Workhorse: Learning Robust Whole-Body Humanoid Loco-Manipulation from Human Data

arXiv:2610.09117 · cs.RO, cs.LG · Submitted 2026-10-06 · Read on arXiv

cs.RO, cs.LG

Submitted: 2026-10-06

Updated: 2026-10-08

Comments: 9 pages, 8 figures, 2 tables. Project page: https://hybridrobotics.github.io/workhorse/

Project page: https://hybridrobotics.github.io/workhorse

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Alignment — 4× in this paper
• Ablation — 2× in this paper · explained in 1 episode
• Gaussian Splatting — 2× in this paper · explained in 4 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Active Perception — 1× in this paper · explained in 2 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Diffusion Model — 1× in this paper · explained in 10 episodes
• Diffusion Models — 1× in this paper · explained in 9 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Rectified Flow — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion
• GMT: General Motion Tracking for Humanoid Whole-Body Control
• OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning
• TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System
• Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations
• BifrostUMI: Bridging Robot-Free Demonstrations and Humanoid Whole-Body Manipulation
• HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations
• Track Any Motions under Any Disturbances
• Robust and Generalized Humanoid Motion Tracking
• HOVER: Versatile Neural Whole-Body Controller for Humanoid Robots
• MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting
• BFM-Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning
• AnyBody: Free-Form Whole-Body Humanoid Control from Arbitrary Keypoint Guidance
• AMASS: Archive of Motion Capture as Surface Shapes
• TransPose: Real-time 3D Human Translation and Pose Estimation with Six Inertial Sensors
• Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots
• DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation
• HumanoidExo: Scalable Whole-Body Humanoid Manipulation via Wearable Exoskeleton
• HALOMI: Learning Humanoid Loco-Manipulation with Active Perception from Human Demonstrations
• EgoHumanoid: Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies