HOVER: Versatile Neural Whole-Body Controller for Humanoid Robots

TL;DR

HOVER introduces a unified neural control framework for humanoid robots that seamlessly integrates multiple control modes, enabling flexible, efficient, and scalable whole-body control without retraining for each mode.

Contribution

The paper presents HOVER, a multi-mode policy distillation framework that unifies diverse control modes into a single adaptable policy for humanoid robots.

Findings

Enables seamless transition between control modes

Reduces need for retraining for new control tasks

Improves efficiency and scalability of humanoid control

Abstract

Humanoid whole-body control requires adapting to diverse tasks such as navigation, loco-manipulation, and tabletop manipulation, each demanding a different mode of control. For example, navigation relies on root velocity tracking, while tabletop manipulation prioritizes upper-body joint angle tracking. Existing approaches typically train individual policies tailored to a specific command space, limiting their transferability across modes. We present the key insight that full-body kinematic motion imitation can serve as a common abstraction for all these tasks and provide general-purpose motor skills for learning multiple modes of whole-body control. Building on this, we propose HOVER (Humanoid Versatile Controller), a multi-mode policy distillation framework that consolidates diverse control modes into a unified policy. HOVER enables seamless transitions between control modes while preserving the distinct advantages of each, offering a robust and scalable solution for humanoid control across a wide range of modes. By eliminating the need for policy retraining for each control mode, our approach improves efficiency and flexibility for future humanoid applications.