Think on your feet: Seamless Transition between Human-like Locomotion in Response to Changing Commands

TL;DR

This paper introduces a novel imitation learning approach enabling humanoid robots to achieve seamless, human-like locomotion that adapts to changing commands and environments, with improved generalization and transfer capabilities.

Contribution

It combines Wasserstein divergence, a Hybrid Internal Model, and curiosity-driven exploration to enhance motion transfer, stability, and adaptability in humanoid robot locomotion.

Findings

Achieves highly human-like, adaptable locomotion in simulation and real-world tests.

Demonstrates zero-shot transfer across different terrains and robot models.

Enables seamless transition between various motions and unseen commands.

Abstract

While it is relatively easier to train humanoid robots to mimic specific locomotion skills, it is more challenging to learn from various motions and adhere to continuously changing commands. These robots must accurately track motion instructions, seamlessly transition between a variety of movements, and master intermediate motions not present in their reference data. In this work, we propose a novel approach that integrates human-like motion transfer with precise velocity tracking by a series of improvements to classical imitation learning. To enhance generalization, we employ the Wasserstein divergence criterion (WGAN-div). Furthermore, a Hybrid Internal Model provides structured estimates of hidden states and velocity to enhance mobile stability and environment adaptability, while a curiosity bonus fosters exploration. Our comprehensive method promises highly human-like locomotion that adapts to varying velocity requirements, direct generalization to unseen motions and multitasking, as well as zero-shot transfer to the simulator and the real world across different terrains. These advancements are validated through simulations across various robot models and extensive real-world experiments.