外观
论文arXiv 2602.238433 个月前
OmniXtreme：突破高动态人形控制中的通用性壁垒
原文链接：OmniXtreme: Breaking the Generality Barrier in High-Dynamic Humanoid Control（arXiv 2602.23843 · 发布日期：2026-07-13）
OmniXtreme: Breaking the Generality Barrier in High-Dynamic Humanoid Control
OmniXtreme通过解耦通用运动学习与Sim-to-Real物理细化，在高难数据集和真机上验证高动态人形跟踪。
核心要点
- 运动库多样性扩大时，现有策略跟踪精度易下降，真机高动态部署尤甚。
- 框架将通用运动技能学习与Sim-to-Real物理技能细化解耦。
- 采用flow-matching策略和高容量架构，并加入感知执行器的细化阶段。
- 实验显示其在多样高难数据集保持高保真跟踪，真机可执行多个极端动作。
验证范围与局限：验证范围包括多样高难数据集实验和真实机器人上的多个极端动作执行。
英文摘要 (Abstract)
High-fidelity motion tracking serves as the ultimate litmus test for generalizable, human-level motor skills. However, current policies often hit a "generality barrier": as motion libraries scale in diversity, tracking fidelity inevitably collapses - especially for real-world deployment of high-dynamic motions. We identify this failure as the result of two compounding factors: the learning bottleneck in scaling multi-motion optimization and the physical executability constraints that arise in real-world actuation. To overcome these challenges, we introduce OmniXtreme, a scalable framework that decouples general motor skill learning from sim-to-real physical skill refinement. Our approach uses a flow-matching policy with high-capacity architectures to scale representation capacity without interference-intensive multi-motion RL optimization, followed by an actuation-aware refinement phase that ensures robust performance on physical hardware. Extensive experiments demonstrate that OmniXtreme maintains high-fidelity tracking across diverse, high-difficulty datasets. On real robots, the unified policy successfully executes multiple extreme motions, effectively breaking the long-standing fidelity-scalability trade-off in high-dynamic humanoid control.
作者：Yunshen Wang, Shaohang Zhu, Peiyuan Zhi, Yuhan Li, Jiaxin Li, Yong-Lu Li, Yuchen Xiao, Xingxing Wang, Baoxiong Jia, Siyuan Huang
来源
本页事实对应的公开页面，以原文为准。