OmniXtreme: 突破高动态人形控制中的通用性瓶颈
OmniXtreme: Breaking the Generality Barrier in High-Dynamic Humanoid Control
AI总结：
OmniXtreme通过分离通用运动技能学习与现实物理技能细化，突破高动态人形控制中保真度与可扩展性的长期权衡。
摘要：
高保真动作跟踪是检验通用、人水平运动技能的最终试金石。然而，当前策略往往遇到一个"通用性瓶颈"：随着动作库的多样性增加，跟踪保真度不可避免地下降——尤其是在高动态动作的现实世界部署中。我们将其失败归因于两个叠加因素：多动作优化的学习瓶颈以及现实世界执行中出现的物理可执行性约束。为克服这些挑战，我们引入了OmniXtreme，一个可扩展的框架，将通用运动技能学习与仿真到现实的物理技能细化分离。我们的方法使用具有高容量架构的流匹配策略，在不进行干扰性的多动作强化学习优化的情况下扩展表示能力，随后进行一个执行意识的细化阶段，确保在物理硬件上的鲁棒性能。广泛的实验表明，OmniXtreme在多样、高难度的数据集上保持高保真跟踪。在真实机器人上，统一策略成功执行了多种极端动作，有效突破了高动态人形控制中长期存在的保真度-可扩展性权衡。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
