- [2026.07.16] HoloMotion v1.4 introduces HoloRetarget at 3,000+ FPS on RTX 4090 for training data generation and 300+ FPS entirely on-robot for teleoperation, plus HoloSMPL for 10+ datasets and devices.
- [2026.05.15] HoloMotion v1.3 scales from 60M to 0.4B parameters and 80 to 2000+ hours of motion data, while improving policy inference from ~100 to ~300 FPS.
- [2026.04.04] HoloMotion v1.2 provides pre-trained motion tracking and velocity tracking models for the community to deploy directly.
HoloMotion scales humanoid whole-body control through a reference-conditioned MoE Transformer, large-scale motion data, and an optimized training-to-deployment pipeline, delivering stronger motion tracking with real-time inference efficiency.
The roadmap of HoloMotion advances through four generalization targets, from motion imitation to command following, terrain adaptation, and embodiment transfer.
| Version | Target Capability | Status | Description |
|---|---|---|---|
| v1.x | Any Pose | ✅ Done | Achieve robust tracking and imitation of diverse, whole-body human motions, forming the core of the imitation learning capability. |
| v2.x | Any Command | 🚀 Next | Enable language- and task-conditioned motion generation, allowing for goal-directed and interactive behaviors. |
| v3.x | Any Terrain | 🧭 Planned | Master adaptation to uneven, dynamic, and complex terrains, enhancing real-world operational robustness. |
| v4.x | Any Embodiment | 🧭 Planned | Generalize control policies across humanoids with varying morphologies and kinematics, achieving true embodiment-level abstraction. |
HoloSMPL standardizes VR, inertial, optical, and vision capture into a shared representation for HoloRetarget.
HoloMotion provides a clear, modular framework for bridging motion data, policy learning, simulation evaluation, and real-robot deployment.
Whether you want to replay motions, stream live teleoperation, or train a custom policy, HoloMotion provides a direct path into the workflow:
| User Goal | Start Here | What You Need |
|---|---|---|
| Offline motion tracking Replay local motion clips for demos such as dance or scripted performances. |
Real-world deployment: Offline Motion | The v1.4 Docker image and retargeted .npz motion clips. No model training is required. |
| Online motion tracking Follow live VR or teleoperation motion streams. |
Real-world deployment: Teleoperation | The v1.4 Docker image, robot deployment setup, and a live motion source. No model training is required. |
| Train your own model Build a custom policy from your own motion data. |
Environment setup → HoloSMPL conversion → Retargeting → Training → Evaluation | Training environment, curated motion data, retargeted HDF5 datasets, and GPU resources. |
We are hiring full-time engineers, new graduates, and interns who are excited about humanoid robots, motion control, and embodied intelligence. Send your resume by scanning the WeChat QR code below to get in touch with us.
We are glad to see HoloMotion being used as a motion control foundation for humanoid research and applications.
| Project | Description | Links |
|---|---|---|
| OMG: Omni-Modal Motion Generation for Generalist Humanoid Control | Uses HoloMotion as the motion control foundation for omni-modal motion generation and generalist humanoid control. | Paper / Project / Code |
| HoloAgent-0: A Unified Embodied Agent Framework with 3D Spatial Memory | Uses HoloMotion as the humanoid whole-body motion skill within its closed-loop Embodied AgentOS. | Paper / Project / Code |
If your project uses HoloMotion, feel free to open a PR to add it here.
@misc{chen2026holomotion1,
title = {HoloMotion-1 Technical Report},
author = {Maiyue Chen and Kaihui Wang and Bo Zhang and Xihan Ma and Zhiyuan Yang and Yi Ren and Qijun Huang and Zihao Zhu and Yucheng Wang and Zhizhong Su},
year = {2026},
eprint = {2605.15336},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2605.15336}
}
This project is built upon and inspired by several outstanding open source projects: