Retargeted_AMASS_for_robotics

Project Overview

This project aims to retarget motion data from the AMASS dataset to various robot models and open-source the retargeted data to facilitate research and applications in robotics and human-robot interaction. AMASS (Archive of Motion Capture as Surface Shapes) is a high-quality human motion capture dataset, and the SMPL-X model is a powerful tool for generating realistic human motion data.

By adapting the motion data from AMASS to different robot models, we hope to provide a more diverse and accessible motion dataset for robot training and human-robot interaction.

Dataset Content

This open-source project includes the following: 1. Retargeted Motions: Motion files retargeted from AMASS to various robot models.

• Unitree G1:

  The retargeted motions for the Unitree G1 robot are generated based on the official open-source model provided by Unitree.

  https://github.com/unitreerobotics/unitree_ros/blob/master/robots/g1_description/g1_29dof_rev_1_0.xml

  The joint positions comply with the constraints defined in the XML file.

  data shape：[-1,36]

  ​ 0:3 root world position

  ​ 3:7 root quaternion rotation, order: xyzw

  ​ 7:36 joint positions

  joint order:

  txt left_hip_pitch_joint left_hip_roll_joint left_hip_yaw_joint left_knee_joint left_ankle_pitch_joint left_ankle_roll_joint right_hip_pitch_joint right_hip_roll_joint right_hip_yaw_joint right_knee_joint right_ankle_pitch_joint right_ankle_roll_joint waist_yaw_joint waist_roll_joint waist_pitch_joint left_shoulder_pitch_joint left_shoulder_roll_joint left_shoulder_yaw_joint left_elbow_joint left_wrist_roll_joint left_wrist_pitch_joint left_wrist_yaw_joint right_shoulder_pitch_joint right_shoulder_roll_joint right_shoulder_yaw_joint right_elbow_joint right_wrist_roll_joint right_wrist_pitch_joint right_wrist_yaw_joint

1. update 2025-4-15: Optimized the handling of elbow and knee joints.

2. Usage Examples: Code examples on how to use the retargeted data.

./g1/visualize.py

1. License Files: Original license information for each sub-dataset within AMASS.

License

The retargeted data in this project is derived from the AMASS dataset and therefore adheres to the original license terms of AMASS. Each sub-dataset within AMASS may have different licenses, so please ensure compliance with the following requirements when using the data: - Propagate Original Licenses: When using or distributing the retargeted data, you must include and comply with the original licenses of the sub-datasets within AMASS. - Attribution Requirements: Properly cite this work and the original authors and sources of the AMASS dataset and its sub-datasets.

For detailed license information, please refer to the LICENSE file in this project.

Acknowledgments

This project is built on the AMASS dataset and the SMPL-X model. Special thanks to the research team at the Max Planck Institute for Intelligent Systems for providing this valuable resource.

Citation

If you use the data or code from this project, please cite this work and relevant papers for AMASS and SMPL-X:

@misc{Retargeted_AMASS_R,
  title={Retargeted AMASS for Robotics},
  author={Kun Zhao},
  url={https://huggingface.co/datasets/fleaven/Retargeted_AMASS_for_robotics}
}

@inproceedings{AMASS2019,
  title={AMASS: Archive of Motion Capture as Surface Shapes},
  author={Mahmood, Naureen and Ghorbani, Nima and Troje, Nikolaus F. and Pons-Moll, Gerard and Black, Michael J.},
  booktitle={International Conference on Computer Vision (ICCV)},
  year={2019}
}

@inproceedings{SMPL-X2019,
  title={Expressive Body Capture: 3D Hands, Face, and Body from a Single Image},
  author={Pavlakos, Georgios and Choutas, Vasileios and Ghorbani, Nima and Bolkart, Timo and Osman, Ahmed A. A. and Tzionas, Dimitrios and Black, Michael J.},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019}
}

Contact

For any questions or suggestions, please contact: - Kun Zhao: [email protected]

For more information, follow my Xiaohongshu and Bilibili:

https://www.xiaohongshu.com/user/profile/60cdc5360000000001007e33

https://space.bilibili.com/678369952