CN108942940B - Teleoperation robot polishing control system based on multi-sensor fusion - Google Patents
Teleoperation robot polishing control system based on multi-sensor fusion Download PDFInfo
- Publication number
- CN108942940B CN108942940B CN201810862389.9A CN201810862389A CN108942940B CN 108942940 B CN108942940 B CN 108942940B CN 201810862389 A CN201810862389 A CN 201810862389A CN 108942940 B CN108942940 B CN 108942940B
- Authority
- CN
- China
- Prior art keywords
- polishing
- mechanical arm
- robot
- force
- controller
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1679—Programme controls characterised by the tasks executed
- B25J9/1689—Teleoperation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
- B25J11/005—Manipulators for mechanical processing tasks
- B25J11/0065—Polishing or grinding
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1679—Programme controls characterised by the tasks executed
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
- Finish Polishing, Edge Sharpening, And Grinding By Specific Grinding Devices (AREA)
- Constituent Portions Of Griding Lathes, Driving, Sensing And Control (AREA)
Abstract
The invention discloses a grinding control system of a teleoperation robot based on multi-sensor fusion, which comprises a robot base, a mechanical arm, a six-dimensional force sensor, a cutter, a motor, an industrial camera and a controller, wherein the six-dimensional force sensor is arranged on the robot base; the controller controls the mobile mechanical arm to reach a working area according to the coordinate and controls the industrial camera to acquire an image of the element to be processed, the image processing extracts the image characteristics and the contour information of the element to be processed, the polishing area is selected, a polishing path is planned according to the polishing area, and a motor and a cutter at the tail end of the mechanical arm are controlled to polish the element to be processed; the six-dimensional force sensor obtains the force and the moment at the tail end of the mechanical arm under different polishing conditions, the controller takes the numerical values of the force and the moment predicted and output by the neural network under the current polishing condition as reference, PI control is carried out on the force and the moment obtained in the polishing process, and PD control is carried out on the motion of the mechanical arm. The invention can realize the polishing of the inner part of the workpiece and the polishing of irregular parts.
Description
Technical Field
The invention relates to a grinding control system of a teleoperation robot based on multi-sensor fusion, and belongs to the technical field of teleoperation robots.
Background
Grinding and polishing are necessary procedures in many industrial production, the traditional grinding and polishing process is mainly performed by manual operation, dust and noise and long-time high-intensity repetitive work can cause physical and mental fatigue of operators, in addition, the manual operation has high requirements on the proficiency of the operators, and a certain processing error rate exists.
The robot replaces people to finish heavy work, which is an important trend of intelligent robot development, and the industrial robot applied to the polishing industry can only polish some basic and regular parts at present, the polishing mode is that a cutter or a grinding wheel is fixed on a workbench, a mechanical arm grabs a workpiece and is close to the cutter or the grinding wheel to polish, the polishing mode can only achieve regular polishing of the outer surface of the workpiece, and the polishing requirements on the inner surface of the workpiece or irregular shapes cannot be achieved generally. In addition, the automatic polishing system of the existing robot can only realize polishing of a fixed flow through a teaching mode, and the robot lacks certain autonomous capacity and is difficult to realize customized polishing requirements.
Based on the technical current situation, the robot automatic polishing work needs to realize shared control of a human and a robot based on multi-sensor fusion, needs to meet the requirement of customized polishing of a customer, and needs to flexibly control the position of a cutter to realize polishing of the inner part of a workpiece and polishing of irregular parts.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a grinding control system of a teleoperation robot based on multi-sensor fusion, which solves the problems that the prior robot can only realize regular grinding of the outer surface of a workpiece and cannot realize the grinding requirement on the inner surface or irregular shape of the workpiece.
The invention specifically adopts the following technical scheme to solve the technical problems:
a teleoperation robot polishing control system based on multi-sensor fusion comprises a robot base, a mechanical arm, a six-dimensional force sensor, a cutter, a motor, an industrial camera and a controller, wherein the mechanical arm is rotatably arranged on the robot base; the motor is fixedly arranged on a force transmission shaft of the six-dimensional force sensor, and an output shaft of the motor is connected with the cutter through a fixing mechanism; the controller controls the mobile mechanical arm to reach a working area according to the coordinate and controls the industrial camera to collect an image of an element to be processed, the controller performs image processing on the collected image of the element to be processed, extracts image characteristics and outline information of the element to be processed, selects a polishing area according to burr conditions in the image characteristics and the outline information and polishing requirements of the appearance, plans a polishing path according to the polishing area and controls a motor and a cutter at the tail end of the mechanical arm to polish the element to be processed; meanwhile, the six-dimensional force sensor acquires the force and the moment at the tail end of the mechanical arm under different polishing conditions and inputs the force and the moment into the neural network in the controller for training so as to construct and obtain a trained neural network, the controller takes the numerical values of the force and the moment predicted and output by the neural network under the current polishing condition as reference, PI control is carried out on the feeding amount of the cutter in the polishing process according to the feedback of the force and the moment at the tail end of the mechanical arm acquired by the six-dimensional force sensor, and PD control is carried out on the motion of the mechanical arm through the acquired position feedback of the mechanical arm.
Further, as a preferred technical solution of the present invention: the controller adopts a machine vision algorithm to extract image characteristics and contour information of the element to be processed.
Further, as a preferred technical solution of the present invention: the controller also includes creating a template for the element to be machined based on the image features and the contour information for the element to be machined.
Further, as a preferred technical solution of the present invention: the controller plans the grinding path in a manual planning or automatic planning mode.
Further, as a preferred technical solution of the present invention: and the mechanical arm is provided with a joint encoder, and the joint encoder is used for acquiring joint angles of all joints of the robot and resolving to obtain the feedback of the tail end position of the mechanical arm.
Further, as a preferred technical solution of the present invention: the controller carries out PI control and PD control to the motion of arm to the feed rate of the in-process cutter of polishing, specifically is:
set at a certain moment in the grinding process the desired displacement of the robot is
And under the current polishing condition, the expected acting force is predicted and output through a neural network
Obtaining the current actual displacement of the mechanical arm as
The difference value between the expected displacement and the actual displacement of the robot is obtained by calculation
And calculating to obtain the current displacement of the robot
Move to the desired displacement
Required excitation electrical signal
As a PD control parameter;
six-dimensional force sensor obtains the actual acting force at the tail end of the mechanical arm under the current polishing condition
Calculating to obtain expected acting force of the robot
And the actual acting force
By a difference of
And calculating to obtain an excitation signal to the robot
As PI control parameters;
from the resulting excitation electrical signal
And an excitation signal
And calculating to obtain a control signal of the robot, and controlling the robot to move under the action of the output control signal.
Further, as a preferred technical solution of the present invention: the control signals obtained by the controller are as follows:
wherein k ispAnd kfGain coefficients of displacement and force control links, respectively, for adjustment
And
the effect of (1).
By adopting the technical scheme, the invention can produce the following technical effects:
the invention provides a grinding control system of a teleoperation robot based on multi-sensor fusion, which can meet the grinding requirements of the interior of a workpiece and irregular workpieces, uses machine vision to guide the robot to identify an object, and performs accurate force position control through a six-dimensional force sensor, thereby having better automatic grinding effect.
Compared with the prior art, the automatic grinding machine has the advantages that sensors such as an industrial camera and a six-dimensional force sensor are used, automatic grinding with fusion of machine vision and the force sensor is achieved, customization of a grinding area can be achieved, a complex teaching process for grinding different elements is not needed, a robot automatically identifies grinding elements, and automatic grinding is achieved according to a planned grinding area; the cutter is arranged at the tail end of the mechanical arm, the movement is flexible, and the grinding of the interior of a workpiece and the grinding of irregular parts can be realized; by adopting the design of multi-sensor fusion, the sharing cooperative control of the robot and the human is realized, and the sharing control of the manual decision and the local automatic control fusion of the operator is realized. The system has good control effect, can realize customized grinding of nonstandard and irregular workpieces, can realize grinding of areas which are difficult to process by the traditional grinding process, and has good application value.
Drawings
Fig. 1 is a schematic structural diagram of a teleoperated robot polishing control system according to the present invention.
Fig. 2 is a schematic diagram of the operation of the teleoperated robot sanding control system of the present invention.
Fig. 3 is a schematic diagram of selecting a polishing area by taking an automobile hub as an example in the invention.
Fig. 4 is a schematic diagram of the principle of control during the grinding process of the present invention.
Detailed Description
The following describes embodiments of the present invention with reference to the drawings.
As shown in fig. 1, the present invention provides a teleoperation robot polishing control system based on multi-sensor fusion, which includes a robot base, a mechanical arm 1 rotatably disposed on the robot base, a six-dimensional force sensor 2, a fixing mechanism 3, a motor 4, a tool 5, an industrial camera 8, and a controller, and controls a working area 6 to be polished and an element to be processed 7 in the process.
Taking the six-degree-of-freedom mechanical arm 1 shown in fig. 1 as an example, the tail end of the mechanical arm 1 is vertically downward, and the six-dimensional force sensor 2 and the industrial camera 8 are both fixedly arranged at the tail end of the mechanical arm 1; the motor 4 is fixedly arranged on a force transmission shaft of the six-dimensional force sensor 2, an output shaft of the motor 4 is connected with the cutter 5 through the fixing mechanism 3, the cutter can flexibly move along with a joint at the tail end of the mechanical arm 1, the grinding can be performed in the part, and the grinding of parts in irregular shapes can be realized. And a joint encoder is arranged on the mechanical arm 1 and used for acquiring joint angles of all joints of the robot and resolving to obtain the tail end position feedback of the mechanical arm.
As shown in fig. 2, the specific implementation process of the present invention is as follows:
step 1: the cutter 5 is arranged behind an output shaft of the motor 4 through the fixing mechanism 3, the motor 4 is arranged on a force transmission shaft of the six-dimensional force sensor 2, and the six-dimensional force sensor 2 and the industrial camera 8 are assembled at the tail end of the mechanical arm together; the industrial camera 8 is arranged on the side surface of the tail end of the mechanical arm 1 and is parallel to the tail end direction of the mechanical arm 1. Then, an operator selects an automobile hub as an element 7 to be processed, the automobile hub is placed in the working area 6, the mechanical arm 1 is controlled by the controller to reach the working area 6 according to coordinates, and the industrial camera 8 is controlled by the controller to acquire an image of the automobile hub 7.
Step 2: the controller carries out image processing on the collected element image to be processed, extracts the image characteristics and the contour information of the element to be processed, and can feed back the processing result to an image interface of an upper computer for an operator to analyze; the system can dynamically create a template of the automobile hub according to the image information of the automobile hub, so that in the automatic polishing operation process, the system can automatically identify and match polishing parts with the same shape as required, such as the automobile hub, according to the image information and move the polishing parts to the position above the automobile hub. And the controller selects a polishing area according to the burr condition in the image characteristic and the contour information and the polishing requirement of the contour, wherein an operator can draw the polishing area shown by a dotted outline in figure 3 on an image interface according to the burr condition of the image and the polishing requirement of the contour of the hub, so as to create the polishing area for the system and realize the customized polishing area.
Preferably, the image of the element to be machined is saved by the controller and the image characteristics and the contour information are extracted through a machine vision algorithm based on Halcon software, and the workpiece to be ground can be automatically identified through template matching and automatically moved to the position above the workpiece in the robot autonomous mode.
And step 3: an optimal polishing path is planned according to the polishing area, and the motor 4 and the cutter 5 at the tail end of the mechanical arm 1 are controlled to polish the element 7 to be processed, for example, if the polishing area is circular, the mechanical arm 1 moves along the radial direction and the tangential direction of the circle, and if the polishing area is an arc, interpolation points are calculated through a polynomial interpolation algorithm to control the movement of the mechanical arm 1. Wherein, a manual planning or automatic planning mode is adopted.
Meanwhile, the six-dimensional force sensor acquires the force and the moment of the tail end of the mechanical arm under different polishing conditions, the force and the moment are input into the neural network in the controller for training, the trained neural network is obtained, the numerical values of the force and the moment predicted and output by the neural network under the current polishing condition are used as reference by the controller, PI control is carried out on the feeding amount of the cutter in the polishing process according to the feedback of the force and the moment of the tail end of the mechanical arm acquired by the six-dimensional force sensor, and PD control is carried out on the motion of the mechanical arm through the acquired position feedback of the mechanical arm.
The system needs to acquire required data through a teaching mode before use. On one hand, an operator needs to control the mechanical arm to move through a teaching mode, select a grinding workpiece and dynamically create an image template; on the other hand, an operator needs to collect force and torque data fed back by a six-dimensional force sensor for a system by using different tools, different polishing materials and different polishing degrees to provide a training sample for building a BP neural network, firstly, force and torque information in three directions of the different polishing tools, the different polishing materials and the different polishing degrees are processed into a resultant force and resultant torque form, then, different polishing tools, the different polishing materials and different polishing programs are quantized in a digital form, are listed together with the resultant force and the resultant torque, a data table is built by taking teaching times as rows, normalization processing is carried out on the data, then, the different polishing tools, the different polishing materials and different polishing programs are input as the neural network, the resultant force and the resultant torque are output through an empirical formula
Calculating the number of hidden layer nodes (wherein n is the number of neurons in an input layer, m is the number of neurons in an output layer, and a is a constant between 1 and 10), establishing a 3 x 8 x 2 three-layer BP neural network, setting excitation functions of the hidden layer and the output layer of the network as a tan sig bipolar S function and a logsig unipolar S function respectively, and adopting t as a network training functionAnd 4, a network performance function selects mse (mean square error), and the magnitude of force and moment required in the automatic polishing process is predicted through a trained neural network. And realizing the cooperative control of the robot and the human. Wherein the robot sanding operation is mainly done by controlling two parameters, i.e. the desired displacement of the robot
And desired force of the tool
The control principle is shown in fig. 4, and the expected displacement of the robot at a certain moment in the grinding process is set as
The expected acting force of the cutter is predicted to be
Firstly, the joint angle of each joint is calculated through the feedback of an encoder at the joint of the mechanical arm, the tail end position of the mechanical arm is obtained through positive solution of kinematics, and the current actual displacement of the mechanical arm is calculated to be
The difference value between the expected displacement and the actual displacement of the robot is
Then, the PD control parameters are set according to the performance parameters of the actual robot, and the current displacement of the robot can be calculated through the PD controller
Move to the desired displacement
Required excitation electrical signal
Meanwhile, a six-dimensional force sensor on the robot can acquire the force and the moment applied to the X, Y, Z shaft direction on the three-dimensional space coordinate system in real time, and the original force and moment signals output by the six-dimensional force sensor
White noise with certain intensity is mixed in the sensor, and the current force sensor signal is obtained after the white noise is processed by a filter
At which time the desired force is applied
And the actual acting force
By a difference of
Outputting an excitation signal to the robot through a PI controller
As a PI control parameter; control signal of robot at this time
Wherein k ispAnd kfGain coefficients for the displacement control element and the force control element for adjustment
And
the robot moves under the action of a control signal u, and when the grinding tool approaches the target edge, kfRapid decrease, kpThe size of the workpiece is properly reduced, and the workpiece is slowly close to the workpiece, so that the workpiece is prevented from being damaged. Meanwhile, the current displacement of the robot can be monitored in real time through data returned by the encoder
The six-dimensional force sensor can monitor the changes of force and moment in the polishing process in real time, and feed data back to the control system to form a feedback loop. By repeating the steps, the system can move according to the expected displacement of the robot
And expected force
Continuously adjusting the current displacement of the robot
And carrying out PI control on the feed quantity of the cutter in the grinding process. Therefore, force and position mixed control is realized, and automatic polishing of the automobile hub is completed.
In conclusion, the automatic grinding machine can automatically identify grinding elements, automatically grind according to a planned grinding area, load a cutter at the tail end of a mechanical arm, move flexibly and realize grinding of the inner part of a workpiece and grinding of irregular parts; and the design of multi-sensor fusion is adopted, so that the shared cooperative control of the robot and the human is realized.
The embodiments of the present invention have been described in detail with reference to the drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (6)
1. A teleoperation robot polishing control system based on multi-sensor fusion comprises a robot base and a mechanical arm rotatably arranged on the robot base, and is characterized by further comprising a six-dimensional force sensor, a cutter, a motor, an industrial camera and a controller, wherein the six-dimensional force sensor and the industrial camera are fixedly arranged at the tail end of the mechanical arm; the motor is fixedly arranged on a force transmission shaft of the six-dimensional force sensor, and an output shaft of the motor is connected with the cutter through a fixing mechanism; the controller controls the mobile mechanical arm to reach a working area according to the coordinate and controls the industrial camera to collect an image of an element to be processed, the controller performs image processing on the collected image of the element to be processed, extracts image characteristics and outline information of the element to be processed, selects a polishing area according to burr conditions in the image characteristics and the outline information and polishing requirements of the appearance, plans a polishing path according to the polishing area and controls a motor and a cutter at the tail end of the mechanical arm to polish the element to be processed; meanwhile, the six-dimensional force sensor acquires the force and moment at the tail end of the mechanical arm under different polishing conditions and inputs the force and moment into the neural network in the controller for training so as to construct and obtain the trained neural network, the controller takes the force and moment numerical values predicted and output by the neural network under the current polishing condition as reference, PI control is carried out on the feeding amount of the cutter in the polishing process according to the feedback of the force and moment at the tail end of the mechanical arm acquired by the six-dimensional force sensor, and PD control is carried out on the motion of the mechanical arm through the acquired mechanical arm position feedback, and the method specifically comprises the following steps:
set at a certain moment in the grinding process the desired displacement of the robot is
And under the current polishing condition, the expected acting force is predicted and output through a neural network
Obtaining the current actual displacement of the mechanical arm as
The difference value between the expected displacement and the actual displacement of the robot is obtained by calculation
And calculating to obtain the current displacement of the robot
Move to the desired displacement
Required excitation electrical signal
As a PD control parameter;
six-dimensional force sensor obtains the actual acting force at the tail end of the mechanical arm under the current polishing condition
Calculating to obtain expected acting force of the robot
And the actual acting force
By a difference of
And calculating to obtain an excitation signal to the robot
As PI control parameters;
from the resulting excitation electrical signal
And an excitation signal
And calculating to obtain a control signal of the robot, and controlling the robot to move under the action of the output control signal.
2. The teleoperated robotic sanding control system based on multi-sensor fusion of claim 1, wherein: the controller adopts a machine vision algorithm to extract image characteristics and contour information of the element to be processed.
3. The teleoperated robotic sanding control system based on multi-sensor fusion of claim 1, wherein: the controller also includes creating a template for the element to be machined based on the image features and the contour information for the element to be machined.
4. The teleoperated robotic sanding control system based on multi-sensor fusion of claim 1, wherein: the controller plans the grinding path in a manual planning or automatic planning mode.
5. The teleoperated robotic sanding control system based on multi-sensor fusion of claim 1, wherein: and the mechanical arm is provided with a joint encoder, and the joint encoder is used for acquiring joint angles of all joints of the robot and resolving to obtain the feedback of the tail end position of the mechanical arm.
6. The teleoperated robotic sanding control system based on multi-sensor fusion of claim 1, wherein: the control signals obtained by the controller are as follows:
wherein k ispAnd kfRespectively, the gain coefficients of displacement and applied force.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810862389.9A CN108942940B (en) | 2018-08-01 | 2018-08-01 | Teleoperation robot polishing control system based on multi-sensor fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810862389.9A CN108942940B (en) | 2018-08-01 | 2018-08-01 | Teleoperation robot polishing control system based on multi-sensor fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108942940A CN108942940A (en) | 2018-12-07 |
| CN108942940B true CN108942940B (en) | 2022-02-22 |
Family
ID=64466936
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810862389.9A Active CN108942940B (en) | 2018-08-01 | 2018-08-01 | Teleoperation robot polishing control system based on multi-sensor fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108942940B (en) |
Families Citing this family (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109623568A (en) * | 2018-12-10 | 2019-04-16 | 苏州丰川电子科技有限公司 | Metal shell processing feeding polishing all-in-one machine |
| CN109850293A (en) * | 2018-12-12 | 2019-06-07 | 楚天科技股份有限公司 | A kind of robot film cutting apparatus and the flexible method for cutting film |
| CN109940605B (en) * | 2019-01-29 | 2021-04-20 | 中国工程物理研究院激光聚变研究中心 | Compliant assembly system and method integrating three-dimensional vision and contact force analysis |
| CN109732625B (en) * | 2019-03-15 | 2020-11-27 | 珠海格力电器股份有限公司 | Industrial robot flexible polishing method and system based on machine vision |
| CN111823221A (en) * | 2019-03-27 | 2020-10-27 | 天津工业大学 | Robot polishing method based on multiple sensors |
| CN110328560A (en) * | 2019-07-31 | 2019-10-15 | 上海建桥学院 | A kind of mechanical arm system and method for processing complicated sphere curved surface shell |
| CN110861097B (en) * | 2019-12-24 | 2023-05-23 | 中国科学院宁波材料技术与工程研究所 | Force control end actuating mechanism for reducing vibration of mechanical arm and force control method |
| CN113021082B (en) * | 2019-12-24 | 2022-06-07 | 沈阳智能机器人创新中心有限公司 | Robot casting polishing method based on teleoperation and panoramic vision |
| CN111590577B (en) * | 2020-05-19 | 2021-06-15 | 台州中盟联动企业管理合伙企业(有限合伙) | Mechanical arm multi-parameter digital frequency conversion control method and device |
| CN112247680A (en) * | 2020-10-22 | 2021-01-22 | 广州文冲船厂有限责任公司 | Ship workpiece polishing method, device and system |
| CN112809666B (en) * | 2020-12-17 | 2023-04-28 | 安徽工业大学 | 5-DOF mechanical arm strength position tracking algorithm based on neural network |
| CN112907590B (en) * | 2021-04-09 | 2022-08-23 | 南开大学 | Polishing method and system based on metal ingot polishing information visual identification |
| CN113199491A (en) * | 2021-05-26 | 2021-08-03 | 广西大学 | Industrial robot constant-force polishing method |
| CN113459099A (en) * | 2021-07-02 | 2021-10-01 | 上海机器人产业技术研究院有限公司 | Ship body weld joint polishing robot and using method thereof |
| CN113787424A (en) * | 2021-10-11 | 2021-12-14 | 北京好运达智创科技有限公司 | Upper die polishing device and polishing method |
| CN113954070B (en) * | 2021-10-27 | 2023-05-02 | 苏州艾利特机器人有限公司 | Mechanical arm motion control method and device, storage medium and electronic equipment |
| CN114662410A (en) * | 2022-05-23 | 2022-06-24 | 季华实验室 | Method and device for determining polishing process parameter combination, electronic equipment and medium |
| CN115488736A (en) * | 2022-07-05 | 2022-12-20 | 港珠澳大桥管理局 | Automatic positioning polishing system and polishing method based on wall-climbing robot |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS62114808A (en) * | 1985-11-12 | 1987-05-26 | Dainichi Kiko Kk | Floating type rotary tool |
| CN104626168A (en) * | 2014-12-16 | 2015-05-20 | 苏州大学 | Robot force position compliant control method based on intelligent algorithm |
| CN106914904A (en) * | 2017-03-17 | 2017-07-04 | 华中科技大学 | A kind of complex-curved blade force-location mix control system of processing based on ROS |
| CN107009368A (en) * | 2017-03-30 | 2017-08-04 | 东南大学 | Robot polishing operation control system and its control method based on force snesor |
| CN107598775A (en) * | 2017-07-27 | 2018-01-19 | 芜湖微云机器人有限公司 | It is a kind of by laser detect the method that simultaneously multi-axis robot is polished |
| CN108182689A (en) * | 2016-12-08 | 2018-06-19 | 中国科学院沈阳自动化研究所 | The plate workpiece three-dimensional recognition positioning method in polishing field is carried applied to robot |
-
2018
- 2018-08-01 CN CN201810862389.9A patent/CN108942940B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS62114808A (en) * | 1985-11-12 | 1987-05-26 | Dainichi Kiko Kk | Floating type rotary tool |
| CN104626168A (en) * | 2014-12-16 | 2015-05-20 | 苏州大学 | Robot force position compliant control method based on intelligent algorithm |
| CN108182689A (en) * | 2016-12-08 | 2018-06-19 | 中国科学院沈阳自动化研究所 | The plate workpiece three-dimensional recognition positioning method in polishing field is carried applied to robot |
| CN106914904A (en) * | 2017-03-17 | 2017-07-04 | 华中科技大学 | A kind of complex-curved blade force-location mix control system of processing based on ROS |
| CN107009368A (en) * | 2017-03-30 | 2017-08-04 | 东南大学 | Robot polishing operation control system and its control method based on force snesor |
| CN107598775A (en) * | 2017-07-27 | 2018-01-19 | 芜湖微云机器人有限公司 | It is a kind of by laser detect the method that simultaneously multi-axis robot is polished |
Non-Patent Citations (1)
| Title |
|---|
| 黄伟等.BP神经网络及其在磨削力序列预测中的应用.《金刚石与磨料磨具工程》.2001,(第02期),第42-43页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108942940A (en) | 2018-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108942940B (en) | Teleoperation robot polishing control system based on multi-sensor fusion | |
| CN109434843B (en) | Equipment and method for robot force-controlled blade polishing based on dragging teaching | |
| CN109955122A (en) | Full-automatic sanding system and full-automatic sanding method based on machine vision | |
| CN105643399B (en) | The complex-curved automatic grinding-polishing system of robot and processing method based on Shared control | |
| CN103831695B (en) | Large-scale free form surface robot polishing system | |
| CN108284388B (en) | A kind of intelligent Force control grinding and polishing apparatus of vision guide | |
| CN108115705A (en) | A kind of robot polishing control system and method | |
| CN105690209B (en) | A kind of large-scale curved grinding self-adaptation control method | |
| CN105290925B (en) | Roll adjustment paddle type facing sand band grinding attachment and its processing method based on industrial robot | |
| CN114515924B (en) | Automatic welding system and method for tower foot workpiece based on weld joint identification | |
| KR940009090B1 (en) | Grinder robot | |
| CN109093477B (en) | Device and method for polishing flashes of casting and forging pieces through cooperation of multiple robots | |
| CN104858782A (en) | Constant pressure automatic grinding device and method based on fuzzy adaptive force control | |
| CN107378324B (en) | Welding system and method for special-shaped workpiece based on visual extraction | |
| CN207953500U (en) | A kind of adaptive surface sanding and polishing system based on robot | |
| CN107598724A (en) | Glass mold polishing robot based on parallel institution | |
| CN209811886U (en) | Full-automatic system of polishing based on machine vision | |
| US20110288673A1 (en) | Method for Machining Composite Components | |
| CN111452033A (en) | Double NURBS curve milling trajectory planning method for industrial robot | |
| CN108161664B (en) | Laser scanning polishing system and method | |
| CN111823100A (en) | Robot-based small-curvature polishing and grinding method | |
| CN114310540A (en) | Equipment and method for automatically grinding weld joint of flow channel of casing by robot | |
| CN114453729A (en) | Laser cooperation device for multi-axis turning and milling composite machine tool and control method | |
| CN113932753A (en) | Method for calibrating grinding profile of hub flange plate | |
| CN108068122A (en) | A kind of large ship groove face processing unit (plant) and localization method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |