CN108748160A - Manipulator motion planning method based on particle cluster algorithm on multiple populations - Google Patents
Manipulator motion planning method based on particle cluster algorithm on multiple populations Download PDFInfo
- Publication number
- CN108748160A CN108748160A CN201810642320.5A CN201810642320A CN108748160A CN 108748160 A CN108748160 A CN 108748160A CN 201810642320 A CN201810642320 A CN 201810642320A CN 108748160 A CN108748160 A CN 108748160A
- Authority
- CN
- China
- Prior art keywords
- particle
- mechanical arm
- population
- cluster algorithm
- motion planning
- 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
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
- B25J9/1607—Calculation of inertia, jacobian matrixes and inverses
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Automation & Control Theory (AREA)
- Numerical Control (AREA)
- Feedback Control In General (AREA)
Abstract
The present invention proposes a kind of manipulator motion planning method based on particle cluster algorithm on multiple populations, and step is:Sixdegree-of-freedom simulation is modeled using DH parametric methods, mechanical arm positive kinematics is carried out and solves coordinate of the robot arm end effector in basis coordinates system;Evaluation function is established by robot arm end effector in three-dimensional system of coordinate and the space length of setting target;The initialization function for improving conventional particle group's algorithm will show several optimal particles and form an elite population, carries out EVOLUTIONARY COMPUTATION to elite population, obtain the particle of global optimum in multiple sub- populations;It is identical in parameter setting, the motion planning problem of mechanical arm is realized with other evolution algorithmics, is compared with improved particle cluster algorithm on multiple populations in step 3, is verified the superiority of particle cluster algorithm on multiple populations.The present invention has obtained manipulator motion planning optimal solution, and requires no knowledge about the initial position of executor tail end, also need not be to mechanical arm inverse kinematics.
Description
Technical field
The technical field that is automatically controlled the present invention relates to robot more particularly to a kind of based on particle cluster algorithm on multiple populations
Manipulator motion planning method.
Background technology
Now, robot has in fields such as industry, agricultural, military, medical treatment, scientific research exploration and service trades and widely answers
With.In terms of medical treatment, there are healing robot and medical robot;In military aspect, there is Detecting Robot (such as Libya battlefield
Unmanned plane) and explosive-removal robot etc.;On Scientific Exploration, there is underwater robot;In industrial aspect, there are welding robot, dress
With robot and transfer robot etc.;In terms of amusement, there are Soccer robot and Robet for boxing etc.;It is useful in space industry
The arch maintenance robot etc. of space station.The application of robot has covered various fields, and most of in the application in these fields
All it be unable to do without motion planning.Motion planning is the important technology in mechanical arm system, and good motion planning technology can ensure
The completion task of mechanical arm safety, and meet the kinematic accuracy index of mechanical arm.Although manipulator motion planning technology has taken
Many achievements were obtained, but were not mature enough at many aspects.Therefore the path Motion Technology of research mechanical arm has critically important
Realistic meaning and value.The task of motion planning is in the case of a given initial point and target point, according to certain
Evaluation criterion cooks up one (such as shortest path length, minimal energy consumption or full accuracy) from starting point to target point
Optimal or sub-optimal path.
In recent years, many researchers proposed that various algorithms were applied to setting for manipulator motion planning, including heredity
Algorithm (Genetic Algorithm, GA), simulated annealing algorithm (Simulate Anneal Arithmetic, SAA), taboo
Search for (Taboo Search, TS), ant colony optimization algorithm (Ant Colony Optimization, ACO), neural network calculation
Method (Neural Network Algorithm, NEA) and Artificial Immune Algorithm (Immune Clonal Selection
Algorithm, ICSA) etc..These methods can Fast Convergent, but can in entire manipulator motion planning design process
Can not be optimal.
Invention content
The technical issues of may not be optimal in entire manipulator motion planning design process for existing method, this
Invention proposes a kind of manipulator motion planning method based on particle cluster algorithm on multiple populations, using with a variety of of preferentially mechanism in advance
Group's particle cluster algorithm more efficiently solves the problems, such as manipulator motion planning, can obtain manipulator motion planning optimal solution.
In order to achieve the above object, the technical proposal of the invention is realized in this way:One kind is calculated based on population on multiple populations
The manipulator motion planning method of method, its step are as follows:
Step 1:Sixdegree-of-freedom simulation is modeled using DH parametric methods, mechanical arm positive kinematics is carried out and solves machine
Coordinate of the tool arm end effector in basis coordinates system;
Step 2:Evaluation letter is established by the space length of robot arm end effector in three-dimensional system of coordinate and setting target
Number;
Step 3:The initialization function for improving conventional particle group's algorithm will show optimal several in multiple sub- populations
Particle forms an elite population, carries out EVOLUTIONARY COMPUTATION to elite population, obtains the particle of global optimum;
Step 4:It is identical in parameter setting, realize that the motion planning of mechanical arm is asked with other evolution algorithmics
Topic, is compared with improved particle cluster algorithm on multiple populations in step 3, verifies the superiority of particle cluster algorithm on multiple populations.
On the basis of DH parametric methods are the basis coordinates system established with first artis of mechanical arm in the step 1, each
A rectangular coordinate system is established in joint, and point (0,0,0) is the origin of basis coordinates system, and (X-end, Y-end, Z-end) is mechanical arm
Coordinate of the end in basis coordinates system obtains robot arm end effector in basis coordinates system by the rotation and translation of coordinate system
Coordinate;
Ai indicates transformation of i-th of coordinate system to i+1 coordinate system, i.e.,:
Wherein, (0, d Trani, 0) and it indicates to press Y direction translation distance di, Rot (x, αi) indicate to rotate clockwise X-axis
Angle [alpha]i, Rot (z, θi) indicate Z axis rotating clockwise angle, θi, Tran (ai, 0,0) and it indicates to press X-direction translation distance ai;
From basis coordinates system to the transformation matrix of mechanical arm tail end coordinate system following formula subrepresentation:
(px, py, pz) be mechanical arm tail end coordinate;nx、
ny、nz、ox、oy、oz、ax、ay、azAlgebraic expression after representing matrix derivation.
The method for solving of evaluation function is in the step 2:If coordinate (the X of target pointt, Yt, Zt) indicate, then it is mechanical
The space length of arm end to target point indicates that is, evaluation function is with Fitness:
Multiple sub- populations are initialized in the step 3, traditional particle cluster algorithm is improved, introduce son
Population and elite population, improved step:
The first step:N sub- populations are initialized, every sub- population includes the N number of particle generated at random;
Second step:As unit of single sub- population, Utilization assessment function Fitness evaluates the adaptation of wherein each particle
Value, and be ranked up by from excellent to bad, it selects and shows optimal preceding N/n particle, the table that then will be selected in every sub- population
Existing N/n optimal particle forms an elite population containing N number of particle;
Third walks:The parameter for initializing elite population carries out speed and location updating, profit to each particle in elite population
Its adaptive value is evaluated with evaluation function Fitness, its adaptive value is made comparisons with the desired positions pbest that it passes through, if compared with
It is good, then as current desired positions pbest;
4th step:It makes comparisons with the desired positions gbest in entire population to the current desired positions of each particle, if
Preferably, then it is stored as global desired positions gbest;Judge whether to meet global optimum's index, if not, returning to third
Step, if so, executing the 5th step;
5th step:The global best particle of selection simultaneously exports result.
Particle in the third step in elite population updates its speed and position by following two formula:
vk+1=ωkvk+c1r1(pk best–ak)+c2r2(gk best-ak),
ak+1=ak+vk;
Wherein, vk+1And vkSpeed of the expression particle at k moment and k+1 moment respectively;ak+1It is the current location of particle, ak
For the position of particle eve;ωkFor inertial factor;pk bestAnd gk bestIndicate respectively k moment Particle Swarms part and it is global most
Excellent position;r1And r2It is the random number between (0,1) that rand () function generates;c1And c2It is Studying factors;Speed
Maximum value be maximum flying speed be vmaxIf speed vk+1More than vmax, then the speed is utilized to replace maximum flying speed:
vmax=vk+1。
Beneficial effects of the present invention:First, theory analysis is carried out to Mechanical transmission test and gives six degree of freedom module machine
The method of device people D-H modelings simultaneously derives its direct kinematics equation;Then, robot arm end effector and setting mesh are established
The three dimensions range equation of punctuate;Finally have the particle cluster algorithm on multiple populations of pre- preferentially mechanism to constraining feelings using improved
Performance indicator under condition is iterated optimization, to realize effective tracking of the robot arm end effector to target point.The present invention
Manipulator motion planning optimal solution is finally obtained using improved particle cluster algorithm on multiple populations;And require no knowledge about executor tail end
Initial position, mechanical arm inverse kinematics need not more rapidly can also be restrained and be optimal and meet kinematic accuracy and refer to
Mark.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Obtain other attached drawings according to these attached drawings.
Fig. 1 is the schematic diagram of the mechanical arm modeling of the present invention.
Fig. 2 is the flow chart of present invention particle cluster algorithm on multiple populations.
Fig. 3 is the comparison figure of the present invention and the evaluation of other evolution algorithmics.
Fig. 4 is the trajectory diagram of the robot arm end effector of the present invention.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other under the premise of not making the creative labor
Embodiment shall fall within the protection scope of the present invention.
A kind of manipulator motion planning method based on particle cluster algorithm on multiple populations, its step are as follows:
Step 1:Sixdegree-of-freedom simulation is modeled using DH parametric methods, carries out mechanical arm positive kinematics solution.
The modeling of mechanical arm carries out mechanical arm positive kinematics solution with DH methods, what is established with first artis of mechanical arm
On the basis of basis coordinates system, a rectangular coordinate system is established in each joint, then obtains machine by the rotation and translation of coordinate system
Coordinate of the tool arm end effector in basis coordinates system.
Mechanical arm is modeled first, by taking the mechanical arm of six degree of freedom as an example, will be converted shown in mechanical arm such as Fig. 1 (b)
For the schematic diagram as shown in Fig. 1 (a), each artis establishes a coordinate system, is basis coordinates system at first artis,
In, point (0,0,0) is the origin of basis coordinates system, and (X-end, Y-end, Z-end) is seat of the mechanical arm tail end in basis coordinates system
Mark.The DH parameters of mechanical arm system are as shown in table 1, wherein ΘiIndicate the angle for rotating clockwise Z axis, DiIt indicates to press Y-axis
The distance of direction translation, aiIndicate the distance a by X-direction translationi, αiThe angle that expression rotates clockwise X-axis, i=1,
2 ..., l, l are the number of node.
The DH parameters of 1 mechanical arm system of table
Indicate that a coordinate system is converted to the rotation and translation of another coordinate system with matrix A, then Ai indicates i-th of coordinate
It is the transformation to i+1 coordinate system, i.e.,:
Wherein, (0, d Trani, 0) and it indicates to press Y direction translation distance di, Rot (x, αi) indicate to rotate clockwise X-axis
Angle [alpha]i, Rot (z, θi) indicate Z axis rotating clockwise angle, θi, Tran (ai, 0,0) and it indicates to press X-direction translation distance ai。
Then, the transformation matrix from basis coordinates system to the coordinate system in mechanical arm tail end coordinate system i.e. the 6th joint can use the following formula
It indicates:
(px, py, pz) be mechanical arm tail end coordinate.nx、
ny、nz、ox、oy、oz、ax、ay、azThe multiplication calculating of algebraic expression after representing matrix derivation, six matrixes is considerably complicated, does not do superfluous
It states.
Step 2:Evaluation letter is established by the space length of robot arm end effector in three-dimensional system of coordinate and setting target
Number.
Coordinate (the X of target pointt, Yt, Zt) indicate, then the space length of mechanical arm tail end to target point Fitness tables
Show, i.e., evaluation function is:
Step 3:The initialization function for improving conventional particle group's algorithm will show optimal several in multiple sub- populations
Particle forms an elite population, carries out EVOLUTIONARY COMPUTATION to elite population, obtains the particle of global optimum.
In algorithm initialization, relatively more sub- population is initialized, and select showed in each sub- population it is optimal
Several particles form new elite population, it is ensured that the particle in first generation elite population is entirely to show preferably particle, so
EVOLUTIONARY COMPUTATION is carried out to elite population afterwards, obtains the particle of global optimum.Machinery is realized with improved particle cluster algorithm on multiple populations
Motion planning of the arm from arbitrary initial position to target location, obtains optimal solution.
Traditional particle cluster algorithm is improved, the improvement of algorithm introduces the concept of sub- population and elite population,
Flow chart is as shown in Fig. 2, development is as follows:
The first step:N sub- populations are initialized, every sub- population includes the N number of particle generated at random;
Second step:As unit of single sub- population, Utilization assessment function Fitness evaluates the adaptation of wherein each particle
Value, and be ranked up by from excellent to bad, it selects and shows optimal preceding N/n particle, the table that then will be selected in every sub- population
Existing N/n optimal particle forms an elite population containing N number of particle;
Third walks:The parameter for initializing elite population carries out speed and location updating, profit to each particle in elite population
Its adaptive value is evaluated with evaluation function Fitness, its adaptive value is made comparisons with the desired positions pbest that it passes through, if compared with
It is good, then as current desired positions pbest;
Particle updates speed and the position of oneself by following two formula:
vk+1=ωkvk+c1r1(pk best–ak)+c2r2(gk best-ak)
ak+1=ak+vk
Wherein, vk+1And vkSpeed of the expression particle at k moment and k+1 moment respectively;ak+1It is the current location of particle, ak
For the position of particle eve;ωkFor inertial factor;pk bestAnd gk bestIndicate respectively k moment Particle Swarms part and it is global most
Excellent position;r1And r2It is the random number between (0,1) that rand () function generates;c1And c2It is Studying factors, usually
c1=c2=2;The maximum value of speed, i.e. maximum flying speed are vmax(being more than 0), if v is more than vmax, then v=vmax;It improves and calculates
The above-mentioned formula of method is consistent with the canonical form of traditional PS O.
4th step:It makes comparisons with the desired positions gbest in entire population to the current desired positions of each particle, if
Preferably, then it is stored as global desired positions gbest;Judge whether to meet global optimum's index, if not, returning to third
Step, if so, executing the 5th step;
5th step:The global best particle of selection simultaneously exports result.
Each posture of mechanical arm is regarded as a particle in population by the present invention, i.e., each particle stores mechanical arm
The evaluation function of mechanical arm is imported improved particle cluster algorithm on multiple populations and carried out by one group of angle value in six joints of a certain moment
Iteration develops, to find out the optimal posture of mechanical arm.The realization of particle cluster algorithm of the present invention uses Visual Studio
2015 Software Development Tools, running environment Windows.
Step 4:It is identical in parameter setting, realize that the motion planning of mechanical arm is asked with other evolution algorithmics
Topic, is compared with improved particle cluster algorithm on multiple populations in step 3, verifies the superiority of particle cluster algorithm on multiple populations.
In order to further verify the superiority for improving particle cluster algorithm, while with other five kinds of evolution algorithmics:DE (difference into
Change algorithm), GA (genetic algorithm), PSO (conventional particle group algorithm), DESPS (a kind of innovatory algorithm of DE) and DEAMECo (DE
Another innovatory algorithm) motion planning of mechanical arm is solved.Simulation software is MATLAB2014, and running environment is
Windows。
The parameter of above-mentioned each algorithm used is as shown in table 2, and the comparison of evaluation function is as shown in Figure 3.
Table 2.
As seen from Figure 3, the improved particle cluster algorithm (PSOEL) on multiple populations of the present invention is the most fast calculation of convergence rate
Thus method verifies the superiority of innovatory algorithm.At PSOEL, mechanical arm tail end it is as shown in Figure 4 with the movement locus of iteration.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
With within principle, any modification, equivalent replacement, improvement and so on should all be included in the protection scope of the present invention god.
Claims (5)
1. a kind of manipulator motion planning method based on particle cluster algorithm on multiple populations, which is characterized in that its step are as follows:
Step 1:Sixdegree-of-freedom simulation is modeled using DH parametric methods, mechanical arm positive kinematics is carried out and solves mechanical arm
Coordinate of the end effector in basis coordinates system;
Step 2:Evaluation function is established by robot arm end effector in three-dimensional system of coordinate and the space length of setting target;
Step 3:The initialization function for improving conventional particle group's algorithm, will show several optimal particles in multiple sub- populations
An elite population is formed, EVOLUTIONARY COMPUTATION is carried out to elite population, obtains the particle of global optimum;
Step 4:It is identical in parameter setting, the motion planning problem of mechanical arm is realized with other evolution algorithmics, with
Improved particle cluster algorithm on multiple populations is compared in step 3, verifies the superiority of particle cluster algorithm on multiple populations.
2. the manipulator motion planning method according to claim 1 based on particle cluster algorithm on multiple populations, which is characterized in that
On the basis of DH parametric methods are the basis coordinates system established with first artis of mechanical arm in the step 1, each joint is established
One rectangular coordinate system, point (0,0,0) are the origin of basis coordinates system, and (X-end, Y-end, Z-end) is mechanical arm tail end in base
Coordinate in coordinate system obtains coordinate of the robot arm end effector in basis coordinates system by the rotation and translation of coordinate system;
Ai indicates transformation of i-th of coordinate system to i+1 coordinate system, i.e.,:
Wherein, (0, d Trani, 0) and it indicates to press Y direction translation distance di, Rot (x, αi) indicate X-axis rotating clockwise angle
αi, Rot(Z, θi) indicate Z axis rotating clockwise angle, θi, Tran (ai, 0,0) and it indicates to press X-direction translation distance ai;
From basis coordinates system to the transformation matrix of mechanical arm tail end coordinate system following formula subrepresentation:
(px, py, pz) be mechanical arm tail end coordinate;nx、ny、nz、
ox、oy、oz、ax、ay、azAlgebraic expression after representing matrix derivation.
3. the manipulator motion planning method according to claim 2 based on particle cluster algorithm on multiple populations, which is characterized in that
The method for solving of evaluation function is in the step 2:If coordinate (the X of target pointt, Yt, Zt) indicate, then mechanical arm tail end arrives
The space length of target point indicates that is, evaluation function is with Fitness:
4. the manipulator motion planning method according to claim 1 based on particle cluster algorithm on multiple populations, which is characterized in that
Multiple sub- populations are initialized in the step 3, traditional particle cluster algorithm is improved, introduce sub- population and essence
English population, improved step:
The first step:N sub- populations are initialized, every sub- population includes the N number of particle generated at random;
Second step:As unit of single sub- population, Utilization assessment function Fitness evaluates the adaptive value of wherein each particle, and
It is ranked up by from excellent to bad, selects and show optimal preceding N/n particle, it is then that the performance selected in every sub- population is optimal
N/n particle form an elite population containing N number of particle;
Third walks:The parameter for initializing elite population, to each particle progress speed and location updating in elite population, using commenting
Valence function Fitness evaluates its adaptive value, its adaptive value is made comparisons with the desired positions pbest that it passes through, if preferably,
As current desired positions pbest;
4th step:It makes comparisons with the desired positions gbest in entire population to the current desired positions of each particle, if compared with
It is good, then it is stored as global desired positions gbest;Judge whether to meet global optimum's index, if not, returning to third
Step, if so, executing the 5th step;
5th step:The global best particle of selection simultaneously exports result.
5. the manipulator motion planning method according to claim 4 based on particle cluster algorithm on multiple populations, which is characterized in that
Particle in the third step in elite population updates its speed and position by following two formula:
vk+1=ωkvk+c1r1(pk best–ak)+c2r2(gk best-ak),
ak+1=ak+vk;
Wherein, vk+1And vkSpeed of the expression particle at k moment and k+1 moment respectively;ak+1It is the current location of particle, akFor grain
The position of sub- eve;ωkFor inertial factor;pk bestAnd gk bestPart and the global optimum position of k moment Particle Swarms are indicated respectively
It sets;r1And r2It is the random number between (0,1) that rand () function generates;c1And c2It is Studying factors;Speed is most
It is v that big value, which is maximum flying speed,maxIf speed vk+1More than vmax, then the speed is utilized to replace maximum flying speed:vmax=
vk+1。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810642320.5A CN108748160B (en) | 2018-06-21 | 2018-06-21 | Mechanical arm motion planning method based on multi-population particle swarm algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810642320.5A CN108748160B (en) | 2018-06-21 | 2018-06-21 | Mechanical arm motion planning method based on multi-population particle swarm algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108748160A true CN108748160A (en) | 2018-11-06 |
CN108748160B CN108748160B (en) | 2020-09-25 |
Family
ID=63979648
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810642320.5A Active CN108748160B (en) | 2018-06-21 | 2018-06-21 | Mechanical arm motion planning method based on multi-population particle swarm algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108748160B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111168684A (en) * | 2020-01-22 | 2020-05-19 | 西北工业大学深圳研究院 | On-orbit assembly sequence planning method for large-scale spatial structure |
CN111195915A (en) * | 2020-01-20 | 2020-05-26 | 深圳龙岗智能视听研究院 | Mechanical arm absolute positioning precision calibration method and system based on genetic algorithm |
CN111438687A (en) * | 2019-01-16 | 2020-07-24 | 发那科株式会社 | Determination device |
CN113219996A (en) * | 2021-06-07 | 2021-08-06 | 中国传媒大学 | Multi-path planning method for cultural complex equipment |
CN113733088A (en) * | 2021-09-07 | 2021-12-03 | 河南大学 | Mechanical arm kinematics self-calibration method based on binocular vision |
CN114265364A (en) * | 2021-12-21 | 2022-04-01 | 江苏师范大学 | Monitoring data processing system and method for industrial Internet of things |
CN114896736A (en) * | 2022-05-27 | 2022-08-12 | 太原理工大学 | Anchor rod drill carriage drill arm positioning control method and system based on improved particle swarm optimization |
CN115008468A (en) * | 2022-07-04 | 2022-09-06 | 中国科学院沈阳自动化研究所 | Mechanical arm attitude speed planning control method |
CN115107035A (en) * | 2022-07-26 | 2022-09-27 | 珞石(北京)科技有限公司 | Hybrid control method for monitoring robot single-joint artificial immune system |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2011055145A1 (en) * | 2009-11-05 | 2011-05-12 | Bae Systems Plc | Generating a set of solutions to a multi-objective problem |
CN103336526A (en) * | 2013-06-20 | 2013-10-02 | 苏州经贸职业技术学院 | Robot path planning method based on coevolution particle swarm rolling optimization |
CN103381603A (en) * | 2013-06-29 | 2013-11-06 | 湖南大学 | Autonomous obstacle crossing programming method of deicing and line inspecting robot for high-voltage transmission line |
CN104076685A (en) * | 2014-05-20 | 2014-10-01 | 大连大学 | Space manipulator path planning method for reducing base attitude disturbance |
CN105138000A (en) * | 2015-08-06 | 2015-12-09 | 大连大学 | Seven-freedom-degree space manipulator track planning method optimizing position and posture disturbance of pedestal |
WO2016045615A1 (en) * | 2014-09-25 | 2016-03-31 | 科沃斯机器人有限公司 | Robot static path planning method |
CN105719004A (en) * | 2016-01-18 | 2016-06-29 | 合肥工业大学 | Coevolution-based particle swarm optimization for solving multitask problems |
CN105988366A (en) * | 2015-02-13 | 2016-10-05 | 大连大学 | Space robot minimal base disturbance trajectory planning method |
CN107199569A (en) * | 2017-06-22 | 2017-09-26 | 华中科技大学 | A kind of articulated robot method for planning track distributed based on joint balancing energy |
-
2018
- 2018-06-21 CN CN201810642320.5A patent/CN108748160B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2011055145A1 (en) * | 2009-11-05 | 2011-05-12 | Bae Systems Plc | Generating a set of solutions to a multi-objective problem |
CN103336526A (en) * | 2013-06-20 | 2013-10-02 | 苏州经贸职业技术学院 | Robot path planning method based on coevolution particle swarm rolling optimization |
CN103381603A (en) * | 2013-06-29 | 2013-11-06 | 湖南大学 | Autonomous obstacle crossing programming method of deicing and line inspecting robot for high-voltage transmission line |
CN104076685A (en) * | 2014-05-20 | 2014-10-01 | 大连大学 | Space manipulator path planning method for reducing base attitude disturbance |
WO2016045615A1 (en) * | 2014-09-25 | 2016-03-31 | 科沃斯机器人有限公司 | Robot static path planning method |
CN105988366A (en) * | 2015-02-13 | 2016-10-05 | 大连大学 | Space robot minimal base disturbance trajectory planning method |
CN105138000A (en) * | 2015-08-06 | 2015-12-09 | 大连大学 | Seven-freedom-degree space manipulator track planning method optimizing position and posture disturbance of pedestal |
CN105719004A (en) * | 2016-01-18 | 2016-06-29 | 合肥工业大学 | Coevolution-based particle swarm optimization for solving multitask problems |
CN107199569A (en) * | 2017-06-22 | 2017-09-26 | 华中科技大学 | A kind of articulated robot method for planning track distributed based on joint balancing energy |
Non-Patent Citations (1)
Title |
---|
顾辰: "六自由度机械臂的动态路径规划和控制研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111438687A (en) * | 2019-01-16 | 2020-07-24 | 发那科株式会社 | Determination device |
CN111195915B (en) * | 2020-01-20 | 2022-07-15 | 深圳市鑫君特智能医疗器械有限公司 | Mechanical arm absolute positioning precision calibration method and system based on genetic algorithm |
CN111195915A (en) * | 2020-01-20 | 2020-05-26 | 深圳龙岗智能视听研究院 | Mechanical arm absolute positioning precision calibration method and system based on genetic algorithm |
CN111168684A (en) * | 2020-01-22 | 2020-05-19 | 西北工业大学深圳研究院 | On-orbit assembly sequence planning method for large-scale spatial structure |
CN113219996A (en) * | 2021-06-07 | 2021-08-06 | 中国传媒大学 | Multi-path planning method for cultural complex equipment |
CN113219996B (en) * | 2021-06-07 | 2022-08-19 | 中国传媒大学 | Multi-path planning method for cultural complex equipment |
CN113733088A (en) * | 2021-09-07 | 2021-12-03 | 河南大学 | Mechanical arm kinematics self-calibration method based on binocular vision |
CN113733088B (en) * | 2021-09-07 | 2024-05-14 | 河南大学 | Mechanical arm kinematics self-calibration method based on binocular vision |
CN114265364A (en) * | 2021-12-21 | 2022-04-01 | 江苏师范大学 | Monitoring data processing system and method for industrial Internet of things |
CN114265364B (en) * | 2021-12-21 | 2023-10-03 | 江苏师范大学 | Monitoring data processing system and method of industrial Internet of things |
CN114896736A (en) * | 2022-05-27 | 2022-08-12 | 太原理工大学 | Anchor rod drill carriage drill arm positioning control method and system based on improved particle swarm optimization |
CN114896736B (en) * | 2022-05-27 | 2024-04-09 | 太原理工大学 | Anchor rod drill carriage drill arm positioning control method and system based on improved particle swarm optimization |
CN115008468A (en) * | 2022-07-04 | 2022-09-06 | 中国科学院沈阳自动化研究所 | Mechanical arm attitude speed planning control method |
CN115107035A (en) * | 2022-07-26 | 2022-09-27 | 珞石(北京)科技有限公司 | Hybrid control method for monitoring robot single-joint artificial immune system |
CN115107035B (en) * | 2022-07-26 | 2023-01-06 | 珞石(北京)科技有限公司 | Hybrid control method for monitoring robot single-joint artificial immune system |
Also Published As
Publication number | Publication date |
---|---|
CN108748160B (en) | 2020-09-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108748160A (en) | Manipulator motion planning method based on particle cluster algorithm on multiple populations | |
CN105676642B (en) | A kind of six-DOF robot station layout and run duration cooperative optimization method | |
CN109343345B (en) | Mechanical arm polynomial interpolation track planning method based on QPSO algorithm | |
CN109676610B (en) | Circuit breaker assembly robot and method for realizing work track optimization | |
CN108241339A (en) | The movement solution of apery mechanical arm and configuration control method | |
CN111347429A (en) | Collision detection mechanical arm path planning method based on improved ant colony algorithm | |
CN107450376B (en) | A kind of service mechanical arm crawl attitude angle calculation method based on intelligent family moving platform | |
CN109202904A (en) | A kind of the determination method and determining system in manipulator motion path | |
JP2010058260A (en) | Method for controlling motion of robot based on evolutionary algorithm and imitation learning | |
CN109344477B (en) | 6-degree-of-freedom mechanical arm inverse kinematics solving method | |
CN117103282B (en) | Double-arm robot cooperative motion control method based on MATD3 algorithm | |
CN104678766A (en) | Method for solving optimal batting configuration for flight ball body operation of humanoid manipulator | |
CN111157002B (en) | Aircraft 3D path planning method based on multi-agent evolutionary algorithm | |
CN115890670A (en) | Method for training motion trail of seven-degree-of-freedom redundant mechanical arm based on intensive deep learning | |
Tian | Research on robot optimal path planning method based on improved ant colony algorithm | |
CN112684709B (en) | Cluster tracking kinematics modeling method, device and storage medium | |
JP2021169149A (en) | Disassembly based assembly planning | |
Lai et al. | Self-learning for a humanoid robotic ping-pong player | |
CN107066654A (en) | Towards the TRAJECTORY CONTROL dot picking method and apparatus in the enveloped box face of point cloud model | |
CN114536351B (en) | Redundant double-arm robot teaching method and device, electronic equipment and system | |
CN116501034A (en) | VEX robot path planning method based on transfer reinforcement learning | |
Tang et al. | Coordinated motion planning of dual-arm space robot with deep reinforcement learning | |
Naderi et al. | A reinforcement learning approach to synthesizing climbing movements | |
Nagata et al. | Neural network-based inverse kinematics for an industrial robot and its learning method | |
CN113848725A (en) | Mechanical arm time optimal trajectory planning and optimizing method based on adaptive genetic algorithm |
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 |