OpenHLM: An Empirical Recipe for Whole-Body Humanoid Loco-Manipulation
cs.RO
Submitted: 2026-06-20
Updated: 2026-11-02
Comments: 30 pages
Journal ref: 10th Annual Conference on Robot Learning (2026), Spotlight
Project page: https://openhlm-project.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- HuMI: Humanoid Whole-Body Manipulation from Humanoid-Free Demonstrations
- Expressive Whole-Body Control for Humanoid Robots
- Visual Whole-Body Control for Legged Loco-Manipulation
- HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit
- AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control
- $\Psi_0$: An Open Foundation Model Towards Universal Humanoid Loco-Manipulation
- TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System
- OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning
- SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control
- OpenVLA: An Open-Source Vision-Language-Action Model
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots
- EgoHumanoid: Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration
- Retargeting Matters: General Motion Retargeting for Humanoid Motion Tracking
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- PaliGemma: A versatile 3B VLM for transfer
- Flow Matching for Generative Modeling
- Generative Modeling via Drifting
- TWIST: Teleoperated Whole-Body Imitation System
- HumanPlus: Humanoid Shadowing and Imitation from Humans
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation