In this paper, the Intelligent Impedance Control based Wavelet Neural Network (IIC-WNN) is introduced as a noble adaptive variable impedance approach to enhance the efficiency of tracking the desired force and interaction with varying unknown (in terms of unknown stiffness and unknown geometric) environment. In the proposed method, a systematic online adaptation mechanism using the wavelet neural network is presented to adapt the impedance parameter according to a variable environment. Using the introduced adaptive law, the robot would be able to track the desired force on the moving environment with the unknown stiffness. Unlike the general impedance control which the position and stiffness of the environment need to be available and known for choosing the impedance parameters, the proposed structure for the impedance equation leads to adapt the impedance parameters according to the interaction environment. In addition, the stability conditions and adaptation laws using Lyapunov’s method for the variable impedance are given to guarantee the force tracking and stability of the closed-loop system. Finally, various numerical and experimental results verify the performance of the proposed adaptive approach. The experimental results strongly prove that the presented method has a better force tracking performance than the general impedance with constant parameters.

在本文中，基于智能阻抗控制的小波神经网络（IIC-WNN）被引入作为一种高贵的自适应可变阻抗方法，以提高跟踪所需力以及与未知未知变量（根据未知刚度和未知几何形状）相互作用的效率。环境。在提出的方法中，提出了一种基于小波神经网络的系统在线自适应机制，以根据可变环境来自适应阻抗参数。使用引入的自适应定律，机器人将能够以未知的刚度跟踪运动环境上的所需力。与一般的阻抗控制不同，在选择阻抗参数时需要环境的位置和刚度，并且该已知的阻抗控制是已知的，所提出的阻抗方程的结构导致根据相互作用环境来调整阻抗参数。此外，给出了使用李雅普诺夫方法的可变阻抗的稳定性条件和适应律，以保证闭环系统的力跟踪和稳定性。最后，各种数值和实验结果验证了所提出的自适应方法的性能。实验结果证明，该方法比具有恒定参数的一般阻抗具有更好的力跟踪性能。各种数值和实验结果验证了所提出的自适应方法的性能。实验结果证明，该方法比具有恒定参数的一般阻抗具有更好的力跟踪性能。各种数值和实验结果验证了所提出的自适应方法的性能。实验结果证明，该方法比具有恒定参数的一般阻抗具有更好的力跟踪性能。