AI 中文总结
GenTrack是一种在线生成器-跟踪器框架，通过协同训练缩小重定向参考与机器人原生运动的可执行性差距，在Unitree G1机器人上实现了零样本人形机器人跟踪性能提升。
AI 中文摘要
通用人形机器人跟踪器可执行各类参考动作，但其零样本覆盖范围依赖于庞大的实体语料库，扩展成本高昂。文本到运动生成器提供可扩展的监督信号，但基于人类运动或重定向数据训练的模型，存在运动学合理性与机器人可执行性之间的差距。现有单向流程要么仅优化生成语料，要么仅优化奖励跟踪器。我们提出GenTrack，这是一种在线生成器-跟踪器框架，交替进行基于执行的组相对生成器对齐，以及在新生成参考上训练跟踪器；锚定与重播机制可约束漂移。我们在Unitree G1机器人上，采用ProtoMotions和SONIC两种骨干网络，在三个零样本跟踪分割集上评估GenTrack，包括公开的AMASS和LAFAN基准，以及包含1024个野外提示-运动对的私有分布外测试集。在线协同训练策略持续生成能输出更具机器人可执行性、且语义对齐性更强的运动的生成器，以及零样本覆盖范围显著更广、跟踪精度更高的跟踪器，尤其在分布外参考上表现突出。这些结果表明，联合在线后训练可有效缩小重定向参考与机器人原生运动之间的可执行性差距，无需额外数据收集即可推进零样本人形机器人控制，且突破了静态参考池的局限。
英文摘要
General-purpose humanoid trackers can execute diverse references, but their zero-shot coverage depends on large embodied corpora that are costly to extend. Text-to-motion generators offer scalable supervision, yet models trained on human motion or retargeted data inherit a gap between kinematic plausibility and robot executability. Existing one-way pipelines fix either the generated corpus or the reward tracker. We introduce GenTrack, an online generator--tracker framework that alternates execution-grounded, group-relative generator alignment with tracker training on newly generated references; anchoring and rehearsal constrain drift. On Unitree G1, we evaluate GenTrack with ProtoMotions and SONIC backbones across three zero-shot tracking splits including public AMASS and LAFAN benchmarks, and a private out-of-distribution test set of 1,024 prompt-motion pairs in the wild. The online co-training strategy consistently produces generators that output more robot-executable motions with strong semantic alignment, and trackers with markedly broader zero-shot coverage and improved tracking accuracy, especially on out-of-distribution references. These results demonstrate that joint online post-training effectively narrows the executability gap between retargeted references and robot-native motion, advancing zero-shot humanoid control without additional data collection and beyond the limitations of a static reference pool.
