Next Steps: Learning a Disentangled Gait Representation for Versatile Quadruped Locomotion

TL;DR

This paper introduces a generative model that learns a disentangled gait representation for quadruped robots, enabling continuous and versatile gait variation and robustness in real-time locomotion.

Contribution

It presents a novel latent space learning approach that allows continuous gait parameter control and disturbance mitigation for quadruped robots from a single gait style.

Findings

Achieves continuous blend of trot styles in real robot experiments.

Demonstrates robustness and reactivity to external disturbances.

Enables on-the-fly gait parameter modulation.

Abstract

Quadruped locomotion is rapidly maturing to a degree where robots now routinely traverse a variety of unstructured terrains. However, while gaits can be varied typically by selecting from a range of pre-computed styles, current planners are unable to vary key gait parameters continuously while the robot is in motion. The synthesis, on-the-fly, of gaits with unexpected operational characteristics or even the blending of dynamic manoeuvres lies beyond the capabilities of the current state-of-the-art. In this work we address this limitation by learning a latent space capturing the key stance phases of a particular gait, via a generative model trained on a single trot style. This encourages disentanglement such that application of a drive signal to a single dimension of the latent state induces holistic plans synthesising a continuous variety of trot styles. In fact properties of this drive signal map directly to gait parameters such as cadence, footstep height and full stance duration. The use of a generative model facilitates the detection and mitigation of disturbances to provide a versatile and robust planning framework. We evaluate our approach on a real ANYmal quadruped robot and demonstrate that our method achieves a continuous blend of dynamic trot styles whilst being robust and reactive to external perturbations.