Academic Journals Database
Disseminating quality controlled scientific knowledge

Episodic reinforcement learning control approach for biped walking

ADD TO MY LIST
 
Author(s): Katić Duško

Journal: Serbian Journal of Electrical Engineering
ISSN 1451-4869

Volume: 9;
Issue: 2;
Start page: 231;
Date: 2012;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: humanoid robot | motion control | reinforcement learning | Fuzzy evaluative feedback

ABSTRACT
This paper presents a hybrid dynamic control approach to the realization of humanoid biped robotic walk, focusing on the policy gradient episodic reinforcement learning with fuzzy evaluative feedback. The proposed structure of controller involves two feedback loops: a conventional computed torque controller and an episodic reinforcement learning controller. The reinforcement learning part includes fuzzy information about Zero-Moment- Point errors. Simulation tests using a medium-size 36-DOF humanoid robot MEXONE were performed to demonstrate the effectiveness of our method.

Tango Rapperswil
Tango Rapperswil

    
RPA Switzerland

Robotic Process Automation Switzerland