A hybrid strategy to solve the forward kinematics problem in parallel manipulators
A hybrid strategy to solve the forward kinematics problem in parallel manipulators
复制标题
DOI：
10.1109/tro.2004.833801
复制
发表时间：
2005-02-01
影响因子：
7.8
通讯作者：
Lam, SSY
中科院分区：
文献类型：
--
作者：
Parikh, PJ;Lam, SSY
并联机械臂是一种封闭的运动结构，具有必要的刚度，可以提供高的有效载荷与自重比，适用于制造、飞行仿真系统和医疗机器人的许多应用。由于该机构结构封闭，其运动控制难度较大。该类机械手的逆运动学问题有数学解；然而，正运动学问题（FKP）在数学上是难以解决的。本文解决了FKP问题，提出了一种基于神经网络的混合策略，该策略将问题解决到所需的精度水平，并且可以实时实现解决方案。两个神经网络概念使用改进形式的多层感知器与反向传播学习实现。然后将性能更好的概念与标准牛顿-拉夫森数值技术相结合，产生混合解决策略。在飞行仿真系统上进行了仿真研究，验证了该方法的有效性。的方法。该策略在不到2次迭代和0.02 s的执行时间内实现了接近0.01 mm和0.01度的位置和方向参数精度。
A parallel manipulator is a closed kinematic structure with the necessary rigidity to provide a high payload to self-weight ratio suitable for many applications in manufacturing, flight simulation systems, and medical robotics. Because of its closed structure, the kinematic control of such a mechanism is difficult. The inverse kinematics problem for such manipulators hag a mathematical solution; however, the forward kinematics problem (FKP) is mathematically intractable. This paper addresses the FKP and proposes a neural-network-based hybrid strategy that solves the problem to a desired level of accuracy, and can achieve the solution in real time. Two neural-network concepts using a modified form of multilayered perceptrons with backpropagation learning were implemented. The better performing concept was then combined with a standard Newton-Raphson numerical technique to yield a hybrid solution strategy. Simulation studies were carried out on a flight simulation system to check the validity of the. approach. Accuracy of close to 0.01 mm and 0.01 degrees in the position and orientation parameters was achieved in less than two iterations and 0.02 s of execution time for the proposed strategy.