# HALOMI: Learning Humanoid Loco-Manipulation with Active Perception from Human Demonstrations

arXiv: https://arxiv.org/abs/2606.18772 · HTML: https://mlsanity.com/paper/2606.18772/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2026.

## Built on by (most cited first, 2 of 2)

- [STRIDER: Stepping-Enabled Multi-Gait Hierarchical 3D Loco-Manipulation Framework for Humanoid Robots](https://mlsanity.com/paper/2609.23483/) (2026)
- [Workhorse: Learning Robust Whole-Body Humanoid Loco-Manipulation from Human Data](https://mlsanity.com/paper/2610.09117/) (2026)

## Abstract (arXiv)

Human demonstrations, which can be collected at scale and naturally capture active hand-eye coordination, are a promising data source for learning humanoid loco-manipulation. However, directly transferring human demonstrations to humanoids requires a precise world-frame tracking controller, which is often brittle under Out-of-Distribution(OOD) targets, while human-to-humanoid gaps persist in both egocentric observation and action execution. To address these challenges, we present HALOMI, a scalable framework for learning humanoid loco-manipulation with active perception from human demonstrations. HALOMI extends Universal Manipulation Interface (UMI) with egocentric sensing to collect ego-view and wrist-view observations along with head-hand trajectories at scale. We further propose a manifold-constrained controller that plans in a learned latent behavior manifold to enable precise and robust head-hand tracking in the world frame. To bridge the human-to-humanoid gap, we perform ego-view alignment and introduce a controller-aware reference trajectory adaptation to reduce mismatch in both observation and action execution. We validate HALOMI on a Unitree G1 humanoid robot with an actuated neck across five real-world tasks involving navigation, grasping, bimanual manipulation, whole-body coordination, and dynamic behaviors. Across the three quantitatively evaluated tasks, HALOMI achieves an average success rate of 85%, while additional qualitative demonstrations show its ability to support dynamic tossing and deep-squat grasping.