AI 中文总结
该研究提出首个用于人形机器人全身控制的行为世界模型GigaBrain-WBC-0.5，通过训练因果Transformer联合预测动作、状态与指令分布，在多场景下实现鲁棒控制，成功率优于现有基线。
AI 中文摘要
全身运动跟踪策略将人形机器人转变为鲁棒控制接口：远程操作者或上游模型仅提供粗略的运动意图，而低级策略则保持机器人平衡并确保运动物理可行性。现有跟踪器仅在平坦地面上提供此接口：在空场景中训练的它们从未学习到与地形和物体的接触如何改变机器人动力学，并且它们试图通过不断扩大参考运动语料库来训练策略以在任何指令下保持平衡，但一旦可行行为依赖于环境，这种方法就失效了。我们提出GigaBrain-WBC-0.5，这是首个用于人形机器人全身控制的行为世界模型（Behavior World Model, BWM）。它并非纯反应式跟踪器，我们训练了一个因果Transformer来联合预测下一个动作、下一个状态以及下一个潜在行为指令的分布，因此执行动作的网络同时对环境如何影响其后续可执行任务进行建模。一条自动地形标注流水线从重定向运动中恢复完整的3D接触几何，能够在现有运动数据集的规模上实现地形标注。在部署阶段，该预测分布被用于在线检测不合理指令并将其撤回至已学习的行为，使机器人以“尽最大努力”的方式尝试任务。最终得到的统一策略可接收实时指令、与环境交互，并对不合理指令、摔倒和干扰保持鲁棒性。GigaBrain-WBC-0.5在三种大规模跟踪器基线的全部四种场景中均实现最高成功率：地形交互场景下为81.3%（是最强基线的4.3倍），不合理指令场景下为83.1%，摔倒恢复场景下为99.3%（是最强基线的16.8倍）。硬件试验显示其在支撑缺失和干扰下具备鲁棒交互能力；Unitree G1检查点经简单微调即可迁移至Maker L01机器人。
英文摘要
General-purpose motion trackers enable humanoid robots to follow diverse whole-body motions while maintaining balance, but are trained only on flat ground, failing to exploit bipedal mobility over complex terrain. Cross-terrain controllers, meanwhile, are task-specific or accept only low-dimensional locomotion commands. We introduce InterTrack, the first behavior world model (BWM) for robust whole-body tracking with environment interaction. Its Transformer jointly predicts the next action, state, and behavior distribution, learning environment-conditioned dynamics. To scale interaction training data, an automatic annotation pipeline reconstructs 3D support geometry from retargeted motions. At deployment, the policy handles commands implausible in the current environment in a "best-effort" manner. Quantitatively, InterTrack achieves an 81.3% success rate on terrain interaction (4.3 times the best evaluated baseline) and a 99.3% fall-recovery rate, while also improving free-space tracking and outperforming three leading tracking baselines across all of these regimes. To our knowledge, we provide the first demonstration of real-time cross-terrain whole-body teleoperation on a humanoid robot, alongside object interaction, stable responses to missing supports, and robust recovery from falls.
CommentsTechnical report. Project page: https://shepherd1226.github.io/gigabrain-wbc-0.5/
