MaskAdapt：基于掩码不变先验的物理角色灵活运动适配学习
MaskAdapt: Learning Flexible Motion Adaptation via Mask-Invariant Prior for Physics-Based Characters
随机身体部位掩码加动作分布一致性正则化训练出的掩码不变先验，可迁移到视觉观测缺失下的姿态/动作估计与条件生成；两阶段残差策略则提供了一种只改动目标部位、保留其余行为的可控生成范式。
原文依据 we train a mask-invariant base policy using stochastic body-part masking and a regularization term that enforces consistent action distributions across masking conditions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 MaskAdapt，一个用于物理仿真人形控制中灵活运动适配的框架。该框架遵循两阶段残差学习范式。第一阶段，利用随机身体部位掩码以及一个强制不同掩码条件下动作分布一致的正则化项，训练掩码不变的基础策略。由此得到一个鲁棒的运动先验，在观测缺失时仍保持稳定，并为后续在这些区域上的适配做好准备。第二阶段，在冻结的基础控制器之上训练残差策略，仅修改目标身体部位，同时保持其他部位的原有行为。我们通过两个应用展示了该设计的通用性：(i) 运动组合，其中变化掩码可在单个序列内实现多部位适配；(ii) 文本驱动的部分目标跟踪，其中指定身体部位跟随由预训练的文本条件自回归运动生成器提供的运动学目标。实验表明，MaskAdapt 具有强鲁棒性与适应性，在掩码观测下产生多样行为，并且相比已有工作实现了更优的目标运动适配。
英文原文摘要 1208 字符
We present MaskAdapt, a framework for flexible motion adaptation in physics-based humanoid control. The framework follows a two-stage residual learning paradigm. In the first stage, we train a mask-invariant base policy using stochastic body-part masking and a regularization term that enforces consistent action distributions across masking conditions. This yields a robust motion prior that remains stable under missing observations, anticipating later adaptation in those regions. In the second stage, a residual policy is trained atop the frozen base controller to modify only the targeted body parts while preserving the original behaviors elsewhere. We demonstrate the versatility of this design through two applications: (i) motion composition, where varying masks enable multi-part adaptation within a single sequence, and (ii) text-driven partial goal tracking, where designated body parts follow kinematic targets provided by a pre-trained text-conditioned autoregressive motion generator. Through experiments, MaskAdapt demonstrates strong robustness and adaptability, producing diverse behaviors under masked observations and delivering superior targeted motion adaptation compared to prior work.