Humanoid Hanoi: Investigating Shared Whole-Body Control for Skill-Based Box Rearrangement

TL;DR

This paper presents a shared whole-body control framework for humanoid robots to perform long-horizon box rearrangement tasks, demonstrating improved robustness and autonomy through skill sequencing and data augmentation.

Contribution

It introduces a shared, task-agnostic whole-body controller for skill-based humanoid manipulation, addressing robustness issues with a novel data aggregation training method.

Findings

Successful autonomous box rearrangement over extended horizons.

Shared-WBC approach outperforms non-shared baselines.

Effective use of domain randomization enhances robustness.

Abstract

We investigate a skill-based framework for humanoid box rearrangement that enables long-horizon execution by sequencing reusable skills at the task level. In our architecture, all skills execute through a shared, task-agnostic whole-body controller (WBC), providing a consistent closed-loop interface for skill composition, in contrast to non-shared designs that use separate low-level controllers per skill. We find that naively reusing the same pretrained WBC can reduce robustness over long horizons, as new skills and their compositions induce shifted state and command distributions. We address this with a simple data aggregation procedure that augments shared-WBC training with rollouts from closed-loop skill execution under domain randomization. To evaluate the approach, we introduce Humanoid Hanoi, a long-horizon Tower-of-Hanoi box rearrangement benchmark, and report results in simulation and on the Digit V3 humanoid robot, demonstrating fully autonomous rearrangement over extended horizons and quantifying the benefits of the shared-WBC approach over non-shared baselines. Project page: https://osudrl.github.io/Humanoid_Hanoi/