发表机构
Hunan University; China Mobile Group Hunan Company Ltd.; National Engineering Research Center of Robot Visual Perception and Control Technology（湖南大学; 中国移动通信集团湖南有限公司; 国家机器人视觉感知与控制技术工程研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
OmniMimic通过时间反转、动力学补全和反射增强，将方向受限的动物演示转化为多步态策略，显著降低足部位置和速度跟踪误差。
AI 中文摘要
动物演示为四足机器人提供了自然且独特的步态风格，这些风格难以通过手工设计的奖励来指定。然而，其狭窄的方向覆盖范围使得在后退、侧向和转弯指令下缺乏风格一致的监督。我们提出了OmniMimic，一个训练框架，将方向受限的动物演示转化为一个覆盖目标各轴速度范围的单一多步态策略。OmniMimic首先结合时间反转、约束动力学补全和矢状面反射，构建超出观测方向的机器人特定运动学和物理监督。然后，它逐步将命令从演示的速度分布扩展到目标各轴边界，并使用带有软门控、步态专用残差专家的共享actor，以平衡可复用的运动技能与步态特定修正。在模拟中的四种步态上，与匹配的APEX基线相比，OmniMimic在前向和后向参考速度下的平均足部位置RMSE降低了12.9%，在统一笛卡尔命令网格上的速度跟踪RMSE降低了63.1%。项目页面位于此https URL。
英文摘要
Animal demonstrations provide quadruped robots with natural and distinctive gait styles that are difficult to specify through hand-crafted rewards. However, their narrow directional coverage leaves little style-consistent supervision for backward, lateral, and turning commands. We present OmniMimic, a training framework that turns directionally limited animal demonstrations into a single multi-gait policy over target per-axis velocity ranges. OmniMimic first combines temporal reversal, constrained dynamics completion, and sagittal reflection to construct robot-specific kinematic and physical supervision beyond the observed directions. It then expands commands progressively from the demonstrated velocity distribution toward the target per-axis bounds, and uses a shared actor with soft-gated, gait-specialized residual experts to balance reusable locomotion skills with gait-specific corrections. Across four gaits in simulation, OmniMimic reduces mean foot-position RMSE at forward and backward reference velocities by 12.9% and velocity-tracking RMSE on a uniform Cartesian command grid by 63.1%, compared with the matched APEX baseline. The project page is at https://OmniMimic.github.io.
CommentsThe project page is at https://OmniMimic.github.io
