Kick Motions for the NAO Robot using Dynamic Movement Primitives

TL;DR

This paper applies Dynamic Movement Primitives to enable flexible and adaptive kick motions in soccer-playing NAO robots, including a motor model to compensate for control delays, validated through real robot experiments.

Contribution

It introduces the first application of DMPs to soccer kicks in humanoid robots and proposes a motor model to improve balance during kicking.

Findings

DMPs effectively generate adaptable kick motions.

The motor model improves balance and stability.

All methods were successfully tested on real NAO robots.

Abstract

In this paper, we present the probably first application of the popular \emph{Dynamic Movement Primitives (DMP)} approach to the domain of soccer-playing humanoid robots. DMPs are known for their ability to imitate previously demonstrated motions as well as to flexibly adapt to unforeseen changes to the desired trajectory with respect to speed and direction. As demonstrated in this paper, this makes them a useful approach for describing kick motions. Furthermore, we present a mathematical motor model that compensates for the NAO robot's motor control delay as well as a novel minor extension to the DMP formulation. The motor model is used in the calculation of the Zero Moment Point (ZMP), which is needed to keep the robot in balance while kicking. All approaches have been evaluated on real NAO robots.