Learning Locomotion Skills in Evolvable Robots

TL;DR

This paper presents a modular learning method for evolvable robots to acquire targeted locomotion skills, validated on different robot morphologies in real-world scenarios.

Contribution

It introduces a novel controller architecture and learning approach enabling arbitrary-shaped robots to learn targeted walking behaviors.

Findings

Successful learning of targeted locomotion on three robot types

Robust walking behavior in real-world environments

Applicable to various robot morphologies

Abstract

The challenge of robotic reproduction -- making of new robots by recombining two existing ones -- has been recently cracked and physically evolving robot systems have come within reach. Here we address the next big hurdle: producing an adequate brain for a newborn robot. In particular, we address the task of targeted locomotion which is arguably a fundamental skill in any practical implementation. We introduce a controller architecture and a generic learning method to allow a modular robot with an arbitrary shape to learn to walk towards a target and follow this target if it moves. Our approach is validated on three robots, a spider, a gecko, and their offspring, in three real-world scenarios.