An Inverse Dynamics-Based Control Approach for Compliant Control of Pneumatic Artificial Muscles

Rehabilitation is an area of robotics in which human–robot collaboration occurs, requiring adaptation and compliance. Pneumatic artificial muscles (PAM) are soft actuators that have built-in compliance making them usable for rehabilitation robots. Conversely, arises from nonlinear characteristics generates obstructions modeling controlling actions. It a critical issue limiting the use PAM. In this work, multi-input single-output (MISO) inverse dynamics model learning approaches combined to obtain novel adaptive control scheme single PAM-actuated 1-DoF devices, instance, continuous passive motion (CPM) devices. The objective proposed system bring alternative solution compliant operation PAM while performing exercise trajectories, satisfy requirements such as larger range (ROM) adaptability external load impedance variations. combines autoregressive network with exogenous inputs (NARX)-based estimator used global controller cascade PIDs local position pressure loops. Implementation results demonstrated efficacy introduced method terms dynamic variations well stable case impulsive disturbances. To summarize, simple but efficient illustrated facilitate common