CN108972545A - A kind of robot constant force curved surface tracking method based on fuzzy iterative algorithm - Google Patents
A kind of robot constant force curved surface tracking method based on fuzzy iterative algorithm Download PDFInfo
- Publication number
- CN108972545A CN108972545A CN201810648484.9A CN201810648484A CN108972545A CN 108972545 A CN108972545 A CN 108972545A CN 201810648484 A CN201810648484 A CN 201810648484A CN 108972545 A CN108972545 A CN 108972545A
- Authority
- CN
- China
- Prior art keywords
- robot
- curved surface
- power
- force
- error
- 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.)
- Granted
Links
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
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- 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
- B25J9/1628—Programme controls characterised by the control loop
- B25J9/1633—Programme controls characterised by the control loop compliant, force, torque control, e.g. combined with position control
Abstract
The invention discloses a kind of robot constant force curved surface tracking method based on fuzzy iterative algorithm, comprising steps of feature when (1) is contacted for industrial robot end effector and curved surface profile, establishes the mapping relations of curved surface normal force and known sensor coordinate system；(2) error of the power according to obtained in experiment and desired power changes the motion profile of robot, while according to the track of power error and power error change amount fuzzy compensation robot in last time experiment；(3) iteration experiment is until obtaining power and desired error within the scope of setting.The present invention solves the problems, such as to be difficult to obtain constant tracking power in existing robot curved surface tracking, have the advantages that realize simple, the unknown transmission function for not needing to obtain robot interior also haves no need to change robot end's sensor attitude, and obtained curved surface profile track provides initial reference locus for processing such as subsequent polishing, polishings.
Description
Technical field
The present invention relates to robot constant force control technology field, in particular to a kind of robot based on fuzzy iterative algorithm
Constant force curved surface tracking method.
Background technique
During machine human and environment contacts, machine human and environment contact condition can be adjusted by power control, thus
Reach ideal contact effect, therefore power control widely applies to robot polishing, polishing, curved surface tracking etc..Utilize machine
When people tracks Unknown curve surface contact, the contact force kept constant can obtain accurate curved surface profile, however in contact process
Since robot self attributes (such as robot dynamics' characteristic, Robot Stiffness) and circumstances not known are time-varying (such as curved surface wheels
Exterior feature variation), the contact force for causing robot and curved surface is unstable, fluctuation is larger, inadequate so as to cause the curved surface profile of acquisition
Accurately.
Traditional control algorithm (such as impedance control, power/position mixing control, self adaptive control) is difficult Compensating Robot and tracked
Various uncertainties in journey, such as the uncertainty of robot kinematics, while the change of the sensor attitude of robot end
Cause the variation of sensor registration；And intelligent control algorithm design comparison is complicated, rests on simulation stage mostly at present.
Summary of the invention
The purpose of the present invention is to overcome the shortcomings of the existing technology and deficiency, provides a kind of machine based on fuzzy iterative algorithm
Device people's constant force curved surface tracking method, it is intended to solve robot interior transmission function is unknown and robot end's sensor attitude
In immovable situation, the effect of robot constant force curved surface tracking is realized.
The purpose of the present invention is realized by the following technical solution: a kind of robot constant force based on fuzzy iterative algorithm is bent
Face tracking, comprising the following steps:
(1) feature when contacting for industrial robot end effector and curved surface profile establishes curved surface normal force and
Know the mapping relations of sensor coordinate system；
(2) it is tracked along Unknown curve surface, initial control algolithm is PD algorithm, obtains initial track and force parameter；
(3) error of the power according to obtained in experiment and desired power sets the initial knots modification of motion profile of robot,
Simultaneously according to the track of power error and power error change amount fuzzy compensation robot in last time experiment, sum of the two is machine
The displacement knots modification of people；Power error is that the power of acquisition subtracts expected force；
(4) iterative step (3) is until obtaining the error of power and desired power within the threshold range of setting.
Preferably, before carrying out step (1), the signal acquired according to force snesor, host computer operation are further comprised the steps of:
Algorithm sends position command to robot.
Further, the above-mentioned signal host computer operation algorithm according to force snesor acquisition sends position to robot and refers to
The step of enabling include:
A) force signal in the direction x and y of data collecting module collected force snesor, and send a signal to host computer；
B) host computer sends analog signal and gives robot control cabinet, and robot generates offset, offset displacement direction and simulation
Signal code is consistent, and offset displacement is directly proportional to absolute value of voltage size.
Preferably, the step (1) specifically includes:
Establish the mapping relations of research object curved surface normal force and known sensor coordinate system:
Fn=T Fxsinθ-TFycosθ
F in formulanFor surface normal vector power,TFxFor the power on the direction x in sensor coordinate system { T },TFyFor sensor coordinates
It is the power on the direction y, θ is curved surface inclination angle.
Preferably, the step (2) specifically includes:
(21) initial control algolithm is PD algorithm, is tracked along Unknown curve surface, is obtained by way of being displaced difference
Initial θ；
(22) utilization measures θ and obtains FnValue.
Preferably, the step (3) specifically includes:
(31) the force signal F obtainednSubtract desired value Fd, the signal of error e is obtained, the absolute value of e is greater than the part of threshold value
Waveform is divided into two kinds of situations, and a kind of situation is that force signal has falling, is similar to parabola, is type I；Another situation is that power is believed
It number does not fall after rise, force signal increases or reduces always, is Type II；
(32) the part iteration renewal equation of type I are as follows:
U in formulak+1It (t) is the robot displacement input quantity of current k+1 iteration；Robot displacement knots modification is by initially changing
Variable kp(t)ek(t) and fuzzy compensation amount kd(t)g(ek(t),eck(t)) it constitutes；ekIt (t) is normal force FnWith expected force FdMistake
Difference；
eckIt (t) is error change amount, kp(t) and kdIt (t) is respectively ek(t), eck(t) coefficient；g(ek(t),eck(t))
For compensation rate, with ek(t) and eck(t) related, it is obtained by fuzzy algorithmic approach；tsFor the iteration time started；teAt the end of iteration
Between；tpFor tsTo teThe maximum value of the absolute value of the period e corresponding time.
(33) in fuzzy controller, modulus paste domain is identical with basic domain, ek(t), eck(t) and g (ek(t),
eck(t)) domain defines five Linguistic Values { NB, NS, ZO, PS, PB }, respectively correspond negative big, small, zero point is born, it is just small, just
Greatly }, subordinating degree function selects triangular function；
(34) part of Type II, iteration renewal equation are as follows:
uk+1(t)=uk(t)+kp(t)ek(t)+kd(t)g(ek(t),eck(t))ts< t≤tp。
Preferably, the step (4) specifically includes:
(41) procedures of turn-off of the part iteration of type I is stopping criterion for iteration are as follows: the error of obtained power is all in threshold
Be worth in range, i.e., | | e | | < FTH, wherein FTHFor oneself given threshold, unit N；
(42) procedures of turn-off of the part iteration of Type II is stopping criterion for iteration are as follows: the error 90% of obtained power is in threshold
Value FTHIn range.
Compared with the prior art, the invention has the following advantages and beneficial effects:
The present invention solves the problems, such as to be difficult to obtain constant tracking power in existing robot curved surface tracking, has and realizes simply
The advantages of, the unknown transmission function for not needing to obtain robot interior also haves no need to change robot end's sensor attitude, obtains
The curved surface profile track arrived is subsequent polishing, and the processing such as polishing provide initial reference locus.
Detailed description of the invention
Fig. 1 is embodiment robot constant force curved surface tracking platform schematic diagram.
Fig. 2 is embodiment robot constant force curved surface tracking platform partial enlarged view schematic diagram；
In figure: 1- robot；2- six-dimension force sensor；3- probe；4- curve surface work pieces；5- workbench.
Specific embodiment
Present invention will now be described in further detail with reference to the embodiments and the accompanying drawings, but embodiments of the present invention are unlimited
In this.
Embodiment 1
Robot constant force curved surface tracking method based on fuzzy iterative algorithm, method are based on robot constant force tracking platform,
Including six-shaft industrial robot, workbench, curve surface work pieces, six-dimension force sensor, host computer, data acquisition module.Robot begins
Moved eventually with constant speed along the direction x, when robot and workpiece contact, according to power size along the direction y
Offset, tracks, it is ensured that robot end is without departing from curve surface work pieces along Unknown curve surface.
Specifically includes the following steps:
(1) mapping relations of curved surface normal force and known sensor coordinate system are established；
(2) it is tracked along Unknown curve surface, initial control algolithm is PD algorithm, obtains initial track and force parameter；
(3) track and the force signal for obtaining robot compare the error of force signal and desired power with threshold value
Afterwards by Modulation recognition；The error of the power according to obtained in experiment and desired power changes the motion profile of robot, while basis
Fuzzy iterative algorithm is designed in the track of power error and power error change amount fuzzy compensation robot in last time experiment；
(4) iterative step (3) is until obtaining power and desired error within the threshold value of setting.
Before carrying out step (1), further comprises the steps of: and calculated according to the upper function operation of signal of six-dimension force sensor acquisition
Method sends position command to robot.
The upper function operation algorithm of the signal according to six-dimension force sensor acquisition sends position command to robot
The step of specifically include:
(a) force signal of data collecting module collected six-dimension force sensor, and send a signal to host computer；
(b) host computer sends analog signal and gives robot control cabinet, and robot generates offset, offset displacement direction and simulation
Signal code is consistent, and offset displacement is directly proportional to absolute value of voltage size.
The step (1) specifically includes:
Establish the mapping relations of research object curved surface normal force and known sensor coordinate system:
Fn=T Fxsinθ-TFycosθ
Wherein FnFor surface normal vector power,TFxFor the power on the direction x in sensor coordinate system { T },TFyFor sensor coordinates
It is the power on the direction y, θ is curved surface inclination angle.
The step (2) specifically includes:
(21) initial control algolithm is PD algorithm, is tracked along Unknown curve surface, is obtained by way of being displaced difference
Initial θ；
(22) utilization measures θ and obtains FnValue.
The step (3) specifically includes:
(31) the force signal F obtainednSubtract desired value FdThe signal of error e is obtained, the absolute value of e is greater than the part of threshold value
Waveform is divided into two kinds of situations, and a kind of situation is that force signal has falling, is similar to parabola, is type I；Another situation is that power is believed
It number does not fall after rise, force signal increases or reduces always, is Type II；
(32) the part iteration renewal equation of type I are as follows:
U in formulak+1It (t) is the robot displacement input quantity of current k+1 iteration；Robot displacement knots modification is by initially changing
Variable kp(t)ek(t) and fuzzy compensation amount kd(t)g(ek(t),eck(t)) it constitutes；ekIt (t) is normal force FnWith expected force FdMistake
Difference；eckIt (t) is error change amount, kp(t) and kdIt (t) is respectively ek(t), eck(t) coefficient；g(ek(t),eckIt (t)) is benefit
The amount of repaying, with ek(t) and eck(t) related, it is obtained by fuzzy algorithmic approach；tsFor the iteration time started；teFor the iteration end time；tp
For tsTo teThe maximum value of the absolute value of the period e corresponding time.
(33) in fuzzy controller, modulus paste domain is identical with basic domain, ek(t), eck(t) and g (ek(t),
eck(t)) domain defines five Linguistic Values { NB, NS, ZO, PS, PB }, respectively correspond negative big, small, zero point is born, it is just small, just
Greatly }, subordinating degree function selects triangular function；
(34) part of Type II, iteration renewal equation are as follows:
uk+1(t)=uk(t)+kp(t)ek(t)+kd(t)g(ek(t),eck(t))ts< t≤tp
The step (4) specifically includes:
(41) procedures of turn-off of the part iteration of type I is stopping criterion for iteration are as follows: i.e. | | e | | < FTH, wherein FTHFor certainly
Own given threshold, unit N；
(42) procedures of turn-off of the part iteration of Type II is stopping criterion for iteration are as follows: the error 90% of obtained power is in threshold
Value FTHIn range.
Each components of the present invention can type selecting it is as follows, but type selecting is without being limited thereto:
Six-shaft industrial robot: the robot of other same types can be selected；Workpiece 2: the same type of regular shape can be selected
Workpiece.
The above embodiment is a preferred embodiment of the present invention, but embodiments of the present invention are not by above-described embodiment
Limitation, other any changes, modifications, substitutions, combinations, simplifications made without departing from the spirit and principles of the present invention,
It should be equivalent substitute mode, be included within the scope of the present invention.
Claims (7)
1. a kind of robot constant force curved surface tracking method based on fuzzy iterative algorithm, which comprises the following steps:
(1) feature when contacting for industrial robot end effector and curved surface profile, establishes curved surface normal force and known biography
The mapping relations of sensor coordinate system；
(2) it is tracked along Unknown curve surface, initial control algolithm is PD algorithm, obtains initial track and force parameter；
(3) error of the power according to obtained in experiment and desired power sets the initial knots modification of motion profile of robot, simultaneously
According to the track of power error and power error change amount fuzzy compensation robot in last time experiment, sum of the two is robot
It is displaced knots modification；Power error is that the power of acquisition subtracts expected force；
(4) iterative step (3) is until obtaining the error of power and desired power within the threshold range of setting.
2. the robot constant force curved surface tracking method according to claim 1 based on fuzzy iterative algorithm, which is characterized in that
Before carrying out step (1), the signal acquired according to force snesor is further comprised the steps of:, host computer operation algorithm gives machine human hair
Send position command.
3. the robot constant force curved surface tracking method according to claim 2 based on fuzzy iterative algorithm, which is characterized in that
Include: to the step of robot transmission position command according to the signal host computer operation algorithm of force snesor acquisition
A) force signal in the direction x and y of data collecting module collected force snesor, and send a signal to host computer；
B) host computer sends analog signal and gives robot control cabinet, and robot generates offset, offset displacement direction and analog signal
Symbol is consistent, and offset displacement is directly proportional to absolute value of voltage size.
4. the robot constant force curved surface tracking method according to claim 1 based on fuzzy iterative algorithm, which is characterized in that
Step (1) specifically includes:
Establish the mapping relations of research object curved surface normal force and known sensor coordinate system:
Fn=TFxsinθ-TFycosθ
F in formulanFor surface normal vector power,TFxFor the power on the direction x in sensor coordinate system { T },TFyFor the sensor coordinate system side y
Upward power, θ are curved surface inclination angle.
5. the robot constant force curved surface tracking method according to claim 1 based on fuzzy iterative algorithm, which is characterized in that
Step (2) specifically includes:
(21) initial control algolithm is PD algorithm, is tracked along Unknown curve surface, is obtained by way of being displaced difference initial
θ；
(22) utilization measures θ and obtains FnValue, FnFor surface normal vector power, θ is curved surface inclination angle.
6. the robot constant force curved surface tracking method according to claim 1 based on fuzzy iterative algorithm, which is characterized in that
Step (3) specifically includes:
(31) the force signal F obtainednSubtract desired value Fd, the signal of error e is obtained, the absolute value of e is greater than the portion waveshape of threshold value
It is divided into two kinds of situations, a kind of situation is that force signal has falling, is similar to parabola, is type I；Another situation is that force signal does not have
There is falling, force signal increases or reduces always, is Type II；
(32) the part iteration renewal equation of type I are as follows:
U in formulak+1It (t) is the robot displacement input quantity of current k+1 iteration；Robot displacement knots modification is by initial knots modification kp
(t)ek(t) and fuzzy compensation amount kd(t)g(ek(t),eck(t)) it constitutes；ekIt (t) is normal force FnWith expected force FdError；eck
It (t) is error change amount, kp(t) and kdIt (t) is respectively ek(t), eck(t) coefficient；g(ek(t),eckIt (t)) is compensation rate, with
ek(t) and eck(t) related, it is obtained by fuzzy algorithmic approach；tsFor the iteration time started；teFor the iteration end time；tpFor tsTo te
The maximum value of the absolute value of the period e corresponding time；
(33) in fuzzy controller, modulus paste domain is identical with basic domain, ek(t), eck(t) and g (ek(t),eck(t))
Domain define five Linguistic Values { NB, NS, ZO, PS, PB }, respectively correspond { negative big, bear small, zero point, just small, honest }, be subordinate to
It spends function and selects triangular function；
(34) part of Type II, iteration renewal equation are as follows:
uk+1(t)=uk(t)+kp(t)ek(t)+kd(t)g(ek(t),eck(t)) ts< t≤tp。
7. the robot constant force curved surface tracking method according to claim 6 based on fuzzy iterative algorithm, which is characterized in that
Step (4) specifically includes:
(41) procedures of turn-off of the part iteration of type I is stopping criterion for iteration are as follows: the error of obtained power is all in threshold value model
In enclosing, i.e., | | e | | < FTH, wherein FTHFor oneself given threshold, unit N；
(42) procedures of turn-off of the part iteration of Type II is stopping criterion for iteration are as follows: the error 90% of obtained power is in threshold value FTH
In range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810648484.9A CN108972545B (en) | 2018-06-22 | 2018-06-22 | Robot constant-force curved surface tracking method based on fuzzy iterative algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810648484.9A CN108972545B (en) | 2018-06-22 | 2018-06-22 | Robot constant-force curved surface tracking method based on fuzzy iterative algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108972545A true CN108972545A (en) | 2018-12-11 |
| CN108972545B CN108972545B (en) | 2021-08-10 |
Family
ID=64538081
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810648484.9A Active CN108972545B (en) | 2018-06-22 | 2018-06-22 | Robot constant-force curved surface tracking method based on fuzzy iterative algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108972545B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110281152A (en) * | 2019-06-17 | 2019-09-27 | 华中科技大学 | A kind of robot constant force polishing paths planning method and system based on online examination touching |
| CN111975579A (en) * | 2020-07-29 | 2020-11-24 | 华南理工大学 | Robot constant-force polishing system based on polishing model and iterative algorithm |
| CN112318319A (en) * | 2020-10-20 | 2021-02-05 | 天津大学 | Programming-free robot online constant-force grinding control system and method |
| CN112405536A (en) * | 2020-11-10 | 2021-02-26 | 东南大学 | High-precision constant force control method combining offline compensation and online tracking hybrid strategy |
| CN114040203A (en) * | 2021-11-26 | 2022-02-11 | 京东方科技集团股份有限公司 | Video data processing method, device, equipment and computer storage medium |
| CN114029789A (en) * | 2021-11-16 | 2022-02-11 | 武汉理工大学 | Curved surface polishing robot polishing method and system based on track correction |
| CN114800500A (en) * | 2022-04-21 | 2022-07-29 | 无锡斯帝尔科技有限公司 | Flexible constant force control method and system for polishing robot |
| CN115338736A (en) * | 2021-12-09 | 2022-11-15 | 上海爱仕达机器人有限公司 | Constant-force automatic grinding and polishing machine |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001065121A2 (en) * | 2000-03-01 | 2001-09-07 | Massachusetts Institute Of Technology | Force-controlled hydro-elastic actuator |
| CN104858782A (en) * | 2015-04-03 | 2015-08-26 | 华南理工大学 | Constant pressure automatic grinding device and method based on fuzzy adaptive force control |
| CN106383495A (en) * | 2016-09-12 | 2017-02-08 | 华南理工大学 | Curved surface profile constant force tracking method and application based on non-linear double closed loop control |
| CN107838920A (en) * | 2017-12-20 | 2018-03-27 | 芜湖哈特机器人产业技术研究院有限公司 | A kind of robot polishing Force control system and method |
-
2018
- 2018-06-22 CN CN201810648484.9A patent/CN108972545B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001065121A2 (en) * | 2000-03-01 | 2001-09-07 | Massachusetts Institute Of Technology | Force-controlled hydro-elastic actuator |
| CN104858782A (en) * | 2015-04-03 | 2015-08-26 | 华南理工大学 | Constant pressure automatic grinding device and method based on fuzzy adaptive force control |
| CN106383495A (en) * | 2016-09-12 | 2017-02-08 | 华南理工大学 | Curved surface profile constant force tracking method and application based on non-linear double closed loop control |
| CN107838920A (en) * | 2017-12-20 | 2018-03-27 | 芜湖哈特机器人产业技术研究院有限公司 | A kind of robot polishing Force control system and method |
Non-Patent Citations (3)
| Title |
|---|
| 刘志学等: "模糊迭代学习在单关节机器人运动控制中的应用 ", 《辽宁科技大学学报》 * |
| 张航等: "机器人模糊迭代学习控制及其仿真研究 ", 《自动化技术与应用》 * |
| 张钰玲等: "模糊迭代学习控制器的研究与设计 ", 《煤炭技术》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110281152A (en) * | 2019-06-17 | 2019-09-27 | 华中科技大学 | A kind of robot constant force polishing paths planning method and system based on online examination touching |
| CN111975579A (en) * | 2020-07-29 | 2020-11-24 | 华南理工大学 | Robot constant-force polishing system based on polishing model and iterative algorithm |
| CN111975579B (en) * | 2020-07-29 | 2022-06-14 | 华南理工大学 | Robot constant-force polishing system based on polishing model and iterative algorithm |
| CN112318319A (en) * | 2020-10-20 | 2021-02-05 | 天津大学 | Programming-free robot online constant-force grinding control system and method |
| CN112405536A (en) * | 2020-11-10 | 2021-02-26 | 东南大学 | High-precision constant force control method combining offline compensation and online tracking hybrid strategy |
| CN112405536B (en) * | 2020-11-10 | 2021-12-28 | 东南大学 | High-precision constant force control method combining offline compensation and online tracking hybrid strategy |
| CN114029789A (en) * | 2021-11-16 | 2022-02-11 | 武汉理工大学 | Curved surface polishing robot polishing method and system based on track correction |
| CN114040203A (en) * | 2021-11-26 | 2022-02-11 | 京东方科技集团股份有限公司 | Video data processing method, device, equipment and computer storage medium |
| CN115338736A (en) * | 2021-12-09 | 2022-11-15 | 上海爱仕达机器人有限公司 | Constant-force automatic grinding and polishing machine |
| CN115338736B (en) * | 2021-12-09 | 2024-02-27 | 上海爱仕达机器人有限公司 | Constant force automatic polishing machine |
| CN114800500A (en) * | 2022-04-21 | 2022-07-29 | 无锡斯帝尔科技有限公司 | Flexible constant force control method and system for polishing robot |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108972545B (en) | 2021-08-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108972545A (en) | A kind of robot constant force curved surface tracking method based on fuzzy iterative algorithm | |
| Li et al. | Learning of grasp adaptation through experience and tactile sensing | |
| Qi et al. | Contour moments based manipulation of composite rigid-deformable objects with finite time model estimation and shape/position control | |
| CN108927801B (en) | Method and device for adjusting tail end attitude of mechanical arm | |
| CN108972546A (en) | A kind of robot constant force curved surface tracking method based on intensified learning | |
| CN111975579B (en) | Robot constant-force polishing system based on polishing model and iterative algorithm | |
| JP2002018754A (en) | Robot device and its control method | |
| CN103963057A (en) | Robot control method, robot control device, robot and robot system | |
| Funabashi et al. | Morphology-specific convolutional neural networks for tactile object recognition with a multi-fingered hand | |
| WO2022121003A1 (en) | Robot control method and device, computer-readable storage medium, and robot | |
| Garg et al. | Learning to grasp under uncertainty using POMDPs | |
| CN111673733A (en) | Intelligent self-adaptive compliance control method of robot in unknown environment | |
| CN205121556U (en) | Robot grasping system | |
| Zhang et al. | Robotic curved surface tracking with a neural network for angle identification and constant force control based on reinforcement learning | |
| CN113500597B (en) | Multi-end teleoperation sliding mode impedance control method based on force translation mechanism | |
| Katyara et al. | Vision based adaptation to kernelized synergies for human inspired robotic manipulation | |
| Sadun et al. | An overview of active compliance control for a robotic hand | |
| CN114131617A (en) | Intelligent compliance control method and device for industrial robot | |
| Sang et al. | A zero phase adaptive fuzzy Kalman filter for physiological tremor suppression in robotically assisted minimally invasive surgery | |
| Zhao et al. | POSITIONING AND GRABBING TECHNOLOGY OF INDUSTRIAL ROBOT BASED ON VISION. | |
| Zhu et al. | Adaptive impedance control method for industrial manipulator writing based on Kalman filter | |
| Prasad et al. | Multi-agent Polygon Formation using Reinforcement Learning. | |
| Al-Mohammed et al. | A switched adaptive controller for robotic gripping of novel objects with minimal force | |
| Wei et al. | Multisensory visual servoing by a neural network | |
| Suh et al. | A visual servoing algorithm using fuzzy logics and fuzzy-neural networks |
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 |