摘要
基于ＰＵＭＡ５６０工业机器人的第２，３关节设计了位置／力混合控制器。在力控制环建立了基于ＢＰ网络的自适应ＰＩＤ控制器，该网络可辩识所接触环境的动力学特性。实验表明，这种位置／力混合控制器经训练后，不仅能对训练样本所代表的环境作出正确响应，而且对介于样本之间的环境有很强的自适应能力。
A hybrid position/force controller is designed for the joint 2 and joint 3 of PUMA 560 industrial robot. An adaptive PID controller Which utilizes a BP network is also devised in the force control loop. This network can identify the dynamics of the contacting environment. The experiments' results show that after having been trained, the hybrid controller not only can have good response for the training patterns but also have stronger adaptive ability to the situation between the trainjng patterns.
出处
《哈尔滨工业大学学报》
EI
CAS
CSCD
北大核心
1995年第1期118-122,共5页
Journal of Harbin Institute of Technology
基金
航天工业部资助
关键词
机器人
位置/力
混合控制
神经网络
s: Robotic hybrid position/force control
adaptive PID control
BP network
gladient rule
