<abstract xmlns="http://www.w3.org/1999/xhtml"><p>COMAN is a compliant humanoid robot. The introduction of passive compliance in some of its joints affects the dynamics of the whole system. Unlike traditional stiff robots, there is a deflection of the joint angle with respect to the desired one whenever an external torque is applied. Following a bottom up approach, the dynamic equations of the joints are defined first. Then, a new model which combines the inverted pendulum approach with a three-dimensional (Cartesian) compliant model at the level of the center of mass is proposed. This compact model is based on some assumptions that reduce the complexity but at the same time affect the precision. To address this problem, additional parameters are inserted in the model equation and an optimization procedure is performed using reinforcement learning. The optimized model is experimentally validated on the COMAN robot using several ZMP-based walking gaits.</p></abstract>

COMAN is a compliant humanoid robot. The introduction of passive compliance in some of its joints affects the dynamics of the whole system. Unlike traditional stiff robots, there is a deflection of the joint angle with respect to the desired one whenever an external torque is applied. Following a bottom up approach, the dynamic equations of the joints are defined first. Then, a new model which combines the inverted pendulum approach with a three-dimensional (Cartesian) compliant model at the level of the center of mass is proposed. This compact model is based on some assumptions that reduce the complexity but at the same time affect the precision. To address this problem, additional parameters are inserted in the model equation and an optimization procedure is performed using reinforcement learning. The optimized model is experimentally validated on the COMAN robot using several ZMP-based walking gaits.

Optimization of a Compact Model for the Compliant Humanoid Robot COMAN Using Reinforcement Learning

Department of Advanced Robotics, Istituto Italiano di Tecnologia (IIT), Via Morego 30, 1616 Genova

Cybernetics and Information Technologies

COMAN is a compliant humanoid robot. The introduction of passive compliance in some of its joints affects the dynamics of the whole system. Unlike traditional...

Optimization of a Compact Model for the Compliant Humanoid Robot COMAN Using Reinforcement Learning

Data publikacji: 22 mar 2013

Zakres stron: 76 - 85

DOI: https://doi.org/10.2478/cait-2012-0023

Słowa kluczowe
Humanoid robot, Reinforcement learning, Dynamic walking

This content is open access.

Optimization of a Compact Model for the Compliant Humanoid Robot COMAN Using Reinforcement Learning

Data publikacji: 22 mar 2013

Zakres stron: 76 - 85

DOI: https://doi.org/10.2478/cait-2012-0023

Słowa kluczoweHumanoid robot, Reinforcement learning, Dynamic walking

This content is open access.

Słowa kluczowe
Humanoid robot, Reinforcement learning, Dynamic walking