Unleashing Humanoid Reaching Potential via Real-World-Ready Skill Space

Zhikai Zhang, Chao Chen, Han Xue, Jilong Wang, Sikai Liang, Yun Liu, Zongzhang Zhang, He Wang, Li Yi

Abstract: Humans possess a large reachable space in the 3D world, enabling interactions with objects at varying heights and distances. However, realizing such large-space reaching on humanoids is a complex whole-body control (WBC) problem. Learning from scratch often leads to optimization difficulty and poor sim2real transferability. To address these challenges, we present Real-world-Ready Skill Space ($\text{R}^{2}\text{S}^{2}$), a structural skill prior that helps autonomous whole-body-control task execution in an efficient manner while maintaining sim2real transferability. Inheriting knowledge from a set of real-world-ready primitive skills to ease multi-skill learning, $\text{R}^{2}\text{S}^{2}$ further expands the capability of primitive skills and learns a unified structural skill representation. By sampling from $\text{R}^{2}\text{S}^{2}$, we unleash humanoid reaching potential in many real-world tasks. As a beneficial side effect, $\text{R}^{2}\text{S}^{2}$ can also support humanoid whole-body teleoperation with a large reachable space. We validate the generalizability of $\text{R}^{2}\text{S}^{2}$ in various challenging goal-reaching tasks across different robot platforms, simulation and real world. We show some examples in Fig. 1.

External IDs:dblp:journals/ral/ZhangCXWLLZWY26