UNITAS: A 3D-Native World Action Model for Embodied Manipulation

世界动作模型试图回答一个耦合的物理问题：给定任务指令，机器人应执行什么运动，以及该运动会如何改变世界。现有 WAM 多建立在预训练视频生成器上，用图像或视觉潜变量表示世界演化；但机器人交互发生在度量三维空间，图像只是视角相关投影，像素距离并不直接编码物理距离。UNITAS 将观测、动作和场景动态统一到每次交互的共享度量 3D 帧，并跨机器人本体与人类手使用共同表示。action flow 将人类手和机器人夹爪表示为 3D 点轨迹，scene flow 在该轨迹条件下描述场景点位移；世界对齐 3D 位置嵌入可在有无深度输入时为视觉 token 提供空间锚定，物理时间轨迹 tokenizer 将每条点轨迹编码为一个锚定在当前 3D 位置的 token。该接口同时支持直接动作执行和动作条件场景预测。1.7B 参数下，UNITAS 在 RoboTwin 动作条件场景预测中取得对比方法最佳结果，位移误差较 PointWorld 最多降低 49%，并在 LIBERO 达 99.8%、真实任务平均约 85%。

World action models (WAMs) aim to answer a coupled physical question: given a task instruction, what motion should the robot execute, and how will that motion change the surrounding world? Most existing WAMs build on pretrained video generators and represent world evolution through images or visual latents. Robotic interaction, however, takes place in metric three-dimensional space, while images are view-dependent projections whose pixel distances do not directly encode physical distances. We introduce UNITAS, to our knowledge the first 3D-native world action model that unifies observations, actions, and scene dynamics in a shared metric 3D frame within each interaction, using a common representation across robot embodiments and human hands. Action flow represents human hands and robot grippers as 3D point trajectories, while scene flow describes scene-point displacements conditioned on these trajectories. World-aligned 3D positional embeddings ground visual tokens with or without depth input, and a physical-time trajectory tokenizer encodes each point trajectory as one token anchored at its current 3D position. This interface supports both direct action execution and action-conditioned scene prediction. With 1.7B parameters, UNITAS achieves the best action-conditioned scene prediction on RoboTwin among the compared methods, with up to 49% lower displacement errors than PointWorld, and state-of-the-art manipulation success, including 99.8% on LIBERO and an average of 85% across real-world tasks.