Morphological Wobbling Can Help Robots Learn

TL;DR

This paper demonstrates that oscillating a robot's physical traits during learning, such as mass and size, can significantly enhance its locomotion performance and exploration capabilities.

Contribution

It introduces the concept of morphological wobbling during robot learning, showing its benefits for performance and search space exploration in simulated soft robots.

Findings

High-frequency, large-amplitude oscillations yield the best performance improvements.

Morphological wobbling enhances exploration of the search space.

Oscillating physical parameters can significantly improve robot learning outcomes.

Abstract

We propose to make the physical characteristics of a robot oscillate while it learns to improve its behavioral performance. We consider quantities such as mass, actuator strength, and size that are usually fixed in a robot, and show that when those quantities oscillate at the beginning of the learning process on a simulated 2D soft robot, the performance on a locomotion task can be significantly improved. We investigate the dynamics of the phenomenon and conclude that in our case, surprisingly, a high-frequency oscillation with a large amplitude for a large portion of the learning duration leads to the highest performance benefits. Furthermore, we show that morphological wobbling significantly increases exploration of the search space.