Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.10918 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918253269352448 |
|---|---|
| author | Zhang, Zhikai Chen, Chao Xue, Han Wang, Jilong Liang, Sikai Liu, Yun Zhang, Zongzhang Wang, He Yi, Li |
| author_facet | Zhang, Zhikai Chen, Chao Xue, Han Wang, Jilong Liang, Sikai Liu, Yun Zhang, Zongzhang Wang, He Yi, Li |
| contents | Humans possess a large reachable space in the 3D world, enabling interaction with objects at varying heights and distances. However, realizing such large-space reaching on humanoids is a complex whole-body control problem and requires the robot to master diverse skills simultaneously-including base positioning and reorientation, height and body posture adjustments, and end-effector pose control. Learning from scratch often leads to optimization difficulty and poor sim2real transferability. To address this challenge, we propose Real-world-Ready Skill Space (R2S2). Our approach begins with a carefully designed skill library consisting of real-world-ready primitive skills. We ensure optimal performance and robust sim2real transfer through individual skill tuning and sim2real evaluation. These skills are then ensembled into a unified latent space, serving as a structured prior that helps task execution in an efficient and sim2real transferable manner. A high-level planner, trained to sample skills from this space, enables the robot to accomplish real-world goal-reaching tasks. We demonstrate zero-shot sim2real transfer and validate R2S2 in multiple challenging goal-reaching scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_10918 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unleashing Humanoid Reaching Potential via Real-world-Ready Skill Space Zhang, Zhikai Chen, Chao Xue, Han Wang, Jilong Liang, Sikai Liu, Yun Zhang, Zongzhang Wang, He Yi, Li Robotics Humans possess a large reachable space in the 3D world, enabling interaction with objects at varying heights and distances. However, realizing such large-space reaching on humanoids is a complex whole-body control problem and requires the robot to master diverse skills simultaneously-including base positioning and reorientation, height and body posture adjustments, and end-effector pose control. Learning from scratch often leads to optimization difficulty and poor sim2real transferability. To address this challenge, we propose Real-world-Ready Skill Space (R2S2). Our approach begins with a carefully designed skill library consisting of real-world-ready primitive skills. We ensure optimal performance and robust sim2real transfer through individual skill tuning and sim2real evaluation. These skills are then ensembled into a unified latent space, serving as a structured prior that helps task execution in an efficient and sim2real transferable manner. A high-level planner, trained to sample skills from this space, enables the robot to accomplish real-world goal-reaching tasks. We demonstrate zero-shot sim2real transfer and validate R2S2 in multiple challenging goal-reaching scenarios. |
| title | Unleashing Humanoid Reaching Potential via Real-world-Ready Skill Space |
| topic | Robotics |
| url | https://arxiv.org/abs/2505.10918 |