Reinforcement learning control algorithm for humanoid robot walking

Abstract

The integrated dynamic control of humanoid locomotion mechanisms based on the spatial dynamic model of humanoid mechanism is presented in this paper. The control scheme was synthesized using the centralized model with proposed structure of dynamic controller that involves two feedback loops position-velocity feedback of the robotic mechanism joints and reinforcement learning feedback around Zero-Moment Point. The proposed reinforcement learning is based on the modified version of GARIC architecture for dynamic reactive compensation. Simulation experiments were carried out in order to validate the proposed control approach.