迭代闭环运动合成：扩展人形控制能力
Iterative Closed-Loop Motion Synthesis for Scaling the Capabilities of Humanoid Control
提出闭环自动运动数据生成与迭代框架，通过物理指标和客观评估实现策略与数据的难度迭代，可复用于视觉驱动的运动合成与具身控制任务，突破固定数据分布的性能上限。
原文依据 we propose a closed-loop automated motion data generation and iterative framework
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于物理的人形控制依赖于具有多样数据分布的运动数据集进行训练。然而，数据集固定的难度分布限制了训练所得控制策略的性能上限。此外，通过专业运动捕捉系统获取高质量数据的方法受成本制约，难以实现大规模可扩展性。为解决这些问题，我们提出了一种闭环自动运动数据生成与迭代框架。该框架能够生成具有丰富动作语义的高质量运动数据，包括武术、舞蹈、格斗、体育、体操等。此外，我们的框架通过物理指标和客观评估实现策略与数据的难度迭代，使训练后的跟踪器能够突破其原始难度限制。在PHC单基元跟踪器上，仅使用约1/10的AMASS数据集规模，测试集（2201个片段）上的平均失败率相比基线降低了45%。最后，我们进行了全面的消融和对比实验，以突出我们框架的合理性和优势。
英文原文摘要 1186 字符
Physics-based humanoid control relies on training with motion datasets that have diverse data distributions. However, the fixed difficulty distribution of datasets limits the performance ceiling of the trained control policies. Additionally, the method of acquiring high-quality data through professional motion capture systems is constrained by costs, making it difficult to achieve large-scale scalability. To address these issues, we propose a closed-loop automated motion data generation and iterative framework. It can generate high-quality motion data with rich action semantics, including martial arts, dance, combat, sports, gymnastics, and more. Furthermore, our framework enables difficulty iteration of policies and data through physical metrics and objective evaluations, allowing the trained tracker to break through its original difficulty limits. On the PHC single-primitive tracker, using only approximately 1/10 of the AMASS dataset size, the average failure rate on the test set (2201 clips) is reduced by 45% compared to the baseline. Finally, we conduct comprehensive ablation and comparative experiments to highlight the rationality and advantages of our framework.