SOURCE-LINKED INTELLIGENCE

RoboDreamer: Anticipatory Humanoid Locomotion with Predictive State-Space Models

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Humanoid locomotion requires control policies that remain stable under imperfect sensing while exploiting temporal context for consistent motion. We present RoboDreamer, a two-stage teacher--student framework that combines next-observation consistency with randomized continuous temporal masking. A teacher is first trained on clean observations, and a student is then distilled under masked recent observations, encouraging the policy to infer missing current information from history. At inference, the same masking interface is reused for implicit closed-loop action refinement and optional multi-

Read original source ↗ Open in workspace

recordType

paper

region

Global