Direct Trajectory Planning Method Based on IEPSO and Fuzzy Rewards and Punishment Theory for Multi-Degree-of Freedom Manipulators
Manipulator is a kind of commonly used multi-degree-of-freedom nonlinear system. There is a strong coupling between the links, and the movement of each link constraints and affects each other, which increases the difficulty of motion analysis of the system and reduces its trajectory planning efficie...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8638767/ |
| _version_ | 1818379683732914176 |
|---|---|
| author | Xueying Lv Zhaoxia Yu Mingyang Liu Guanyu Zhang Liu Zhang |
| author_facet | Xueying Lv Zhaoxia Yu Mingyang Liu Guanyu Zhang Liu Zhang |
| author_sort | Xueying Lv |
| collection | DOAJ |
| description | Manipulator is a kind of commonly used multi-degree-of-freedom nonlinear system. There is a strong coupling between the links, and the movement of each link constraints and affects each other, which increases the difficulty of motion analysis of the system and reduces its trajectory planning efficiency under specific task targets. To solve this problem, a direct trajectory planning method based on an improved particle swarm optimization (PSO) algorithm, called IEPSO, and the fuzzy rewards and punishment theory is proposed in this paper. First, on the basis of preserving the local search ability of PSO, the global search ability of the population is improved by increasing a population exchange item. At the same time, in order to avoid the population falling into the local optimal value, the last elimination principle is incorporated into the standard PSO algorithm. Second, the fuzzy rewards and punishment theory is introduced to reduce the redundant decoupling operation, which can not only ensure the accuracy of manipulator trajectory planning but also effectively reduce the calculation amount of the trajectory planning for the multi-degree-of-freedom manipulator, to improve the optimization efficiency. Finally, the direct trajectory planning method of the multi-degree-of-freedom manipulator is compared and tested. It can be seen that the efficiency scalar and accuracy of the proposed direct trajectory planning method are significantly higher than those of other optimization methods. |
| first_indexed | 2024-12-14T02:06:41Z |
| format | Article |
| id | doaj.art-fe8e74829bc9436b88c1f20e8ea050b3 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T02:06:41Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-fe8e74829bc9436b88c1f20e8ea050b32022-12-21T23:20:53ZengIEEEIEEE Access2169-35362019-01-017204522046110.1109/ACCESS.2019.28982188638767Direct Trajectory Planning Method Based on IEPSO and Fuzzy Rewards and Punishment Theory for Multi-Degree-of Freedom ManipulatorsXueying Lv0Zhaoxia Yu1Mingyang Liu2Guanyu Zhang3https://orcid.org/0000-0002-3108-5604Liu Zhang4College of Instrumentation and Electrical Engineering, Jilin University, Changchun, ChinaShanghai Institute of Satellite Engineering, Shanghai, ChinaCollege of Instrumentation and Electrical Engineering, Jilin University, Changchun, ChinaCollege of Instrumentation and Electrical Engineering, Jilin University, Changchun, ChinaCollege of Instrumentation and Electrical Engineering, Jilin University, Changchun, ChinaManipulator is a kind of commonly used multi-degree-of-freedom nonlinear system. There is a strong coupling between the links, and the movement of each link constraints and affects each other, which increases the difficulty of motion analysis of the system and reduces its trajectory planning efficiency under specific task targets. To solve this problem, a direct trajectory planning method based on an improved particle swarm optimization (PSO) algorithm, called IEPSO, and the fuzzy rewards and punishment theory is proposed in this paper. First, on the basis of preserving the local search ability of PSO, the global search ability of the population is improved by increasing a population exchange item. At the same time, in order to avoid the population falling into the local optimal value, the last elimination principle is incorporated into the standard PSO algorithm. Second, the fuzzy rewards and punishment theory is introduced to reduce the redundant decoupling operation, which can not only ensure the accuracy of manipulator trajectory planning but also effectively reduce the calculation amount of the trajectory planning for the multi-degree-of-freedom manipulator, to improve the optimization efficiency. Finally, the direct trajectory planning method of the multi-degree-of-freedom manipulator is compared and tested. It can be seen that the efficiency scalar and accuracy of the proposed direct trajectory planning method are significantly higher than those of other optimization methods.https://ieeexplore.ieee.org/document/8638767/Improved particle swarm optimization algorithmfuzzy rewards and punishment theorytrajectory planningmulti-degree-of-freedom manipulators |
| spellingShingle | Xueying Lv Zhaoxia Yu Mingyang Liu Guanyu Zhang Liu Zhang Direct Trajectory Planning Method Based on IEPSO and Fuzzy Rewards and Punishment Theory for Multi-Degree-of Freedom Manipulators IEEE Access Improved particle swarm optimization algorithm fuzzy rewards and punishment theory trajectory planning multi-degree-of-freedom manipulators |
| title | Direct Trajectory Planning Method Based on IEPSO and Fuzzy Rewards and Punishment Theory for Multi-Degree-of Freedom Manipulators |
| title_full | Direct Trajectory Planning Method Based on IEPSO and Fuzzy Rewards and Punishment Theory for Multi-Degree-of Freedom Manipulators |
| title_fullStr | Direct Trajectory Planning Method Based on IEPSO and Fuzzy Rewards and Punishment Theory for Multi-Degree-of Freedom Manipulators |
| title_full_unstemmed | Direct Trajectory Planning Method Based on IEPSO and Fuzzy Rewards and Punishment Theory for Multi-Degree-of Freedom Manipulators |
| title_short | Direct Trajectory Planning Method Based on IEPSO and Fuzzy Rewards and Punishment Theory for Multi-Degree-of Freedom Manipulators |
| title_sort | direct trajectory planning method based on iepso and fuzzy rewards and punishment theory for multi degree of freedom manipulators |
| topic | Improved particle swarm optimization algorithm fuzzy rewards and punishment theory trajectory planning multi-degree-of-freedom manipulators |
| url | https://ieeexplore.ieee.org/document/8638767/ |
| work_keys_str_mv | AT xueyinglv directtrajectoryplanningmethodbasedoniepsoandfuzzyrewardsandpunishmenttheoryformultidegreeoffreedommanipulators AT zhaoxiayu directtrajectoryplanningmethodbasedoniepsoandfuzzyrewardsandpunishmenttheoryformultidegreeoffreedommanipulators AT mingyangliu directtrajectoryplanningmethodbasedoniepsoandfuzzyrewardsandpunishmenttheoryformultidegreeoffreedommanipulators AT guanyuzhang directtrajectoryplanningmethodbasedoniepsoandfuzzyrewardsandpunishmenttheoryformultidegreeoffreedommanipulators AT liuzhang directtrajectoryplanningmethodbasedoniepsoandfuzzyrewardsandpunishmenttheoryformultidegreeoffreedommanipulators |