Neural Dynamic Movement Primitives -- a survey

TL;DR

This survey reviews recent advances in Neural Dynamic Movement Primitives, highlighting how deep learning techniques enhance robot motion control and trajectory encoding.

Contribution

It provides a comprehensive overview of neural approaches to Dynamic Movement Primitives, complementing existing literature and emphasizing recent deep learning developments.

Findings

Neural methods improve trajectory accuracy.

Deep learning enhances motion control flexibility.

Survey consolidates recent research in Neural DMPs.

Abstract

One of the most important challenges in robotics is producing accurate trajectories and controlling their dynamic parameters so that the robots can perform different tasks. The ability to provide such motion control is closely related to how such movements are encoded. Advances on deep learning have had a strong repercussion in the development of novel approaches for Dynamic Movement Primitives. In this work, we survey scientific literature related to Neural Dynamic Movement Primitives, to complement existing surveys on Dynamic Movement Primitives.