Hold My Beer: Learning Gentle Humanoid Locomotion and End-Effector Stabilization Control
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_ | 1866918045287448576 |
|---|---|
| author | Li, Yitang Zhang, Yuanhang Xiao, Wenli Pan, Chaoyi Weng, Haoyang He, Guanqi He, Tairan Shi, Guanya |
| author_facet | Li, Yitang Zhang, Yuanhang Xiao, Wenli Pan, Chaoyi Weng, Haoyang He, Guanqi He, Tairan Shi, Guanya |
| contents | Can your humanoid walk up and hand you a full cup of beer, without spilling a drop? While humanoids are increasingly featured in flashy demos like dancing, delivering packages, traversing rough terrain, fine-grained control during locomotion remains a significant challenge. In particular, stabilizing a filled end-effector (EE) while walking is far from solved, due to a fundamental mismatch in task dynamics: locomotion demands slow-timescale, robust control, whereas EE stabilization requires rapid, high-precision corrections. To address this, we propose SoFTA, a Slow-Fast Two-Agent framework that decouples upper-body and lower-body control into separate agents operating at different frequencies and with distinct rewards. This temporal and objective separation mitigates policy interference and enables coordinated whole-body behavior. SoFTA executes upper-body actions at 100 Hz for precise EE control and lower-body actions at 50 Hz for robust gait. It reduces EE acceleration by 2-5x relative to baselines and performs much closer to human-level stability, enabling delicate tasks such as carrying nearly full cups, capturing steady video during locomotion, and disturbance rejection with EE stability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_24198 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hold My Beer: Learning Gentle Humanoid Locomotion and End-Effector Stabilization Control Li, Yitang Zhang, Yuanhang Xiao, Wenli Pan, Chaoyi Weng, Haoyang He, Guanqi He, Tairan Shi, Guanya Robotics Can your humanoid walk up and hand you a full cup of beer, without spilling a drop? While humanoids are increasingly featured in flashy demos like dancing, delivering packages, traversing rough terrain, fine-grained control during locomotion remains a significant challenge. In particular, stabilizing a filled end-effector (EE) while walking is far from solved, due to a fundamental mismatch in task dynamics: locomotion demands slow-timescale, robust control, whereas EE stabilization requires rapid, high-precision corrections. To address this, we propose SoFTA, a Slow-Fast Two-Agent framework that decouples upper-body and lower-body control into separate agents operating at different frequencies and with distinct rewards. This temporal and objective separation mitigates policy interference and enables coordinated whole-body behavior. SoFTA executes upper-body actions at 100 Hz for precise EE control and lower-body actions at 50 Hz for robust gait. It reduces EE acceleration by 2-5x relative to baselines and performs much closer to human-level stability, enabling delicate tasks such as carrying nearly full cups, capturing steady video during locomotion, and disturbance rejection with EE stability. |
| title | Hold My Beer: Learning Gentle Humanoid Locomotion and End-Effector Stabilization Control |
| topic | Robotics |
| url | https://arxiv.org/abs/2505.24198 |