Agile legged locomotion in reconfigurable modular robots

TL;DR

This paper introduces autonomous modular legs for reconfigurable legged robots, enabling rapid adaptation, repair, and diverse morphologies, which enhances agility and resilience in unstructured environments.

Contribution

It presents a novel modular leg design that can be freely reconfigured, learned to perform complex behaviors, and encoded into a compact design space for exploring diverse forms.

Findings

Modular legs enable rapid reconfiguration and repair.

Robots can learn complex dynamic behaviors with these modules.

A compact latent space captures diverse body configurations.

Abstract

Legged machines are becoming increasingly agile and adaptive but they have so far lacked the morphological diversity of legged animals, which have been rearranged and reshaped to fill millions of niches. Unlike their biological counterparts, legged machines have largely converged over the past decade to canonical quadrupedal and bipedal architectures that cannot be easily reconfigured to meet new tasks or recover from injury. Here we introduce autonomous modular legs: agile yet minimal, single-degree-of-freedom jointed links that can learn complex dynamic behaviors and may be freely attached to form multilegged machines at the meter scale. This enables rapid repair, redesign, and recombination of highly-dynamic modular agents that move quickly and acrobatically (non-quasistatically) through unstructured environments. Because each module is itself a complete agent, the bodies that contain them can sustain deep structural damage that would completely disable other legged robots. We also show how to encode the vast space of possible body configurations into a compact latent design space that can be efficiently explored, revealing a wide diversity of novel legged forms.