CN109465834A - A kind of mechanical arm fast worktodo planing method based on planning knowledge base - Google Patents
A kind of mechanical arm fast worktodo planing method based on planning knowledge base Download PDFInfo
- Publication number
- CN109465834A CN109465834A CN201910006488.1A CN201910006488A CN109465834A CN 109465834 A CN109465834 A CN 109465834A CN 201910006488 A CN201910006488 A CN 201910006488A CN 109465834 A CN109465834 A CN 109465834A
- Authority
- CN
- China
- Prior art keywords
- task
- planning
- knowledge base
- environment
- mechanical arm
- 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.)
- Pending
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
- B25J9/1661—Programme controls characterised by programming, planning systems for manipulators characterised by task planning, object-oriented languages
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
Abstract
The embodiment of the invention provides a kind of mechanical arm mission planning methods based on planning knowledge base, on the one hand, the embodiment of the present invention obtains task whole story position, environmental information and predecessor's business planing method；To, task space environmental constraints information has been compared with the environmental information for planning planning tasks unit in knowledge base based on planning knowledge base principle, the random road sign map in planning tasks unit is obtained in planning knowledge base, point sequence among the executable task between whole story position is searched for；Finally, completing the mission planning of mechanical arm according to point sequence among gained task and executable predecessor's business planing method.
Description
[technical field]
The present invention relates to a kind of mechanical arm fast path planing methods based on planning knowledge base, belong to manipulator motion rule
Draw technical field.
[background technique]
With the fast development of science and technology, has many advantages, such as the high high-freedom degree mechanical arm of flexible operation, precision
It is widely used in the fields such as industrial production, aerospace.Industrial production environment constraint is numerous, when mechanical arm executes mobile task
It tends not to that robotic arm path planning algorithm is directly utilized to solve manipulator motion track.Mechanical arm mission planning technology is as rule
Draw system it is top, be responsible for complex task reception, analysis, dismantling, it is impossible to directly planning complete task dismantling be can
Directly carry out the former task sequence of path planning.The ability to work for being proposed for improving mechanical arm of mission planning technology increases
Mechanical arm can operational readiness be of crucial importance.
It is existing to be planned immediately about mechanical arm mission planning method using random road sign Map Method, i.e., often receive a new rule
When the task of drawing, first building adapts to the random road sign map of this task space environmental constraints, searches again for the task intermediate point in map
Sequence completes the dismantling of complicated movement task.After planning is completed, constructed random road sign map is destroyed immediately, algorithm rule
Draw inefficiency.
[summary of the invention]
In view of this, the embodiment of the invention provides a kind of mechanical arm fast path planning sides based on planning knowledge base
Method, to solve the problems, such as that efficiency of algorithm is not able to satisfy complex task requirement in the prior art.
During the above-mentioned mechanical arm fast path planing method based on planning knowledge base, the method used is included at least:
Acquisition task whole story position, the executable predecessor's business planing method of mechanical arm and task space environmental constraints, predecessor's business
Planing method is specially joint of mechanical arm space path planing method；
According to manipulator motion whole story position, task space environmental constraints and its execute predecessor business planing method, based on advise
Draw point sequence among the executable task between knowledge base principle acquisition whole story position；
According to point sequence among gained task and executable planing method of being engaged in of formerly helding the post of, the mission planning of mechanical arm is completed.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, according to mechanical arm
Movement whole story position, task space environmental constraints and its execute predecessor business planing method, based on planning knowledge base principle obtain beginning
Last bit set between executable task among point sequence, comprising:
Saving element in definition planning knowledge base is the TU task unit planned, wherein each TU task unit includes task ring
Border information matrix M, environmental characteristic λ, learn to obtain random road sign map G；
According to planning knowledge base principle, by job order in the mechanical arm task space environmental constraints and all planning knowledge bases
The task environment information matrix of member is matched；
According to matching result, point sequence among search or the executable task of planning.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, according to planning knowledge
Library principle, by the task space ring of known task unit in the mechanical arm task space environmental constraints and all planning knowledge bases
Border constraint is matched, comprising:
Task space environmental constraints, referred to as environmental information matrix M are characterized using three-dimensional matrice M, construction method is in office
The information of each position is extracted in business space environment constraint information, if coordinate is then to enable at (i, j, k) with the presence of environmental constraints
Element M in three-dimensional matrice Mijk=1, conversely, Mijk=0；
This task environment information matrix is compared with the environment matrix in each TU task unit in planning knowledge base, is obtained
To comparing result；
If comparing result is that two matrixes are equal, then it is assumed that task space environmental constraints are identical, if comparing result is two
Matrix etc., then by the environmental information in other TU task units in this step 2 the method comparison planning knowledge base, if knowing
Know in library and be not present and the matched TU task unit of task space environmental constraints, then it is assumed that task space environmental constraints and planning knowledge
Any TU task unit all mismatches in library.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, by this task ring
Border information matrix is compared with the environment matrix in each TU task unit in planning knowledge base, obtains comparing result, comprising:
Solve the number of the element " 1 " of three-dimensional environment matrix, referred to as environmental characteristic λ；
Compare the environmental characteristic of two environment matrixes；
If environmental characteristic etc., then it is assumed that two matrixes are unequal, if environmental characteristic is equal, by the ring of element comparison task
Environment matrix in border matrix and planning knowledge base TU task unit, judges whether two matrixes are equal.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, according to matching result
Point sequence among executable task is planned in search, comprising:
If the environmental information of a TU task unit exactly matches in task space environmental constraints and planning knowledge base, directly mention
The random road sign map in the TU task unit is taken, searches for program results in random road sign map using random road sign Map Method,
Intermediate point sequence is the shortest path mark sequence in random road sign map from task initial position to target position；
If any TU task unit all mismatches in task space environmental constraints and planning knowledge base, plans and save again
Task result under this environment.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, if task space
Any TU task unit all mismatches in environmental constraints and planning knowledge base, then plans again and save the task knot under this environment
Fruit, comprising:
Using the random road sign map of random road sign Map Method planing method building mechanical arm in such circumstances, and agree to machine
Road sign Map Method searches for point sequence among from initial position to the task of target position in map, and intermediate point sequence is as random
Shortest path mark sequence in road sign map from task initial position to target position；
Using the environmental information matrix M of the task, environmental characteristic λ, learn random road sign map G as a new task unit
It saves to planning knowledge base, TU task unit is stored in planning knowledge base as a mission planning result and uses this to subsequent
Secondary program results.
[Detailed description of the invention]
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it is therefore apparent that drawings in the following description are only some embodiments of the invention, common for this field
For technical staff, under the premise of not paying creative and laborious, it can also be obtained according to these attached drawings other attached drawings.
Fig. 1 is the flow diagram of the mission planning method of mechanical arm provided by the embodiment of the present invention；
Fig. 2 is to utilize the mechanical arm mission planning embodiment of the method provided in an embodiment of the present invention based on planning knowledge base
Flow diagram；
Fig. 3 is to utilize the structural representation that knowledge base is planned in mechanical arm mission planning method provided by the embodiment of the present invention
Figure；
Fig. 4 is the task optimization effect contrast figure using mechanical arm mission planning method provided by the embodiment of the present invention.
[specific embodiment]
For a better understanding of the technical solution of the present invention, being retouched in detail to the embodiment of the present invention with reference to the accompanying drawing
It states.
It will be appreciated that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Base
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts it is all its
Its embodiment, shall fall within the protection scope of the present invention.The embodiment of the present invention provides a kind of mission planning method of space manipulator,
Referring to FIG. 1, its flow diagram for the mission planning method of space manipulator provided by the embodiment of the present invention, such as Fig. 1
It is shown, method includes the following steps:
Mechanical arm task whole story position, task space environmental constraints and predecessor's business planing method, business side of formerly helding the post of are obtained first
Method is mechanical arm basic joint space path planing method, and this method can construct the path of task whole story position, the road Dan Ruoci
Diameter is unsatisfactory for task space environmental constraints, then planning failure, and mechanical arm need to use mission planning method at this time.
The complex task that mechanical arm mission planning will be unsatisfactory for constraint is planned to a series of executable former task sequences,
Be characterized as point sequence among task herein, specific method referring to FIG. 2, specifically includes the following steps:
The task space environmental constraints extracted can be characterized as three-dimensional matrice M, save mechanical arm workspace by pixel
Environmental information in domain.It is assumed that mechanical arm working region is the square that side length is l, n is divided by square is latticed3A side
The identical small square of a length of l/n, wherein n is the measurement of equal part.If then being enabled at coordinate (i, j, k) with the presence of environmental constraints
Element M in three-dimensional matrice Mijk=1, conversely, Mijk=0.
The matrix character λ, λ for extracting task environment matrix M are the number for the element that environment matrix M intermediate value is 1.
It can be applied to current scene with the presence or absence of planning information in retrieval planning knowledge base, planning knowledge base includes more
A TU task unit is stored in the environment matrixes of planning tasks, environmental characteristic in TU task unit and plans random road sign map,
Its specific structure please refers to Fig. 3.
The environment matrix character and the environment matrix character in TU task unit for comparing task space environmental constraints；If two environment
Feature is unequal, then it is assumed that task space environmental constraints are not identical as the task space environmental constraints of this TU task unit；If two rings
Border feature is equal, then continues the environment matrix for comparing task space environmental constraints and the environment matrix in compared TU task unit.
If two environment matrixes are equal, then it is assumed that the task space environmental constraints of task space environmental constraints and this TU task unit
It is identical, then it is assumed that the constraint of mechanical arm current task space environment is identical as the task space environmental constraints of this TU task unit；
If two environment matrixes are unequal, then it is assumed that the task space environmental constraints of current task and the task space environment of this TU task unit
Constraint is different.
If the environment matrix of current task space environment constraint is different from the task space environmental constraints of this TU task unit,
The TU task unit in other planning knowledge bases is retrieved, until there are the task space environmental constraints and current task of a TU task unit
Space environment constrains identical or TU task unit until being not present in planning knowledge base with current task space environment constrained matching.
If the constraint of current task space environment is identical as the task space environmental constraints of a TU task unit, this task is extracted
Random road sign map in unit, the point sequence among search mission in road sign map complete mission planning process.
If planning, there is no the task space environmental constraints of TU task unit and current task space environment to constrain in knowledge base
It is identical, then the random road sign map under this task space environmental constraints, and random road herein are planned using random road sign Map Method
Search mission centre point sequence in map is marked, mission planning process is completed；After completing search process, by the task environment of the task
Information matrix M, environmental characteristic λ, learn random road sign map G is saved as a new task unit to planning knowledge base.
Planing method design planning is tested according to the above method, and side described in task with traditional planing method and this patent is respectively adopted
Method is planned that program results are as shown in Figure 4, it can be seen that the mission planning time can reduce using this patent the method,
Planning efficiency is improved, there is very strong application value in engineering practice.
As can be seen from the above technical solutions, the embodiment of the present invention has the advantages that
The technical solution provided according to embodiments of the present invention, the task intermediate point sequence between available task whole story position
Column, to complete the planning of complex task using task intermediate point；Moreover, by introducing planning knowledge base, with TU task unit shape
Formula saves the program results under each varying environment, can efficiently use each projected resources, substantially reduce in actual operation
The mechanical arm mission planning time improves operating efficiency.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of the present invention.
Claims (6)
1. a kind of mechanical arm mission planning method based on planning knowledge base, it is characterised in that method includes the following steps:
(1) task whole story position, the executable predecessor's business planing method of mechanical arm and task space environmental constraints, predecessor's business rule are obtained
The method of drawing is specially joint of mechanical arm space path planing method；
(2) according to manipulator motion whole story position, task space environmental constraints and its execute predecessor business planing method, based on plan
Knowledge base principle obtains point sequence among the executable task between whole story position；
(3) according to point sequence among gained task and executable planing method of being engaged in of formerly helding the post of, the mission planning of mechanical arm is completed.
2. the method according to claim 1, wherein realizing described according to manipulator motion whole story position, task
Space environment constraint executes business planing method of formerly helding the post of with it, and executable between whole story position is obtained based on planning knowledge base principle
The process of point sequence includes at least among being engaged in:
(1) defining and saving element in planning knowledge base is the TU task unit planned, wherein each TU task unit includes task ring
Border information matrix M, environmental characteristic λ, learn to obtain random road sign map G；
(2) according to planning knowledge base principle, by job order in the mechanical arm task space environmental constraints and all planning knowledge bases
The task environment information matrix of member is matched；
(3) according to matching result, search or the executable task centre point sequence of planning.
3. according to the method described in claim 2, it is characterized in that, according to planning knowledge base principle, by the mechanical arm task sky
Between in environmental constraints and all planning knowledge bases the space environment constraint of known task unit carry out matched process and include at least:
(1) task space environmental constraints, referred to as environmental information matrix M are characterized using three-dimensional matrice M, construction method is in task
The information of each position is extracted in space environment constraint information, if coordinate is then to enable three with the presence of environmental constraints at (i, j, k)
Tie up the element M in matrix Mijk=1, conversely, Mijk=0；
(2) this task environment information matrix is compared with the environment matrix in each TU task unit in planning knowledge base, is obtained
To comparing result；
(3) if comparing result is that two matrixes are equal, then it is assumed that task space environmental constraints are identical, if comparing result is two squares
Battle array differs, then by the environment letter in other TU task units in this 2 the method for claim steps comparison planning knowledge base
Breath, if in knowledge base be not present and the matched TU task unit of task space environmental constraints, then it is assumed that task space environmental constraints with
Any TU task unit all mismatches in planning knowledge base.
4. according to the method described in claim 3, it is characterized in that, by every in this task environment information matrix and planning knowledge base
Environment matrix in a TU task unit is compared, and the process for obtaining comparing result includes at least:
(1) number of the element " 1 " of three-dimensional environment matrix, referred to as environmental characteristic λ are solved；
(2) environmental characteristic of two environment matrixes is compared；
(3) if environmental characteristic etc., then it is assumed that two matrixes are unequal, if environmental characteristic is equal, by the ring of element comparison task
Environment matrix in border matrix and planning knowledge base TU task unit, judges whether two matrixes are equal.
5. according to the method described in claim 2, it is characterized in that, executable task intermediate point is searched for or planned according to matching result
The process of sequence includes at least:
(1) it if the environmental information of a TU task unit exactly matches in task space environmental constraints and planning knowledge base, directly mentions
The random road sign map in the TU task unit is taken, searches for program results in random road sign map using random road sign Map Method,
Intermediate point sequence is the shortest path mark sequence in random road sign map from task initial position to target position；
(2) it if any TU task unit all mismatches in task space environmental constraints and planning knowledge base, plans and saves again
Task result under this environment.
6. according to the method described in claim 5, it is characterized in that, if task space environmental constraints with planning knowledge base in it is any
TU task unit all mismatches, then plans again and the process for saving the task result under this environment includes at least:
(1) the random road sign map using random road sign Map Method planing method building mechanical arm in such circumstances, and agree to machine
Road sign Map Method searches for point sequence among from initial position to the task of target position in map, and intermediate point sequence is as random
Shortest path mark sequence in road sign map from task initial position to target position；
(2) using the environmental information matrix M of the task, environmental characteristic λ, learn random road sign map G as a new task unit
It saves to planning knowledge base, TU task unit is stored in planning knowledge base as a mission planning result and uses this to subsequent
Secondary program results.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910006488.1A CN109465834A (en) | 2019-01-04 | 2019-01-04 | A kind of mechanical arm fast worktodo planing method based on planning knowledge base |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910006488.1A CN109465834A (en) | 2019-01-04 | 2019-01-04 | A kind of mechanical arm fast worktodo planing method based on planning knowledge base |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109465834A true CN109465834A (en) | 2019-03-15 |
Family
ID=65677601
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910006488.1A Pending CN109465834A (en) | 2019-01-04 | 2019-01-04 | A kind of mechanical arm fast worktodo planing method based on planning knowledge base |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109465834A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113967913A (en) * | 2021-10-22 | 2022-01-25 | 中冶赛迪上海工程技术有限公司 | Motion planning method and system of steel grabbing device |
| CN114580576A (en) * | 2022-05-05 | 2022-06-03 | 中国科学院自动化研究所 | Robot task planning method and device based on knowledge processing |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120165982A1 (en) * | 2010-12-27 | 2012-06-28 | Samsung Electronics Co., Ltd. | Apparatus for planning path of robot and method thereof |
| JP5162530B2 (en) * | 2008-12-22 | 2013-03-13 | 韓國電子通信研究院 | Robot task model generation and execution method and apparatus |
| CN104462188A (en) * | 2014-10-23 | 2015-03-25 | 北京空间飞行器总体设计部 | Spacecraft intelligent task planning test method and system |
| CN107291811A (en) * | 2017-05-18 | 2017-10-24 | 浙江大学 | A kind of sense cognition enhancing robot system based on high in the clouds knowledge fusion |
-
2019
- 2019-01-04 CN CN201910006488.1A patent/CN109465834A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5162530B2 (en) * | 2008-12-22 | 2013-03-13 | 韓國電子通信研究院 | Robot task model generation and execution method and apparatus |
| US20120165982A1 (en) * | 2010-12-27 | 2012-06-28 | Samsung Electronics Co., Ltd. | Apparatus for planning path of robot and method thereof |
| CN104462188A (en) * | 2014-10-23 | 2015-03-25 | 北京空间飞行器总体设计部 | Spacecraft intelligent task planning test method and system |
| CN107291811A (en) * | 2017-05-18 | 2017-10-24 | 浙江大学 | A kind of sense cognition enhancing robot system based on high in the clouds knowledge fusion |
Non-Patent Citations (1)
| Title |
|---|
| 黄旭东: "多约束条件下空间机械臂多目标任务规划方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113967913A (en) * | 2021-10-22 | 2022-01-25 | 中冶赛迪上海工程技术有限公司 | Motion planning method and system of steel grabbing device |
| CN113967913B (en) * | 2021-10-22 | 2024-03-26 | 中冶赛迪上海工程技术有限公司 | Motion planning method and system for steel grabbing device |
| CN114580576A (en) * | 2022-05-05 | 2022-06-03 | 中国科学院自动化研究所 | Robot task planning method and device based on knowledge processing |
| CN114580576B (en) * | 2022-05-05 | 2022-09-06 | 中国科学院自动化研究所 | Robot task planning method and device based on knowledge processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110207710B (en) | Robot repositioning method and device | |
| US9075938B2 (en) | Method and apparatus for mapping of multiple-floor structures | |
| Behring et al. | An algorithm for robot path planning with cellular automata | |
| CN102495927B (en) | Space dimension chain tolerance analytical method based on graphic representation | |
| CN109839927B (en) | Method and device for robot path planning | |
| CN109465834A (en) | A kind of mechanical arm fast worktodo planing method based on planning knowledge base | |
| CN107146026A (en) | A kind of space planning land used difference automatic synchronization method | |
| Garcia et al. | GPU-based dynamic search on adaptive resolution grids | |
| CN105869512A (en) | Multi-information mixed measurement mapping method and device | |
| CN110802601A (en) | Robot path planning method based on fruit fly optimization algorithm | |
| US10628976B2 (en) | Information processing system, information processing method, and storage medium | |
| CN109073390A (en) | A kind of localization method and device, electronic equipment and readable storage medium storing program for executing | |
| Chen et al. | Planning to build block structures with unstable intermediate states using two manipulators | |
| Zhang et al. | A mip-based approach for multi-robot geometric task-and-motion planning | |
| Portugal et al. | Extracting Topological Information from Grid Maps for Robot Navigation. | |
| Idjaton et al. | Transformers with YOLO network for damage detection in limestone wall images | |
| CN115437372B (en) | Robot path planning method and device, electronic equipment and storage medium | |
| Worcester et al. | Distributed assembly with online workload balancing and visual error detection and correction | |
| Abdymanapov et al. | Motion planning algorithms using DISC | |
| US20230001920A1 (en) | Method and system for narrow passage path sampling based on levy flight | |
| US20120075415A1 (en) | Method and system for removing redundancy from among panoramic images, and computer-readable recording medium | |
| Yongxiang et al. | Improvement and application of heuristic search in multi-robot path planning | |
| CN102456073A (en) | Partial extremum inquiry method | |
| JP7359207B2 (en) | Polygon search method | |
| Mantzouratos et al. | On embeddability of modular robot designs |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190315 |
|
| WD01 | Invention patent application deemed withdrawn after publication |