We present a physics-based humanoid controller that achieves high-fidelity motion imitation and fault-tolerant behavior in the presence of noisy input (e.g. pose estimates from video or generated from language) and unexpected falls. Our controller scales up to learning ten thousand motion clips without using any external stabilizing forces and learns to naturally recover from fail-state. Given reference motion, our controller can perpetually control simulated avatars without requiring resets. At its core, we propose the progressive multiplicative control policy (PMCP), which dynamically allocates new network capacity to learn harder and harder motion sequences. PMCP allows efficient scaling for learning from large-scale motion databases and adding new tasks, such as fail-state recovery, without catastrophic forgetting. We demonstrate the effectiveness of our controller by using it to imitate noisy poses from video-based pose estimators and language-based motion generators in a live and real-time multi-person avatar use case.

翻译：我们提出了一种基于物理的人形控制器，该控制器能在存在噪声输入（例如，来自视频的姿态估计或由语言生成的姿态）以及意外摔倒的情况下，实现高保真度的动作模仿和容错行为。我们的控制器在无需使用任何外部稳定力的情况下，可扩展学习多达一万个运动片段，并能自然地学会从失败状态中恢复。给定参考动作，我们的控制器可以永久控制模拟虚拟人，而无需重置。其核心在于，我们提出了渐进式乘法控制策略（Progressive Multiplicative Control Policy, PMCP），该策略能够动态分配新的网络容量，以学习越来越困难的动作序列。PMCP允许从大规模运动数据库中进行高效扩展学习，并能在不产生灾难性遗忘的情况下添加新任务，例如从失败状态中恢复。我们通过在一个实时多人物体化身用例中，使用来自视频姿态估计器和语言生成器的噪声姿态进行模仿，展示了我们控制器的有效性。