MaskedManipulator: Versatile Whole-Body Manipulation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915669004517376 |
|---|---|
| author | Tessler, Chen Jiang, Yifeng Coumans, Erwin Luo, Zhengyi Chechik, Gal Peng, Xue Bin |
| author_facet | Tessler, Chen Jiang, Yifeng Coumans, Erwin Luo, Zhengyi Chechik, Gal Peng, Xue Bin |
| contents | We tackle the challenges of synthesizing versatile, physically simulated human motions for full-body object manipulation. Unlike prior methods that are focused on detailed motion tracking, trajectory following, or teleoperation, our framework enables users to specify versatile high-level objectives such as target object poses or body poses. To achieve this, we introduce MaskedManipulator, a generative control policy distilled from a tracking controller trained on large-scale human motion capture data. This two-stage learning process allows the system to perform complex interaction behaviors, while providing intuitive user control over both character and object motions. MaskedManipulator produces goal-directed manipulation behaviors that expand the scope of interactive animation systems beyond task-specific solutions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19086 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MaskedManipulator: Versatile Whole-Body Manipulation Tessler, Chen Jiang, Yifeng Coumans, Erwin Luo, Zhengyi Chechik, Gal Peng, Xue Bin Robotics Artificial Intelligence Graphics We tackle the challenges of synthesizing versatile, physically simulated human motions for full-body object manipulation. Unlike prior methods that are focused on detailed motion tracking, trajectory following, or teleoperation, our framework enables users to specify versatile high-level objectives such as target object poses or body poses. To achieve this, we introduce MaskedManipulator, a generative control policy distilled from a tracking controller trained on large-scale human motion capture data. This two-stage learning process allows the system to perform complex interaction behaviors, while providing intuitive user control over both character and object motions. MaskedManipulator produces goal-directed manipulation behaviors that expand the scope of interactive animation systems beyond task-specific solutions. |
| title | MaskedManipulator: Versatile Whole-Body Manipulation |
| topic | Robotics Artificial Intelligence Graphics |
| url | https://arxiv.org/abs/2505.19086 |