A new model-free approach to precisely control humanoid robot joints is presented in this article. An input–output online identification procedure will permit to compensate neglected or uncertain dynamics, such as, on the one hand, transmission and compliance nonlinear effects, and, on the other hand, network transmission delays. Robustness to parameter variations will be analyzed and compared to other advanced PID-based controllers. Simulations will show that not only good tracking quality can be obtained with this novel technique, but also that it provides a very robust behavior to the closed-loop system. Furthermore, a locomotion task will be tested in a complete humanoid simulator to highlight the suitability of this control approach for such complex systems.
A model‐free approach for testing association
