Issue |
JNWPU
Volume 37, Number 3, June 2019
|
|
---|---|---|
Page(s) | 488 - 495 | |
DOI | https://doi.org/10.1051/jnwpu/20193730488 | |
Published online | 20 September 2019 |
Solving Approach of Inverse Kinematics for Manipulators Based on Improved Adaptive Niche Genetic Algorithm
基于改进自适应小生境遗传算法的机械臂逆运动学求解
1
School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, 710072, China
2
National Key Laboratory of Underwater Information and Control, Xi’an, 710072, China
Received:
24
May
2018
Solving the inverse kinematics for a manipulator is of great importance to the manipulator's pose control and trajectory planning. Aiming at the poor generality and difficulty of finding an optimal solution from the multiple inverse kinematics solutions, a novel solution approach based on the modified adaptive niche genetic algorithm is proposed in this study. The principle of 'most suppleness' is integrated into the fitness function such that the only optimal solution can be found; The clustering is introduced into the approach for enhancing the generality and the genetic algorithm is improved for increasing the convergence speed and accuracy. Simulation results based on a six degree of freedom manipulator show that the proposed approach is effective and high precision, and can find the optimal solution.
摘要
逆运动学求解对机械臂位姿控制和轨迹规划具有重要意义,针对逆运动学求解存在多解及通用性差的问题,提出了一种基于改进自适应小生境遗传算法的逆运动学求解算法。适应度函数融合位姿误差和"最柔顺"原则,不存在多解及奇异解问题;引入减法聚类分析,提升算法通用性;对遗传算法进行改进,提升了算法收敛速度及精度。利用六自由度机械臂进行仿真实验,结果表明该算法收敛快、精度高,可求得唯一解。
Key words: inverse kinematics (IK) / manipulator / adaptive niche / genetic algorithm / optimal solution
关键字 : 逆运动学 / 自适应小生境 / 遗传算法
© 2019 Journal of Northwestern Polytechnical University. All rights reserved.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.