摘要
机器人化装配是一个复杂的动力学过程 ,在高速装配时不可避免地会对工件造成损伤 .为了寻求解决该问题的有效方法 ,根据采用阻抗控制方法推导出的装配过程的动力学方程 ,提出了一种采用径向基函数网络 (RBFN)来学习装配过程动力学的渐进学习机制和通过梯度下降法调整阻抗参数的强化学习算法 .数值仿真结果证明了该方法的有效性和渐进学习的优越性 .
Robotic assembly is a complicated dynamic process. High speed assembly may incur serious damage to robotic systems and workpieces. In order to find out an effective method to resolve the problem, this paper presents a progressive learning strategy of RBFN to learn the dynamics of the assembly process. We then implement an intensified learning algorithm using gradient search method to adjust impedance components. All of the strategies are based on the dynamic equations that are derived on the basis of the concept of impedance control. Computational simulation results are given to demonstrate the effectiveness and advantage of the approach.
出处
《自动化学报》
EI
CSCD
北大核心
2000年第2期169-175,共7页
Acta Automatica Sinica
基金
国家自然科学基金
关键词
阻抗控制
装配动力学
机器人
自适应控制
Impedance control, assembly dynamics, gradient search method, progressive learning, radial basis function network (RBFN).
