182054A CN106182054A (en) 2016-12-07
CN106182054B true CN106182054B (en) 2018-11-30

Family

ID=57514424

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610640748.7A Expired - Fee Related CN106182054B (en) 2016-08-05 2016-08-05 Finger tip vision crest line identifies adaptive robot arm device

Country Status (1)

Country Link
CN (1) CN106182054B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106829515B (en) * 2017-03-31 2023-07-25 江南大学 Stacking manipulator adopting connecting rod mechanism to be capable of being stretched and opened and closed
CN108145731A (en) * 2017-11-28 2018-06-12 浙江卓怡纺织有限公司 A kind of feeding device for tubing
CN112757334A (en) * 2020-12-28 2021-05-07 清华大学 Robot gripper and control method thereof
CN113291790B (en) * 2021-05-25 2022-08-30 武汉理工大学 Self-adaptive grabbing mechanism

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102259340A (en) * 2011-07-11 2011-11-30 浙江理工大学 Underactuated end effector
CN103395067A (en) * 2013-07-31 2013-11-20 北京航空航天大学 Self-adaption claw mechanism of spatial on-orbit service robot
CN104972475A (en) * 2015-07-29 2015-10-14 苏州拓德机器人科技有限公司 Under-actuated mechanical hand with self-adaptive shape

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA2856622C (en) * 2011-11-25 2017-01-10 Robotiq Inc. A gripper having a two degree of freedom underactuated mechanical finger for encompassing and pinch grasping

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102259340A (en) * 2011-07-11 2011-11-30 浙江理工大学 Underactuated end effector
CN103395067A (en) * 2013-07-31 2013-11-20 北京航空航天大学 Self-adaption claw mechanism of spatial on-orbit service robot
CN104972475A (en) * 2015-07-29 2015-10-14 苏州拓德机器人科技有限公司 Under-actuated mechanical hand with self-adaptive shape

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
图像焊缝检测的圆形子窗口多步GPI方法;郑哲伟;《焊接学报》;20070831;第28卷(第8期);第78-80页 *
拟人机器人手多指欠驱动机构研究;张文增等;《机械设计与研究》;20071231;第23卷(第6期);第21-23页 *
末端强力抓取的欠驱动拟人机器人手;张文增等;《清华大学学报》;20091231;第49卷(第2期);第195-197页 *
直线检测的灰度投影积分方法;张文增等;《清华大学学报》;20051231;第45卷(第11期);第1447-1450页 *

Also Published As

Publication number Publication date
CN106182054A (en) 2016-12-07

Similar Documents

Publication Publication Date Title
CN106182054B (en) Finger tip vision crest line identifies adaptive robot arm device
CN105598965B (en) The autonomous grasping means of robot drive lacking hand based on stereoscopic vision
US10913151B1 (en) Object hand-over between robot and actor
JP6450960B2 (en) Robot, robot system and teaching method
CN102120307B (en) System and method for grinding industrial robot on basis of visual information
CN106853639A (en) A kind of battery of mobile phone automatic assembly system and its control method
CN108908374A (en) A kind of express sorter device people and control system
CN107598920A (en) A kind of manipulator of view-based access control model control
CN113618709B (en) Multi-mode force control nondestructive grabbing device for intelligent production line
CN106272427A (en) A kind of industrial robot intelligence picking up system
CN207641883U (en) A kind of part stream waterline automatic sorting boxing apparatus of view-based access control model
CN111359915B (en) Material sorting method and system based on machine vision
CN105184019A (en) Robot grabbing method and system
CN108393870B (en) Asymmetric double-arm cooperative robot
CN106956263A (en) Automobile component vision guide handgrip
CN104772286A (en) Kinect based novel sorting system and operation method thereof
CN107649406A (en) A kind of efficient more material picking up system of binocular vision and method
CN104801023A (en) Tennis ball picking system and method of tennis ball picking machine
Chapman et al. A locally-adaptive, parallel-jaw gripper with clamping and rolling capable, soft fingertips for fine manipulation of flexible flat cables
CN113538459A (en) Multi-mode grabbing obstacle avoidance detection optimization method based on drop point area detection
CN114043482A (en) Mechanical arm based on visual identification control
CN106695851A (en) Two-direction perception adaptive robot finger device with closed-ring flexible piece and control method of two-direction perception adaptive robot finger device
KR101385022B1 (en) Lens side cutting tool
CN205121556U (en) Robot grasping system
JP2015150673A (en) Control device, robot, robot system and control method

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20181130